Topic

Artificial Intelligence in Healthcare

Presenter Bio

Rajendra Aldis, MD is the Associate Medical Director of Research Informatics at Cambridge Health Alliance (CHA) and an Instructor in Psychiatry at Harvard Medical School. He provides direct patient care as a board certified psychiatrist in CHA’s Primary Care Integrated Behavioral Health Program. As a physician informaticist in the CHA IT department, he has a leadership role in developing CHA’s research informatics and predictive analytics capacity. Dr. Aldis is also a clinician researcher in the CHA Health Equity Research Lab. where his research interests include the application of machine learning and electronic health record data to assess and mitigate health disparities. Dr. Aldis received his MD from Dartmouth Medical School and a Master of Science in Computer Science from Northeastern University. He completed residency in adult psychiatry at Cambridge Health Alliance/Harvard Medical School and completed his fellowship training in global mental health delivery at Harvard Medical School/Partners in Health.

Learning Objectives

• Describe AI and its subtypes

• Describe the uses of AI in healthcare

• Identify the challenges of AI in healthcare

• Evaluate the suitability of an AI model for deployment in a healthcare setting

Additional resources (pre-readings, readings, links, etc.)

Kocak, B., Kus, E. A., & Kilickesmez, O. (2021). How to read and review papers on machine learning and artificial intelligence in radiology: a survival guide to key methodological concepts. European Radiology, 31(4), 1819–1830. https://doi.org/10.1007/s00330-020-07324-4

Grzenda, A., Kraguljac, N. V., McDonald, W. M., Nemeroff, C., Torous, J., Alpert, J. E., … Widge, A. S. (2021). Evaluating the Machine Learning Literature: A Primer and User’s Guide for Psychiatrists. American Journal of Psychiatry, appi.ajp.2020.2. https://doi.org/10.1176/appi.ajp.2020.20030250

Obermeyer, Z., Powers, B., Vogeli, C., & Mullainathan, S. (2019). Dissecting racial bias in an algorithm used to manage the health of populations. Science (American Association for the Advancement of Science), 366(6464), 447–453. https://doi.org/10.1126/science.aax2342

The purpose of this training is to describe the ways in which measurement-based care can be used as a communication and clinical decision support tool in youth mental health care.

Dynamic Treatment Regimes

Dr. Phil Wang

The purpose of this training is to explore how we could potentially implement lessons learned from the e-STORY center, to create a network of Learning Health Systems throughout the U.S.

The learning objectives are to:

1. Understand how learning health systems can continuously improve access, quality, equity and outcomes.

2. Understand how to scale lessons learned from e-STORY, to establish national learning health systems.The purpose of this training is to explore how we could potentially implement lessons learned from the e-STORY center, to create a network of Learning Health Systems throughout the U.S. 

Qualitative Data Collection Individual interviews and Focus groups

Dr. Dharma E. Cortés

The purpose of this interactive workshop is to introduce participants to some qualitative data collection tools: interview guides and focus groups. Designing interview guides, the use of Focus groups will be covered.

The Impact of School-Based Mental Health Support on Adolescent Mental Health at Williamstown High School

Christina Copeland

Christina Copeland is a Williamstown High School, and Rowan College of South Jersey graduate. She completed her associate's degree in arts and science while in high school. Throughout her career, she conducted several research projects. She worked for the Rowan University of Osteopathic Medicine to provide mental health professionals with resources to connect with their patients during the Covid-19 Pandemic. She also researched at Cooper University Hospital in Camden, New Jersey on using alternative treatments such as Indole-3-Carbinol to measure their effectiveness in limiting the growth of cancer cells. At Williamstown High School, she conducted a study to measure the effectiveness of mental health programs on student mental health. Currently, She is a Karsh Stem Scholar Biology student at Howard University. Her goal upon graduation is to complete an MD/Ph.D. and become a researcher.

NIH Budgeting

Angela Orangio

Qualitative Analysis - Thematic Coding & Analysis

Dr. Dharma Cortes

Dr. Dharma E. Cortés has been conducting community-based research with Latinos in the U.S. for more than 25 years, focusing on acculturation, health, mental health, obesity prevention, and access to healthcare. She has made major contributions to the understanding of the process of acculturation, cultural, language, and literacy issues among Latinos in the United States through several of her publications and research activities. As a public health researcher, she has devoted her professional career to study and address health disparities. She received a Ph.D. in Medical Anthropology from Harvard University, and she is an Instructor at Harvard Medical School’s Department of Psychiatry and Senior Scientist and Instructor at the Health Equity Research Laboratory at Cambridge Health Alliance/Harvard Medical School. She is also the Director of Latino Projects at Environment & Health Group, and is a co-founder of The Philanthropy Connection.

Casual Inference Approaches for Binary & Multi-Valued Treatments: A Brief Introduction

Dr. Sharon-Lise Normand

Sharon-Lise Normand, Ph.D., is S. James Adelstein Professor of Health Care Policy (Biostatistics) in the Department of Health Care Policy at Harvard Medical School and Professor in the Department of Biostatistics at Harvard School of Public Health. Her research focuses on the development of statistical methods for health services and outcomes research, including the evaluation of medical devices, causal inference, provider profiling, evidence synthesis, item response theory, and latent variables analyses. Her application areas include cardiovascular disease, severe mental illness, medical device safety and effectiveness, and medical technology diffusion. Dr. Normand is Director of the Medical Device Epidemiology Network’s Methodology Center, and was Director of the Massachusetts Data Analysis Center (2002-2017). She was a consultant to and served on the US FDA’s Circulatory System Devices Advisory Panel, and served on the Medicare Evidence Development and Coverage Advisory Committee for the US Centers for Medicare and Medicaid Services. Dr. Normand was the 2010 President of the Eastern North American Region of the International Biometrics Society and inaugural Vice Chair of the Patient Centered Outcomes Research Institute’s Methodology Committee (2010-2012). She earned her Ph.D. in Biostatistics, M.Sc. and B.Sc. in Statistics, and completed a post-doctoral fellowship in Health Care Policy. In 2011, Dr. Normand was awarded the ASA Health Policy Statistics Section’s Long Term Excellence Award; in 2012, the American Heart Association’s Distinguished Scientist Award; in 2013, elected to the Society for Research Synthesis Methodology; in 2015, awarded the L. Adrienne Cupples’ Award for Excellence in Teaching, Research, and Service in Biostatistics from Boston University; in 2017, was awarded the American Heart Association Council on Quality of Care and Outcomes Research Outstanding Lifetime Achievement Award; in 2018, awarded Mosteller Statistician of the Year by the American Statistical Association Boston Chapter; and in 2019, elected Fellow to the American Association for the Advancement of Science.

Identifying & Treating Early Psychosis

Dr. Marcela Horvitz-Lennon

Marcela Horvitz-Lennon is a senior physician scientist at the RAND Corporation and a faculty member of the Pardee RAND Graduate School. She is an associate professor of psychiatry (part-time) at Harvard Medical School and a practicing psychiatrist at Cambridge Health Alliance. Previously, she was affiliated with the University of Pittsburgh Medical School and the Chilean Ministry of Health. Her research focuses on the quality and value of health care received by adults with serious mental illnesses. Much of her work has been public sector-related. Horvitz-Lennon has conducted research on racial/ethnic and geographic disparities in care; Medicaid and federal health care policy; utilization patterns and safety of antipsychotic drugs; underuse and overuse of mental health interventions; integration of physical and mental healthcare; diffusion of mental health innovations; and global mental health. She serves as principal investigator or co-investigator on NIH (NIMH/NIMHD) and other federally-funded research. Through her clinical position, Horvitz-Lennon is actively involved in medical student education and resident training. She has also mentored pre-doctoral students and served as member/director of Ph.D. dissertation committees. Horvitz-Lennon earned her M.D. in Santiago, Chile, and a Master's degree in public health at Johns Hopkins University School of Public Health. She completed her psychiatric residency training at the University of Maryland Medical School, and a fellowship in Community Psychiatry at Johns Hopkins Medical School.

The Adaptive Measurement of Suicidality and Risk with Dr. Robert Gibbons

Dr. Robert Gibbons

Dr. Gibbons will discuss adaptive testing in which different individuals may receive different scale items that are targeted to their specific impairment level. In particular, he will discuss how the shift in paradigm is from small fixed-length tests with questionable psychometric properties to large item banks from which an optimal small subset of items is adaptively drawn for each individual, targeted to their level of impairment. The focus of today’s presentation is on the adaptive measurement of suicidality and risk prediction and stratification.