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.  Located in the UCSF Department of Anesthesia and Periperative Care, we are broadly interested in problems of prediction and causal inference. In particular, 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 work to 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.

Featured Publications







Mortality prediction in intensive care units with the Super ICU Learner Algorithm (SICULA): a population-based study.
The Lancet. Respiratory medicine

Pirracchio R, Petersen ML, Carone M, Rigon MR, Chevret S, van der Laan MJ