Principal Investigators
Romain Pirracchio, MD, PhD
Dr. Pirracchio is a M.D., MPH, Ph.D., hailing from Paris. He obtained his M.D. in 2003, with a specialization in Anesthesiology and Critical Care Medicine. In 2008, he obtained an MPH and completed his doctoral studies in Biostatistics in Paris, France in 2012. In 2012-2013, he spent a year as a postdoctoral fellow in Biostatistics in the School of Public Health at the University of California, Berkeley. Back in Paris, he was the clinical director of the surgical and trauma ICU at European Hospital Georges Pompidou (2013-2015) and a researcher in Biostatistics with the INSERM U-1153 unit. In 2015-2016, he spent 18 months in the Department of Anesthesia and Perioperative care at the San Francisco General Hospital & Trauma Center (UCSF) as Visiting Associate Professor. In September 2016, he went back to Paris to serve as Full Professor and Chair for the Department of Anesthesia and Critical Care Medicine at European Hospital Georges Pompidou in Paris. Since 2018, he is now Professor of Anesthesia and Critical Care, Professor of Biostatistics at UCSF. He is the chief of Anesthesia and Perioperative Care at ZSFG and vice chair in the department of anesthesia and perioperative medicine at UCSF. In 2019, he became the first recipient of the Ronald D. Miller Distinguished Professorship, Anesthesia and Perioperative Medicine, UCSF. Since 2023, he is the AI Associate Editor for JAMA.
His two main research areas are clinical research in Anesthesiology and Critical care Medicine and applied research in Biostatistics. In Biostatistics, he is broadly interested in problems of predictive analytics, machine learning and causal inference. Dr. Pirracchio founded the epochAI research lab in 2018.
Alan Hubbard, PhD
Dr. Alan Hubbard, Professor and Head of Biostatistics at the Univ. of California, Berkeley, is co-director of the Center of Targeted Learning and head of the computational biology core of the SuperFund Center at UC Berkeley (NIH), as well as a consulting statistician on several federally funded and foundation projects. His current methods research focuses on precision medicine, variable importance, statistical inference for data-adaptive parameters, and statistical software implementing targeted learning methods. He works in several applied research areas including early childhood development in developing countries, environmental genomics, and critical care.
Lab Members
Andrew Bishara, MD
Dr. Andrew Bishara is a UCSF Assistant Professor in Residence in the Department of Anesthesia and the EpochAI Lab @ UCSF. He is also a part of Dr. Atul Butte's Lab at the Bakar Computational Health Sciences Institute (BCHSI). He is a practicing anesthesiologist, and his research focuses on the implementation of AI algorithms in clinical workflows and how to design and build systems that augment rather than hinder clinical care. He is currently building and implementing multiple models to improve outcomes after surgery as part of a NIH K23 grant.
Sylvia Cheng
Sylvia is a Ph.D. Candidate in Epidemiology and concurrently a M.A. student in Biostatistics at UC Berkeley. She is dedicated to advancing the quality of healthcare through the lens of causal inference using machine learning and rigorous statistical methods . Her research focuses on addressing disparities in care and treatment across diverse population groups, and developing methods that target these gaps with emphasis on precision and optimization.
Jean Digitale, PhD
Dr. Jean Digitale is a post-doctoral fellow at UCSF. Her research interests include the intersection of casual inference and machine learning, clinical informatics, and improving quality of care using electronic health record data.
Jean Feng, PhD
Jean Feng is an Assistant Professor in the Department of Epidemiology and Biostatistics at the University of California, San Francisco and the UCSF-UC Berkeley Joint Program in Computational Precision Health and a principal investigator at the UCSF-Stanford Center of Excellence in Regulatory Science and Innovation (CERSI). She is also the data science lead on the predictive analytics team for the Zuckerberg San Francisco General Hospital.
Website
Yunwen (Wendy) Ji
Yunwen (Wendy) Ji is a Biostatistics MA-PhD candidate at UC Berkeley, specializing in causal inference and machine learning. She excels in applying machine learning models to EHR data to explore causal relationships between risk factors and diseases. Her research focuses on developing methodologies for double robust estimators in causal inference and applying state-of-the-art models to real-world clinical data.
Aarti Lalwani
Aarti Lalwani is a senior software engineer specializing in data parallelism for AI chips and a researcher at EpochAI Lab. Her work focuses on medical predictive ensemble algorithms, with an emphasis on uncertainty quantification and reliability. Her interests include machine learning for precision medicine, high-performance learning at scale, and learning theory.
Maxime Léger, MD, PhD
Dr. Maxime Léger is a clinical anesthesiologist and critical care physician currently practicing at UCSF. He conducts both clinical and fundamental research, with a primary focus on optimizing postoperative recovery. Dr. Léger is dedicated to leveraging innovative statistical methodologies to advance the field of causal inference, aiming to enhance patient outcomes in perioperative and critical care settings.
Ivana Malenica, PhD
Dr. Ivana Malenica is an Assistant Professor in the Department of Biostatistics at UNC, specializing in causal inference, machine learning, and non/semiparametric inference. Previously, she was a Wojcicki-Troper Data Science Fellow in the Department of Statistics at Harvard University and completed her Ph.D. in Biostatistics at UC Berkeley. Her research focuses on adaptive sequential design, reinforcement learning, and personalized health.
Rachael Phillips, PhD
Junming (Seraphina) Shi
Junming (Seraphina) Shi is a Ph.D. candidate in Biostatistics at UC Berkeley. Her research focuses on developing methods and applications in precision medicine, causal inference, and machine learning. She is interested in high-dimensional, patient-centered real-world data, such as electronic health records (EHR) and omics data.
Vadim Shteyler, MD
Dr. Vadim Shteyler is a UCSF Pulmonary and Critical Care Fellow doing health data science research at the EpochAI lab. Dr. Shteyler applies novel targeted machine learning methods for causal inference to advance the care of critically ill patients. His research interests include sepsis, healthcare value, and health equity.
Andre Waschka, PhD
Dr. Andre Kurepa Waschka is an Assistant Professor at Mercer University doing research with the EpochAI Lab @ UCSF. His research is in applied statistics and spans biostatistics, data science, and machine learning. He works on semi-parametric and nonparametric statistical models that involve high dimensional data and use causal framework and machine learning to estimate targeted parameters and obtain causal inference. Most of his work is motivated by problems from biomedical fields with application to treatment regime protocols, health equity, and precision medicine.
Tianyue Zhou
Tianyue is currently a PhD student in Biostatistics at UC Berkeley. His research interests lie in the intersection of causal inference, machine learning and healthcare. Recently he has been collaborating with the UCSF Hypoxia Lab on photoplethysmogram (PPG) waveform analysis.