Department of Public Health

Machine Learning in Public Health:
A Mount Sinai 2.5 Day Workshop
Advancing Public Health Innovation in Clinical Science
for Health Professionals and Researchers

Offered by the Department of Public Health in collaboration with the
Department of Environmental Medicine

July 7 & 8: 9:00 am - 5:00 pm
July 9: 9:00 am - Noon
Offered in-person or online (via Zoom)

Onsite Location:
Annenberg Building, 1468 Madison Avenue
Icahn School of Medicine at Mount Sinai
Classroom A5-212
New York, NY

2.5-Day workshop offered by the Department of Public Health and the Department of Environmental Medicine at the Icahn School of Medicine at Mount Sinai
Prerequisite: Basic knowledge of epidemiology and biostatistics

The application of machine learning (ML) has struck a crucial note in addressing major issues in public health. The use of ML is transdisciplinary and ranges from:

Improving disease diagnosis
Developing personalized treatment strategies
Understanding health behavior analysis
Outbreak detection
Pattern of exposures to environmental chemicals

The tremendous potential of ML methods to benefit healthcare professionals and researchers is just now beginning to be realized. As with the recent surge in artificial intelligence and machine learning methods, there is a tremendous opportunity in both the public and private sectors to develop innovative solutions to present-day critical public health issues (e.g., climate and health, pandemic response, mental health and others). Organizations and commercial companies, including public health departments, health policy institutes, research organizations, medical centers, and health insurance organizations, are utilizing novel machine learning approaches to solve these complex real world problems integrating large data streams. Therefore, a solid understanding of the underlying techniques and methodologies is needed to better appreciate the nuances of ML techniques applicable to public health is critical.

Instructor: Vishal Midya, PhD, MSTAT

E-mail: vishal.midya@mssm.edu

Learning Objectives

By the end of this workshop, participants should be able to:

Build basic machine-learning models to solve public health problems.
Have an advanced understanding of machine-learning methods, specifically when to use one and when not to use one.
Understand the statistical underpinning of the models and how they can be modeled to address a public health problem.
Have the knowledge and skill sets to develop and conduct their machine learning research projects independently.

Registration deadline: July 1

Mount Sinai Employee/Staff*: $1,000/pp Click here to register and submit payment.

*Potential CTSA funding for faculty, post docs may be available. Apply by June 26 (details on registration form)
Non-Mount Sinai Employee/Staff: $1,200/pp Click here to register and submit payment.

Mount Sinai Current Student special discounted rate: $250/pp. Click here to register and submit payment. *Potential CTSA funding for students may be available. Apply by June 26 (details on registration form)

Total includes breakfast and lunch

Questions? Email healthcaremasters@mssm.edu

Overview

Overview: This introductory workshop will include a detailed overview of statistical machine-learning methods for application in public health. This workshop is an excellent source of information for anyone who wants to learn the fundamentals of statistical machine learning. It is designed to accommodate epidemiologists, clinicians, public health professionals, biostatisticians, and other health professionals. The course is led by Dr. Vishal Midya from the Department Environmental Medicine, Icahn School of Medicine at Mount Sinai. This workshop will integrate in-class lectures with many applications related to public health, especially environmental health.

Course learning objectives and training approach:

We will cover the foundational concepts of statistical machine learning with emphasis on problems in public health. We will introduce the:

Basics of regression and classification problems
Concepts of regularized linear models
Basics of stacking in multi-layer models
Tree-based machine learning models
Techniques of unsupervised modeling
Basics of mixture models

All techniques will be illustrated with extensive examples, and specific skills and epidemiological concepts will be introduced in relation to the methods. This course will include lectures, extensive demonstrations of each technique, and coding guidance for practical data analysis. We will only use free and open-source tools (R and R studio) widely available for academic use. By the end of the course, students will understand and will be able to implement basic machine-learning techniques to enhance public health and epidemiological research.

Requirements

Basic knowledge of epidemiology and biostatistics will be helpful. Some familiarity with programming languages like R is welcomed, but this is an introductory workshop; therefore, presented materials will be suitable for beginners. As for the technical requirements, in-class labs will require a laptop and the various software tools used in the course. Please bring a compatible laptop (Windows/macOS/Linux) to the workshop. Ensure the laptop has internet connection capabilities (Wi-Fi), a web browser, and permission to install software (R and R Studio).

Main software used: R and R Studio