Predicting the Predictable in the Psychiatric High Risk

Eric Strobl
Proceedings of the 10th Machine Learning for Healthcare Conference, PMLR 298, 2025.

Abstract

Most investigators in precision psychiatry force models to predict clinically meaningful but ultimately predefined outcomes in a high-risk population. We instead advocate for an alternative approach: let the data reveal which symptoms are predictable with high accuracy and then assess whether those predictable symptoms warrant early intervention. We correspondingly introduce the Sparse Canonical Outcome REgression (SCORE) algorithm, which combines items from clinical rating scales into severity scores that maximize predictability across time. Our findings show that this simple shift in perspective significantly boosts prognostic accuracy, uncovering predictable symptom profiles such as social difficulties and stress-paranoia from those at clinical high risk for psychosis, and social passivity from infants at genetic high risk for autism. The predictable scores differ markedly from conventional clinical metrics and offer clinicians memorable, actionable insights even when full diagnostic criteria are unmet. An R implementation is available at https://anonymous.4open.science/r/SCORE-B06C.

Cite this Paper

BibTeX
@InProceedings{pmlr-v298-strobl25a, title = {Predicting the Predictable in the Psychiatric High Risk}, author = {Strobl, Eric}, booktitle = {Proceedings of the 10th Machine Learning for Healthcare Conference}, year = {2025}, editor = {Agrawal, Monica and Deshpande, Kaivalya and Engelhard, Matthew and Joshi, Shalmali and Tang, Shengpu and Urteaga, Iñigo}, volume = {298}, series = {Proceedings of Machine Learning Research}, month = {15--16 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v298/main/assets/strobl25a/strobl25a.pdf}, url = {https://proceedings.mlr.press/v298/strobl25a.html}, abstract = {Most investigators in precision psychiatry force models to predict clinically meaningful but ultimately predefined outcomes in a high-risk population. We instead advocate for an alternative approach: let the data reveal which symptoms are predictable with high accuracy and then assess whether those predictable symptoms warrant early intervention. We correspondingly introduce the Sparse Canonical Outcome REgression (SCORE) algorithm, which combines items from clinical rating scales into severity scores that maximize predictability across time. Our findings show that this simple shift in perspective significantly boosts prognostic accuracy, uncovering predictable symptom profiles such as social difficulties and stress-paranoia from those at clinical high risk for psychosis, and social passivity from infants at genetic high risk for autism. The predictable scores differ markedly from conventional clinical metrics and offer clinicians memorable, actionable insights even when full diagnostic criteria are unmet. An R implementation is available at https://anonymous.4open.science/r/SCORE-B06C.} }
Endnote
%0 Conference Paper %T Predicting the Predictable in the Psychiatric High Risk %A Eric Strobl %B Proceedings of the 10th Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2025 %E Monica Agrawal %E Kaivalya Deshpande %E Matthew Engelhard %E Shalmali Joshi %E Shengpu Tang %E Iñigo Urteaga %F pmlr-v298-strobl25a %I PMLR %U https://proceedings.mlr.press/v298/strobl25a.html %V 298 %X Most investigators in precision psychiatry force models to predict clinically meaningful but ultimately predefined outcomes in a high-risk population. We instead advocate for an alternative approach: let the data reveal which symptoms are predictable with high accuracy and then assess whether those predictable symptoms warrant early intervention. We correspondingly introduce the Sparse Canonical Outcome REgression (SCORE) algorithm, which combines items from clinical rating scales into severity scores that maximize predictability across time. Our findings show that this simple shift in perspective significantly boosts prognostic accuracy, uncovering predictable symptom profiles such as social difficulties and stress-paranoia from those at clinical high risk for psychosis, and social passivity from infants at genetic high risk for autism. The predictable scores differ markedly from conventional clinical metrics and offer clinicians memorable, actionable insights even when full diagnostic criteria are unmet. An R implementation is available at https://anonymous.4open.science/r/SCORE-B06C.
APA
Strobl, E.. (2025). Predicting the Predictable in the Psychiatric High Risk. Proceedings of the 10th Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 298 Available from https://proceedings.mlr.press/v298/strobl25a.html.

Related Material