The epochAI (Equitable, Precise, Outcome-centered Critical care Health informatics and Artificial Intelligence) Lab @ UCSF uses machine learning and other advanced epidemiologic and statistical methods to understand treatment patterns, uncover disparities, and predict clinically relevant outcomes in the perioperative and critical care environment. We are broadly interested in problems of prediction and causal inference. We enjoy working on the development of novel methodologies for addressing scientific questions using complex observational data subject to sampling biases. Our work primarily focuses on the following domains: Predictive Analytics Harnessing the power of data to foresee patient outcomes is at the core of our research. Through predictive analytics, we employ advanced statistical models and machine learning algorithms to anticipate post-operative and critical care scenarios, enabling proactive interventions and personalized patient care pathways. Clinical Decision Support Systems We develop Clinical Decision Support Systems (CDSS) tailored to the individual patient, integrating comprehensive patient data with clinical guidelines and expert knowledge. Through personalized approaches, we strive to optimize care delivery to ensure that each patient receives the most appropriate interventions based on their unique characteristics and clinical context. AI Equity and Fairness Ensuring equity and fairness in healthcare AI is a paramount concern. Our lab is dedicated to developing algorithms and methodologies that mitigate bias and promote fairness across diverse patient populations. By addressing disparities in healthcare access and outcomes, we aim to create AI solutions that contribute to equitable healthcare delivery for all. AI Vigilance and Monitoring Continuous monitoring and vigilance are essential for the safe and effective deployment of AI in clinical settings. Our group is actively investing in creating frameworks to understand and monitor clinically relevant AI models.
