Dr. Gruen is the chief medical officer of IBM Watson Health Imaging.

David Gruen, MD, MBA, FACR - Chief Medical Officer, IBM Watson Health Imaging

If only we were as good at prevention and early detection as we are at treating complex disease in U.S. healthcare. Generally, people know what they should do, and in some cases, they do it. For example, many patients religiously go to the dentist for a cleaning every six months to prevent cavities. 

But screening women with consistent mammograms beginning at age 40 to detect breast cancer?

 Not so much. Just imagine how many lives we could save if we looked for breast cancer with the rigor and diligence with which we prevent tooth decay.

An Ounce of Prevention: Weighing Evidence and Personal Risk Factors

Unfortunately, when it comes to breast cancer screening recommendations,

 there are multiple sets of guidelines, many of them different. Conflicting recommendations can breed confusion and, far worse, can potentially threaten lives. One study estimated that if women followed less stringent recommendations and started screening at age 50 (instead of 40), and women aged 50-74 only screened every other year (instead of annually), it could result in about 6,500 more deaths from breast cancer every year in the United States.

To further complicate matters, even the best evidence-based guidelines may not be the best approach for every patient. All patients need to make sure their complete history is part of their healthcare decision making, and that is particularly important for breast cancer patients. Each woman has a unique personal and family history which may impact her risk of getting breast cancer. There are many factors that women and their physicians should consider when determining the best approach to breast cancer screening, such as personal health history, family history, genetic profile and hormonal considerations, among many others.

Doctors don’t know their patients as well as patients know themselves. For example, who in the family has had cancer, especially breast, ovarian or cancer of the gastrointestinal tract? Has the patient ever had a breast biopsy that showed abnormal cells, or prior cancer? At what age did she have her first period? Go through menopause? How many pregnancies? How dense is the patient’s breast tissue? Women and their doctors must work through these issues together to pursue more effective prevention.

Where Artificial Intelligence (AI) Can Help With Breast Cancer Prevention Efforts

As a breast radiologist, I believe one of the keys to better outcomes will be a more personalized level of risk assessment for every patient. AI can help deliver this personalization. For example, women with the densest breast tissue have a higher risk of breast cancer.

 These women may benefit from more extensive screenings, such as ultrasound or breast MRI. AI can help conduct density assessments to identify higher-risk patients.

In addition to density assessment, AI can enhance breast cancer detection by helping clinicians identify abnormalities on a mammogram, including a 3D (tomosynthesis) mammogram, that might be overlooked by even the most experienced radiologist. 

There is some promising research around applying data and AI to identifying breast cancer. An IBM research team analyzed de-identified mammography images, linked to comprehensive clinical data and biomarkers, to create a new algorithm designed to predict breast cancer.

 The combined machine- and deep-learning model correctly predicted the development of breast cancer in 87 percent of the cases it analyzed – an accuracy comparable to radiologists.

There are many exciting possibilities that could result from this type of research. For example, this may be the first study to incorporate both mammograms and electronic health record data for the prediction of breast cancer, which shows the potential of one day harnessing multiple data sets and AI algorithms to tailor risk assessment to each patient. The research team 

 analyzing clinical risk elements to better understand their relationship to an individual’s personalized risk.

To be clear, AI will never replace the radiologist. Another large-scale IBM Research study found that no single AI algorithm could outperform radiologists, but the combination of AI with radiologist assessment improved overall accuracy.

And no matter how good the technology gets, there will never be a replacement for good, patient-centered care. I encourage women to know their risk and talk to their doctors about breast cancer screenings. I’d like to see all patients do for the rest of our bodies what we so willingly do to prevent dental disease. The benefits to our lives can be dramatic.

This article does not provide medical advice. For information on the benefits of breast cancer screening starting at age 40, visit the 

For a more detailed discussion of differences between recommendations, see 

“Clearing up confusion over breast cancer screening recommendations”

Hendrick and Helvie, “United States Preventive Services Task Force Screening Mammography Recommendations: Science Ignored.” 

 2011;196: W112-W116. 10.2214/AJR.10.5609

Source: NIH National Cancer Institute. https://www.cancer.gov/types/breast/breast-changes/dense-breasts

Akselrod-Ballin A, Chorev M, Shoshan Y, et al. Predicting breast cancer by applying deep learning to linked health records and mammograms. 

Schaffter T, Buist DSM, Lee CI, et al. Evaluation of combined artificial intelligence and radiologist assessment to interpret screening mammograms. 

Articles

Artificial intelligence can help seek out and identify high-risk patients who might benefit from more extensive screening. 

Personalizing Breast Cancer Risk Assessment 

“If we told clinicians, ‘we will use advanced math to help you improve care,’ they would probably be fine with it. But the term ‘artificial intelligence’ raises natural skepticism about what it really means.” – Mark D. Weisman, MD, MBA, Chief Medical Information Officer, TidalHealth

“First, do no harm” is a promise many of us make when becoming clinicians. To me it means that, for as long as I practice medicine, I must carefully weigh the risks and benefits of my decisions for patients. This principle underpins a healthy skepticism from some clinicians when learning about new approaches and technologies, such as artificial intelligence (AI), that claim to improve patient care.

In my conversations with other clinicians, I sometimes encounter a wariness that AI could one day replace us, which could negatively affect quality patient care. This is why trust and evidence are essential to incorporating AI into medical practice. But that trust and evidence stems from rich involvement from clinicians themselves.

TidalHealth, a health system serving the Delmarva Peninsula, a peninsula between the Chesapeake Bay and the Atlantic Ocean shared by the states of Delaware, Maryland and Virginia, is successfully integrating AI into its clinical workflows. The health system has taken a proactive, thoughtful and – most importantly – ongoing journey to adoption.

 Two critical leaders in TidalHealth’s journey are John Jordan, PharmD, BCPS, Senior Director of Pharmacy Services, and Mark D. Weisman, MD, MBA, Chief Medical Information Officer.

Based on my experience with TidalHealth, the day-to-day challenges I experience as a practicing radiologist, the feedback I receive from my fellow clinicians and the research that Watson Health has conducted on the topic, I believe there are three guiding principles hospitals can follow as they begin to build up their AI capabilities.

Trustworthy AI begins with projects that address real-world challenges and enhance clinical processes.

“AI will establish more trust with physicians when it solves the challenges we’re actually struggling with. For example, when I see a patient for abdominal pain in the office, I need to find if they’ve had endoscopies, colonoscopies, MRIs, lab work, and any other parts of the medical record that can help me diagnose that abdominal pain. If there’s an AI tool that searches multiple data bases and pulls those records for me into one spot, that’s the type of problem I need help with.” – Dr. Weisman

For example, integrating an AI-powered clinical decision support tool into the right part of TidalHealth clinicians’ EMR workflow has made the tool easier to use and increased the number of searches ten-fold. Time studies also revealed that 73 percent of AI-assisted searches at the health system provided answers in less than one minute, saving up to three minutes over other search methods.

Emerging research also backs up TidalHealth’s real-world results. One recent study

 found that AI can help radiologists in one of their most important, but time consuming, manual tasks – finding and extracting all relevant information within a patient’s EMR during an exam. In the study, clinicians manually created a list of 1,385 key medical terms they would use to find relevant patient information. Researchers used natural language processing, a form of AI, to expand that list to nearly 30,000 by suggesting clinically or semantically relevant terms. Radiologists reviewed the broader list of terms and validated 97.32 percent of terms as useful and relevant.

Clinician involvement in the development and training of AI is imperative.

“As an early adopter, I was part of development efforts around IBM Micromedex with Watson. The results were not always great in the early days of testing. But using feedback from clinicians, that algorithm learned over time. I watched it get better and better with every iteration.” – Dr. Jordan

Not all AI algorithms are created equal. Clinicians want assurance that they are using well-trained, mature, non-biased AI. Using a balanced scorecard during development can help teams keep an eye on the big-picture strategy while also helping them follow the right processes. And it’s important to ask the right questions up front, such as: How was the algorithm developed and trained to date? What kind of diversity was in the data set? Who published the data and looked for bias? What about security protocols?

Data scientists, clinicians and researchers at Watson Health Imaging are exploring new ways to train AI, and there are some promising results. For example, one study

 used a two-stage pipeline to detect pulmonary embolus (PE) with a model that used sparsely annotated chest CT images with a high level of performance (AUC .94 validation set, AUC .85 test set). Input from radiologists was incredibly important to this work and other development efforts. When we developed IBM Patient Synopsis, for example, we worked with nearly 100 radiologists to determine the information they would find helpful at the time of interpretation.

Clinicians will embrace and celebrate AI when they see for themselves how it can augment their capabilities.

“Think about all the manual tasks physicians are being asked to do these days – like capturing quality indicators, keeping up with the latest evidence, looking through databases to pull records together for a patient – imagine if we didn’t have to do all that alone? AI is something that can help us do more than we did in the past. It’s here to help us, not to replace us.” – Dr. Jordan

Clinician involvement in developing and training AI algorithms is valuable, but finding accurately annotated, timely and diverse data sets can be challenging. When we look at the field of radiology, for example, identifying large datasets of medical images acquired in diverse settings, from a variety of equipment manufacturers that have been expertly annotated by clinicians of varied training and experience, creates a high bar.

Additionally, clinicians often provide rich information, but that data often resides in unstructured clinical notes. This means that key areas of documentation – such as a problem list in the EMR, an admission note or a discharge summary – may not reflect this wealth of insights.

Furthermore, it’s been said that “diseases don’t read textbooks.” In just the chest, for instance, think about the myriad ways in which a pulmonary nodule, emphysema, or a pulmonary embolus might appear on a CT, which might have been acquired at thick or thin slices, with or without contrast, or early or late in enhancement.

 indicates that AI, in the form of automated text analysis, can help clinicians detect relevant information and discrepancies held within unstructured and annotated notes. Using 1,323 unstructured clinical notes annotated by 46 clinicians to create 5,372 annotated notes, an AI algorithm detected disease concepts with 0.94 precision and detected discrepancies in the information with 0.98 precision. An application of these types of tools within EMRs could lead to more accurate, complete, and updated patient records.

AI may never replace clinicians, but it might be more accurate to predict that clinicians that use AI could one day replace clinicians that don’t. “It has to be a partnership – the clinician and AI, working hand-in-hand,” Dr. Jordan said. “If we do that, these tools will make us better.”

For more coverage based on industry expert insights and research, subscribe to the Diagnostic Imaging e-Newsletter 

TidalHealth results from EMR integration from a 2020 case study, 

“IBM Micromedex: Improving efficiency and care with AI”

 Automatic Patient Data Summarization for Radiologists. Jadhav A et al. Presented at the 2019 RSNA Conference

 Pi-PE: A Pipeline for Pulmonary Embolism Detection Using Sparsely Annotated 3D CT Images. Rajan D. et al. 

Proc Machine Learning for Health NeurIPS Workshop, PMLR

 “Improving the Path from Diagnoses to Documentation: A Cognitive Review Tool for Clinical Notes and Administrative Records.” Guo Y et al. 

David Gruen, MD, MBA, FACR - Chief Medical Officer, IBM Watson Health Imaging

Articles

Personalizing Breast Cancer Risk Assessment

Achieving Real-World Success with AI