Unlocking the EPIC potential to promote Precision Child Mental Health

The big problem in healthcare Is that that about 80% of medical data remains unstructured and untapped after it is created. It’s hard to handle this type of data for Electronic Medical Record (EPIC), it tends to be ignored, unsaved or abandoned, and therefore is not effectively used in medical treatment or research. It’s highly complicated, ineffective and with high possibility of mistakes of prejudices to conduct any research regarding precision child mental health until there is a structured and reliable mental health data accessible. Our goal is to achieve the ability to reliably infer mental health status from the EPIC used at the Hospital for Sick Children, which is key to unlocking the potential of EPIC for big data mental health research.
We propose to evaluate and improve the reliability of mental health data derived from EPIC and submit that addressing this issue is pivotal for our precision children mental health ambition. We set three aims which will help us to achieve our global goal: 1) Compare three main sources of mental health data; 2) Calculate the sensitivity and specificity metrics of the three sources using manually curated diagnoses as the gold standard.

Faculty Supervisor:

Michael Brudno

Student:

Partner:

Lviv Polytechnic National University

Discipline:

Computer science

Sector:

Artificial Intelligence; Other; Technology

University:

University of Toronto

Program: