2023 Biomedical Informatics Seminars
December 8, 2023
Alan Moazzam, MD, Assistant Professor of Medicine, Division of Hospital Medicine, University of California San Diego. "Creating a Computer Simulation of UCSD Hospital".
Abstract: Hospital bed occupancy and throughput are important parameters to track for hospital administrators. This is especially so at UCSD La Jolla given the acute problem of EDIP overflow and hallway patient care. Clinical informatics data and Python code can be used to create a computer simulation of the hospital. This simulation can be used to experiment with potential interventions to help alleviate the EDIP and hallway overflow problem.
Bio: Alan Moazzam is an Assistant Professor with the Division of Hospital Medicine at UCSD. He joined the Division 2017 and has worked primarily as a nocturnist. He is currently pursuing an MBA degree at Rady School of Management and is interested in healthcare and biotech entrepreneurship. He serves as an advisor to two UCSD-based accelerator programs, HealthLink and IGE, helping UCSD students develop start-up ventures from projects they have worked on in academia. Prior to joining UC San Diego Health, Dr. Moazzam was a hospitalist at Huntington Memorial Hospital in Pasadena, CA. He completed residency in Internal Medicine at the LA County-USC Hospital. He earned his medical degree from Saint Louis University and is a UCSD undergrad alum.
December 1, 2023
Marc Triola, MD, Associate Dean for Educational Informatics, Director, Institute for Innovations in Medical Education (IIME), Professor, Department of Medicine, NYU Grossman School of Medicine. "Recent advances in Artificial Intelligence within the realm of Medical Education".
Abstract: This presentation will discuss recent advances in Artificial Intelligence within the realm of Medical Education. The talk will cover examples of AI in use today in both education and clinical care, future directions, and AI's revolutionary capacity to redefine how we teach and assess medical students and trainees.
Bio: Marc Triola, MD is a professor of medicine, the associate dean for educational informatics, and the founding director of the Institute for Innovations in Medical Education (IIME) at NYU Grossman School of Medicine. IIME combines education strategies with new informatics solutions to connect patient care and education at NYU Langone in a research and innovation initiative that is translational, empowers transformational change in our school, and benefits our patients. Dr. Triola’s research focuses on the use of AI tools to efficiently personalize education and give new insights to programs and coaches. His lab develops new learning technologies, AI-driven educational interventions, and defines educationally sensitive patient and system outcomes that can be used to assess training.
November 24, 2023 - Thanksgiving break
November 17, 2023
Toluwalase Ajayi, MD, FAAP, HS Associate Professor, Medicine & Pediatrics, Program Co-Director, UCSD/ Scripps HPM Fellowship, Digital Health Equity Lead, Jacobs Center for Innovation, University of California San Diego, "PowerMom: A maternal health remote clinical trial".
Abstract: This presentation will describe PowerMom, a remote clinical trial that combines digital health technology and patient reported data to help democratize clinical trials and reduce disparities in who has access to clinical research. During this presentation, I will discuss the origin story of PowerMom, describe the successes and pain points of launching a remote clinical trial and share some preliminary results.
Bio: Dr. Tolúwalàṣẹ “Làṣẹ” Ajayi, MD, FAAP (she/her; pronunciation), is a physician in the Division of Geriatrics, Gerontology, and Palliative Care in the Department of Medicine and in the Division of Pediatric Hospital Medicine in the Department of Pediatrics at the University of California San Diego. She serves as the Program Director of the joint UC San Diego & Scripps Health Hospice & Palliative Medicine Fellowship and the Digital Health Equity Lead in the Joan & Irwin Jacobs Center for Health Innovation. She is the PI of the PowerMom research study. As Faculty for many years and now as Director, Dr. Ajayi is dedicated to expanding the benefits of palliative care across all ages, as well as improving communication with seriously ill patients and leveraging advances in digital medicine to improve pain assessment and care. Her research focuses on opportunities at the intersection of novel digital medicine technologies and unmet needs in maternal fetal health as well as pain and palliative medicine.
November 10, 2023 -Veterans' Day
November 3, 2023
Judith Somkeh, Lecturer, Faculty of Social Sciences, Department of Information Systems, University of Haifa, "Computational systems biology – predicting receptor functions to facilitate drug development".
Abstract: In this talk, I will briefly present several works utilizing in-silico modeling to understand disease comorbidities and will mainly focus on a work aimed at predicting novel metabolic and inflammatory functions of receptors within human tissues. These receptor proteins are pivotal in transmitting signals within cells and are targets for drug development. Our methodology suggests new features based on enrichment analysis scores of co-expression networks of related receptors. These are fed into machine learning classifiers to predict the tissue-specific metabolic and inflammatory roles of receptors. The method can identify which receptors to prioritize in drug development and has the potential to predict side effects specific to tissues.
Bio: Judith Somekh, Ph.D., is an Assistant Professor at the Information Systems Department at the University of Haifa, Israel. Her BSc (2001), MSc (2007), and Ph.D. (2013) in Information Systems Engineering are from the Technion–Israel Institute of Technology. Dr. Judith Somekh received the Promoting Women in Science Award from the Israeli Ministry of Science during her Ph.D. studies. Between 2015-2017 she was a post-doctoral researcher at Isaac Kohane's lab at the Department for Biomedical Informatics, Harvard Medical School at Harvard University, USA. Her research interests lie in the computational systems biology and biomedical informatics domains and concern developing methodologies combining data-driven and model-driven methods to understand better the development of diseases in general and neurodevelopmental and neurodegenerative disorders in particular.
October 27, 2023
Gondy Leroy, PhD, Professor of MIS, Associate Dean for Research, University of Arizona Eller College of Management. " Transparent machine learning for diagnosis of autism spectrum disorders: an overview of our approach and results, obstacles, and (attempted) creative solutions.
Abstract: In this presentation, I will provide a high-level overview of our machine-learning approach to identifying children at risk for autism using information in the clinical notes in electronic health records. I will show how our approach is transparent and provides excellent results even though we use deep learning algorithms with small datasets. I will also highlight a few technical and clinical problems and how we attempt to overcome them creatively, for example by creating synthetic data using generative AI and with crowdsourcing. Finally, I will introduce tentative future plans to make this a trustworthy tool for clinicians, and would welcome ideas and feedback
Bio: Gondy Leroy, Ph.D., is Professor of MIS and Associate Dean for Research at the University of Arizona’s Eller College of Management. Her research focuses on natural language processing (NLP) and machine learning (ML). She has won grants from NIH (NLM and NIMH), AHRQ, NSF, Microsoft Research, and several foundations, totaling more than $5.7M as principal investigator. She earned a combined BS and MS (1996) in cognitive, experimental psychology from the Catholic University of Leuven (1996) in Belgium and a MS (1999) and PhD (2003) in management information systems from the University of Arizona. She serves on the editorial board of the Journal of Database Management, International Journal of Social and Organizational Dynamics in IT, Health Systems, Journal of Business Analytics, and co-chairs several special issues, sessions, tracks, workshops, and conferences focusing on design science and healthcare IT. She is the author of the book “Designing User Studies in Informatics (Springer, 2011). Finally, she actively contributes to increasing diversity and inclusion in computing through mentoring students early in their academic careers starting in high school and through graduate school.
October 20, 2023
Rickey E. Carter, PhD, Professor of Biostatistics, Vice Chair, Department of Quantitative Health Sciences, Mayo Clinic. "AI Applications in Clinical Medicine: Challenges and Breankthroughs".
Abstract: The practice of medicine is rapidly evolving with the advent of new equipment and digital strategies to process high dimensional data. Despite this innovation, the health care field may be lagging other technology-driven fields. In this talk, we will reveal some opportunities, and challenges, that medicine faces. Discussion of model development, model validation, and the role of software as a medical device will be had.
Bio: Rickey Carter, PhD is Professor of Biostatistics at Mayo Clinic in Jacksonville, Florida. He received his training in biostatistics at the Medical University of South Carolina and has over 20 years of experience with study design and analysis for clinical and translational research. Administratively, he serves as a Vice Chair for the Department of the Quantitative Health Sciences and as the Scientific Director for the Digital Innovation Lab, a machine learning shared resource on Mayo Clinic’s Florida campus. Dr. Carter has research interests that span clinical trial optimization to the development of digital biomarkers using machine learning techniques. He is an active collaborator and has over 375 peer reviewed publications.
October 13, 2023
Degui Zhi, PhD, Glassell Family Professor of Biomedical Informatics, Director of Center for AI and Genome Informatics, McWilliams School of Biomedical Informatics (MSBMI), University of Texas Health Science Center at Houston (UTHealth Houston). "Clinical foundation models with structured clinical data".
Abstract: Large language models (LLMs) are taking the world by storm, unlocking clinical insights in unstructured data in clinical notes. However, clinical notes are often siloed due to barriers for data sharing. On the other hands, large amount of clinical information, in the form of structured electronic health records (EHRs) and insurance claims, are becoming widely available. In this talk, we discuss our early attempts of developing foundation models for structured clinical data. We primarily focus on how our pretrained Med-BERT model can boost performance of predictive modeling with limited local training data. We will also some potential new applications.
Bio: Dr. Degui Zhi is Glassell Family Professor of Biomedical Informatics and Director of Center for AI and Genome Informatics at the McWilliams School of Biomedical Informatics (MSBMI) at the University of Texas Health Science Center at Houston (UTHealth Houston). Dr. Zhi received his Ph.D. in Bioinformatics from UCSD in 2006. After a postdoc training at UC Berkeley, he started as an assistant professor of biostatistics at University of Alabama at Birmingham and got promoted to Association professor with tenure in 2015. Dr. Zhi joined UTHealth in 2016. His research cut through bioinformatics, biostatistics, biomedical informatics, and medical AI. Funded by multiple NIH grants, his recent projects focus on methods development for efficient population genetics informatics, new phenotype discovery for imaging genetics, and modeling of structured electronic health records (EHR) data.
October 6, 2023
Ben Smarr, PhD, Assistant Professor, Bioengineering and Data Science, UC San Diego. Title and abstract pending. "Seeing the forest and the trees - big data approaches to individual and public health insights".
Abstract: The emergence of wearable sensors and other persistent data gathering devices has the potential to transform medicine because now patients can be represented by rich wakes of data they leave behind them, as opposed to only being known by the relatively sparse data generated by the odd visit to a clinic. These new data sources provide two opportunities that complement each other. First, these data can provide a more complete view of the diverse health states and dynamics that compose populations, and reveal new patterns that make certain people more similar to each other in ways that might not be covered by categories like ethnicity or sex. Second, individuals can be contextualized within their own data, and within these new, data-derived groups of similar people. Together these opportunities will improve, rapid, persistent public health awareness as populations change during pandemics or under other influences. At the same time, they will allow individuals to receive algorithm feedback that will be tuned to them individually, improving precision in detection and prevention of negative health conditions.
Bio: Dr. Benjamin L. Smarr, Ph.D. Neurobiology, is an assistant professor at UCSD’s Shu Tsien-Gene Lay Department of Bioengineering and the Halicioğlu Data Science Institute. His work leverages his domain expertise in biological rhythms and neuroendocrinology to uncover patterns in diverse sets of time series data that carry actionable information to impact health and cognitive performance. In 2020 he became the technical lead of the global collaborative TemPredict study, which developed algorithms for early detection of COVID-19 infection, and unique cyberinfrastructure to serve rapid, collaborative explorations of population-scale, personal time series data. Beyond the pandemic, Dr. Smarr contributes broadly through science outreach, popular media, and industry liaisons. His personal passions lie in advancing women’s health, and in increasing participant engagement to map physiological diversity in service to precision individual and public health.
June 9, 2023
Virginia de Sa, PhD, Professor of Cognitive Science, HDSI Chancellor's Endowed Chair, Halıcıoğlu Data Science Institute, University of California, San Diego. "Recognizing and exploiting Multiple Views to Read Humans".
Abstract: EEG is known to be non-stationary and "noisy". In this talk I will show that some of this "noise" reflects response to perceived task performance and can actually be used to improve performance in an EEG-based motor-imagery brain-computer interface. I will also show a related situation where we found that the environmental sensitivity of automatically computed computer vision features impaired pain classification in new environments. I will show a simple solution we used to leverage some concurrently human-labeled data to improve performance of automatic pain classification in facial videos of postoperative children. I will then show our current deep learning approach and discuss racial biases in facial expression recognition.
Bio: Virginia de Sa is a professor of Cognitive Science, HDSI Chancellor's Endowed Chair, and associate director of the Halicioglu Data Science Institute at UC San Diego. She received a B.Sci. (Engineering) from Queens University in Ontario, and a PhD in Computer Science (machine learning) from the University of Rochester before receiving postdoctoral training in machine learning with Geoff Hinton at the University of Toronto and in neuroscience, with Michael Stryker and Michael Merzenich, at UCSF. Her research goal is to better understand the neural basis of human perception and learning, both from a neural and computational point of view. She investigates the computational properties of machine learning algorithms and what physiological recordings and the constraints and limitations of human performance tell us about how our brains perceive and learn.
June 2, 2023
Tiffany Amaruita, PhD Assistant Professor of Medicine, Division of Biomedical Informaticsd, University of California, San Diego. "Algorithims for robust and scalable indentification of genetic regulation of gene expression."
Abstract: Genetic models of gene expression can be used to identify which genetic variants have impacts on gene expression. A precise understanding of which variants modulate which genes is important because it promotes the translational potential of genome-wide association studies (GWAS). GWAS have identified hundreds of thousands of variants associated with human complex traits and diseases, but ~90% of variants are in gene regulatory regions and don’t implicate a specific target gene. Our understanding of which variants regulate which genes is still limited due to statistical challenges stemming from finite sample sizes, multiple hypothesis burdens, underdetermined systems, and systemic model misspecification. We develop new algorithms that address these limitations and enable the identification of (1) gene-regulating genetic variation important to non-European populations, (2) genome-wide genetic variation impacting gene expression, and (3) cell-type-specific gene-regulating genetic variation from single cell genomics.
Bio: Before starting her lab in San Diego, Tiffany earned a B.S. in Biological Engineering at MIT and went on to conduct graduate research with Dr. Soumya Raychaudhuri as part of the Bioinformatics and Integrative Genomics PhD program at Harvard Medical School, where she studied the genetic susceptibility of autoimmune diseases and other polygenic diseases. During graduate school, Tiffany developed machine learning methods to predict the functionality of regulatory variants, which had applications to transcription factor binding prediction, eQTL mapping, heritability enrichment analysis, and trans-ancestry portability of polygenic risk scores. She pursued post-doctoral research studying tissue-mediated genetic effects with Dr. Alkes Price at the Harvard School of Public Health. Now, Tiffany is an Assistant Professor in the Halıcıoğlu Data Science Institute and the Department of Medicine at the University of California San Diego.
May 26, 2023
Michael Snyder, PhD, Stanford Ascherman Professor and Chair of Genetics and the Director of the Center of Genomics and Personalized Medicine, Stanford. "Transforming healthcare using deep data and remte monitoring".
Abstract: Our present healthcare system focuses on treating people when they are ill rather than keeping them healthy. We have been using big data and remote monitoring approaches to monitor people while they are healthy to keep them that way and detect disease at its earliest moment presymptomatically. We use advanced multiomics technologies (genomics, immunomics, transcriptomics, proteomics, metabolomics, microbiomics) as well as wearables and microsampling for actively monitoring health. Following a group of 109 individuals for up to 13 years revealed numerous major health discoveries covering cardiovascular disease, oncology, metabolic health and infectious disease. We have also found that individuals have distinct aging patterns that can be measured in an actionable period of time. Finally, we have used wearable devices for early detection of infectious disease, including COVID-19 as well as microsampling for monitoring and improving lifestyle. We believe that advanced technologies have the potential to transform healthcare and keep people healthy.
Bio: Michael Snyder is the Stanford Ascherman Professor and Chair of Genetics and the Director of the Center of Genomics and Personalized Medicine. He received his Ph.D. training at the California Institute of Technology and carried out postdoctoral training at Stanford University. Dr. Snyder has pioneered the use of “big data” and multiomics to advance scientific discovery and transform healthcare. His laboratory has invented many technologies that are widely used in medicine and research, including methods for characterizing genomes and their products (e.g. RNA-Seq, NGS paired end sequencing, ChIP-Chip and later Chip-Seq, protein arrays, machine learning for disease gene discovery). His application of omics and wearables technologies to perform longitudinal profiling of people when they are healthy and ill is transforming medicine and healthcare. Indeed, his laboratory’s recent work to use smartwatches and wearables to detect illness, including infectious disease such as COVID-19, prior to symptom onset is being used by many thousands of people. He has helped colead many large scale projects including ENCODE, HMP, HuBMAP and HTAN. He has cofounded 16 biotechnologies companies, including Personalis, Qbio, January AI, Filtricine and RTHM.
May 19, 2023
Virginia de Sa, PhD, Professor of Cognitive Science, HDSI Chancellor's Endowed Chair, Halıcıoğlu Data Science Institute, University of California, San Diego. "Recognizing and Exploiting Multiple Views to Read Humans".
Abstract: EEG is known to be non-stationary and "noisy". In this talk I will show that some of this "noise" reflects response to perceived task performance and can actually be used to improve performance in an EEG-based motor-imagery brain-computer interface. I will also show a related situation where we found that the environmental sensitivity of automatically computed computer vision features impaired pain classification in new environments. I will show a simple solution we used to leverage some concurrently human-labeled data to improve performance of automatic pain classification in facial videos of postoperative children. I will then show our current deep learning approach and discuss racial biases in facial expression recognition.
Bio: Virginia de Sa is a professor of Cognitive Science, HDSI Chancellor's Endowed Chair, and associate director of the Halicioglu Data Science Institute at UC San Diego. She received a B.Sci. (Engineering) from Queens University in Ontario, and a PhD in Computer Science (machine learning) from the University of Rochester before receiving postdoctoral training in machine learning with Geoff Hinton at the University of Toronto and in neuroscience, with Michael Stryker and Michael Merzenich, at UCSF. Her research goal is to better understand the neural basis of human perception and learning, both from a neural and computational point of view. She investigates the computational properties of machine learning algorithms and what physiological recordings and the constraints and limitations of human performance tell us about how our brains perceive and learn.
May 12, 2023
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, UCSDH. "Good little data - the source of happiness for biomedical informatics".
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.
May 5, 2023
John W. Ayers, PhD, Vice Chief of Innovation, Div. Infectious Disease & Global Public Health, Associate Adjunct Professor of Medicine, University of California San Diego. "Putting the Public Back in Public Health."
Bio: Dr. Ayers is committed to getting the public back in public health, by harnessing big media data (including Internet search queries, news media, social media, and online networks) to listen to the public voicing their health needs in near real time. Beginning in 2011 he showed electronic cigarettes were the most popular smoking alternative on the market, being the first to predict their rise. This study has been followed by several examples of unique discoveries making public health science more responsive to the public and more effective in the process. For instance, his recent JAMA Internal Medicine report describing how Charlie Sheen’s HIV-positive disclosure prompted record-levels of public engagement with condoms, HIV symptoms, and HIV testing was covered in more than 6,000 news outlets and trended on both Facebook and Twitter. The publication of this report was later linked to a significant increase in HIV testing and made more impactful by partnering with several medical device makers to implement follow-up campaigns encouraging at-home HIV testing and condom use. His work has also been trans-disciplinary (e.g., he has published with more than 60 different collaborators, from more than 50 different research institutes representing many fields, such as applied mathematics, climatology, communications, computer science, economics, engineering, political science, sociology, and more). Dr. Ayers has published more than 60 peer-reviewed articles and several commentaries/op-eds, many of which rank in the very top of Altmetric’s research rankings (including one study that ranked among the top 1,000 most circulated articles of all time). He has an h-index of 26 (26 publications with 26 or more citations). Dr. Ayers is a frequently featured expert in the international media, including coverage in traditional news (e.g., ABC, BBC, CBC, CBS, CNN, Fox, NBC, NPR, etc.), tech or business focused news (e.g., Bloomberg, Forbes, Popular Science, Scientific American, Wired, etc.), and entertainment news (e.g., Dr. Drew, Dr. Oz, Perez Hilton, Rolling Stone, Saturday Night Live, etc.). Dr. Ayers is committed to promoting rapid improvements in public health science and leveraging public health science to save lives.
April 28, 2023
Colin Walsh, MD, MA, FACMI, FAMIA Associate Professor, Department of Biomedical Informatics, School of Medicine, Vanderbilt University. "Digital Health Innovation from the Lab to the Clinic: Trialing Ethical, AI-driven Clinical Decision Support to Enable Prevention."
Bio: Colin G. Walsh, MD, MA, is an Associate Professor of Biomedical Informatics, Medicine, and Psychiatry at Vanderbilt University Medical Center. He is an internist. He received a degree in Mechanical Engineering from Princeton University and his medical degree at the University of Chicago. He completed residency and chief residency in internal medicine at Columbia University Medical Center. He received a degree in Biomedical informatics at Columbia University and joined the faculty at Vanderbilt University in 2015.
Dr. Walsh's research includes: 1) predictive decision support to enable prevention; 2) scalable phenotyping for precision medicine; and 3) population health informatics. His research with an international team of collaborators has been funded by diverse agencies including the NIH, FDA, DoD, Wellcome Leap , and philanthropy. His work has been featured in Newsweek, Wired, Quartz, NBC News, ACM Tech News, the Washington Post, Reuters Health, and more.
April 21, 2023
Karandeep Singh, MD, MMSc, Assistant Professor of Learning Health Sciences, Internal Medicine, Urology, and Information at the University of Michigan. "Reproducibility and Generalizability of Risk Prediction Models."
Abstract: The use of risk prediction models to guide clinical decision-making is growing due to the incorporation of risk into clinical guidelines coupled with their rising availability and ease of integration. In this talk, I will discuss how risk prediction models are evaluated with an emphasis on proprietary models, the importance of model transparency in the evaluation process, and approaches to studying their reproducibility and generalizability in real-world settings. I will draw on our work in sepsis and acute kidney injury to highlight challenges in reproducibility and generalizability, and I will touch on the changing regulatory landscape around the use of prediction models in clinical care.
Bio: Karandeep Singh, MD, MMSc, is an Assistant Professor of Learning Health Sciences, Internal Medicine, Urology, and Information at the University of Michigan. He directs the Machine Learning for Learning Health Systems (ML4LHS) Lab, which focuses on translational issues related to the implementation of machine learning models within health systems. He serves as an Associate Chief Medical Information Officer of Artificial Intelligence for Michigan Medicine and is the Associate Director for Implementation for Precision Health at the University of Michigan. He teaches a health data science course for graduate and doctoral students, and provides clinical care for people with kidney disease.
He completed his internal medicine residency at UCLA Medical Center, where he served as chief resident, and a nephrology fellowship in the combined Brigham and Women’s Hospital/Massachusetts General Hospital program in Boston, MA. He completed his medical education at the University of Michigan Medical School and holds a master’s degree in medical sciences in Biomedical Informatics from Harvard Medical School. He is board certified in internal medicine, nephrology, and clinical informatics.
His work in machine learning and digital health has been published in leading journals in their respective fields, including the New England Journal of Medicine, Lancet, British Medical Journal, JAMA Internal Medicine, Nature Machine Intelligence, Health Affairs, Clinical Journal of the American Society of Nephrology, Ophthalmology, Radiology, and European Urology.
April 14, 2023
Sara Murray, MD, M.A.S., Associate Chief Medical Information Officer, Inpatient Care and Data Science Associate Professor of Clinical Medicine, Department of Medicine UCSF Health. "Artificial Intelligence: A Catalyst for Digital Transformation in Healthcare."
Abstract: Applying advanced analytics to the wealth of data available in the EHR has allowed us to improve healthcare for patients, the experience of providing care, and the strength of our academic and educational programs. However, most attempts to leverage artificial intelligence (AI) in healthcare have at best demonstrated incremental improvements. We are now entering an era in which AI will catalyze the digital transformation that has long been promised. Emerging AI technologies have extraordinary potential, and both the data science and healthcare communities recognize the importance of ensuring that we are implementing trustworthy AI, which is robust, equitable, transparent, responsible, and secure. To be stewards of this new technology, we must focus on building the necessary infrastructure and governance to support research and development, implementation, and monitoring of AI in healthcare. With powerful tools such as GPT-4 now widely available, it is critical that health systems, researchers, and industry form partnerships to ensure that these revolutionary tools improve healthcare to their highest potential. In this seminar, I will discuss important factors that must be considered in the planning, development, and implementation of AI, and how university health systems should not only prepare for the impact of new AI technologies but also serve as key facilitators during this transformative time.
Bio: Sara Murray, MD, MAS, is Associate Professor of Clinical Medicine and serves as Associate Chief Medical Information Officer for Inpatient Care and Data Science at UCSF Health. She also directs the Data Science and Innovation (DSI) team, which uses data science to understand and address the most pressing issues facing the health system.
Dr. Murray is a strategic health system leader for clinical informatics, digital health, and data science. She strives to leverage healthcare data in new and impactful ways to support improvements in quality, safety, and value for patients and providers. She has a focus on predictive analytics and artificial intelligence (AI) in healthcare, and her team has built infrastructure and governance processes to ensure deployment of ethical and robust AI. Her team evaluates commercially available tools and algorithms for trustworthiness prior to implementation and develops new machine learning models to address pressing health system problems. She also works to optimize the EHR to support clinical workflows and deploy tools to improve quality and safety, partnering with stakeholders both at UCSF and partner institutions.
Dr. Murray received her BS in Chemistry from the College of William and Mary and her MD from the University of California, San Francisco. She completed her internship and residency in Internal Medicine at UCSF as well as a MAS in Clinical Research and joined the Division of Hospital Medicine as faculty in 2015. She spends her clinical time caring for patients and teaching medical students and residents on the Hospital Medicine service at UCSF.
April 7, 2023
Leslie Lenert, MD, MS, Associate Vice President for Data Science and Informatics, Cheif Research Information Officer, Distinguished Professor of Medicine, Medical University of South Carolina, Charleston, SC. "Translational Challenges in the Implementation of an Enterprise-Wide Precision Medicine Initiative."
Bio: Dr. Lenert is the Associate Vice President for Data Science and Informatics and the Chief Research Information Officer for the Medical University of South Carolina (MUSC). He is also Distinguished Professor of Internal Medicine, and Smart State Chair in Healthcare Quality. In these roles, he leads work on the development of Learning Health System infrastructure for the MUSC Enterprise, with his latest efforts being focused on MUSC’s 100,000 person gene sequencing initiative, in our DNA SC.
Dr. Lenert is a primary care physician with a 30-year history of research in biomedical informatics. He has published more than 200 papers in peer reviewed journals. His work spans many areas: the 1990’s, he was a pioneer in use of data science methods in clinical medicine. In response to 2001 9-11 attacks, Dr. Lenert led a team of engineers and computer scientists at UCSD that developed a wireless “location aware” intelligent EHR system for first responders. In 2007, Dr. Lenert became the founding Director of the National Center for Public Health Informatics at Centers for Disease Control and Prevention (CDC), where he managed national biodefense computer systems. After coming to MUSC 2013, in addition to his work on translational infrastructure, Dr. Lenert leads NIH funded research decision support for T3–T4 translation. Dr. Lenert is also an active contributor in the informatics health policy space. He was a member of HHS/ONC’s Health Information Technology Advisor Committee from 2017-22 and continues to publish articles on how health policies can promote interoperability. Dr. Lenert is an Associate Editor of JAMIA, a fellow of the American College of Medical Informatics and American College of Physicians and has won awards for his research work from the American Federation for Clinical Research and the American Medical Informatics Association.
March 17, 2023
Charles Jaffe, MD, PhD, FACP, FACMI, CEO, Health Level 7 International, Visiting Scholar, UCSD Health System Department of Biomedical Informatics. "HL7 FHIR: The journey and the future of interoperability."
Bio: Charles Jaffe is the Chief Executive Officer of Health Level 7 International (HL7). He completed his medical training at Johns Hopkins and Duke Universities and post-doctoral training at the National Institutes of Health and the Lombardi Cancer Center. He has served in various academic positions in the Departments of Medicine and Pathology, as well as in the School of Engineering. Prior to joining HL7, he was the Senior Global Strategist at Intel. In addition, he led a national research consortium, found a consultancy for research informatics, served as the VP of Medical Informatics at AstraZeneca, and the VP of Life Sciences at SAIC. Dr. Jaffe has been the contributing editor for several journals and has published on clinical management, informatics deployment, and healthcare policy.
March 10, 2023
Mor Peleg, PhD, Editor-in-Chief, Journal of Biomedical Infornatics, Professor of Information Systems, Chief, Data Science Center, Univerity of Haifa, Haifa, Israel. " Personalized clinical-guideline based AI desicion-support for patients: what data is needed and how to make it FAIR."
Abstract: I will start with a background on how we have been developing and applying, since 2000, ontologies and AI methods and tools to develop an architecture for delivering clinical guideline-based patient-specific recommendations, and what our current vision is (focus on patient's wellbeing). Then I will share our lessons learned from the MobiGuide project (https://mpeleg.hevra.haifa.ac.il/research/mobiguide), about what is needed to provide personalized decision support to patients and their care providers anytime, everywhere. We are now applying these lessons in the CAncer PAtients Better Life Experience (CAPABLE) project (https://capable-project.eu/). I will discuss the data needed to provide the decision support and the ways in which we make it FAIR (Findable, Accessible, Interoperable, and Reusable).
Bio: Mor Peleg holds a BSc and MSc degrees in biology and PhD (1999) in Information Systems, from the Technion and postdoctoral studies (2003) at Stanford’s Medical Informatics program. She is Full Professor at the Department of Information Systems, University of Haifa, which she joined in 2003, Head of the University of Haifa’s Data Science Center, and former Chair of the Department of Information Systems and of the BSc in Data Science program. She is the Editor-in-Chief of the Journal of Biomedical Informatics and is Fellow of the American College of Medical Informatics and of the International Academy of Health Sciences Informatics. Prof. Peleg is internationally renowned in the area of clinical decision support, with a focus on using ontologies to integrate patient data with clinical knowledge. She led the large-scale European project MobiGuide, providing sensor-monitoring and evidence-based personalized decision-support to patients any time everywhere. Her current research exploits AI and Big Data for a new model of cancer care (https://capable-project.eu/ ). web page: https://mpeleg.hevra.haifa.ac.il/ LinkedIn: https://www.linkedin.com/in/mor-peleg-1593452/
February 24, 2023
Jialin Mao, PhD Assitant Professor of PopulationHealth Sciences, Weill Cornell School of Medicine. "Real-world study of drug-coated device safety using linked registry-claims data."
Abstract: This presentation will focus on a real-world study using linked registry-claims data to examine mortality after peripheral vascular intervention with drug-coated device. There has been controversies surrounding drug-coated device safety after a previous meta-analysis. We constructed three cohorts from real-world data intended to mirror the cohorts of previous studies and demonstrate that robust and niche real world evidence can help understand and reconcile previously discrepant findings.
Bio: Dr. Jialin Mao is an Assistant Professor in the Department of Population Health Sciences at Weill Cornell Medicine. She is an epidemiologist with a background in medicine and a research focus on medical device outcomes. Dr. Mao received her MD from Shanghai Jiao Tong University School of Medicine and completed an internship and part of her residency in General Surgery at Ruijin Hospital in Shanghai, China. She received her MS in Epidemiology from Harvard School of Public Health and her PhD in Epidemiology at Columbia University Mailman School of Public Health. Her expertise is in epidemiologic study design and advanced data analysis for surgical and device research. Her current research focus is on the application and development of advanced multidisciplinary methods to support the evaluation of surgical and device outcomes. She is also interested in health disparity questions related to medical device use and outcomes.
February 3, 2023
Usha Govindarajulu, PhD, Associate Professor, Center for Biostatistics, Department of Population Health Sciences, Icahn School of Medicine, Mount Sinai, New York. "A Bioststistician's Encounter with COVID-19 and the Future."
Abstract: In this presentation, I will discuss how working in a biostatistics center at a major New York City hospital system and being in the epicenter of the COVID-19 pandemic changed my life as a biostatistician. Around late March 2020 at the height of the pandemic, I was redeployed to work on COVID research for the hospital. Suddenly being put on a team of people who I had never met was a new challenge as well as keeping up with the daily download of updated patient data and analysis requests from infectious disease specialists to anesthesiologists in analyzing potential treatments. Dealing with real-time data analysis suddenly became the new normal. Handling messy data and constantly changing the focus were issues at that time. Thereafter, moving onwards to other pressing COVID-19 projects and also simultaneously trying to improve and address data analytic issues in these research projects then overtook my research career for an additional year and a half. Returning to my regular statistical methods research was also important but the COVID-19 research as certainly made an impact on my research and how I view the use of statistical methods. I will discuss the challenges faced and possible solutions.
Bio: Usha Govindarajulu is an Associate Professor in the Center for Biostatistics in the Department of Population Health Sciences of the Icahn School of Medicine at Mount Sinai. She graduated from Boston University with a PhD in Biostatistics and spent two years as a postdoctoral fellow at Harvard School of Public Health. Her research interests are in survival analysis, frailty models, smoothing, causal inference, and machine learning. She is an elected member of the American Statistical Association as a Chair of the Statistical Computing section.
January 13, 2023
Robert McDougal, PhD, Assistant Professor, Department of Biostatistics, Yale University, "Event-based approximations to in silico biophysical neuron models with partial history."
Abstract: Neurological diseases remain difficult to treat, due in part to difficulty in translating promising results from animal studies into human treatments. Biophysically-based computational models offer a promising alternative, but are limited due to their computational complexity and to the large number of spatial and temporal scales separating a drug and the desired behavioral outcome. We show that interpreting neurons as event-receiving and sending mechanisms allows the reconstruction of states and spiking behavior of a biophysically-detailed model without the overhead or temporal dependency of integrating large systems of differential equations from initial conditions through continuous time. Reducing neuron compute complexity while retaining the ability to reconstruct original states offers the potential to combine realistic responses with larger models for better insight into network outcomes.
Bio: Robert McDougal received his Bachelor's degree in 2004 from the University of Maryland, Baltimore County in Mathematics, his MS and PhD in Mathematics from The Ohio State University (2006 and 2011, respectively), and an MS in Computational Biology and Bioinformatics from Yale in 2015. After postdocs in computer science, neurobiology, and medical informatics, he started as an Associate Research Scientist in Neuroscience at Yale in 2016 and became an Assistant Professor of Biostatistics in 2019. His research interests are focused on neuroinformatics methods and on extracting information from health-related publications.