2024 Biomedical Informatics Seminars
December 6, 2024
Griffin Weber, MD, PhD, Associate Professor of Medicine and Biomedical Informatics,Harvard Medical School, Beth Israel Deaconess Medical Center. Federated Clinical Data Research Networks.
Abstract: Federated clinical data research networks enable investigators to leverage the electronic health record (EHR) data from multiple organizations for clinical studies, without requiring sites to share patient-level data. Instead, queries or analysis code are distributed to sites to run locally, and only aggregate counts or statistical summaries are returned to the investigators. This protects patient privacy and lowers barriers to participation in the network. This presentation will describe how several consortia are using federated clinical data networks and discuss methods of addressing data quality and biases in EHR data, including data harmonization, computed phenotypes, and managing patient overlap between organizations in the network.
Bio: Griffin Weber, M.D., Ph.D., is an Associate Professor of Medicine and Biomedical Informatics at Beth Israel Deaconess Medical Center (BIDMC) and Harvard Medical School (HMS). He is also the Faculty Lead of Harvard’s Clinical and Translational Science Award (CTSA) Informatics Program and Director of the Biomedical Research Informatics Core (BRIC) at BIDMC. Dr. Weber helped develop Informatics for Integrating Biology and the Bedside (i2b2), an open-source platform for query and analysis of clinical data, and the Shared Health Research Information Network (SHRINE), which connects i2b2 and OMOP databases across organizations to form federated data networks. Dr. Weber is a Fellow of the American College of Medical Informatics (FACMI), in recognition of his contributions to the field of medical informatics.
Abstract: Federated clinical data research networks enable investigators to leverage the electronic health record (EHR) data from multiple organizations for clinical studies, without requiring sites to share patient-level data. Instead, queries or analysis code are distributed to sites to run locally, and only aggregate counts or statistical summaries are returned to the investigators. This protects patient privacy and lowers barriers to participation in the network. This presentation will describe how several consortia are using federated clinical data networks and discuss methods of addressing data quality and biases in EHR data, including data harmonization, computed phenotypes, and managing patient overlap between organizations in the network.
Bio: Griffin Weber, M.D., Ph.D., is an Associate Professor of Medicine and Biomedical Informatics at Beth Israel Deaconess Medical Center (BIDMC) and Harvard Medical School (HMS). He is also the Faculty Lead of Harvard’s Clinical and Translational Science Award (CTSA) Informatics Program and Director of the Biomedical Research Informatics Core (BRIC) at BIDMC. Dr. Weber helped develop Informatics for Integrating Biology and the Bedside (i2b2), an open-source platform for query and analysis of clinical data, and the Shared Health Research Information Network (SHRINE), which connects i2b2 and OMOP databases across organizations to form federated data networks. Dr. Weber is a Fellow of the American College of Medical Informatics (FACMI), in recognition of his contributions to the field of medical informatics.
November 15, 2024
Jejo Koola, MD, Associate Professor of Medicine UC San Diego Health Dept. of Biomedical Informatics University of California San Diego, "Modeling Learning Effects for Medical Device Safety Surveillance Using Machine Learning."
Abstract: Hands-on experience with implantable medical devices significantly improves clinical outcomes through learning effects. The FDA has stressed the importance of increased post-market surveillance of drugs and medical devices. However, contemporary post-market surveillance strategies for medical devices currently do not separate risk attributable to the device itself versus risk attributable to the operator. Robust medical device safety surveillance that can provide information regarding the etiology of the safety signal requires accurate adjustments for the complex relationships among device characteristics, learning by physicians and institutions, and patient clinical heterogeneity.
Bio: I am a practicing hospital medicine physician with ten years practicing experience in multiple medical centers. I focus on treating multi-morbid patients hospitalized for a variety of conditions including sepsis, organ failure, and chronic kidney, heart, or liver disease. During my fellowship in Biomedical Informatics at the Department of Veterans Affairs in conjunction with a master’s degree from Vanderbilt University I have gained formal skills in database management, data mining, information retrieval, software engineering, and natural language processing. As part of the R2D2 Consortium, I helped develop processes to aggregate and harmonize healthcare data from twelve institutions regarding Coronavirus Disease-2019 using the Observational Medical Outcomes Partnership (OMOP) Common Data Model. I am currently leading multiple studies diagnosing cognitive and frailty complications of chronic illness, particularly cirrhosis, via digital phenotyping. These studies involve gold standard testing within a study clinic environment for cognitive, mood, and frailty followed by passive monitoring in the outpatient setting using smartphone kinematic metadata as well as actigraphy data from a commercial grade actigraph. Additionally, I constructed machine learning models to phenotype Hepatorenal Syndrome (a complication of cirrhosis) using Natural Language Processing. I have been working on ways to use observational cohort data to predict decompensation in patients with significant medical comorbidities.
November 1, 2024
Amy Sitapati, MD, Clinical Professor, Division of Biomedical Informatics, Division of General Internal Medicine Chief Medical Information Officer, Population Health, UCSDH Interim Chief, Division of Biomedical Informatics, UCSD Interim Chair, Department of Biomedical Informatics, "Solving Healthcare Delivery Problems with Data Science: The Friedman Risk Score: A Custom Primary Care Score Predicting Consumption."
Abstract: Have you wondered how to create systems that build from good little data sets to drive improved clinical care? This lecture will review a heart of clinical data and discuss where we have come from and the future possibilities based on registries, metrics, and more to promote improved health and equity in our world.
Bio: Amy M. Sitapati, MD, is Professor of Medicine, Chief of the Division of Biomedical Informatics, Chair of the UC San Diego Health Department of Biomedical Informatics, and a primary care physician at UC San Diego Health. She is Medical Director of Internal Medicine in La Jolla and leads the population health team that focuses on how clinical informatics can be used to improve the quality of care. Dr. Sitapati is nationally recognized for her work in primary care. She has more than ten years of experience providing high-quality, patient-centered care in ambulatory settings, and strives to build multidisciplinary teams that effectively work together to improve patient care coordination. In support of patient participation in chronic disease management, Dr. Sitapati combines evidence-based medicine with patient empowerment, prevention methods, and alternative medicine (e.g., Kelee meditation) to help patients achieve their best health. She also has expertise in providing gender-affirming care to transgender and nonbinary patients. Dr. Sitapati first joined UC San Diego Health in 2001 following completion of her residency. In 2005, she established the Center for Infectious Disease Management and Research (CIDMAR) at Howard University, a center dedicated to providing culturally competent, state-of-the-art HIV medical care to its 225 patients. In 2007, she met with First Lady, Mrs. Laura Bush, to discuss the first hospital-wide, routine HIV screening program to be implemented in the nation. In 2015, Dr. Sitapati assumed the role of medical director of internal medicine in La Jolla. She also leads a population health team that focuses on using computer systems to improve the quality of care. In 2022 she was recognized for her humanistic approach to medicine and delivery of care for patients and their families by receiving the Leonard Tow Humanism in Medicine Award. Dr. Sitapati believes bringing humanism into the practice of medicine is the highest pinnacle in health care delivery, benefiting both patients and health care colleagues. As a professor of medicine her clinical research has been related to patient-centered care, quality improvement, and meditation. Dr. Sitapati serves as an instructor for medical students and residents. She completed her medical residency training at UC San Diego School of Medicine, and earned her medical degree from Case Western Reserve University, School of Medicine, in Cleveland, Ohio. Dr. Sitapati is board certified in internal medicine and clinical informatics.
October 18, 2024
Florence Bourgeois, MD, MPH, Associate Professor of Pediatrics, Director, Harvard-MIT Center for Regulatory Science, Harvard Medical School, Boston, MA. Postmarketing Surveillance for Medical Devices Using EHR data: An Analysis of EVAR Devices.
Bio: Dr. Bourgeois, M.D., M.P.H. is Associate Professor of Pediatrics at Harvard Medical School and Director of the Harvard-MIT Center for Regulatory Science. She is a clinician-scientist at Boston Children’s Hospital, where she serves as Scientific Director of the institutional PrecisionLink Biobank for Health Discovery and directs the Initiative in Pediatric Therapeutics and Regulatory Science. At Harvard Medical School, she directs a fellowship program in regulatory science and leads cross-disciplinary projects across Harvard-affiliated institutions. In this capacity, she has partnered with regulatory agency scientists on projects analyzing regulatory processes and developing novel approaches and statistical tools to support evaluation of FDA-regulated products. Outside the U.S., Dr. Bourgeois has served as an Expert Visitor to the European Medicines Agency to analyze the EU’s pediatric drug legislation and is the recipient of an Innovation in Regulatory Science Award from the Burroughs Wellcome Fund to investigate the impact of drug and device policies on product access and use in pediatric populations. Her clinical training and experience are in pediatrics and pediatric emergency medicine.
Florence Bourgeois, MD, MPH, Associate Professor of Pediatrics, Director, Harvard-MIT Center for Regulatory Science, Harvard Medical School, Boston, MA. Postmarketing Surveillance for Medical Devices Using EHR data: An Analysis of EVAR Devices.
Bio: Dr. Bourgeois, M.D., M.P.H. is Associate Professor of Pediatrics at Harvard Medical School and Director of the Harvard-MIT Center for Regulatory Science. She is a clinician-scientist at Boston Children’s Hospital, where she serves as Scientific Director of the institutional PrecisionLink Biobank for Health Discovery and directs the Initiative in Pediatric Therapeutics and Regulatory Science. At Harvard Medical School, she directs a fellowship program in regulatory science and leads cross-disciplinary projects across Harvard-affiliated institutions. In this capacity, she has partnered with regulatory agency scientists on projects analyzing regulatory processes and developing novel approaches and statistical tools to support evaluation of FDA-regulated products. Outside the U.S., Dr. Bourgeois has served as an Expert Visitor to the European Medicines Agency to analyze the EU’s pediatric drug legislation and is the recipient of an Innovation in Regulatory Science Award from the Burroughs Wellcome Fund to investigate the impact of drug and device policies on product access and use in pediatric populations. Her clinical training and experience are in pediatrics and pediatric emergency medicine.
October 11, 2024
Farhan Tanvir, PhD, Lecturer, Department of Computer Science, Georgia State University. Heterogeneous Graph Learning and Application to Biomedicine.
Abstract: Computational biomedicine is a critical field for improving our understanding of biological systems and drug discovery and development. Existing computational models address several problems on this domain such as drug-drug interaction (DDI) prediction, drug-target interaction prediction, drug-disease association prediction, and drug-target-disease association prediction. Heterogeneous biomedical graphs are gaining attention to address different problems because of their ability to model distinct biomedical entities including drug and protein and ability to capture complex relationships between these distinct entities.
Farhan Tanvir, PhD, Lecturer, Department of Computer Science, Georgia State University. Heterogeneous Graph Learning and Application to Biomedicine.
Abstract: Computational biomedicine is a critical field for improving our understanding of biological systems and drug discovery and development. Existing computational models address several problems on this domain such as drug-drug interaction (DDI) prediction, drug-target interaction prediction, drug-disease association prediction, and drug-target-disease association prediction. Heterogeneous biomedical graphs are gaining attention to address different problems because of their ability to model distinct biomedical entities including drug and protein and ability to capture complex relationships between these distinct entities.
Bio: Farhan Tanvir is a lecturer in the Department of Computer Science at Georgia State University. His research focuses on graph mining with applications to bioinformatics/computational biomedicine. Understanding the intricate relationships between biological entities, including drugs, proteins, pathways, substructures, ATC codes and diseases, is crucial for various biomedical applications such as drug-drug interaction (DDI) prediction, drug development and repurposing, and patient treatment recommendation. He designs heterogeneous networks to model these intricate relations. He has been involved in several scientific projects related to bioinformatics and computational biology and has published in KDD, ACM BCB, ICDE, CIKM, and Frontiers in Big Data.
October 4, 2024
Christian Dameff, MD, MS, Assistant Professor of Emergency Medicine, Biomedical Informatics, & Computer Science, Medical Director of Cyber Security, University of California San Diego Health. Hackers and Ransomware and Data Breaches, Oh My!
Christian Dameff, MD, MS, Assistant Professor of Emergency Medicine, Biomedical Informatics, & Computer Science, Medical Director of Cyber Security, University of California San Diego Health. Hackers and Ransomware and Data Breaches, Oh My!
Abstract: Ransomware attacks affecting healthcare delivery organizations have increased in frequency and sophistication. Disruptions to clinical care workflows following ransomware infection may result in degradation of patient care, particularly for time sensitive medical conditions like sepsis, heart attack, or stroke. They often result in large financial losses from impacted billing and regulatory fines. Come learn about the state of healthcare cybersecurity and how you can have a significant impact in this emerging field of healthcare cybersecurity.
Bio: Dr. Christian Dameff is an assistant professor of Emergency Medicine, Biomedical Informatics, and Computer Science (affiliate) at the University of California San Diego. He co-directs the UCSD Center for Healthcare Cybersecurity. At UCSD Health he was hired as the nation’s first Medical Director of Cyber Security. Dr. Dameff is also a hacker and security researcher interested in the intersection of healthcare, patient safety, and cybersecurity. He has spoken at some of the world’s most prominent Cyber Security forums including DEFCON, RSA, Blackhat, Derbycon, and BSides and is one of the cofounders of the CyberMed Summit. Published cybersecurity topics include hacking 911 systems, HL7 messaging vulnerabilities, and malware.
September 27, 2024
Haoran Niu, PhD, Postdoctoral Research Associate, Division of Computational Sciences and Engineering
Oak Ridge National Laboratory, Oak Ridge, Tennessee. Towards effective anomaly detection in electronic health records.
Haoran Niu, PhD, Postdoctoral Research Associate, Division of Computational Sciences and Engineering
Oak Ridge National Laboratory, Oak Ridge, Tennessee. Towards effective anomaly detection in electronic health records.
Abstract: While modern complex computer systems provide enormous benefits to our daily lives, the increasing complexity of these large-scale systems also makes them more susceptible to unexpected software malfunctions and malicious attacks. This is especially true for Health Information Technology (HIT), which has revolutionized healthcare delivery by making it more efficient, effective, and accessible. Nevertheless, the widespread adoption of HIT has introduced new challenges related to ensuring system reliability and security. As a result, the development of novel algorithms and frameworks to detect anomalies in such systems has become increasingly important for enhancing patient safety and improving the efficiency and effectiveness of healthcare services. This seminar presents one of the recent developments in this area, focusing on detecting anomalous event sequences on Electronic Health Records (EHR) data using Natural Language Processing (NLP) Models. The approach, EHR-BERT (Bidirectional Encoder Representations from Transformers), leverages advanced natural language processing techniques to learn patterns bidirectionally for EHR sequence anomaly detection tasks, resulting in improved accuracy and reduced false negatives. Additionally, the proposed approaches have the potential to be applied to other complex computer systems beyond HIT, where anomaly detection is critical for maintaining system reliability and security.
Bio: Haoran Niu is a Postdoctoral Research Associate in the Computational Sciences and Engineering Division at Oak Ridge National Laboratory (ORNL). Haoran received his Ph.D. degree from the University of Tennessee, Knoxville in Computer Engineering in 2023. During his PhD program, he also worked as a visiting researcher at ORNL in 2019~2023. His research aims to tackle critical challenges in HIT systems, focusing on safeguarding patient data privacy and enhancing the security of sensitive information in healthcare environments. In addition, Haoran also focuses on topics such as the system reliability, predictive analytics, and data-driven decision-making, and contributes to the development of innovative solutions and strategies that enhance the efficiency, sustainability, and resilience of urban environments.
Bio: Haoran Niu is a Postdoctoral Research Associate in the Computational Sciences and Engineering Division at Oak Ridge National Laboratory (ORNL). Haoran received his Ph.D. degree from the University of Tennessee, Knoxville in Computer Engineering in 2023. During his PhD program, he also worked as a visiting researcher at ORNL in 2019~2023. His research aims to tackle critical challenges in HIT systems, focusing on safeguarding patient data privacy and enhancing the security of sensitive information in healthcare environments. In addition, Haoran also focuses on topics such as the system reliability, predictive analytics, and data-driven decision-making, and contributes to the development of innovative solutions and strategies that enhance the efficiency, sustainability, and resilience of urban environments.
June 7, 2024
Spyros Kitsiou, PhD, Associate Professor, Biomedical and Health Information Sciences, Associate Chief Research Information Officer, University of Illinois at Chicago. "iCardia4HF trial: Using commercially available mHealth technoligies to deliver patient-centered self-care intervention in patients with chronic heart failure".
Abstract: Heart failure (HF) is one of the most frequent principal diagnoses for hospitalization and a leading cause of death in the United States. Many of these hospital readmissions are the result of insufficient self-care, which is manifested in patients with heart failure as nonadherence to prescribed medications, daily self-monitoring of symptoms, and sodium-restricted diet. Consumer-grade mobile health (mHealth) technologies such as mobile apps, wearable activity trackers, and other connected health devices that are commercially available hold promise for promoting heart failure self-care and expanding intervention delivery. However, their efficacy remains largely underexplored. This talk aims to present key findings from the development and evaluation of a patient-centered intervention (iCardia4HF) that integrates multiple commercially available mHealth apps and connected health devices (e.g., Fitbit, Withings) with a program of individually tailored text messages through a novel digital health platform to improve self-care adherence in patients with heart failure.
Bio: Dr. Spyros Kitsiou is Associate Professor in the Department of Biomedical and Health Information Sciences and Director of the mHealth Innovation Lab at the University of Illinois at Chicago. He is also Associate Chief Research Information Officer in the Office of Vice Chancellor for Research. With a background in computer science, biomedical informatics, and behavioral medicine, he specializes in the development and evaluation of mobile health (mHealth) technology interventions to promote healthy lifestyle behaviors and improve self-management of chronic conditions such as heart failure, hypertension, asthma, and chronic obstructive pulmonary disease. He has experience in designing and conducting randomized controlled trials and other experimental studies of complex mHealth interventions involving smartphones, mobile health apps, text messages, wearable activity tracking devices, and other connected health technologies. Dr. Kitsiou has secured more than $5 million in NIH funding as principal investigator to test the efficacy of various innovative mHealth technologies and interventions that address significant health problems and disparities among racially/ethnically and socioeconomically diverse adult populations. He has also created a novel digital health research platform (iCardia) that enables researchers to remotely collect large volumes of patient-generated health data and deliver biobehavioral interventions using commercial mHealth apps and devices. iCardia has been used in more than 15 NIH-funded trials. Dr. Kitsiou's research has appeared in high impact factor clinical and health informatics journals including the Journal of the American College of Cardiology, Canadian Journal of Cardiology, Journal of Cardiac Failure, Journal of Medical Internet Research, and Journal of the American Medical Informatics Association.
May 31, 2024
Shunpu Zhang, PhD, Professor and Chair, Department of Statistics & Data Science, University of Central Florida. " Large Scale Multiple Hypothesis Testing: Theory and Applications".
Abstract: We propose a new multiple test called the minPOP test and two of its modified versions (the left truncated and the double truncated minPOP tests) for testing multiple hypotheses simultaneously. We show that these tests have multiple testing procedures based on these tests have strong control of the family-wise error rate. A method for finding the p-values for the proposed multiple testing procedures after adjusting for multiplicity is also developed. Simulation results show that the minPOP tests in general have higher global power than the existing well known multiple tests, especially when the number of hypotheses being compared is relatively large. Among the multiple testing procedures we developed, we find that the ones based on the left truncated and double truncated minPOP tests tend to have higher number of rejections than the existing multiple testing procedures. In the case of correlated test statistics, simulation results show that only the double truncated minPOP test is reasonably robust to positively correlated test statistics, while all the other tests seem to be robust to negatively correlated test statistics.
Bio: Dr. Zhang is currently professor and chair of the UCF Department of Statistics & Data Science. He received his Ph.D. in Statistics from the University of Alberta, Canada. Before joining UCF in 2015, he was an assistant/associate professor of statistics at the University of Alaska-Fairbanks and an associate/full professor of statistics at the University of Nebraska, Lincoln.
While at Nebraska he served as a mathematical statistician at National Cancer Institute (NCI). His research at NCI led to the creation of the government website ‘CI*Rank’ under the NCI portal (https://surveillance.cancer.gov/cirank/). The website presents ranked, age-adjusted cancer incidence and mortality rates by state, county, and special regions in the U.S. It has become a major source for researchers and the general public to obtain the information on the health condition of the community in the U.S., and a useful tool to help the government’s policy making and to evaluate the effect of a current policy or healthcare program.
Dr. Zhang’s research interests include general statistical methodology, Bayes and empirical Bayes methodology, bioinformatics, large scale multiple hypothesis testing and its applications, financial portfolio optimization, sampling technology, statistical methods related to influenza virus genotyping and big data analytics.
May 31, 2024
Shunpu Zhang, PhD, Professor and Chair, Department of Statistics & Data Science, University of Central Florida. " Large Scale Multiple Hypothesis Testing: Theory and Applications".
Abstract: We propose a new multiple test called the minPOP test and two of its modified versions (the left truncated and the double truncated minPOP tests) for testing multiple hypotheses simultaneously. We show that these tests have multiple testing procedures based on these tests have strong control of the family-wise error rate. A method for finding the p-values for the proposed multiple testing procedures after adjusting for multiplicity is also developed. Simulation results show that the minPOP tests in general have higher global power than the existing well known multiple tests, especially when the number of hypotheses being compared is relatively large. Among the multiple testing procedures we developed, we find that the ones based on the left truncated and double truncated minPOP tests tend to have higher number of rejections than the existing multiple testing procedures. In the case of correlated test statistics, simulation results show that only the double truncated minPOP test is reasonably robust to positively correlated test statistics, while all the other tests seem to be robust to negatively correlated test statistics.
Bio: Dr. Zhang is currently professor and chair of the UCF Department of Statistics & Data Science. He received his Ph.D. in Statistics from the University of Alberta, Canada. Before joining UCF in 2015, he was an assistant/associate professor of statistics at the University of Alaska-Fairbanks and an associate/full professor of statistics at the University of Nebraska, Lincoln.
While at Nebraska he served as a mathematical statistician at National Cancer Institute (NCI). His research at NCI led to the creation of the government website ‘CI*Rank’ under the NCI portal (https://surveillance.cancer.gov/cirank/). The website presents ranked, age-adjusted cancer incidence and mortality rates by state, county, and special regions in the U.S. It has become a major source for researchers and the general public to obtain the information on the health condition of the community in the U.S., and a useful tool to help the government’s policy making and to evaluate the effect of a current policy or healthcare program.
Dr. Zhang’s research interests include general statistical methodology, Bayes and empirical Bayes methodology, bioinformatics, large scale multiple hypothesis testing and its applications, financial portfolio optimization, sampling technology, statistical methods related to influenza virus genotyping and big data analytics.
May 24, 2024
Adam Rodman, MD, MPH, FACP, Hospitalist at Beth Israel Deaconess Medical Center, Co-director, iMED Initiative at BIDMC, Assistant Professor of Medicine, Harvard Medical School. "Large Language Models, Clinical Reasoning, and Automated Oversight: The Future of Physician Performance".
Abstract: Dr. Rodman will discuss the opportunities for improving clinician reasoning with large language models. He will discuss the current psychological model of clinical reasoning, the evidence base for influencing physician reasoning behaviors, the roles of LLMs, including a review of the literature in this field, and his current work on improvement on reasoning, including developing and validating psychometrics that can be used in automated oversight, as well as human-computer interaction studies.
Abstract: Dr. Rodman will discuss the opportunities for improving clinician reasoning with large language models. He will discuss the current psychological model of clinical reasoning, the evidence base for influencing physician reasoning behaviors, the roles of LLMs, including a review of the literature in this field, and his current work on improvement on reasoning, including developing and validating psychometrics that can be used in automated oversight, as well as human-computer interaction studies.
Bio: Adam Rodman is a general internist and medical educator at Beth Israel Deaconess Medical Center and an assistant professor at Harvard Medical School, where he leads the task force for integration of AI into the medical school curriculum. He is also an associate editor at NEJM AI. His research focuses on medical education, clinical reasoning, integration of digital technologies, and human-computer interaction, especially with AI. His first book is entitled "Short Cuts: Medicine," and he is the host of the American College of Physicians podcast Bedside Rounds.
May 17, 2024
Aliya Bari, PhD Candidate in Applied Ethics, Unversity of Zurich. "Exploring the Future of Healthcare Data: Ethics, Innovation, and Patient Equity".
Abstract: This interdisciplinary dialogue aims to dig deeper into the ethical, social, and practical dimensions surrounding healthcare data access, ownership, and use. Emphasizing practical and theoretical strategies, the seminar seeks to incentivize responsible data sharing, empowering patients as data creators while maintaining ethical standards. The presentation will aim to raise awareness on the topic and explore ethical frameworks for data ownership and control, innovative incentive structures, transparency in data access, and emerging technologies like blockchain and differential privacy.
Bio: Aliya Bari is a Bioethics Fellow and Ph.D. student in Applied Ethics at the University of Zurich. Her research goes beyond theory; it's dedicated to finding practical solutions that protect the rights and well-being of vulnerable individuals amidst the technological rise of data-driven healthcare. By uncovering the disproportionate impact of biased algorithms and commercialization on marginalized communities, she is raising awareness for a shift towards research that amplifies the voices and experiences of those often overlooked. Her work emphasizes the crucial balance between technology enabled medical progress and ethical considerations, particularly for vulnerable populations. With a focused commitment to understanding and addressing the unique challenges they face with healthcare data. She hopes to highlight methodologies to create better patient equity and inclusivity in ethical decision-making processes of systems.
May 10, 2024
Jessica Golbus, MD, MS, Clinical Instructor, Div. of Cardiovascular Medicine, Advanced Heart Failure and Transplant, University of Michigan. "Using Digital Health Technologies in Cardiovascular Innovation".
Abstract: Mobile health technologies have been increasingly used in healthcare for the diagnosis and management of cardiovascular diseases. The talk will focus on an emerging area in the field which is the use of mobile health technologies to deliver just-in-time adaptive interventions (JITAIs), a novel intervention design that uses contextual information from mobile devices to provide in the moment to support to users. The session will provide two examples of recently deployed JITAIs targeting two cardiovascular disease populations: the VALENTINE Study, a JITAI delivered to participants enrolled in cardiac rehabilitation, and the myBPmyLife study, a JITAI delivered to participants with hypertension.
Bio: Jessica Golbus MD, MS is a Clinical Instructor in the Division of Cardiovascular Medicine at the University of Michigan. She received her MD from the University of Michigan and completed her residency in Internal Medicine at the University of Pennsylvania. She then completed her training in General and Advanced Heart Failure and Transplant Cardiology at the University of Michigan. She also received her MS through the University of Michigan School of Public Health. Dr. Golbus is actively engaged in clinical practice in the areas of heart failure, heart transplantation, and mechanical circulatory support. Dr. Golbus’s research focuses on using mobile health technology to improve the delivery of cardiovascular care with a particular interest in how mobile health technologies can be used to promote cardiovascular disease self-management.
March 15, 2024
Mattheus Ramsis, MD, Assistant Professor of Medicine, Diretor, Cardiology Informatics, UCSD Division of Cardiovascular Medicine. "Validation of Cardiovascular Algorithms and Devices."
Mattheus Ramsis, MD, Assistant Professor of Medicine, Diretor, Cardiology Informatics, UCSD Division of Cardiovascular Medicine. "Validation of Cardiovascular Algorithms and Devices."
Bio: I am an Assistant Professor, Cardiologist, and Medical Director of Cardiology Informatics at the University of California, San Diego. I previously trained in internal medicine at Harvard Medical School-Brigham and Women's Hospital with subsequent training in cardiovascular disease, trial design, and preventative cardiology at the University of California, San Francisco where I served as a clinical instructor. Awards include the NIH T-32 award and the BMSF career development award. My previous and ongoing work consists of validating algorithms and devices for cardiovascular disease and developing digital biomarkers. I collaborate with multidisciplinary teams of clinicians, researchers, and engineers to leverage data from wearable devices, biomarkers, and electronic health records to create innovative solutions, improve patient outcomes, and enhance quality of care.
February 23, 2024
Jejo Koola, MD, MS, Associate Professor of Medicine, Division of Biomedical Informatics and Hospital Medicine, Medical Director, Information Systems, University of California San Diego. "Identifying Early Hepatic Encephalopathy Through Digital Phenotyping."
Abstract: Hepatic Encephalopathy (HE) leads to frequent hospitalization, costing $2.0 billion annually. Early identification may motivate early treatment; however, diagnosing covert HE requires complex and protracted neuropsychological testing, which is often infeasible in the clinic setting. We conducted a feasibility study using passive sensing technologies as a means of “digitally phenotyping” HE. We recruited adult subjects with cirrhosis and prospectively followed them up to 6 months. We measured cognitive function monthly in a study clinic by a battery of neuropsych testing. We collected interaction data from the subjects’ smartphone utilizing the BiAffect app, which runs in the background and unobtrusively and continuously collects typing speed, typing accuracy, and accelerometer data. Additionally, we fitted subjects with a wrist-worn activity tracker (Fitbit, Inc.) for sleep, activity level, and heart rate measurement. Dr. Koola will present early pilot results on the feasibility of using digital phenotyping to identify hepatic encephalopathy.
Bio: Dr. Jejo Koola is Associate Professor in the Department of Medicine within the UC School of Medicine with a joint appointment in Hospital Medicine and Biomedical Informatics. His research interests are in using statistical and machine learning models for risk prediction using big data. He applies models to improving the care of multi-morbid patients, particularly patients with advanced liver disease, for which he has been funded by the NIH, the Department of Veterans Affairs, and AHRQ. In addition to his faculty role, he holds a medical directorship within UC San Diego Health Information Systems and is Epic certified to perform infrastructure “build” within the Electronic Health Record. He is currently involved as the data coordinating center lead for two randomized clinical trials piloting clinical decision support interventions within the EHR. Dr. Koola received his MD degree from the Medical University of South Carolina and subsequently completed his residency in Internal Medicine at the Medical College of Virginia in Richmond, Virginia in 2011. Following residency, Dr. Koola completed a post-doctoral fellowship in Biomedical Informatics through the Department of Veterans Affairs in conjunction with Vanderbilt University in 2016. Clinically, he sees a wide variety of hospitalized patients at UCSD on the hospitalist service.
Jejo Koola, MD, MS, Associate Professor of Medicine, Division of Biomedical Informatics and Hospital Medicine, Medical Director, Information Systems, University of California San Diego. "Identifying Early Hepatic Encephalopathy Through Digital Phenotyping."
Abstract: Hepatic Encephalopathy (HE) leads to frequent hospitalization, costing $2.0 billion annually. Early identification may motivate early treatment; however, diagnosing covert HE requires complex and protracted neuropsychological testing, which is often infeasible in the clinic setting. We conducted a feasibility study using passive sensing technologies as a means of “digitally phenotyping” HE. We recruited adult subjects with cirrhosis and prospectively followed them up to 6 months. We measured cognitive function monthly in a study clinic by a battery of neuropsych testing. We collected interaction data from the subjects’ smartphone utilizing the BiAffect app, which runs in the background and unobtrusively and continuously collects typing speed, typing accuracy, and accelerometer data. Additionally, we fitted subjects with a wrist-worn activity tracker (Fitbit, Inc.) for sleep, activity level, and heart rate measurement. Dr. Koola will present early pilot results on the feasibility of using digital phenotyping to identify hepatic encephalopathy.
Bio: Dr. Jejo Koola is Associate Professor in the Department of Medicine within the UC School of Medicine with a joint appointment in Hospital Medicine and Biomedical Informatics. His research interests are in using statistical and machine learning models for risk prediction using big data. He applies models to improving the care of multi-morbid patients, particularly patients with advanced liver disease, for which he has been funded by the NIH, the Department of Veterans Affairs, and AHRQ. In addition to his faculty role, he holds a medical directorship within UC San Diego Health Information Systems and is Epic certified to perform infrastructure “build” within the Electronic Health Record. He is currently involved as the data coordinating center lead for two randomized clinical trials piloting clinical decision support interventions within the EHR. Dr. Koola received his MD degree from the Medical University of South Carolina and subsequently completed his residency in Internal Medicine at the Medical College of Virginia in Richmond, Virginia in 2011. Following residency, Dr. Koola completed a post-doctoral fellowship in Biomedical Informatics through the Department of Veterans Affairs in conjunction with Vanderbilt University in 2016. Clinically, he sees a wide variety of hospitalized patients at UCSD on the hospitalist service.
February 16, 2024
Ming Tai Seale, PhD, MPH Professor, Department of Family Medicine and Public Health, Professor, Division of Biomedical Informatics, Vice Chair for Research, Department of Family Medicine and Public Health, Director, Health IS Outcomes Analysis, University of California San Diego. "AI-Generated Draft Replies Integrated into the EHR and Physicians' Electronic Communication."
Abstract: Groundbreaking quality improvement project of Electronic Health Record (EHR)-integrated generative AI-drafted replies & physician engagement with patient messages. This work is currently embargoed and details will be shared in person during the presentation.
Bio: Dr. Ming Tai-Seale is Professor and Vice Chair for Research in the Department of Family Medicine and Professor in Division of Biomedical Informatics in UC School of Medicine. Her research investigates the practice of medicine, patient-physician communications, and healthcare economics. She pioneered the use of user action log data in electronic health records to study physician practice and wellbeing. She was also the first to use video and audio recordings of clinical encounters to study time allocation in primary care practice. She is the Principal Investigator of the P30 UC San Diego Learning Health Systems Science Center funded by the Agency for Healthcare Research and Quality. In addition to her faculty appointment, she is the Director for Outcomes Analysis and Scholarship at the UC San Diego Health and Director for Research and Learning in the Population Health Services Organization at UC San Diego Health. Dr. Tai-Seale earned her Ph.D. in Health Services with a cognate in Economics from UCLA.
February 9, 2024
Ming Tai Seale, PhD, MPH Professor, Department of Family Medicine and Public Health, Professor, Division of Biomedical Informatics, Vice Chair for Research, Department of Family Medicine and Public Health, Director, Health IS Outcomes Analysis, University of California San Diego. "AI-Generated Draft Replies Integrated into the EHR and Physicians' Electronic Communication."
Abstract: Groundbreaking quality improvement project of Electronic Health Record (EHR)-integrated generative AI-drafted replies & physician engagement with patient messages. This work is currently embargoed and details will be shared in person during the presentation.
Bio: Dr. Ming Tai-Seale is Professor and Vice Chair for Research in the Department of Family Medicine and Professor in Division of Biomedical Informatics in UC School of Medicine. Her research investigates the practice of medicine, patient-physician communications, and healthcare economics. She pioneered the use of user action log data in electronic health records to study physician practice and wellbeing. She was also the first to use video and audio recordings of clinical encounters to study time allocation in primary care practice. She is the Principal Investigator of the P30 UC San Diego Learning Health Systems Science Center funded by the Agency for Healthcare Research and Quality. In addition to her faculty appointment, she is the Director for Outcomes Analysis and Scholarship at the UC San Diego Health and Director for Research and Learning in the Population Health Services Organization at UC San Diego Health. Dr. Tai-Seale earned her Ph.D. in Health Services with a cognate in Economics from UCLA.
February 9, 2024
Amy Sitapati, MD, Clinical Professor, Division of Biomedical Informatics, Division of General Internal Medicine, Chief Medical Information Officer, Population Health, UCSDH, Interim Chief, Division of Biomedical Informatics, UCSD, Interim Chair, UC San Diego Health Department of Biomedical Informatics. "Biomedical Informatics: Systems Science and Diagnostic Safety Incidental Pulmonary Nodules Registries and Population Health to Support SureNet."
Bio: Amy M. Sitapati, MD, is Professor of Medicine, Chief of the Division of Biomedical Informatics, Chair of the UC San Diego Health Department of Biomedical Informatics, and a primary care physician at UC San Diego Health. She is Medical Director of Internal Medicine in La Jolla and leads the population health team that focuses on how clinical informatics can be used to improve the quality of care.
Dr. Sitapati is nationally recognized for her work in primary care. She has more than ten years of experience providing high-quality, patient-centered care in ambulatory settings, and strives to build multidisciplinary teams that effectively work together to improve patient care coordination. In support of patient participation in chronic disease management, Dr. Sitapati combines evidence-based medicine with patient empowerment, prevention methods, and alternative medicine (e.g., Kelee meditation) to help patients achieve their best health. She also has expertise in providing gender-affirming care to transgender and nonbinary patients.
Bio: Amy M. Sitapati, MD, is Professor of Medicine, Chief of the Division of Biomedical Informatics, Chair of the UC San Diego Health Department of Biomedical Informatics, and a primary care physician at UC San Diego Health. She is Medical Director of Internal Medicine in La Jolla and leads the population health team that focuses on how clinical informatics can be used to improve the quality of care.
Dr. Sitapati is nationally recognized for her work in primary care. She has more than ten years of experience providing high-quality, patient-centered care in ambulatory settings, and strives to build multidisciplinary teams that effectively work together to improve patient care coordination. In support of patient participation in chronic disease management, Dr. Sitapati combines evidence-based medicine with patient empowerment, prevention methods, and alternative medicine (e.g., Kelee meditation) to help patients achieve their best health. She also has expertise in providing gender-affirming care to transgender and nonbinary patients.
Dr. Sitapati first joined UC San Diego Health in 2001 following completion of her residency. In 2005, she established the Center for Infectious Disease Management and Research (CIDMAR) at Howard University, a center dedicated to providing culturally competent, state-of-the-art HIV medical care to its 225 patients. In 2007, she met with First Lady, Mrs. Laura Bush, to discuss the first hospital-wide, routine HIV screening program to be implemented in the nation. In 2015, Dr. Sitapati assumed the role of medical director of internal medicine in La Jolla. She also leads a population health team that focuses on using computer systems to improve the quality of care.
In 2022 she was recognized for her humanistic approach to medicine and delivery of care for patients and their families by receiving the Leonard Tow Humanism in Medicine Award. Dr. Sitapati believes bringing humanism into the practice of medicine is the highest pinnacle in health care delivery, benefiting both patients and health care colleagues. As a professor of medicine her clinical research has been related to patient-centered care, quality improvement, and meditation. Dr. Sitapati serves as an instructor for medical students and residents.She completed her medical residency training at UC San Diego School of Medicine, and earned her medical degree from Case Western Reserve University, School of Medicine, in Cleveland, Ohio. Dr. Sitapati is board certified in internal medicine and clinical informatics.
February 2, 2024
Zhe He, PhD, FAMIA, Associate Professor, School of Information, Director, eHEALTH Lab, Director of Biostatistics, Informatics, and Research Design Program (BIRD) of UF-FSU CTSA Hub, Florida State University, Chair-Elect, AMIA Knowledge Discovery. "Harnessing Explainable, Equitable, and Actionable Data Science to Improve Health and Clinical Research."
Abstract: Data science and AI have been revolutionizing biomedical research and healthcare. The availability of large amounts of data such as electronic health records (EHRs) along with a significant increase in computational power has enabled researchers to further investigate the benefits of applying data science and AI to solving challenging problems in biomedical research and healthcare. In the healthcare, while prior research has shown superior performance of deep learning when predicting health outcomes using electronic health record (EHR) data, it has not been adequately adopted in EHR systems in the US. Evidence has shown that improved transparency and interpretability of the deep learning models will increase their trustworthiness for medical doctors, thereby increasing their adoption by healthcare systems. In clinical research, there is lack of generalizability of clinical trials due to unjustified use of overly stringent eligibility criteria. In this talk, I will discuss our recent research efforts on enhancing the interpretability of machine learning models for predicting health outcomes and using EHR data to optimize eligibility criteria design for Alzheimer’s disease clinical trials.
Bio: Dr. Zhe He is an Associate Professor at Florida State University School of Information. He is also holding courtesy appointments with Department of Behavioral Sciences and Social Medicine of College of Medicine and Department of Computer Science. He is also Team Lead of Biostatistics, Informatics, and Research Design (BIRD) Program of UF-FSU Clinical and Translational Science Award. His research lies at the intersection of Biomedical & Health Informatics, Computers Science, and Information Science. He currently serves as Chair-Elect of AMIA Knowledge Discovery and Data Mining Working Group. As an informatician, his research expertise includes machine learning, natural language processing, knowledge representation, and big data analytics. At FSU, he is leading the eHealth Lab. The overarching goal of his research is to improve population health and advance biomedical research through the collection, analysis, and application of electronic health data from heterogeneous sources. As Principal Investigator, Dr. He has been funded by National Institutes of Health, Eli Lilly and Company, Amazon, NVIDIA, and Institute for Successful Longevity. His papers received prestigious recognitions including two Distinguished Paper Awards of AMIA 2015 and 2017 Annual Symposium. In 2022, he was inducted as a Fellow of the American Medical Informatics Association.
January 19, 2024
Eugenia McPeek Hinz, MD, MS, Associate Chief Medical Information Officer, Associate Program Director, Clinical Informatics Fellowship, Duke University Health System. "Screening and Connecting Patients to Resources for Health Related Social Needs."
Abstract: Health-Related Social Needs (HRSN) are the non-medical factors that adversely impact as much as 70% of a patient's health outcomes. Challenges in identifying and linking patients to relevant resources result in a typical success rates of only 15-30%. The successful connection rate reflects the sequential and interdependent steps with multiple potential points for failure, for the patient to receive a resource from a community based organization (CBO). The Duke Health journey began in 2018 with ad hoc discrete data capture of HRSN. In 2021, we began systematic screening for Social Determinant of Health (SDOH) with the integration of NCCARE360 on the Unite Us platform in our Electronic Health Record (EHR). In this presentation, I will share Duke Health’s experiences with SDOH screening, challenges encountered, lessons learned, and future steps to automate connections to resources.
Bio: Eugenia McPeek Hinz MD MS is an Associate Chief Medical Information Officer for Duke University Health System and Physician Informatician with extensive experience in the build and configuration of Duke Health's Electronic Health Record (EHR). She completed a Master of Science in Biomedical Informatics at Vanderbilt University in 2012 as a National Library of Medicine Fellow. In August 2012, she joined Duke University Health System to lead more than 30 physician champions in support of the implementation of our EHR across Inpatient, Surgical and Ambulatory environments. In her work she supports EHR usability, provider well-being, regulatory, compliance, research and SDOH integration.
In 2022 she was recognized for her humanistic approach to medicine and delivery of care for patients and their families by receiving the Leonard Tow Humanism in Medicine Award. Dr. Sitapati believes bringing humanism into the practice of medicine is the highest pinnacle in health care delivery, benefiting both patients and health care colleagues. As a professor of medicine her clinical research has been related to patient-centered care, quality improvement, and meditation. Dr. Sitapati serves as an instructor for medical students and residents.She completed her medical residency training at UC San Diego School of Medicine, and earned her medical degree from Case Western Reserve University, School of Medicine, in Cleveland, Ohio. Dr. Sitapati is board certified in internal medicine and clinical informatics.
February 2, 2024
Zhe He, PhD, FAMIA, Associate Professor, School of Information, Director, eHEALTH Lab, Director of Biostatistics, Informatics, and Research Design Program (BIRD) of UF-FSU CTSA Hub, Florida State University, Chair-Elect, AMIA Knowledge Discovery. "Harnessing Explainable, Equitable, and Actionable Data Science to Improve Health and Clinical Research."
Abstract: Data science and AI have been revolutionizing biomedical research and healthcare. The availability of large amounts of data such as electronic health records (EHRs) along with a significant increase in computational power has enabled researchers to further investigate the benefits of applying data science and AI to solving challenging problems in biomedical research and healthcare. In the healthcare, while prior research has shown superior performance of deep learning when predicting health outcomes using electronic health record (EHR) data, it has not been adequately adopted in EHR systems in the US. Evidence has shown that improved transparency and interpretability of the deep learning models will increase their trustworthiness for medical doctors, thereby increasing their adoption by healthcare systems. In clinical research, there is lack of generalizability of clinical trials due to unjustified use of overly stringent eligibility criteria. In this talk, I will discuss our recent research efforts on enhancing the interpretability of machine learning models for predicting health outcomes and using EHR data to optimize eligibility criteria design for Alzheimer’s disease clinical trials.
Bio: Dr. Zhe He is an Associate Professor at Florida State University School of Information. He is also holding courtesy appointments with Department of Behavioral Sciences and Social Medicine of College of Medicine and Department of Computer Science. He is also Team Lead of Biostatistics, Informatics, and Research Design (BIRD) Program of UF-FSU Clinical and Translational Science Award. His research lies at the intersection of Biomedical & Health Informatics, Computers Science, and Information Science. He currently serves as Chair-Elect of AMIA Knowledge Discovery and Data Mining Working Group. As an informatician, his research expertise includes machine learning, natural language processing, knowledge representation, and big data analytics. At FSU, he is leading the eHealth Lab. The overarching goal of his research is to improve population health and advance biomedical research through the collection, analysis, and application of electronic health data from heterogeneous sources. As Principal Investigator, Dr. He has been funded by National Institutes of Health, Eli Lilly and Company, Amazon, NVIDIA, and Institute for Successful Longevity. His papers received prestigious recognitions including two Distinguished Paper Awards of AMIA 2015 and 2017 Annual Symposium. In 2022, he was inducted as a Fellow of the American Medical Informatics Association.
January 19, 2024
Eugenia McPeek Hinz, MD, MS, Associate Chief Medical Information Officer, Associate Program Director, Clinical Informatics Fellowship, Duke University Health System. "Screening and Connecting Patients to Resources for Health Related Social Needs."
Abstract: Health-Related Social Needs (HRSN) are the non-medical factors that adversely impact as much as 70% of a patient's health outcomes. Challenges in identifying and linking patients to relevant resources result in a typical success rates of only 15-30%. The successful connection rate reflects the sequential and interdependent steps with multiple potential points for failure, for the patient to receive a resource from a community based organization (CBO). The Duke Health journey began in 2018 with ad hoc discrete data capture of HRSN. In 2021, we began systematic screening for Social Determinant of Health (SDOH) with the integration of NCCARE360 on the Unite Us platform in our Electronic Health Record (EHR). In this presentation, I will share Duke Health’s experiences with SDOH screening, challenges encountered, lessons learned, and future steps to automate connections to resources.
Bio: Eugenia McPeek Hinz MD MS is an Associate Chief Medical Information Officer for Duke University Health System and Physician Informatician with extensive experience in the build and configuration of Duke Health's Electronic Health Record (EHR). She completed a Master of Science in Biomedical Informatics at Vanderbilt University in 2012 as a National Library of Medicine Fellow. In August 2012, she joined Duke University Health System to lead more than 30 physician champions in support of the implementation of our EHR across Inpatient, Surgical and Ambulatory environments. In her work she supports EHR usability, provider well-being, regulatory, compliance, research and SDOH integration.