Publication

Toward Generalizable and Transdiagnostic Tools for Psychosis Prediction: An Independent Validation and Improvement of the NAPLS-2 Risk Calculator in the Multisite PRONIA Cohort

Downloadable Content

Persistent URL
Last modified
  • 09/18/2025
Type of Material
Authors
    Nikolaos Koutsouleris, Klinikum der Universität MünchenMichelle Worthington, Yale UniversityDominic B Dwyer, Klinikum der Universität MünchenLana Kambeitz-Ilankovic, Klinikum der Universität MünchenRachele Sanfelici, Klinikum der Universität MünchenPaolo Fusar-Poli, Università degli Studi di PaviaMarlene Rosen, Medizinische FakultätStephan Ruhrmann, Medizinische FakultätAlan Anticevic, Yale UniversityJean Addington, Hotchkiss Brain InstituteDiana O Perkins, The University of North Carolina at Chapel HillCarrie E Bearden, Jane & Terry Semel Institute for Neuroscience & Human BehaviorBarbara A Cornblatt, Zucker Hillside HospitalKristin S Cadenhead, University of California, San DiegoDaniel H Mathalon, University of California, San FranciscoThomas McGlashan, Yale School of MedicineLarry Seidman, Beth Israel Deaconess Medical CenterMing Tsuang, University of California, San DiegoElaine Walker, Emory UniversityScott W Woods, Yale School of MedicinePeter Falkai, Klinikum der Universität MünchenRebekka Lencer, Westfälische Wilhelms-Universität MünsterAlessandro Bertolino, Università degli studi di Bari Aldo MoroJoseph Kambeitz, Medizinische FakultätFrauke Schultze-Lutter, Heinrich-Heine-Universität DüsseldorfEva Meisenzahl, Heinrich-Heine-Universität DüsseldorfRaimo KR Salokangas, Turun yliopistoJarmo Hietala, Turun yliopistoPaolo Brambilla, Ospedale Maggiore Policlinico MilanoRachel Upthegrove, University of BirminghamStefan Borgwardt, Universität zu LübeckStephen Wood, Centre for Youth Mental HealthRaquel E Gur, University of Pennsylvania Perelman School of MedicinePhilip McGuire, King's College LondonTyrone eD Cannon, Yale University
Language
  • English
Date
  • 2021-11-01
Publisher
  • Emory University Libraries
Publication Version
Copyright Statement
  • © 2021 Society of Biological Psychiatry.
License
Final Published Version (URL)
Title of Journal or Parent Work
Volume
  • 90
Issue
  • 9
Start Page
  • 632
End Page
  • 642
Grant/Funding Information
  • PRONIA is a Collaboration Project funded by the European Union under the 7th Framework Programme under grant agreement n° 602152.
  • NAPLS-2 was further supported by NIH grants U01 MH081902 (to Dr. Cannon), P50 MH066286 (to Dr. Bearden), U01 MH081857 (to Dr. Cornblatt), U01 MH82022 (to Dr. Woods), U01 MH066134 (to Dr. Addington), U01 MH081944 (to Dr. Cadenhead), R01 U01 MH066069 (to Dr. Perkins), R01 MH076989 (to Dr. Mathalon), U01 MH081928 (to Dr. Seidman), and U01 MH081988 (to Dr. Walker).
  • The HARMONY collaboration was supported by the NIH administrative supplement 3U01MH081928-07S1 (Dr. Seidman).
Supplemental Material (URL)
Abstract
  • Background: Transition to psychosis is among the most adverse outcomes of clinical high-risk (CHR) syndromes encompassing ultra-high risk (UHR) and basic symptom states. Clinical risk calculators may facilitate an early and individualized interception of psychosis, but their real-world implementation requires thorough validation across diverse risk populations, including young patients with depressive syndromes. Methods: We validated the previously described NAPLS-2 (North American Prodrome Longitudinal Study 2) calculator in 334 patients (26 with transition to psychosis) with CHR or recent-onset depression (ROD) drawn from the multisite European PRONIA (Personalised Prognostic Tools for Early Psychosis Management) study. Patients were categorized into three risk enrichment levels, ranging from UHR, over CHR, to a broad-risk population comprising patients with CHR or ROD (CHR
  • ROD). We assessed how risk enrichment and different predictive algorithms influenced prognostic performance using reciprocal external validation. Results: After calibration, the NAPLS-2 model predicted psychosis with a balanced accuracy (BAC) (sensitivity, specificity) of 68% (73%, 63%) in the PRONIA-UHR cohort, 67% (74%, 60%) in the CHR cohort, and 70% (73%, 66%) in patients with CHR
  • ROD. Multiple model derivation in PRONIA–CHR
  • ROD-based vs. UHR-based performance: 67% [68%, 66%] vs. 58% [61%, 56%]). Support vector machines were superior in CHR
  • ROD and validation in NAPLS-2–UHR patients confirmed that broader risk definitions produced more accurate risk calculators (CHR
  • ROD (BAC = 71%), while ridge logistic regression and support vector machines performed similarly in CHR (BAC = 67%) and UHR cohorts (BAC = 65%). Attenuated psychotic symptoms predicted psychosis across risk levels, while younger age and reduced processing speed became increasingly relevant for broader risk cohorts. Conclusions: Clinical-neurocognitive machine learning models operating in young patients with affective and CHR syndromes facilitate a more precise and generalizable prediction of psychosis. Future studies should investigate their therapeutic utility in large-scale clinical trials.
Author Notes
  • Nikolaos Koutsouleris, Professor for Neurodiagnostic Applications in Psychiatry, Department of Psychiatry and Psychotherapy, Ludwig-Maximilian-University Munich, Nussbaumstr. 7, D-80336, Munich, Germany; Tel.: 0049 (0) 89 4400 55885, Fax: 0049 (0) 89 4400 55776. Email: nikolaos.koutsouleris@med.uni0muenchen.de
Keywords

Tools

Relations

In Collection:

Items

Thumbnail Title File Description Date Uploaded Visibility Actions
file details Publication File - w3m6s.pdf Primary Content 2025-06-10 Public Download