Using machine learning to allocate stratified care in an electronic cognitive behavioural therapy program for depression

Depression is a leading cause of disability worldwide, yet only one third of patients with depression receive care. This is because the traditional in-person format of mental health care delivery can be inaccessible, inefficient, and expensive. Electronic cognitive behavioural therapy (e-CBT) has been shown to be an effective solution to expand care access, efficiency, and affordability. Combining depression-based e-CBT with artificial intelligence, this study aims to develop an effective decision-making model that matches an individual’s needs with the right amount of care. Our goal at OPTT is to develop a platform that makes e-CBT more efficient and highly accessible to individuals facing mental health issues and this project will use artificial intelligence and tailored interventions to efficiently allocate mental health care resources. At a time when mental health challenges are on the rise due to the pandemic, this technique could scale up care capacity without sacrificing the quality of care.

Faculty Supervisor:

Nazanin Alavi

Student:

Partner:

OPTT

Discipline:

Life Sciences

Sector:

Health and Related Sciences & Technology; Information and cultural industries

University:

Queen's University

Program: