Publication

Predicting conversion to psychosis using machine learning: response to Cannon

Downloadable Content

Persistent URL
Last modified
  • 02/25/2026
Type of Material
Authors
    Jason Smucny, University of California, DavisTyrone D. Cannon, Yale UniversityCarrie E. Bearden, University of California, Los AngelesJean Addington, University of CalgaryKristen S. Cadenhead, University of North Carolina, Chapel HillBarbara A. Cornblatt, Zucker Hillside HospitalMatcheri Keshavan, Harvard UniversityDaniel H. Mathalon, University of California, San FranciscoDiana O. Perkins, University of San DiegoWilliam Stone, Harvard UniversityElaine F. Walker, Emory UniversityScott W. Woods, Yale UniversityIan Davidson, University of California, DavisCameron S. Carter, University of California, Irvine
Language
  • English
Date
  • 2025-01-15
Publisher
  • Frontiers
Publication Version
Copyright Statement
  • © 2025 Smucny, Cannon, Bearden, Addington, Cadenhead, Cornblatt, Keshavan, Mathalon, Perkins, Stone, Walker, Woods, Davidson and Carter
License
Final Published Version (URL)
Title of Journal or Parent Work
Volume
  • 15
Start Page
  • 1520173
Grant/Funding Agency
  • NIMH
Grant/Funding Information
  • This work was supported by NIMH grants K01-MH125096 (JS), R01-MH122139 (CC), U01-MH081902 (TC), P50-MH066286 (CB), U01-MH081857 (BC), U01-MH082022 (SW), U01-MH066134 (JA), U01-MH081944 (KC), U01-MH066069 (DP), R01-MH076989 (DM), and U01-MH081988 to (EW).
Abstract
  • Background We previously reported that machine learning could be used to predict conversion to psychosis in individuals at clinical high risk (CHR) for psychosis with up to 90% accuracy using the North American Prodrome Longitudinal Study-3 (NAPLS-3) dataset. A definitive test of our predictive model that was trained on the NAPLS-3 data, however, requires further support through implementation in an independent dataset. In this report we tested for model generalization using the previous iteration of NAPLS-3, the NAPLS-2, using the identical machine learning algorithms employed in our previous study. Method Standard machine learning algorithms were trained to predict conversion to psychosis in clinical high risk individuals on the NAPLS-3 dataset and tested on the NAPLS-2 dataset. Results NAPLS-2 and -3 individuals significantly differed on most features used in machine learning models. All models performed above chance, with Naive Bayes and random forest methods showing the best overall performance. Importantly, however, overall performance did not match those previously observed when using only NAPLS-3 data. Conclusion The results of this study suggest that a machine learning model trained to predict conversion to psychosis on one dataset can be used to train an independent dataset. Performance on the test set was not in the range necessary for clinical application, however. Possible reasons that limited performance are discussed.
Keywords
Subject - Topics
  • Mental health
  • Machine learning

Tools

Relations

In Collection:

Items

Thumbnail Title File Description Date Uploaded Visibility Actions
file details Predicting conversion to psychosis using machine learning: response to Cannon Primary Content 2026-02-25 Public Download