Predicting conversion to psychosis using machine learning: response to Cannon

Predicting conversion to psychosis using machine learning: response to Cannon

BackgroundWe 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...

Full description

Saved in:
Bibliographic Details
Main Authors: Jason Smucny, Tyrone D. Cannon, Carrie E. Bearden, Jean Addington, Kristen S. Cadenhead, Barbara A. Cornblatt, Matcheri Keshavan, Daniel H. Mathalon, Diana O. Perkins, William Stone, Elaine F. Walker, Scott W. Woods, Ian Davidson, Cameron S. Carter
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-01-01
Series:Frontiers in Psychiatry
Subjects:
schizophrenia
clinical high risk (CHR)
NAPLS
out of sample evaluation
scale of psychosis risk symptoms
generalizability
Online Access:https://www.frontiersin.org/articles/10.3389/fpsyt.2024.1520173/full
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:BackgroundWe 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.MethodStandard 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.ResultsNAPLS-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.ConclusionThe 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.
ISSN:1664-0640

Similar Items