Skip to main content

2022 Biomedical Informatics Seminars

June 3, 2022

James J. Collins, PhD, Massachusetts Institute of Technology, Termeer Professor of Medical Engineering and Science, MIT. "Harnessing synthetic biology and deep learning of fight pathogens."

Abstract: TBA

Bio: The Collins Lab works in synthetic biology and systems biology, with a particular focus on using network biology approaches to study antibiotic action, bacterial defense mechanisms, and the emergence of resistance. They employ engineering principles to model, design and build synthetic gene circuits and programmable cells, in order to create novel classes of diagnostics & therapeutics.  They also use deep learning approaches to discover new genetic parts and enhance the synthetic biology design process. As part of the Antibiotics-AI Project, they are harnessing the power of artificial intelligence (AI) to discover novel classes of antibiotics and rapidly understand how they work. The Collins lab also uses deep learning approaches for the de novo design of new antibiotics and the development of combination treatments. 

April 29, 2022

CT Lin, MD, Chief Medical Information Officer, Professor of Medicine, University of Colorado at Denver. "Sepsis, AI and the Centaur."

Abstract: How did UCHealth move into predictive analytics, machine learning and AI? Why is it so hard to move the needle when applying prediction in healthcare? What does the Centaur have to all of this? Come find out!   

Bio: CT Lin MD is CMIO at UCHealth, an 9-hospital, 400-clinic system in the Rocky Mountain region. In 2016, UCHealth achieved HIMSS Stage 7, indicating highest achievement in EHR effectiveness. In 2017, UCHealth achieved Most Wired status from Hospitals and Health Networks.  He is Professor of Medicine at University of Colorado School of Medicine, and board-certified in Internal Medicine and Clinical Informatics. He sees internal medicine patients and also facilitates workshops on "Physician-patient communication to improve health outcomes" for students, residents and practicing physicians. His national publications and talks include: Physician Adoption of IT, EHR Usability, Online patient communication and patient accessible records with Open Test Results and Open Notes. His national awards include "Healthcare IT innovator" and "Electronic Physician of the Year." He leads a team of 32 physician informaticians, whose main work is now reducing physician burnout and the EHR burden. Our vision: "We improve physician and team resilience and effectiveness by building world-class relationships and innovative tools."

April 22, 2022

Biren Kamdar, MD, MBA, MHS , Associate Professor of Medicine, Div. of Pulmonary, Critical Care, and Sleep Medicine, UC San Diego Health. "Delirium Improvement in 4ICU: Novel use of the EHR to bridge the quality chasm." 

Abstract: Delirium is a condition of varying cognition, sometimes termed “brain failure,” that is a common complication of hospitalization, particularly for patients in the Intensive Care Unit. Delirium causes significant morbidity and mortality, including increased length of stay, healthcare costs, and long-term physical and cognitive deficits. Delirium goes undetected one-third to two-thirds of the time, often because healthcare providers do not know how to detect it. There is no proven treatment for delirium, and the primary goal is prevention. Dr. Kamdar will speak about a comprehensive quality improvement initiative to detect and reduce delirium in the Intensive Care Unit.    

Bio: Biren Kamdar, MD, MBA, MS, MHS, is a board-certified pulmonologist and critical care physician. He cares for adult patients in the Medical Intensive Care Unit (MICU) and those with general lung conditions. As an associate professor in the Department of Medicine, Dr. Kamdar trains medical students, residents and fellows at the UC San Diego School of Medicine. His NIH/NIA-funded research focuses on sleep and circadian rhythms in the ICU; in particular, methods to evaluate sleep in critically ill patients and the effect of interventions to improve sleep-wake cycles on delirium and other important outcomes. Dr. Kamdar has presented on this topic at national and international conferences, and has published in various medical journals and textbooks.

Prior to joining UC San Diego Health, Dr. Kamdar was an assistant professor in the Division of Pulmonary and Critical Care Medicine at the David Geffen School of Medicine at UCLA. Dr. Kamdar completed a fellowship in pulmonary and critical care medicine at Johns Hopkins Hospital (Johns Hopkins School of Medicine) in Baltimore. During his fellowship, he received an NIH/Kirschstein NRSA Award and a Master in Health Science (MHS) degree from the Graduate Training Program in Clinical Investigation at the Johns Hopkins Bloomberg School of Public Health. He completed his internal medicine residency at Vanderbilt University Medical Center. He received a joint MD/MBA at the Vanderbilt University School of Medicine and the Vanderbilt Owen Graduate School of Management in Nashville.

April 15, 2022

Jejo Koola, MD., MS, Assistant Professor of Medicine, UCSD Health Department of Biomedical Informatics, University of California San Diego. "Identifying  Early Hepatic Encephalopathy Though 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. Koola is a practicing physician with seven years practicing experience in multiple medical centers. During his fellowship in Biomedical Informatics at the Department of Veterans Affairs in conjunction with a master’s degree from Vanderbilt University he gained formal skills in database management, data mining, information retrieval, software engineering, and natural language processing. He worked with patients who have advanced liver disease (cirrhosis) and constructed risk prediction models using machine learning techniques for mortality, readmission, and phenotyping (case identification). Additionally, he constructed machine learning models to phenotype Hepatorenal Syndrome (a complication of cirrhosis) using Natural Language Processing. He has been working on ways to use observational cohort data to predict decompensation in patients with significant medical comorbidities.

April 8, 2022: No Seminar

April 1, 2022

Jejo Koola, MD., MS, Assistant Professor of Medicine, UCSD Health Department of Biomedical Informatics, University of California San Diego. "Digital Health in Acute Kidney Injury."

Abstract: Digital innovation is rapidly interconnecting the global population. Digital technologies are increasingly becoming essential to daily life. The use of digital innovation and technologies in medicine and related health spheres, referred to as Digital Health, is growing exponentially and is ever more evident in modern healthcare. Digital health applications and solutions have enormous potential to realize improvements and unlock value for individuals, populations and healthcare systems across a wide continuum. In March of 2022, the Acute Disease Quality Initiative (ADQI) held a conference to propose consensus guidelines on Digital Health in Acute Kidney Injury (DH-AKI). The presentation will discuss five key questions addressed at the DH-AKI conference: (a) What is Digital Health? (b) What are the different aspects of Acute Kidney Injury care that may be improved using digital health? (c) What evidence exists for the use of digital health in the care of Acute Kidney Injury? (d) What steps need to be taken from appropriate development, validation, and implementation of Digital Health in AKI; and (e) What are the barriers and facilitators to development, implementation, and dissemination? Finally, we will present a case example of using Digital Health in AKI.

Bio: Dr. Koola is a practicing physician with seven years practicing experience in multiple medical centers. During his fellowship in Biomedical Informatics at the Department of Veterans Affairs in conjunction with a master’s degree from Vanderbilt University he gained formal skills in database management, data mining, information retrieval, software engineering, and natural language processing. He worked with patients who have advanced liver disease (cirrhosis) and constructed risk prediction models using machine learning techniques for mortality, readmission, and phenotyping (case identification). Additionally, he constructed machine learning models to phenotype Hepatorenal Syndrome (a complication of cirrhosis) using Natural Language Processing. He has been working on ways to use observational cohort data to predict decompensation in patients with significant medical comorbidities.

March 11, 2022

Matteo D'Antonio, PhD, Assistant Professor of Medicine, UCSD Health Department of Biomedical Informatics, University of California San Diego. "Fine mapping spatiotemporal mechanisms of genetic variants underlying cardiac traits and disease."

Abstract: The causal variants and genes underlying thousands of cardiac GWAS signals have yet to be identified. To address this issue, we leveraged spatiotemporal information on 966 RNA-seq cardiac samples and performed an expression quantitative trait locus (eQTL) analysis detecting ~26,000 eQTL signals associated with more than 11,000 eGenes and 7,000 eIsoforms. Approximately 2,500 eQTLs were associated with specific cardiac stages, organs, tissues and/or cell types. Colocalization and fine mapping of eQTL and GWAS signals of five cardiac traits in the UK BioBank identified variants with high posterior probabilities for being causal in 210 GWAS loci. Over 50 of these loci represent novel functionally annotated cardiac GWAS signals. Our study provides a comprehensive resource mapping regulatory variants that function in spatiotemporal context-specific manners to regulate cardiac gene expression, which can be used to functionally annotate genomic loci associated with cardiac traits and disease.   
Bio: Matteo D’Antonio is an assistant adjunct professor in DBMI, where his main focus is identifying the molecular mechanisms underlying the associations between genetic variation and disease. He got his Bachelor’s degree in biomedical engineering at Politecnico di Milano in Italy and his Master’s in Bioinformatics at the Technical University of Denmark. After that, he obtained his PhD at the European Institute of Oncology, where he studied the evolution of protein interaction networks and cancer genes. He joined UCSD in 2013 where he transitioned from cancer genomics to human genetics. He worked in Dr. Kelly Frazer’s lab as a postdoc and project scientist before transitioning to assistant professor this month.

March 4, 2022

Brett Beaulieu-Jones, PhD, Instructor in Biomedical Informatics, Harvard Medical School, Research Fellow in Neurology, Brigham and Women's Hospital. "Generalting Robust Insights of Disease Heterogeneity and Patient Outcome with Real-World Data and Machine Learning."
Abstract: The emergence of Real-World Data (RWD) presents unprecedented opportunities to examine longitudinal trajectories of human health. Additionally, heterogeneity of disease and progression indicates differing etiology and/or environment (including healthcare). However, most RWD are not generated with research in mind and the RWD ecosystem is relatively nascent. This presentation illustrates how informatics and machine learning methods can overcome the unique challenges of generating reliable insights from RWD - including 1) small sample sizes of labeled data, 2) missing data, 3) limited data sharing (and therefore reproducibility) due to privacy requirements, 4) patients changing over time, and 5) the integration of clinical knowledge. Finally, these methods will be showcased in the potential of predictive models to provide clinically useful decision support as well as the study of heterogeneous neurological conditions. 
Bio: Brett Beaulieu-Jones received his PhD from the Perelman School of Medicine at the University of Pennsylvania under the supervision of Dr. Jason Moore and Dr. Casey Greene. Beaulieu-Jones’ doctoral research focused on using machine learning-based methods to more precisely define phenotypes from large-scale biomedical data repositories, e.g. those contained in clinical records. At DBMI he is expanding this concentration to include large-scale data integration (genomic, therapeutic, imaging) to both better understand disease etiology as well as provide precise therapeutic recommendations. Initially, he is working to develop targeted models of drug selection for patients with refractory epilepsy and to further develop machine learning methods that model the way patients progress over time using longitudinal data.

February 25, 2022

Michael Hogarth, MD, FACMI, FACP, Professor of Clinical Medicine, UC San Diego Health Department of Biomedical Informatics, University of California San Diego "Building Informatics Systems to Support Clinical Research and a Highly Reliable, Learning Healthcare System."

Abstract: Clinical research is critical to the advancement of medical science and public health. Conducting such research is a complex, resource intensive endeavor comprised of a multitude of actors, workflows, processes, and information resources. Ongoing large-scale efforts have explicitly focused on increasing the clinical research capacity of the biomedical sector and have served to increase attention on clinical research and related biomedical informatics activities throughout the governmental, academic, and private sectors. Dr. Hogarth will outline key strategic goals and their following informatics based strategies to facilitate clinical research as well as quality improvement in a healthcare institution. Finally, Dr. Hogarth will provide an update on clinical research informatics systems and services at UCSD.  

Bio: Dr. Michael Hogarth is board certified Internal Medicine physician and a faculty in biomedical informatics. He currently also serves as Chief Clinical Research Information Officer for UC San Diego Health. He is also engaged in a number of grant and contract funded activities. These include the California Electronic Death Registration System (California EDRS), the Maryland Death Registration System, the Athena Breast Health Network project (http://www.athenacarenetwork.org), the novel I-SPY2 adaptive breast cancer clinical trial, the pSCANNER clinical data research network (CDRN), and the California Precision Medicine Consortium (CaPMC). In 2015 he was elected to the American College of Medical Informatics (ACMI).  Dr. Hogarth's research interests include the development of next generation public health information systems, terminology/ontology infrastructure in biomedical informatics, and developing systems that support clinical research at the point of care.

February 18, 2022

Jonathan Lam, PhD Candidate,  Nemati Lab,  UC San Diego Health Department of Biomedical Informatics, University of California San Diego. "Development and Implementation of a Clinical Decision Support Tool in the Era of COVID-19."

Abstract: Multisystem inflammatory syndrome in children (MIS-C) is a novel disease identified during the COVID-19 pandemic characterized by systemic inflammation following SARS-CoV-2 infection. In this talk, we will describe the development of a machine learning model to distinguish MIS-C from similar pediatric inflammatory diseases such as Kawasaki disease. We will then discuss the implementation of the model at Rady Children’s Hospital as well as the FDA regulatory pathways to export the model nationally.

Bio: Jonathan is a PhD student in the lab of Dr. Shamim Nemati at the University of California San Diego Health Department of Biomedical Informatics. His research focuses on the development and implementation of machine learning models to aid in the clinical diagnosis of multiple inflammatory syndrome, Kawasaki disease, and sepsis in pediatric patients.

February 4, 2022

Jejo Koola, MD., MS, Assistant Professor of Medicine, UCSD Health Department of Biomedical Informatics, University of California San Diego. "Modeling Learning Effects for Medical Device Safety Surveillance Using Maching 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: Dr. Koola a practicing hospital medicine physician with ten years practicing experience in multiple medical centers. He focuses on treating multi-morbid patients hospitalized for a variety of conditions including sepsis, organ failure, and chronic kidney, heart, or liver disease. During his fellowship in Biomedical Informatics at the Department of Veterans Affairs in conjunction with a master’s degree from Vanderbilt University, he gained formal skills in database management, data mining, information retrieval, software engineering, and natural language processing. As part of the R2D2 Consortium, he 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. He currently isleading 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, he constructed machine learning models to phenotype Hepatorenal Syndrome (a complication of cirrhosis) using Natural Language Processing. He has been working on ways to use observational cohort data to predict decompensation in patients with significant medical comorbidities.

January 28, 2022

Tsung-Ting (Tim) Kuo, PhD., Assistant Professor, UCSD Health Department of Biomedical Informatics, University of California San Diego. "Decentralized Predictive Modeling and Misconduct Detection."

Abstract: In this talk, Dr. Tsung-Ting Kuo will first introduce decentralized predictive modeling. Then, Dr. Kuo will discuss a real-world risk of such modeling algorithms: incorrect models may be submitted to the learning process, due to either unforeseen accidents or malicious intent, and could therefore reduce the incentives for institutions to participate in the federated modeling consortium. Finally, Dr. Kuo will describe a detection method for such "model misconducts", aiming at solving the problem in an algorithm-agnostic way.

Bio: Dr. Tsung-Ting Kuo is an Assistant Professor of Medicine in University of California San Diego (UCSD) Health Department of Biomedical Informatics (DBMI). He earned his PhD from National Taiwan University (NTU) in the Institute of Networking and Multimedia. Prior to becoming a faculty member, he was a Postdoctoral Scholar at UCSD DBMI and received the UCSD Chancellor’s Outstanding Postdoctoral Scholar Award. He was a major contributor towards the UCSD DBMI team winning the Office of the National Coordinator for Health Information Technology (ONC) healthcare blockchain challenge, and also the NTU team winning the Association for Computing Machinery (ACM) Knowledge Discovery and Data Mining (KDD) Cup competition four times. He was awarded a NIH K99/R00 Pathway to Independence Award with an Administrative Supplement, as well as UCSD Academic Senate Health Science Research Grants, for blockchain-based biomedical, healthcare and genomic studies. His research focuses on blockchain technologies, machine learning, and natural language processing.

January 21, 2022

Philip R.O. Payne, PhD, FACMI, FAMIA, FAIMBE, FIAHSI, Becker Professor and Director Institute for Informatics (I2), Washington University in St. Louis.  "The Learning Health System: Thinking and Acting Across Scales."

Abstract: A Learning Health System (LHS) can be defined as an environment in which knowledge generation processes are embedded into daily clinical practice in order to continually improve the quality, safety, and outcomes of healthcare delivery. While still largely an aspirational goal, the promise of the LHS is a future in which every patient encounter is an opportunity to learn and improve that patient’s care, as well as the care their family and broader community receives. The foundation for building such an LHS can and should be the Electronic Health Record (EHR), which provides the basis for the comprehensive instrumentation and measurement of clinical phenotypes, as well as a means of delivering new evidence at the patient- and population levels. In this presentation, we will explore the ways in which such EHR-derived phenotypes can be combined with complementary data across a spectrum from biomolecules to population level trends, to both generate insights and deliver such knowledge in the right time, place, and format, ultimately improving clinical outcomes and value.

Bio: Dr. Payne is the Janet and Bernard Becker Professor and founding Director of the Institute for Informatics (I2) at Washington University in St. Louis. He is also the Associate Dean for Health Information and Data Science and Chief Data Scientist for the Washington University School of Medicine, while holding additional appointments as a Professor of Medicine and Computer Science and Engineering. Dr. Payne is an internationally recognized leader in the field of translational bioinformatics (TBI) and clinical research informatics (CRI). He received his PhD with distinction in Biomedical Informatics from Columbia University, where his research focused on the use of knowledge engineering and human-computer interaction design principles in order to improve the efficiency of multi-site clinical and translational research programs. Dr. Payne’s leadership in the informatics community has been recognized through his appointment to numerous national steering, scientific, editorial, and advisory committees, including efforts associated with the American Medical Informatics Association (AMIA), AcademyHealth, the Association for Computing Machinery (ACM), the National Cancer Institute (NCI), the National Library of Medicine (NLM), and the National Center for Advancing Translational Science (NCATS). Dr. Payne is the author of over 200 publications focusing on the intersection of biomedical informatics and the clinical and translational research domains, including several seminal reports that have served to define a new sub-domain of biomedical informatics theory and practice specifically focusing upon those areas. Dr. Payne’s research group currently focuses on efforts in the fields of biomedical data science, applied clinical informatics, and clinical research informatics, including efforts related to: 1) cognitive computing and machine learning based approaches to computational phenotyping; 2) the design and delivery advanced clinical decision support system that can enable shared decision-making; 3) human factors and workflow issues surrounding the use of technology at the point-of-care; and 4) open-science platforms that enable collaborative approaches to biomedical and healthcare data analytics.

January 14, 2022

Wei Qi-Wei, MD, PhD, FAMIA, Assistant Professor, Department of Biomedical Informatics, School of Medicine, Vanderbilt University.  "Challenges and Current Advances for Phenotyping."

Abstract: Phenotyping based on electronic health record (EHR) data, especially high-throughput phenotyping, is a novel scientific field. It overcomes the challenges inherent in manually developing phenotyping algorithms to classify cases and controls from large-scale datasets. In this talk, Dr. Qi-Wei will describe the significant challenges of using EHR for phenotyping and highlight some work in developing high-throughput phenotyping techniques at Wei's lab (http://phenotyping.org/).

Bio: Dr. Wei is a tenure-track assistant professor of biomedical informatics and computer science (secondary) at Vanderbilt University Medical Center (VUMC), specializing in high throughput phenotyping for large-scale discovery using electronic health records (EHRs). He initially received his medical degree from Peking Union Medical College and Chinese Academy of Medical Science in 2005, a Ph.D. in Health Informatics from the University of Minnesota in 2012 working with Chris Chute, and completed post-doctoral training at Vanderbilt with Joshua Denny in 2014. His research program focuses on creating and leveraging informatics tools, including machine learning, natural language processing, and ontology techniques to harvest knowledge from big clinical/genetic data to advance precision medicine. His work has discovered new genetic relationships between common diseases and common drugs, and generated novel approaches (e.g., PheMAP and DDIWAS) and knowledge bases (e.g., Phecode and MEDI) to enable quality research. Dr. Wei is the PI of multiple R01s and P50s. He participates in several collaborative research networks, including eMERGE, MPRINT, and All of Us. He chairs the eMERGE phenotyping workgroup and serves as the director of Precision Phenotyping Core at VUMC. Dr. Wei is an elected Fellow of the American Medical Informatics Association (FAMIA) in 2019. He has published >100 research papers and invited reviews.

January 7, 2022

David Gilbert, PhD, Senior Investigator, Laboratory of Chromosome Replication and Epigenome Regulation, San Diego Biomedical Research Institute. 

Bio: Dave Gilbert focuses on the mechanisms regulating DNA replication during the cell cycle and the relationship between DNA replication and structural and functional organization of chromosomes, most recently during differentiation in human and mouse embryonic stem cells and in pediatric leukemia.

Dr. Gilbert received his BA degrees in Biochemistry/Cell Biology and Philosophy from the University of California at San Diego and his PhD in Genetics from Stanford University. He did two post-doctoral training periods, first as an EMBO Fellow with Pierre Chambon in Strasbourg, France studying transcriptional control, and second as a Roche Fellow with Melvin DePamphilis studying replication origin recognition. In 2006, he moved to Florida State University where he served as J. Herbert Taylor Distinguished Professor of Molecular Biology in the Department of Biological Science and Co-founder and Associate Director of the Center for Genomics and Personalized Medicine at Florida State University (2006-2020). Center for Clinical Informatics and Improvement Research.