Breast cancer awareness is essential for early detection, which is critical for improving survival rates and reducing the burden of this disease. October is Breast Cancer Awareness Month, but education and awareness should not be limited to just one month of the year. A large portion of the global population will experience or be impacted by breast cancer; one in eight women will face a diagnosis in their lives, and this affects both them and their families.

Exciting advancements in the realm of breast cancer detection, such as predictive medicine, value-based care, and artificial intelligence (AI), are on the horizon. There is enormous potential to revolutionize early detection methods, offering not just a reduction in pain and suffering, but also in the financial burdens associated with cancer care and treatment. Annual mammography has long been seen as the gold standard for reducing breast cancer deaths since its introduction in the 1980s, but now the landscape is shifting, and the new era of breast cancer detection is here.

Software and the latest technological advancements enable personalized, optimized, and automated breast cancer detection. AI holds a promising role in the future of prediction and prevention, breaking barriers by turning subjective decisions into objective ones. This advanced technology can take on tasks like repetitive quantification in areas such as image-quality analytics, audit preparations, automated breast density assessment, and evidence-based risk assessment to improve early detection methods.

There is a significant barrier that hinders the promises made by technology to improve breast cancer detection: awareness, particularly in younger women. In the United States, the median age of breast cancer diagnosis is 62 years, but around 9% of cases are diagnosed in women under the age of 45 and these women often have more aggressive cancers diagnosed at a later stage, when treatment is less successful. When routine screening for breast cancer does not begin until the ages of 40-45, women under 40 are at risk of not receiving the care they need. The experts agree that cancer risk assessments should be completed by the age of 25 yet this is not routinely done in the US. Younger women should have the knowledge and support to complete these assessments as they can help preserve their well-being and understand their bodies.

Breast cancer awareness and early detection are essential for improving survival rates and reducing the burden of this disease. New technologies, such as AI, have the potential to revolutionize breast cancer detection, but it is important to ensure that everyone has access to these technologies and the knowledge they need to make informed decisions about their health.

About Teri Thomas, CEO and Managing Director at Volpara Health

Thomas is an American, based in NZ . She has a long history of executive management in healthcare IT ranging from strategy and operations to running global sales & marketing teams. This includes a 20-year career at Epic, a global healthcare systems provider.  Thomas was instrumental in growing the company from under 100 employees with little market recognition to over 10,000 employees. Thomas is also a registered nurse with a Master of Science degree, which gives her a unique perspective on the intersection of IT, clinician workflow and patient experience. Previously, she held executive roles with population health firm Orion Health and IT innovation at University of North Carolina Health Care. Thomas was a key member of the decision-making team behind Volpara successfully acquiring Harvard spin-out CRA Health in February 2021. Her focus is now helping the company to serve its purpose of saving lives, while driving profitable growth.

What You Should Know: 

– Densitas^®, a provider of artificial intelligence solutions for breast cancer screening, announced a strategic partnership with Intelerad Medical Systems^®, a provider of medical imaging software and services to advance AI-driven breast cancer screening. 

– This partnership strengthens clinical decision-making, increases operational efficiencies, reduces costs, and improves mammography quality and mammography facility adherence with MQSA EQUIP standards.

AI-Powered Enhancements for Breast Cancer Screenings

As part of the partnership, Densitas intelliMammo^® will provide actionable information to clinical care teams, managers, and administrators when and where it is needed by leveraging the international scale of Intelerad’s IntelePACS^® diagnostic imaging and PenRad^® breast imaging reporting systems. This partnership will deliver a unique end-to-end solution for breast imaging facilities.

intelliMammo Background

intelliMammo^® is a mammography enterprise software platform that comprises AI engines that generate breast density, mammography positioning quality, and breast cancer risk assessments that support enhanced workflows and continuous mammography quality improvement. Actionable insights from advanced analytics support better patient care, increased operational efficiencies, and strengthened compliance with FDA MQSA EQUIP and American College of Radiology (ACR) standards for mammography facilities. intelliMammo^® densityAI™ is a deep learning algorithm that generates standardized and automated breast density assessments from mammograms that align with the ACR BI-RADS^® breast tissue composition density scale.

“We are excited about this strategic alliance that will instantaneously expand the reach of our intelliMammo^® AI platform, extending it to 2,500 healthcare organizations that form Intelerad’s install base. intelliMammo^® is the nervous system of the breast imaging enterprise. Our advanced AI solutions for mammography inject intelligence and insights into the clinical, administrative, and service delivery needs of breast cancer screening providers,” said Mo Abdolell, CEO of Densitas. 

What You Should Know:

• Ibex Medical Analytics launches Galen Breast HER2™, a novel breast cancer AI-powered biomarker scoring solution developed in collaboration with AstraZeneca and Daiichi Sankyo, to support improved patient outcomes.
• Galen Breast HER2 is an AI-powered biomarker scoring solution to aid pathologists with reproductible HER2 assessment for breast cancer. The platform allows clinicians to rapidly and accurately identify patients with HER2-low who would benefit from targeted therapies, such as AstraZeneca’s recently approved Enhertu, connecting patients with targeted treatment to support improved patient outcomes.

HER2 Proteins Background

HER2, one of the proteins responsible for division and proliferation of breast cancer cells, is expressed in many breast tumors and its accurate assessment is critical for identifying patients who are likely to benefit from HER2-directed therapies. Traditionally, pathologists evaluate HER2 in tumor samples visually, which may result in varied interpretations as scoring is semi-quantitative and thus somewhat subjective. 

The recent emergence of antibody-drug conjugates specifically targeting HER2, which are also effective against HER2-low tumors, meant that a new segment of HER2 expression became clinically actionable. Pathologists now need to be able to evaluate and identify lower levels of HER2 expression, despite limited experience in evaluating those lower cut-offs. AI-powered tools may help pathologists with accurate, rapid, and reproducible interpretation of HER2 protein expression, particularly HER2 low, further supporting oncologists in identifying effective therapies for their patients.

Supporting Improved Biomarker Scoring in Breast Cancer Patients

Galen Breast HER2 was developed and validated by Ibex in collaboration with AstraZeneca and Daiichi Sankyo. A multi-reader validation study compared the HER2 scoring performance of pathologists and demonstrated that pathologists supported by AI showed higher consistency and accuracy for HER2 scoring, particularly on the lower levels of HER2 expression, compared to pathologists who did not use AI3. An early evidence program to generate data on the accuracy and efficiency of Galen Breast HER2 in clinical practice is now ongoing across 15 cancer centers and laboratories in the United States, Canada, Europe, the UK and Brazil. 

What You Should Know:

– A recent study published in JAMA found that conventional genomic tests commonly used for breast cancer tumors can be less accurate for Black women. This news comes at a time when Black women with breast cancer are experiencing mortality rates that are 41% higher than white women.

– Dr. Nathalie Johnson, MD FACS and President of The American Society of Breast Cancer Surgeons is among numerous doctors who advocate for Agendia and its tests which look beyond race, ethnicity, age, or menopausal status, to provide information based solely on biology. This precise information allows women and their care teams to be empowered to select the best treatment option based on their unique cancer.

Understanding and Addressing Racial Disparities in Breast Cancer Care

Racial disparities in medical care continue to pervasively affect the most vulnerable communities. Understanding such disparities within the context of racial inequities and societal institutions allows for systemic discrimination to be addressed. Such discrimination is not the aberrant behavior of a few but is often supported at an institutional level, propagated additionally by implicit biases and negative stereotypes. Stark disparities in breast cancer care have been brought to light recently by a stream of research papers highlighting a glaring issue: Black women disproportionately suffer negative outcomes in breast cancer care, as opposed to their White counterparts.

A recent cohort study shows that Black women in the United States were more likely to have a high-risk recurrence score and to die of axillary node-negative breast cancer compared with non-Hispanic White women with comparable recurrence scores. This shows that the Oncotype DX Breast Recurrence Score test, which is used to analyze the activity of a group of genes that can affect how an early-stage breast cancer tumor is likely to respond to treatment, has lower prognostic accuracy in Black women. This, in turn, suggests that genomic assays used to identify candidates for adjuvant chemotherapy may require model calibration in populations with greater racial/ethnic diversity.

Dr. Johnson is currently the President of The American Society of Breast Cancer Surgeons, as well as the Medical Director of the Legacy Health System Cancer Institute and the Legacy Breast Health Center in Portland, Oregon. She is considered to be one of the world’s leading authorities in breast cancer, not only because of her impeccable reputation as a distinguished surgeon, but also because of the fact that having survived breast cancer herself allows her to empathize with her patients, and understand breast cancer in an unparalleled manner. 

To learn more about racial disparities in breast cancer care, we spoke with Dr. Johnson for her insights: 

When talking about breast cancer, you often bring up the notion of “every woman having her own unique cancer”. What does this mean, and how can more widespread understanding and acceptance of this notion empower Black women and other marginalized communities?

Dr. Johnson, MD FACS and President of The American Society of Breast Cancer Surgeons: The notion of ‘every woman having her own unique cancer’ is, to me, the true definition of personalized medicine. Understanding each patient, what they bring to the disease and where they come from helps one understand the things that would make them most comfortable with the treatment. It also gives one an insight into why certain options feel good, and why some don’t. This also allows us to take the time and explain to the patient certain things that they might not be too happy to have, for instance – chemotherapy. Nobody is happy to have chemotherapy, but by understanding the patient, one is able to teach them about why they need these treatments for their specific tumor. This is one of the reasons why I am a strong advocate of neoadjuvant therapy because it has allowed us to treat people who we initially thought were not going to get better.

For Black women in particular, there are different options. I am trying to educate people about recurrence scores and the genomics of cancer. We have begun to realize that the widely used genomic test ‘Oncotype DX’ does not represent the biology of African American women as well as another genomic score might. This puts Black women with estrogen-positive breast cancer at a disproportionate disadvantage. Trying to understand tumor biology specific to the patient also allows one to consider pre-surgical endocrine therapy, which can provide evidence as to whether the tumor is endocrine-sensitive in the way you might have imagined. 

How would starting the conversation around ‘ethnically representative tumor biology’ address the racial disparities we see in breast cancer?

Dr. Johnson: Because we see Black women with the same Oncotype recurrence score as their white counterparts having a much higher mortality rate, we can extend that logic and apply it to other ethnically marginalized communities as well. Everyone benefits from this conversation. For each ethnic group, we want to do the best that we can, and ultimately help each and every patient that walks through our door, we want to fully understand the biology of their tumor and what nuances there may be. The same principle exists for genomic testing as well. When we do studies, we often don’t have enough representation from under-represented minorities, and this really highlights the need for having representative samples in clinical trials, otherwise, we may not do as good a job as we could of understanding their particular set of genes.

What are some barriers that discourage more Black women to take part in clinical trials, and how can we overcome these barriers?

Dr. Johnson: We can definitely do a better job at having everybody – Black women and all, included in studies. One of the major issues is trust. Being able to sit down and explain the aims and objectives of the study to the patients in detail allows for better trust-building. In some ways, there may be some implicit bias that goes into enrolling patients into trials, which could manifest in ways like not thinking that some patients may not understand the study objectives when in reality they would if you took the time to explain. In some of the recent genomic trials, like the ‘RxPONDER Trial’, there was some concern that Black women were not as compliant with therapy as white women. However, it turned out that Black women were the most compliant group in that entire trial. For other groups, one thing we can do is to ensure that consent forms are in languages spoken and understood by those communities. Having consent forms in different languages is one of the things that The American Society of Breast Cancer Surgeons wants to work on, so we can enroll diverse participants.

What prognostic and predictive value do advanced gene expression profiling solutions such as Agendia provide to Black women?

Dr. Johnson: As an advocate of MammaPrint, I try to educate people about these advanced gene expression profiling solutions. Based on many studies, Agendia’s MammaPrint appears to be a more representative genomic score for Black women in particular. MammaPrint’s prognostic value is far greater than the genomic scores we use today because it accurately classifies African American women as ‘high risk’ which impacts the treatments we give them and also improves their outcomes. Additionally, with MammaPrint, the number of genes tested is greater, which allows you to comprehensively evaluate the impact of other genes on the patient. For instance, obesity has been found to impact the outcomes of breast cancer patients. Therefore, by using MammaPrint you can look at the genes that are differentially expressed, and understand the tumor in a much better way. Using MammaPrint and BluePrint allows you to look at 150 genes, whereas Oncotype DX just accounts for 21 genes, so there is definitely a stark difference in the depth of gene expression change that can be picked up with MammaPrint. The interplay of differential expression amongst genes is something that can and will be further explored in the future across populations, but for now, advanced genomic testing is definitely allowing us to understand and treat breast cancer better.

About Agendia

Agendia’s testing platform provides physicians the ability to comprehensively analyze the biology behind an early-stage breast cancer patient’s tumor, providing unique genomic insights that empower precise treatment decisions. Agendia’s unique, innovative tests include:

• MammaPrint®, its 70-gene prognostic test, determines a specific patient’s breast cancer recurrence risk, and can predict a patient’s response to both chemo and endocrine therapy.
• The 80-gene molecular subtyping test, BluePrint®, identifies the underlying biology of an individual’s breast cancer to provide information about its behavior, long-term prognosis, and potential response to systemic therapy.
• When combined, the two tests capture the underlying biology of a tumor, to holistically inform the most effective treatment approaches for a patient’s unique cancer, regardless of age, menopausal status, race, ethnicity and other clinical factors, enabling physicians to objectively select the best treatment plan.

What You Should Know:

– Maribel Health, a turnkey partner for health systems looking to design, build, and operate a full continuum of advanced home and community services, announced today the completion of a $25 million Series A funding round led by General Catalyst. 

– The new funding will be used to accelerate growth with Maribel’s initial partners, to attract and onboard the talent required to serve its collaborators worldwide and to support continued investment and development of Maribel’s technology platform to manage the clinical workflows, care complexities, and logistics of providing advanced care safely and effectively in the home and community. 

Making home the center of the health system

Health systems face unprecedented challenges with capacity, workforce, and reimbursement. We work for health systems to design, build, and operate advanced clinical care models in the home and community to expand total capacity and improve access​.

In late 2021, Ronald Paulus, MD, a health system CEO, and Adam Groff, MD, a home and community services entrepreneur and hospital medicine physician, came together to enable health systems to respond to inevitable demographic shifts and workforce constraints driving care out of hospitals and into the home. Together, they founded Maribel Health to design, engineer, and operate the capabilities – including technology, clinical models, and operational management services – in order to enable the home and community to be increasingly central to both patients’ and health systems’ success.

Maribel focuses on solutions that augment the home-based workforce to deliver more advanced clinical services. As a technology-enabled operating partner of health systems, Maribel enhances capabilities and integration of existing home and community organizations to expand total health system capacity. Examples of work underway include building out hospital-at-home logistics and clinical operations, community-based palliative care, mobile integrated health / community paramedicine, and longitudinal complex chronic care with our partners.

Who Is Marbel?

Maribel Health is named in honor of Maribel Sanchez Souther who died in 2016 at age 41 after a two-and-a-half-year battle with triple-negative breast cancer. She lived an amazing life as a wife, mother of three, friend, Ivy League coach, and All-American runner. During her treatment, Maribel had multiple hospital admissions that took her away from her young family. Often, these issues could have been addressed more effectively in the home with the right support and technology. Maribel Health exists so that patients like Maribel receive the care they deserve where they need it most – in their home.

Maribel combines deep operating expertise with novel technology to help its partners design, build, and operate advanced clinical care capabilities in the home and community, including hospital-at-home, to sustainably expand total system capacity. Ultimately, Maribel’s mission is to make home the center of the health system so that all patients have access to high-quality, reliable, and compassionate care where they live and increasingly work.

Recent Traction

Collectively, the Maribel team has overseen over 15,000 hospital-at-home admissions, led the design of eight successful advanced home care programs, advised over 100 hospitals and health systems, and designed, developed and deployed technology used in the care of more than 8,000,000 patients.

In conjunction with this financing, Maribel also officially announced founding anchor partnerships with Mercy Health System and BAYADA Home Health Care in separate, joint statements. Both partnerships involve the end-to-end design, build, and operation of hospital-at-home programs that can serve as a chassis for other advanced home care models including community-based palliative care, SNF-at-home, and mobile integrated health.  

What You Should Know:

– H1, the connecting force for global healthcare provider, clinical, science, and research information, today announced the availability of indication-level diversity insights in addition to institution, provider, and patient diversity data within its Trial Landscape solution.

– Additionally, H1 has successfully onboarded its first customer – a top 20 pharmaceutical company – onto the H1 Data Network, a new solution that aggregates sponsor-contributed site and principal investigator (PI) performance data from clinical trial management systems (CTMS) to fuel transparency and clinical trial design.  

Healthcare Data Leader H1 Expands its Offerings With New Capabilities

Site feasibility and clinical operations teams at leading pharmaceutical companies use H1 Trial Landscape to discover diverse physician and patient populations and support more representative clinical trial participation. Trial Landscape is an exhaustive clinical trial intelligence repository, incorporating data from public and proprietary sources including over 10 million healthcare providers (HCPs) and over 420,000 clinical trials. It is the first solution of its kind to fully integrate diversity and inclusion insights at the site, HCP, patient, and now, the indication levels – accelerating site and PI research, validation, prioritization, diversity, and selection. 

By moving beyond the site level to include indication-level data, pharmaceutical companies can surface diversity insights on patients at a more granular level to design more inclusive clinical trials. For example, a user can now identify what percentage of breast cancer patients are African American in Georgia so, if they design a clinical trial in that state, they can recruit a representative population. With access to patient data this granular, clinical operations teams can better plan and design diverse clinical trials.

With the new H1 Data Network, pharmaceutical clients can contribute and share their CTMS data with other companies within the network and increase transparency within the industry. Unlike other networks, the H1 Data Network is open to pharmaceutical companies of all sizes, ensuring that midmarket and smaller companies have the same access to clinical trial performance data as big pharma. A top 20 pharmaceutical company is already contributing its data to the H1 Data Network, with many more planned in the near future. 

“Ensuring diversity in clinical trials is not just our mission; it’s a moral imperative and is essential for the development of effective and equitable healthcare solutions,” said Ariel Katz, CEO and co-founder of H1. “We continuously strive to improve our technology and our data to support this mission. These new capabilities are the latest advancements to equip pharmaceutical companies with the insights needed to meet this imperative by creating more diverse clinical trials and sharing that data back with the broader community.”

While the Food and Drug Administration (FDA) has encouraged clinical diversity over the past few decades, it is only now being enforced. The recently enacted 2023 Omnibus Spending Bill (Public Law 117-328) requires that diversity action plans be submitted for clinical trials used by the FDA to decide whether drugs are safe and effective. Other initiatives supporting clinical trial diversity include the National Institutes of Health’s recently released Minority Health and Health Disparities Strategic Plan 2021-2025, which focuses on improving diversity and inclusion in NIH-funded research with updated clinical trial policies and guidelines. With these laws, it will be up to pharmaceutical companies and researchers to engage and recruit diverse patient populations to take part in their trials.

As the amount of real-world data (RWD) in the pharmaceutical industry continues to grow, so does the usage of machine learning (ML) to analyze that data and gain insights. In fact, in a recent survey, 95% of life sciences executives said they expect to utilize ML in the next few years to generate real-world evidence (RWE) from this data. 

With such a large and growing volume of data available, researchers may be wondering how they can take advantage of all of it to enhance and expand the impact of their research. Many organizations have already adopted ML for certain uses, but in order to maximize the value of data, researchers will need to move beyond the most common applications of the tool. By leveraging ML in new and innovative ways, organizations can push the boundaries of their research and uncover insights that will truly impact patient lives.

How machine learning is currently being used 

Currently, the most common use of ML involves predictive modeling for high-stakes scenarios. Researchers input RWD into a model, and the algorithms predict outcomes based on that data. These predictions can be used as RWE to incorporate into regulatory submissions or to inform further research, or they can be leveraged to guide decisions and take further action.

One example of the former use case is utilizing ML to understand optimal treatments for certain diseases. For example, for patients with metastatic breast cancer (MBC), ML models can analyze information including age, date of diagnosis, cancer stage, and other factors to predict the treatment regimens that will maximize overall survival and speed up time-to-treatment discontinuation. This insight could be used to inform treatment choices and potentially improve outcomes for patients with MBC, once clinically validated.

In the latter case, predictive modeling can have tangible benefits if the findings are actually used to make decisions around patient treatment. Predictive modeling has been particularly successful in assessing sepsis outcomes and determining treatment timelines, for example. Researchers have used ML to predict mortality over time for patients with sepsis and then, using this insight, decided at which point to administer drugs to patients. Using this approach, researchers have successfully been able to reduce mortality for sepsis patients.

Where researchers can expand their uses of machine learning 

Researchers have proven the benefits of utilizing ML to make predictions, but now we need to leverage the technology even further. In order to maximize the potential of the technology for impacting patient lives, researchers must understand not just what the predicted outcomes are, but why they are happening. Causal inference is a well-defined concept in statistics, but what’s new is using ML to derive causal inference. Predictions from ML models can be highly valuable, but if we cannot explain them, then the picture is incomplete. Causal inference can help validate ML outputs by providing explanations for the insights that researchers are finding, and this is an application of ML that researchers should pursue.

Researchers should also further explore the applications of unsupervised machine learning. Unsupervised ML involves analyzing and finding patterns within datasets without any reference to known outcomes. While ML typically involves predicting future outcomes based on known data of past outcomes, unsupervised ML leverages data that is not yet understood to discover hidden patterns and insights in the underlying structure of the data. Predictive ML is useful for answering specific questions, but unsupervised ML can allow researchers to explore questions they hadn’t even thought of, generating hypotheses and truly novel insights.

One specific application of unsupervised ML is identifying and understanding patient subgroups, such as the subset of Alzheimer’s patients with certain characteristics. In one recent study utilizing unsupervised ML, researchers found that female Alzheimer’s patients with a younger age of disease onset, as well as comorbid depression and anxiety, were more likely to have quicker rates of disease progression and worse outcomes. When researchers can define such subgroups, they can focus their attention on further investigating these groups and uncover the best methods to potentially improve outcomes.

Best practices for applying machine learning 

Just because ML is being used does not mean it’s being used correctly. We’ve seen great progress in ML becoming more accessible and widely utilized, but researchers must ensure that they’re using the tool appropriately. For those incorporating ML into their studies, documentation and transparency are key, especially when it comes to regulatory submissions. 

While regulatory institutions such as the FDA used to be focused simply on the findings and insights within a regulatory submission, there has been a shift towards greater attention to the underlying models and data used to conduct the research and uncover those insights. To build a successful submission, researchers must meticulously document all parts of their investigations. As a rule of thumb, methods and findings should be understandable to someone who was not directly involved in the research.

Researchers may choose to utilize software that automatically documents and creates a report of all methods and materials, including the raw data, models used to analyze the data, and outputs from the analysis. However, regardless of whether the documentation is done automatically or manually, studies must be fully transparent, understandable, and reproducible. This will help ensure that researchers not only have successful submissions but that their research truly has a noticeable reach and impact.

The future of machine learning in life sciences

When ML first came onto the life sciences scene, many people were skeptical about whether the tool was actually valuable or if it was overhyped. However, as it has become more widely utilized, researchers have increasingly found its capabilities useful, particularly when it comes to handling high-dimensional healthcare data. And, thanks to recent guidelines from the FDA around using RWD and RWE in regulatory submissions, comfort with using ML to analyze RWD continues to grow. 

We’re not yet at the point where all researchers, regulatory institutions, or patients fully understand ML, but we are seeing a shift toward embracing the technology more. Researchers have realized the benefits of ML in augmenting traditional analytical methods, reducing biases, and strengthening results. For the FDA, providing guidelines around RWD usage and beginning to acknowledge RWE steps in the right direction. The next step will be the FDA fully accepting the use of ML to generate that RWE and its insights.

Now that we’re more comfortable with the basic usages of ML, exploring new applications of it – while ensuring that it’s being used appropriately – is the next frontier. As researchers continue to realize the potential of ML for impacting patient lives, expanded usage is on the horizon.

About Michael Munsell
Michael Munsell, PhD, is the Director of Research at Panalgo, where he is responsible for managing the internal and collaborative research agenda as well as contributing to the scientific development of the IHD platform, including prototyping and validating new machine learning models for IHD Data Science. Mike has a wealth of experience in RWD study design and has authored several publications in a variety of fields, including health economics, outcomes research and data science. He holds a PhD from Brandeis University, with a focus on computational economics, and an undergraduate degree in Economics from the University of Michigan.

Women’s healthcare faces an uphill battle after centuries of being ignored. Yet, ironically enough, women currently share half of the consumerism market, hold power over 80% of household financial decisions, and make 70% of healthcare-related choices in their families.

Despite this, their access to proper healthcare often comes up short.

But with the market for women’s healthcare predicted to be worth over $47 billion, changes are starting to occur. And with the recent attacks and laws on women’s reproductive rights, it’s critical to explore what is happening in women’s health technology. 

Education and conversation around women’s healthcare are evolving, however, women’s health technology is still, by far, an emerging industry. For example, only 3% of the 2,728 US digital health deals since 2011 have focused on women’s health.

Here are five key women’s health technology trends to look out for in 2023 that will help drive change in women’s healthcare.  

AI and Machine Learning

With more data on women’s health, AI and machine learning will continue to emerge as a dominant force in women’s healthcare. AI and machine learning help absorb large data sets, so they talk to each other. AI and machine learning also allow companies to deliver personalized insights based on the collected data.

From sleep to fertility, there is a vast potential to apply this to every area of health. Of course, using digital tools to track your health isn’t new. Still, with AI and machine learning, the potential applications are phenomenal.

Privacy protection is also a part of the trend. After the overturn of Roe vs. Wade, all data-driven technologies will need data protection first. Congress will have to find a way to pass privacy legislation so that people won’t be affected negatively by AI personal information use. 

Employee Wellness: Wellness Programs as Integral Workplace Components 

With the ongoing pandemic and numerous other worldly issues, having employee wellness in the workplace is not only an attraction for potential employees but a critical component of “workplace synergy.”

In the past, employee benefits for women were considered excellent if they offered paid time off, maternity leave, and health insurance. Now companies have realized that wellness benefits such as medical screenings, counseling, fitness programs, and competitions are far more cherished. As Australia’s largest unions are pushing for employers to offer menstrual and menopause leave, more companies worldwide may finally realize that this is crucial for working women’s rights.

Carrot Fertility is the gold standard, offering their employees financial wellness, a flexible time off policy, a shared coworking space and a home office stipend, a productivity stipend, and a $15,000 lifetime maximum benefit for family forming needs.

Positive Menopause

The Menopausal stage significantly impacts women’s lives, as most will go through this experience. A woman goes through menopause regardless of race, ethnicity, socio-economic status, or education, yet how they respond and experience it differs greatly.

Unfortunately, women are often unaware of how to identify the signs of menopause or address the symptoms. According to a Bonafide survey, 45% of women didn’t know the difference between perimenopause and menopause before experiencing symptoms. Therefore, it is imperative to evolve conversation and education around this topic.

A lack of clear guidelines and misperceptions about menopause have hindered innovation in this field. Although the menopausal market has about $600 billion of spending opportunities, only 7 percent of femtech startups address this stage of women’s lives. Yet, many emerging players have been entering the field—from menopause-focused sex toys to vaginal care products that can help women with their individual menopause experiences—and the industry will see more of those in 2023. 

At- Home Hospital and Remote Patient Monitoring

Moving healthcare out of traditional settings (like the hospital) and into people’s everyday lives is the future of healthcare. For example, implementing remote hormone monitoring for fertility treatment protocols will cut blood draws and clinical testing down three times less. As a result, it will ultimately make treatment more accessible and cheaper. 

But to do that, we need technologies that bridge the gap between traditional physical settings and patients’ homes. This helps people play a part in both managing their healthcare and improving their quality of care. A case in point is remote patient monitoring, which uses digital health technologies to transmit information directly to a patient’s care team.     

More than 60 different conditions can be treated appropriately using this system. In the US, programs are growing, and technology offers the potential to meet women’s health needs in new ways. An example of this is patient-friendly devices that provide various solutions for female-specific conditions. 

Attention-Gathering Startups Focusing on Breast Cancer Funding

With startups like Gabbi, RNA Nanotherapeutics, and Vara raising millions of business-backed funding, it’s been an opportune time to tackle breast cancer treatments properly. 

Like most recent startups in breast cancer research, these three companies are technologically focused on making earlier detection and treatment more manageable and less complicated. AI & Machine Learning, RNA nanotechnology, TACC3 inhibitors, and liquid biopsies are just a few tech approaches that will make a big splash in the future.

Startups are usually small in staff but mighty. They are beginning to gain attention and movement, which is why funding is critical for them to access better research resources and materials. Grant support and donations for such a prevalent disease as breast cancer can only gain more momentum in the future.

Conclusion

Although the overall traction is encouraging, funding for female-led startups and women’s health-focused initiatives still needs to catch up to other categories. It will take more advocating, female tech representation, and financial and emotional support for it to come to fruition. Despite these needs, the future of femtech companies meeting the health needs of millions of women looks bright. 

About Sylvia Kang

Sylvia Kang is the co-founder and CEO of Mira, an FDA/CE compliant and AI-infused IoT mobile health platform that provides accurate and personalized point-of-care health tracking and analysis, resulting in higher life quality for individuals and better clinical and economic healthcare outcomes globally. Sylvia holds an MBA from Cornell University and an MS in Biomedical Engineering from Columbia. Before she started Mira, she was in business director roles in a Fortune 500 life science company, running a $100M global business. Like many women in their 20s, Sylvia prioritized advanced education and career opportunities over family planning. When one close friend of hers started to try for a baby, she had no success after six months of trying. Doctors couldn’t find any problems with her or her husband, and Sylvia witnessed her going through a very stressful, guessing and disappointing journey. 

The existing fertility products didn’t help because they couldn’t pinpoint what went wrong or give enough insights to be her guide. She eventually got pregnant through IUI, which was time-consuming and expensive. This is a general and trending issue faced by more and more women today. Shortly, Sylvia left her corporate job and used her biomedical degree to create Mira on a mission to give women the accuracy of lab testing at home. 

What You Should Know:

– One year ago, President Joe Biden and First Lady Jill Biden reignited the Cancer Moonshot, setting an ambitious, achievable goal: to reduce the death rate from cancer by at least 50 percent over the next 25 years, and improve the experience of people and families living with and surviving cancer, ultimately ending cancer as we know it today.

– The Cancer Moonshot has spurred tremendous action across the federal government and from the public and private sectors, building a strong foundation for the work ahead.

Understanding the Biden Administration’s Plans To Combat Cancer

The Biden Administration is announcing new actions from inside and outside of government that will drive additional progress, drawing us closer to ending cancer as we know it today.

Last year, the President stood up the first-ever Cancer Cabinet to mobilize the federal government, and called on individuals, health care providers, and leaders across sectors to step up and take action in five key priority areas: (1) close the screening gap, (2) understand and address environmental exposure, (3) decrease the impact of preventable cancers, (4) bring cutting-edge research through the pipeline to patients and communities, and (5) support patients and caregivers.

To date, the Cancer Moonshot has announced over 25 new programs, policies, and resources to address these five priority areas. The First Lady has traveled the country and the world to hear from cancer patients and their loved ones, as well as the researchers, physicians, nurses, and patient navigators who support them – focusing on the importance of early detection and improving the experience of patients, families, and caregivers. And, the White House and Cancer Cabinet have held more than 50 community conversations and events. More than 60 private companies, non-profits, academic institutions, and patient groups have also stepped up with new actions and collaborations.

These new actions will build on the work done in the first year of the reignited Cancer Moonshot. In addition, today, the President is also announcing his intent to appoint six members to the National Cancer Advisory Board, which plays an important role in guiding the Director of the NCI in setting the course for the national cancer research program.

The Cancer Cabinet is taking the following new actions:

1. National Cancer Institute (NCI) is launching a first-of-its-kind, public-private partnership to bring clinical and patient navigation support to families facing childhood cancer. The National Cancer Institute (NCI) is launching the Childhood Cancer – Data Integration for Research, Education, Care, and Clinical Trials (CC-DIRECT) to support children and Adolescents and Young Adults (AYAs) with cancer throughout their cancer journey; provide patient navigation support to families seeking information and optimal care; facilitate research participation; and establish a portable, shareable, standardized cancer health record. This means families facing childhood cancer can reach out for support and get connected to excellent care and the opportunity to participate in research through clinical trials and data sharing initiatives. This new entity represents a groundbreaking collaboration between NCI, the Office of the National Coordinator for Health Information Technology (ONC), Alliance for Clinical Trials in Oncology (ACTO), American Society of Clinical Oncology (ASCO), American Cancer Society (ACS), the MITRE Corporation, Center for Medicare and Medicaid Services (CMS), Children’s Oncology Group (COG), and the American Association for Cancer Research (AACR).

2. Health Resources and Services Administration (HRSA), is awarding $10 million to improve access to lifesaving cancer screenings and early detection including patient navigation support services. HRSA, a part of the U.S. Department of Health and Human Services (HHS), is doubling its investment in new partnerships to bring community health centers together with NCI-Designated Cancer Centers to facilitate access to lifesaving cancer screenings and early detection services for underserved communities. Health centers that receive funding will conduct patient outreach in these communities to promote early detection of cancer, connect patients to screening services, and provide direct navigation assistance with accessing high quality cancer care and treatment, as needed. Today’s awards total more than $10 million for 22 HRSA-funded health centers, expanding on the $5 million awarded to 11 health centers in 2022

3. HHS is launching “CancerX,” a Public-Private Partnership developed as a national accelerator to boost innovation in the fight against cancer. HHS, ONC and Office of the Assistant Secretary for Health (OASH), is launching the “CancerX” National Innovation Accelerator Initiative, a government wide effort to develop tools, such as digital solutions to improve cancer patient care coordination and communication, new software technology to help community organizations meet cancer patients where they are, or new platforms to support patients with their post-treatment care. This new public-private partnership will drive support for and accelerate the development of biotech and health tech startups solutions focused on the continuum of cancer care, including prevention, detection, treatment, and transitions in care. Organizations whose missions are aligned with the Cancer Moonshot goals will work together to surface innovative solutions and coordinate access to research, mentorship, resources, and other collaborative opportunities. This work will help startups scale their business and work toward creating ‘challenge-focused’ solutions for cancer with health equity in mind. This initiative will build on previous models deployed by successful HHS InnovationX program accelerators such as KidneyX and PandemicX.

The public and private sector is stepping up with the following new actions:

Promoting Cancer Prevention

4. National Minority Quality Forum (NMQF) is launching local community-based activities to increase cancer screenings in at-risk communities. NMQF, a nonprofit, nonpartisan organization that integrates data and expertise in support of initiatives to eliminate health disparities, is releasing a new online hub, which includes several interactive features designed to increase awareness about cancer disparities, innovation in early detection and treatment, and patient- and clinician-oriented resources to close gaps in cancer care delivery. In addition, to help spur action on the ground, the Cancer Stage Shifting Initiative, which was created to move from late stage to early- stage diagnosis and treatment of cancer, improving cancer care and reducing cancer deaths for all, will work together with private and public partners and local advocates to increase awareness of cancer risk and treatment, improve clinical trial diversity, and support efforts to understand the impact of the water crisis on cancer risk in Flint, Michigan.

5. Supergoop! is committing to donate SPF sunscreen to schools and communities across the country to encourage children to start protecting their skin at a young age. Since sun exposure is cumulative throughout a person’s lifetime, Supergoop! is committing to providing the country’s youth the education and resources to keep them protected. Supergoop! is growing the “Ounce by Ounce Program”, designed to give SPF sunscreen to schools for free. So far, Supergoop! has donated more than 6,800 SPF sunscreen pumps to over 1,900 classrooms and youth organizations and is dedicated to expanding this cancer prevention program.

Supporting Patients and Caregivers through their Cancer Fight

6. American Cancer Society and the Richard M. Schulze Family Foundation launch $10 Million challenge grant to benefit five American Cancer Society Hope Lodges. The American Cancer Society and the Richard M. Schulze Family Foundation (RMSFF) announced the launch of a $10 million challenge grant to benefit five American Cancer Society Hope Lodges – in Omaha, NE; Charleston, SC; Lexington, KY; Lubbock, TX; and Kansas City, MO. Funds raised through the RMSFF challenge grant will be used to establish $2 million endowments at each of the five Hope Lodges to support ongoing maintenance of their physical facilities and operations and support physical improvements to those building.

7. Colorectal Cancer Alliance is launching BlueHQ, the first-of-its-kind comprehensive support hub for patients, survivors, and caregivers to navigate colorectal cancer. BlueHQ is a free support service designed to help patients learn, connect, and take action to improve outcomes. The support hub includes features to suggest helpful information and resources that align with the patient’s profile; connects patients to allies with similar experiences, as well as a patient and family support navigator; and safely and securely stores appointments and notes or journal entries, which can be shared with caregivers and healthcare providers.

8. New coalition launches to address the obstacles rural patient communities face accessing care. A broad national advocacy campaign is set to be launched, bringing together a diverse coalition of public-private partners to raise awareness and spur action to address the persistent, underlying issues that have caused rural America to fall behind in healthcare, technology, and infrastructure. The coalition includes Stupid Cancer, the American Cancer Society Cancer Action Network, Prevent Cancer Foundation, Cervivor, National Coalition for Cancer Survivorship, Cancer and Careers, Triage Cancer, Tigerlily Foundation and Fight Colorectal Cancer Patient Advocate Foundation. Underpinning these efforts will be a storytelling campaign led by OffScrip Health, a leading digital health media platform focused on patient engagement, health equity, and access to care, and FINN Partners, a global integrated marketing and communications agency that will tackle critical issues impacting rural communities’ health, such as access to care, broadband infrastructure, consumer goods, clean water, telehealth, and more. The series will also spotlight the new technologies, partnerships, and practices that can make a difference in addressing this crisis of care.

Bringing Cancer Screening to More Communities

9. Prevent Cancer Foundation to launch “Early Detection = Better Outcomes” campaign to improve knowledge and completion of recommended cancer screenings. The Prevent Cancer Foundation is launching a new signature campaign, “Early Detection = Better Outcomes,” to educate Americans on what recommended cancer screenings and cancer-related vaccinations they need and to encourage them to schedule appointments. Better Outcomes shares evidence-based resources, including screening options by age and information on vaccinations to prevent cancer, tools to find free and low-cost cancer screenings, and information on how family history can impact cancer risk. The campaign will address two additional barriers that Americans face — fear of screening examinations and lack of access — and introduce a new, interactive tool to deliver a personalized screening plan that can be shared with a health provider.

10. Siemens Healthineers is committing to address cancer screening disparities in underserved regions. Siemens Healthineers is working to increase breast screening capabilities and capacity by providing a mobile mammography screening truck, as well as dedicated technologists to perform scans and artificial intelligence- (AI-) technology to help read 3D examinations in Pennsylvania and North Carolina. To date 680 free mammography screenings have been administered, in partnership with Penn Medicine and the Office of Children and Families Philadelphia in Southwest Philadelphia and WakeMed Health & Hospitals at Raleigh Medical Park. Expanding on the success of this program, Siemens Healthineers will be purchasing an additional mobile screening truck with the goal to partner on 10-12 additional mobile screening events this year, reaching at least 2,000 women in underserved areas, including urban and rural sites around the country.

Driving Research Advances through Data Sharing and Clinical Trial Expansion

11. CancerLinQ® and Owkin pursue a new research collaboration to improve the care of patients with metastatic non-small cell lung cancer. CancerLinQ®, a health technology platform from the American Society of Clinical Oncology, and Owkin, a French-American AI biotech company, launch an initiative to improve outcomes for people facing metastatic non-small cell lung cancer (NSCLC). They will use data from CancerLinQ Discovery®, a real-world oncology database of de-identified electronic health record (EHR) data from more than 6 million patients with cancer and blood diseases in the United States to identify possible predictive factors of why some patients with NSCLC), the most common form of lung cancer, respond poorly to immunotherapy treatment. The goal is to use the data routinely collected at the point of care to learn how to better tailor treatments for patients with advanced NSCLC.

12. Hyundai Hope On Wheels awards nearly $15 million to accelerate pediatric cancer research and treatments. Hyundai Hope On Wheels, a non-profit organization supported by Hyundai and its U.S. dealers, donated $15 million in research grants to over sixty hospitals and research institutions across the country in 2022. With this contribution, Hyundai Hope On Wheels will surpass $200 million in lifetime funding for research and innovative treatments in pursuit of a cure for pediatric cancer. As Hyundai Hope On Wheels celebrates its 25th anniversary this year, they are more committed than ever to inspire hope around the nation.

13. Susan G. Komen commits resources to improve outcomes and expands services for the breast cancer community. Susan G. Komen awarded $21.7 million to fund 48 new research projects at 26 distinguished academic medical institutions in the United States that are focused on improving patient outcomes – particularly for people with the most aggressive breast cancers, or who have experienced a recurrence or metastasis. With this investment, Komen is now supporting more than 152 active research projects, representing more than $115 million in funding. Additionally, Komen has expanded access and affordability for breast cancer screening and diagnosis by growing its screening and diagnostics program to 12 cities and providing no-cost breast cancer screening mammograms and diagnostic tests to individuals who meet income qualifications.

It’s often said that the National Health Service is the closest thing Britain has to a unifying religion. If that is the case, then the faith of the population is being tested like never before,

With budgets already stretched before the COVID pandemic, additional cost pressures since heaped on health boards across the country by double-digit inflation have brought the NHS closer to breaking point than at any time in its history.

Every passing day seems to bring bleaker news for the beleaguered service, with a seemingly endless roll call of damning statistics and publication of official reports charting yet higher levels of institutional failure. 

If anything, the relentless flow of anecdotes of patient betrayal, breathlessly reported in the pages of the local press, is more shocking.

In the past few weeks we learned that four patients had waited more than 20 hours in the back of ambulances outside Royal Shrewsbury Hospital in England; that GPs in Peterborough are now responsible for the care of more than 2,000 patients each; and that Stockport NHS Foundation Trust is offering food bank vouchers to hospital workers struggling to get by on poverty wages. 

In the same week, a British Medical Association (BMA) survey found that 44% of senior doctors are planning to leave their roles “in some capacity” over the next 12 months, while the Care Quality Commission (CQC) reported 132,000 NHS and 165,000 social care vacancies, meaning a workforce the size of the population of Newcastle-Upon-Tyne is needed to fix the logjam. 

Meanwhile, the average wait for category two, 999 calls for an ambulance — including for chest pains and strokes — in England and Wales is now 60 minutes, compared with a target of 18 minutes. And in Scotland, throughout August, one in ten operations was canceled due to a lack of resources.

Traditionally, the response of politicians to complaints of a ‘crisis’ in the NHS has been to throw more money at it, and right now there’s no money to spare.

While both Conservative and Labour governments have previously toyed with reform, none has dared challenge the universally free, taxpayer-funded model upon which the health service was founded – until now. 

This week it was reported that NHS chief executives in Scotland – one of four autonomous health service areas in the UK – have discussed abandoning its founding principles by having wealthier patients pay for treatment.

The prospect of the first ‘two-tier’ health service in the UK since its founding in 1948 is raised in draft minutes of a meeting of NHS Scotland health board leaders in September. They also discussed the possibility of curtailing some free prescriptions.

While Humza Yousaf, Scotland’s Health Secretary, sought to play down the reports – insisting NHS Scotland would stay publicly owned and operated and free at the point of delivery – the reports represent something of a watershed.

Yousaf’s comments were only to be expected. If there is a single, immutable reality of British political life it is that the NHS is an untouchable shibboleth, and any party that says otherwise risks courting electoral oblivion.

Even if there was a prime minister mad, or drunk, enough to suggest privatizing the service, they would surpass the ends of the earth several times over before finding a private operator madder, or drunker, enough to take on the job.

Yet, there is a dynamic to the latest spot in which the NHS finds itself, which appears materially different to anything in the past. Again, you need only scroll through some of the local press articles to discover that waits are longer, levels of basic care poorer and patient experiences grimmer than ever before.

Figures published by NHS Wales last week revealed more than 60,000 patients are waiting more than two years for treatment. Ian Hembrow, 53, from Maesteg, in Bridgend was told the waiting list for his urgent hip operation was four-and-a -half-years.

In Bonhill, West Dunbartonshire, 69-year-old grandmother Mary Travis has already lived in crippling pain for more than two years, waiting for a back operation to straighten her twisted spine.  Earlier this month she was told that, despite being at the top of a waiting list, she could face a further, two-year wait. 

The NHS has endured because there is an almost spiritual belief in its universality. People of all classes and backgrounds accept the same level of treatment as a right and consequence of being British. 

Those principles have survived because NHS care, as well as being universal, was also universally excellent. That can no longer be said to be the case. The withholding of treatment for years is worse than receiving poor treatment and those who can afford to pay privately for better service will inevitably opt to do so.

The most compelling argument against privatizing the NHS has always been that the provision of healthcare should not be left to the vagaries of market forces. The irony of the current crisis is that those very market forces may now compel its demise. 

No matter how strongly Britons support the NHS, few will be prepared to wait months or years to have an ingrowing toenail treated or a cyst removed if they can have it done privately the following week for a few hundred pounds.

And while we may be happy and willing to pay European levels of taxes in return for a European-style health service, we’re unlikely to do the same for a US-style system.

With the growing development of robotics and telemedicine, as well as an expansion of over-the-counter diagnostics, more people are now seeking remedies, for a greater range of treatments, from their local chemist or from a private therapist or practitioner.

By spending a small amount each month, they can have more or less unlimited telephone or video access to a private GP. 

More is being done online than was the case a few years ago. Much of it remains minor, but the direction of travel is such that, before long, more serious illnesses will be diagnosed remotely and by high street providers. 

If patients can be diagnosed with prostate or breast cancer sooner and treated more effectively, then the way in which the health service is configured and funded will no longer be as important.

We may end up with something approaching the German health service model where a private service handles minor and routine complaints, while accidents and serious illnesses are treated by a publicly funded service, similar to the NHS, which is free at the point of delivery.

It’s unlikely the NHS will ever be wholly privatized, but we could see – slowly and over time – some of its more routine functions being taken over by private companies. 

Even the most traditional religions are forced to adapt and evolve to remain relevant and the NHS is no different. How it responds to the current crisis will determine its role in treating the next generations of patients and whether they will hold it with the same reverence for another 70 years.

About Ivor Campbell

Ivor Campbell is the CEO of Snedden Campbell, a UK-based recruitment agency for the global medical technology industry. IvorIvor has been in a candidate search for more than 30 years. Prior to launching Snedden Campbell, in 2001, he held senior roles for some of the UK’s biggest recruitment companies. Fed up with men in grey suits, pointless KPIs and sharp practice, he decided to launch a new kind of retained medical technology search consultancy that would bring approachability to headhunting, where clients and candidates would be treated equally, and where nobody ever said ‘touching base’. He now spends his time meeting clients and delivering on projects around the UK, Europe and worldwide.

For many years, natural language processing (NLP) has held the promise of dramatically increasing the ability of healthcare organizations to quickly and accurately understand unstructured medical text in clinical notes. Using medical NLP, healthcare providers, clinical researchers, and payers would uncover meaningful insights hidden in unstructured text faster, with fewer errors, and at less cost than manual data review and analysis. This high-quality medical-grade data in turn would drive advances in understanding disease progression, assessing treatment efficacy, and detecting population health trends and other use cases.

Things haven’t quite worked out that way.  While single-institution, single-document-type NLP projects have proven viable, dealing with the complexity of language across multiple institutions and document types has eluded accurate NLP. 

One mistake healthcare organizations commonly make is they assume the medical NLP software they purchased is adequate for their use case. Yet these tools simply are not accurate enough to provide clinical-quality NLP because they are not fluent in the language of medicine. Medical vernacular is full of inherent complexities such as significant ambiguity, a special lexicon, and heavy use of localized medical shorthand. Add in the diversity of medical specialties and dearth of standards for the structure of medical documents, and it is clear that healthcare organizations require highly specialized medical NLP that leverages advanced technologies such as artificial intelligence (AI) and deep learning.

Fortunately, AI models have improved drastically with the advent of deep learning. Still, without any sort of medical expertise guiding the development of these deep learning models, users end up with results that basically say, “We found a whole bunch of things. Now you go figure out what is important.” That’s not exactly clinical-grade information.

What’s needed for a quality medical NLP platform is a combination of technology and medical expertise. By infusing deep learning models with specialized medical expertise, modern medical NLP software can help providers, payers, pharmaceutical companies, and clinical researchers get the most value from the data.

Limits of traditional NLP in medicine

While NLP undoubtedly has proved useful to researchers, the process involved can be labor-intensive and time-consuming. Let’s say researchers wanted to use NLP to find all patients in a target population who had appendicitis last month, with the data to be used in a white paper. Low-precision traditional NLP may identify 1,000 patients – but the NLP can be frequently wrong.   As a result, a researcher must go through the data and confirm it all. Granted, that’s still better than the researcher laboring over manual chart reviews, but that still falls well short of an efficient and effective solution. 

For other healthcare use cases – such as understanding human speech, computer-assisted coding (CAC), and clinical decision support – even “mostly accurate” software is nowhere close to acceptable. Healthcare organizations that implement a medical NLP platform that is extremely accurate will be able to apply their data to uses cases beyond research.

Choosing the right medical-grade NLP platform can be difficult for healthcare organizations that may not know precisely what features or functionality will work for them. Here are three things to look for in a clinical-grade NLP platform:

Accuracy

Does the platform provide enough accuracy for your organization’s purposes? For example, some platforms may have an algorithm for negation detection, the process of determining the presence or absence of conditions or diseases such as cancer or diabetes. However, the accuracy of these algorithms can vary depending on their ability to contextualize language in medical notes. 

The ability of an NLP platform to accurately identify common medical terms, including slang, must be a priority to guarantee high levels of accuracy. Annotation software can perform the work of physicians who traditionally would annotate thousands of medical reports – and do it much faster – but the medical NLP solution must be able to keep pace in speed and accuracy. 

Features

Healthcare organizations must know the specific functionalities of a medical NLP platform. Which ontologies does it support (SNOMED, RadLex, MEDCIN, ICD-10, etc.)? Does it identify questions or uncertainty? Can it extract insights from the unstructured text of clinical, diagnostic, and semi-structured reports?

Another important feature involves the platform’s ability to identify relations within data. Does it identify measurements? Or dates? If the platform is analyzing a report about a patient with a history of appendicitis, does the algorithm understand that appendicitis happened in the past? Or does it just say that the patient has appendicitis now?  If the report contains a statement that the patient’s mother has breast cancer, does it attribute breast cancer to the patient, or can it accurately identify the experience?

Deployment location

Many medical NLP vendors offer only cloud-based services, but not all healthcare organizations are eager to send their patient data to the cloud. Today’s focus on information safety makes cloud-based solutions in this space less attractive. For those organizations, on-premises medical NLP platform deployments are essential. 

Conclusion

Relative to the requirements of provider and payer organizations, medical NLP for too long has left much to be desired in accuracy and flexibility. Recent advances in AI now make it possible for medical NLP to help healthcare organizations leverage highly accurate data for clinical work, research and drug development. Healthcare organizations should ensure a medical NLP platform is accurate enough and includes the features they need to get the most from their data.

About Dr. Tim O’Connell 

Dr. Tim O’Connell is the founder and CEO of emtelligent, a Vancouver-based medical NLP technology solution. He is also a practicing radiologist, and the vice-chair of clinical informatics at the University of British Columbia.

What You Should Know:

– The latest study from Ibex Medical Analytics and the Institut Curie, published in Nature, demonstrates how AI implementation across pathology labs can significantly improve the outcome of cancer care.

– The study analyzed Ibex’s AI-based quality control solution for breast biopsy review on over 15,000 slides over a diverse cohort. The study found the AI algorithm achieved high accuracy in identifying various types of cancer and 51 different morphological features of breast tissue.

– Breast cancer is the most common malignant disease worldwide, with over 2.26 million new cases in 2020. The cumulative probability of a woman receiving at least one false-positive biopsy over 10 years is estimated to be between 4.8% and 9.4%, emphasizing the need for accurate, timely, and objective diagnosis of this disease.

– The algorithm accurately identified invasive carcinoma and ductal carcinoma in situ (DCIS) with 93.79% specificity and 93.20% sensitivity. Additionally, the AI differentiated well between different grades and subtypes of breast cancer.

What You Should Know:

– Exai Bio and researchers at UCSF released data demonstrating that Exai’s novel, RNA-based liquid biopsy platform accurately detected breast cancer at the earliest stages and smallest tumor sizes.

– Earlier detection of breast cancer is crucial for optimal patient outcomes but cannot always be achieved based on symptoms or mammography.

Non-Invasive Blood-Based Platform Delivers Promising Data on Detecting Breast Cancer At It’s Earliest Stages

Exai Bio is a next-generation liquid biopsy company. Its mission is to enable a world where cancer can be detected early, diagnosed accurately, treated in a personalized and targeted way, and ultimately cured. The company’s proprietary RNA and artificial intelligence-based liquid biopsy technology delivers clinical insights into cancer biology to enable the earliest, most accurate diagnosis of cancer.

Exai’s technology uses RNA sequencing to identify a novel category of cancer-associated, small non-coding RNAs, termed orphan non-coding RNAs (oncRNAs). In a poster entitled, “Early-stage breast cancer detection using orphan noncoding RNAs”, presented at the 2022 San Antonio Breast Cancer Symposium, Exai demonstrated that oncRNA biomarkers in blood, combined with deep machine learning, detected breast cancer with high accuracy overall, including across all cancer stages and tumor sizes. The poster further demonstrates that even at the earliest stages and smallest tumors, sensitivity was greater than 80%. These findings suggest that Exai’s liquid biopsy test for earlier detection of cancer could meaningfully improve care and outcomes for cancer patients.

With this study, we again demonstrate that oncRNAs can be used as a biomarker for earlier cancer detection from a blood draw. oncRNAs are secreted from cancer cells and are abundant in the blood of cancer patients. Exai has created a catalog of hundreds of thousands of oncRNAs found in all major cancer types. This vast catalog gives the Exai platform several scientific and practical advantages over tests that rely on circulating tumor DNA.

These 2022 SABCS results also complement and build on the breast cancer data presented at SABCS 2021 where changes in oncRNAs reflected breast cancer treatment response, predicted overall survival and added significant information to other clinical endpoints such as tumor tissue pathology.

“Our results presented at SABCS 2022 represent another important step in establishing the role of oncRNAs in addressing the unmet need of detecting cancer at its earliest stages from a simple blood sample,” said Patrick Arensdorf, Chief Executive Officer of Exai. “The oncRNA-based liquid biopsy technology will be compatible with standard sample requirements enabling easy integration into conventional clinical workflows. Exai’s goal is to improve patient care with a variety of liquid biopsy tests for early cancer detection and monitoring of residual disease and recurrence in multiple types of cancer.”

What You Should Know:

– A consortium of 10 National Health Service Trusts — the publicly funded healthcare system in England — is now deploying the MONAI-based AIDE platform across four of its hospitals, providing artificial intelligence (AI)-enabled disease-detection tools to healthcare professionals serving 5 million patients a year. 

– AIDE, short for AI Deployment Engine, is expected to be rolled out next year across 11 NHS hospitals serving 18 million patients, bringing AI capabilities to clinicians. It’s built on MONAI, an open-source medical imaging AI framework co-developed by NVIDIA and the AI Centre, which allows AI applications to interface with hospital systems. 

AI-Driven Healthcare Platforms

Introduced in 2019, MONAI is reducing the complexity of medical workflows from R&D to the clinic. It allows developers to easily build and deploy AI applications, resulting in a model ready for clinical integration, and making it easier to interpret medical exams and unlock new levels of knowledge about patients.

MONAI provides deep learning infrastructure and workflows optimized for medical imaging. MONAI, with more than 650,000 downloads, is used by leading healthcare institutions Guy’s and St Thomas’ Hospital and King’s College Hospital in the U.K., for its ability to harness the power and potential of medical imaging data to simplify and streamline the process for building AI models. “Across the healthcare ecosystem, researchers, hospitals and startups are realizing the power of incorporating a streamlined AI pipeline into their work,” said Haris Shuaib, AI transformation lead at the AI Centre. “The open-source MONAI ecosystem is standardizing hundreds of AI algorithms for maximum interoperability and impact, enabling their deployment in just a few weeks instead of three-to-six months.”Built in collaboration with the AI Centre for Value-Based Healthcare — a consortium of universities, hospitals and industry partners led by King’s College London and Guy’s and St Thomas’ NHS Foundation Trust — AIDE brings the capabilities of AI to clinicians. This solution equips clinicians with improved information about patients, making healthcare data more accessible and interoperable, in order to improve patient care.

AIDE, short for AI Deployment Engine, is expected to be rolled out next year across 11 NHS hospitals serving 18 million patients, bringing AI capabilities to clinicians. It’s built on MONAI, an open-source medical imaging AI framework co-developed by NVIDIA and the AI Centre, which allows AI applications to interface with hospital systems. 

Together, MONAI and AIDE enable safe and effective validation, deployment and evaluation of medical imaging AI models, which the NHS will apply in diagnosing and treating cancers, stroke, dementia and other conditions. The platform is being deployed at the following facilities: Guy’s and St Thomas’s, King’s College Hospital, East Kent Hospital University and University College London Hospitals NHS Foundation Trusts.

“Deployment of this infrastructure for clinical AI tools is a hugely exciting step in integrating AI into healthcare services,” said James Teo, professor of neurology and data science at King’s College Hospital NHS. “These platforms will provide a scalable way for clinicians to deploy healthcare AI tools to support decision-making to improve the speed and precision of patient care. This is the start of a digital transformation journey with strong, safe and open foundations.” 

The AI Center has already developed algorithms to improve the diagnosis of COVID-19, breast cancer, brain tumor, stroke detection and dementia risk. AIDE connects approved AI algorithms to a patient’s medical record seamlessly and securely, with the data never leaving the hospital trust. Once the clinical data has been analyzed, the results are sent back to the electronic healthcare record to support clinical decision-making. This provides another valuable data point for clinical multidisciplinary teams when reviewing patients’ cases. It’s hoped that AIDE can support speeding up this process to benefit patients.

“The AI Centre has done invaluable work towards integrating AI into national healthcare. Deploying MONAI is a critical milestone in our journey to enable the use of safe and robot AI innovations within the clinic,” said Professor Sebastien Ourselin, deputy director of the AI Centre. “This could only be achieved through our strong partnerships between academic and industry leaders like NVIDIA.”

What You Should Know:

– Central Oklahoma Family Medical Center FQHC (The Clinic) has selected Oatmeal Health, a veteran-owned Patient Success Service to bring tech-enabled lung cancer screenings to their patients.

– As part of the partnership, Oatmeal Health will provide white-glove, concierge service, offering our support without FQHC’s shouldering the burden or cost. 

Tech-Enabled Lung Cancer Screening

Currently, lung screening rates hover at around 4 percent nationally versus 70% for breast cancer. There is a multitude of reasons why lung cancer lags behind education and access, even though it takes more lives annually in the U.S. than the next three deadliest cancers combined, breast, prostate, and pancreatic. Oatmeal Health will help identify The Clinic’s eligible patients and facilitate local CT scanner logistics. By leveraging a virtual nodule clinic model, they will ensure proper follow-up or referral and supplement image evaluation with AI. 

Culturally sensitive educational material and engagement solutions will be utilized to ensure repeat annual visits, with the goal of empowering individuals from historically underserved communities with early detection so no one has to live with a life-threatening late-stage disease.

“We founded Oatmeal Health in May 2022 and in just a few months are in partnership conversations with FQHCs in 5 states and counting,” said Ty Vachon M.D, Oatmeal Health’s CEO, and co-founder.  “We are excited to work alongside Central Oklahoma Family Medical Center at 10 locations in Ada, Konawa, Stratford, and Seminole to meet their patients’ most pressing lung cancer screening needs, and the response from their staff has been overwhelmingly positive.”