Collaboration Stories
The purpose of this series is to tell the story of long-lasting, as well as emergent, stories of collaboration among clinicians and methodologists, content experts, and engineers, who have successfully worked on joint projects at the intersection of AI and health. Such collaborations are at the center of e-HAIL’s mission, and we offer these stories as a way of inspiring collaboration in other researchers.
“Increasing Diversity in Biomedical Research”
Cornelius James, M.D.
Assistant Professor, Department of Internal Medicine
This month, we talked to e-HAIL member Cornelius James, MD, who was awarded an NIH Administrative Supplement Award to study patient and clinician attitudes towards the use of an app designed to help patients decrease sodium intake and lower blood pressure. This award is in conjunction with the NHLBI-funded LowSalt4Life study (A Just-In-Time Adaptive Mobile Application Intervention To Reduce Sodium Intake and Blood Pressure in Hypertensive Patients) led by Mike Dorsch, MS, and Brahmajee Nallamothu, MD.
Cornelius James, MD, is a Clinical Assistant Professor of Internal Medicine, Pediatrics, and Learning Health Sciences who was named a National Academy of Medicine (NAM) Inaugural Scholar in Diagnostic Excellence in 2021 and was the 2022 recipient of the preclinical Kaiser Permanente award, the most prestigious faculty teaching award given by the medical school. The collaboration between him and Brahmajee Nallamothu, MD, MPH, Stevo Julius Research Professor of Cardiovascular Medicine, started almost two years ago when James Woolliscroft, one of James’ mentors, connected them for a MiCHAMP session. Nallamothu was very supportive during James’ NAM fellowship and became a mentor, helping James further his threefold interest in using AI to benefit patients; developing educational materials for clinicians to better understand and engage with AI; and to have an impact when it comes to implementation.
As a result of working with Nallamothu and others, James was able to submit a successful proposal to the National Heart, Lung, and Blood Institute (NHLBI), which participates in the NIH program providing research supplements to “promote diversity in health-related research”. James’ project, Clinician and Patient Attitudes toward a Prescribed Dietary Sodium Just-In-Time Adaptive Intervention: A Mixed Methods Study, builds upon the Aims of the LowSalt4Life study led by Nallamothu and Mike Dorsch, PharmD, MS, Associate Professor of Clinical Pharmacy.
Asked to describe this project, James explains: “LowSalt4Life looks at a mobile application that includes AI-based software to provide “just-in-time” personalized information to patients about sodium intake. These kinds of mHealth applications are called JITAIs, which stands for Just-In-Time Adaptive Intervention. Early work on the Dorsch/Nallamothu “parent grant” for my projects showed that this JITAI reduced dietary sodium intake over the short-term. However, we don’t know very much about features of this mHealth app that will make clinicians more likely to prescribe it, or the features that will make patients more likely to begin and continue to use it. That’s where my research comes in. It will contribute to our knowledge base about digital health tools, where we currently understand little about how clinicians and patients think of utilizing these tools in their routine care. My goal is to understand and ultimately address barriers to clinicians and patients using novel technologies.”
James is pleased to see the focus on fostering diversity and addressing underrepresentation in the scientific research workforce as key components of the NIH “Strategy to identify, develop, support and maintain the quality of our scientific human capital.” Not only does the Diversity Supplement award allow him to focus on research that he’s passionate about, but it also furthers his goal of serving as a mentor for emerging researchers from historically excluded groups. James notes: “Diversity is extremely important on different levels. We need to have various perspectives on health care and clinical care when it comes to clinicians; we need the same diversity in the context of medical education, and finally in the research space. It’s tricky because the percentage of Black, Native American, and Hispanic physicians at Academic Medical Centers is so small to begin with, and the percentages for clinician researchers are even smaller–and even smaller still when it comes to clinician researchers interested in AI and Machine Learning. Yet diverse perspectives are crucial and allow for certain problems to even be addressed in the first place.”
Diversity and equity are also addressed as themes in James’ research project for the supplement award. “One of the aspects I’m looking at is: to whom are clinicians most likely to prescribe these mHealth apps, and are there any disparities by racial or ethnic group. Based on historical evidence, such a scenario is not unlikely, and if that’s the case, then we need to begin to understand and address this now before these technologies become ubiquitous in clinical practice. ,” notes James. At the same time, he has found it eye-opening to learn from U-M researchers who work in Low and Middle Income Countries (LMICs) how prevalent, for example, cell phones are. He explains, “there’s definitely the issue of the digital divide also, but it’s important to realize that we often make assumptions about certain people having access to some technologies like cell phones while others don’t. And those assumptions might prove to be wrong, so we need to be careful.”
Having mentors who are willing to invest in you, and being willing to invest in yourself, are key to becoming a successful researcher in the biomedical field more broadly, and in AI/ML and health research in particular, according to James. “The first step is expressing an informed interest in a specific field. AI/ML seems very fun and exciting, but it took me a while to realize that I was interested in doing research in this space, and it took some immersion in the space to realize this. Even if the interest and passion are there, it can be difficult to navigate a large academic institution like U-M–and for underrepresented individuals it can be even more daunting when you are not seeing very many people that look like you working in this space. step. Mentoring helps, and we have wonderful mentors at U-M–but they’re not always easy to find. Once you find them, they are very good at helping you identify next steps and suggesting to you what questions you need to ask and you didn’t even know to ask. And certainly a lot of work falls on the individual also, from learning all the relevant background information to putting in the work and being productive. I don’t want to oversimplify all that it takes.“
In addition to his current work with patients and clinicians on barriers to the use of mHealth tools in routine care, James also remains committed to his educational work in addressing the impact that AI/ML will have in clinical reasoning and medical education curricula. His team is currently working with the U-M Center for Academic Innovation on the Data Augmented Technology Assisted Medical Decision-making (DATA-MD) curriculum, which is designed to teach clinicians to use AI/ML to augment diagnostic decision making. More recently, he has been working with the American Medical Association to develop an AI/ML in Health Care curriculum. Both of these curricula, which will become available in the second half of 2023, will be available to anybody, anywhere in the world. His hope is that this broad availability and the diversity of learners engaging with these materials may lead to new questions being asked, new research being proposed, or just “prod people who might have not otherwise heard or know about the topic of AI/ML to read and learn more about the topic.”