Predicting readmission and recovery rates of psychiatry patients in mental health facilities within Canada: A machine learning approach

Hospital readmission from in-patient psychiatry is increasingly problematic for patients and care administrators, as they often are associated with poor clinical outcomes and higher care costs. An understanding of factors that predispose in-patient psychiatry patients to hospital readmission would be critical in improving patient care and reducing healthcare-related costs.
My research proposes to use machine learning methods to determine factors predictive of hospital readmission among in-patient psychiatry patients. Machine learning techniques are increasingly useful in healthcare delivery because of the advantage they have over traditional analytic techniques.
Developing machine learning pipelines related to this project will allow me to obtain practical knowledge both in the public health field and artificial intelligence research areas. This research project will also enhance the establishment of collaboration between my home advisor and the University of Waterloo, enabling access to existing academic sources, datasets, and computational resources.

Faculty Supervisor:

John P. Hirdes

Student:

Partner:

National Technical University of Ukraine

Discipline:

Sociology

Sector:

Artificial Intelligence; Health and Related Sciences & Technology

University:

University of Waterloo

Program: