Skip to the content.

This repository contains information about the tutorial Machine Learning in Population and Public Health: challenges and opportunites at ACM Conference on Health, Information and Learning, 2020. A full summary of the tutorial is provided in this document. Citation:
Mhasawade, Vishwali, Yuan Zhao, and Rumi Chunara. “Machine Learning in Population and Public Health.” ArXiv:2008.07278 [Cs], July 21, 2020.

Tutorial video found here.

Table of contents

  1. Audience
  2. Goals, Overview and Slides
  3. Taxonomy
  4. About Us


The primary audience for this tutorial is computer science and statistics researchers, who are interested in how machine learning may provide opportunities to address challenges in health research and practice. In particular, those who may already be working in machine learning in healthcare may find discussions in this tutorial helpful regarding machine learning with respect to the spectrum of health across prevention and promotion, to health protection, diagnosis, treatment and care as well as the integration and balance between these aspects. Public health professionals and researchers who have the prerequisite background of an introductory understanding of machine learning and causal inference may also be interested in this tutorial.

Goals, Overview and Slides

The goals of this tutorial are to:
1) Familiarize the audience with research in public and population health
2) Identify open areas relevant to machine learning and health equity
3) Activate the machine learning community on challenges in public/population health

The tutorial is composed of three parts. Click each icon to access the slides.

  • What are Public and Population health?
  • Theory and framework of social determinants of health (SDoH)
  • Measurement of SDoH
  • SDoH interventions
  • SDoH in machine learning models
  • Taxonomy of health tasks
  • Causal inference in public health
  • Challenges with using proxies
  • Algorithmic fairness and health disparities


In order to demonstrate the use of machine learning across aspects of health, comprehensively, we developed a taxonomy of Machine Learning in health tasks (broadly) and list example studies below.


About Us

Rumi Chunara Vishwali Mhasawade Yuan Zhao
Rumi Chunara is an Assistant Professor at NYU, jointly appointed at the Tandon School of Engineering (in Computer Science) and the School of Global Public Health (in Biostatistics/Epidemiology). Her research group focuses on developing computational and statistical approaches for acquiring, integrating and using data to improve population-level public health, with data from clinical and outside-clinic sources. She is an MIT TR 35 under 35, NSF Career, Facebook Research Award and Max Planck Sabbatical Award winner. Vishwali Mhasawade is a Ph.D. student at NYU Tandon School of Engineering. She is interested in working at the intersection of causal inference and algorithmic fairness with the goal of mitigating health disparities. Her previous work focused on causal transport, to improve understanding of population-level information while incorporating data from multiple environments. Yuan Zhao is a doctoral student at NYU School of Global Public Health. She is interested in application of machine learning in disease prediction and causal inference. Her previous research included modeling transmission and prevention of STI and HIV/AIDS among marginalized populations and evaluating novel drugs treating multidrug resistant tuberculosis using targeted maximum likelihood estimation (TMLE).