About

CSCI 5980/8980: Machine Learning for Health: Concepts and Applications - Spring 2024

Class overview:

Machine Learning (ML) is transforming healthcare. But unlike traditional ML applications, health applications require a careful understanding of the data, the clinical problem, and how they will impact the stakeholders, e.g., patients, caretakers, clinicians, and payers. This course will introduce students to a range of healthcare problems that can be tackled using ML, different health data modalities, relevant machine learning paradigms, and the unique challenges presented by healthcare applications. Applications we will cover include risk stratification, disease progression modeling, precision medicine, diagnosis, prognosis, subtype discovery, clinical text mining with large language models, and improving clinical workflows. We will also cover research topics such as explainability, causality, federated learning, trust, robustness, and fairness. Course will include several coding assignments and a final project allowing students to understand and appreciate the intricacies of working with real world health data.

Textbook: None

Prerequisites: CSCI 5521 or equivalent

Class time and venue:

  • MW 1.00 PM – 2.15 PM
  • 3-111 Keller Hall

Instructor: Prof. Yoga Varatharajah

Class work:

CSCI 5980
Four programming assignments on real-world healthcare ML applications

  • Each will count to 15% of the grade

Final project (student proposed)

  • 40% of the grade

CSCI 8980
Four programming assignments on real-world healthcare ML applications

  • Each will count to 10% of the grade

Final project (student proposed)

  • 40% of the grade

Paper presentation

  • 20% of the grade

Intended audience:

Graduate and senior undergraduate students in CS&E, ECE, BICB, BME, and IHI.

Why should students be interested in the class?

There is a significant interest in the healthcare industry (e.g., hospitals, device companies, medical/bio-tech companies, and health insurance companies) to leverage recent developments in ML to advance their respective products and services. This course will prepare students to be proficient in relevant topics and applications with hands-on experience applying ML to real-world health data. Students will also have the opportunity to meet and interact with guest lecturers from the respective industries throughout the course.