skip to Main Content

A Model to Predict Psychosis Risk from Electronic Health Records Using Natural Language Processing and Machine Learning

This study will apply sentiment analysis — a form of natural language processing — to electronic health records to create a risk score for psychosis among adolescent and young adult Kaiser Permanente members. The findings will be used to establish a foundation for technology-assisted identification of at-risk patients and to offer these patients information and resources to address psychotic symptoms.

Investigator: Hirschtritt, Matthew

Funder: Garfield Memorial Fund

Explore all studies and publications

Back To Top