Dr. Tavpritesh Sethi

IIIT, New Delhi, India.

Dr. Tavpritesh Sethi is an Assistant Professor in Computational Biology at Indraprastha Institute of Information Technology Delhi and the Regional Leader of IASyM for Australasia (AASyM). He was a visiting faculty member at Stanford University, School of Medicine from February 2017 - January 2019 and is a Wellcome Trust/DBT India Alliance sponsored Fellow at Department of Pediatrics, All India Institute of Medical Sciences, New Delhi; He is a clinician (M.B.B.S.) turned computational scientist (Ph.D.) focused on enabling next-generation decision systems using the principles of Systems Medicine and Artificial Intelligence. His focus areas for AI development are Critical Care Medicine, Maternal and Child health, Public Health and AI for Social Good. He is the Regional Editor of Systems Medicine


Systems AI for Critical Care, Public Health, Maternal and Child Health, Health Inequality and Social Good.

Session: Pre-Conference Workshop

Day 1: September 12, 2019 | Session CO-CHAIR | 9:00 AM - 5:00 PM

Tavpritesh Sethi, MBBS, PhD, IIIT, Delhi, India.

Session: Pre-Conference Workshop, HANDS-ON SESSION

Day 1: September 11, 2019 | Pre-Conference Workshop | 10:30 AM - NOON

From Complex Networks To Clinical Decisions With Bayesian Artificial Intelligence

Tavpritesh Sethi, MBBS, PhD, IIIT, Delhi, India.

Networks are one of the most intuitive representations of complex data. However, most networks rely on pair-wise associations which limits their use for making decisions. Bayesian Decision Networks (BDNs) extend a class of probabilistic graphical models known as Bayesian Networks by using decision theory and have been used in business settings for decision making. However, BDNs are under-exploited in clinical and public health settings because of the complex nature of datasets which makes it difficult for these networks to be hand-specified. This tutorial will teach the participants to learn Bayesian-network models directly from data, assess these rigorously with statistical bootstrap evaluations, draw quantitative inferences, learn optimal decisions and deploy their models as a web-application based upon R/Shiny framework. Participants will learn to use these models both for probabilistic reasoning and causal inference depending upon the study design. Unlike most other forms of Artificial Intelligence and Machine Learning, BDNs are white-box models falling in the class of Explainable AI (XAI) and Fair Accountable Transparent ML (FAT-ML). The tutorial will cover an end-to-end walkthrough of the open-source platform, wiseR developed by the instructor and his team in collaboration with computer scientists and clinicians at Stanford and India. The tutorial will cover preliminary theory and two case-studies, in a clinical setting for Sepsis and a public health setting (Health Inequality) for learning decisions and policy, both published and available with linked open-data.


DAY 3: September 13, 2019 | Session 6 | 3:15 PM - 3:35 PM

Learning to Predict Critical Outcomes in the Intensive Care Unit: the Safe-ICU Perspective

Tavpritesh Sethi, MBBS, PhD, IIIT, Delhi, India.

A new machine learning paper is published every 20 minutes, yet a tiny fraction of these makes its way to the bedside. This talk will outline our effort to bridge this gap with Meaningful, Enriching and Discovery-led Artificial Intelligence for Medicine (MED-AIM) for the Intensive Care Units. Case studies from our work on predictive models for the ICU and public health settings will be presented including the creation of SAFE-ICU, the largest Pediatric Big-data resource at All India Institute of Medical Sciences, New Delhi, India. The development of wiseR, our interpretable and interactive AI platform for constructing Bayesian Decision Networks will be highlighted with case studies addressing antimicrobial resistance and maternal health. The talk will conclude with a discussion on social aspects of AI in medicine and our learnings on mitigation of health inequality in the United States.