Protocol for Designing a Model to Predict the Likelihood of Psychosis From Electronic Health Records Using Natural Language Processing and Machine Learning
This proposed model leverages the strengths of the large volume of patient-specific data from an integrated electronic health record with natural language processing to identify patients at elevated chance of developing a PSD. This project carries the potential to reduce the duration of untreated psychosis and thereby improve long-term patient outcomes.
Authors
- Andrea H. Kline‐Simon (ORCID: https://orcid.org/0000-0002-6303-7308)
- Ben J. Marafino (ORCID: https://orcid.org/0000-0003-2385-7376)
- Matthew E. Hirschtritt (ORCID: https://orcid.org/0000-0001-8654-1825)
- Icelini Stavers-Sosa (ORCID: https://orcid.org/0000-0001-9040-3724)
- David Carrell (ORCID: https://orcid.org/0000-0002-8471-0928)
- Lawrence Gerstley
- David Cronkite (ORCID: https://orcid.org/0000-0002-2797-5102)
- Arvind Ramaprasan
- Linda Kiel
- Ann E. Kelley
Institutions
- Kaiser Permanente (US)
- Kaiser Permanente Washington Health Research Institute (US)
- University of California, San Francisco (US)
- Kaiser Permanente Oakland Medical Center (US)
Publication Details
- Journal
- The Permanente Journal
- Published
- 2024-09-02
- DOI
- https://doi.org/10.7812/tpp/23.139
- Citations
- 1
- Primary Topic
- Schizophrenia research and treatment
- Type
- article
- Field-Weighted Citation Impact
- 0.39
Funders
- Kaiser Permanente