Development and validation of a prognostic model and risk calculator for the estimation of bipolar-spectrum disorder risk in hospitalised adolescents with non-psychotic/non-bipolar mental disorders
Source check: Source checked. Not independent scientific confirmation.
Finding: Among 105 hospitalized adolescents followed longitudinally, 18 developed bipolar-spectrum disorder; the model identified mania-like symptom variables associated with onset and reported estimated risk through four years, with discrimination peaking around month 20. Leave-one-out cross-validation (AUC 0.72 at month 20) and bootstrap out-of-bag validation (AUC up to 0.86). This is internal validation in a small cohort with 18 transitions; external and outpatient validation are absent, and attrition limits generalizability.
Technology: Lasso-Cox machine-learning analysis uses baseline clinical and prodromal symptom characteristics from a prospective adolescent cohort to estimate risk of later bipolar-spectrum disorder.
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- Lasso-Cox machine-learning analysis uses baseline clinical and prodromal symptom characteristics from a prospective adolescent cohort to estimate risk of later bipolar-spectrum disorder.
- Test and result
- Among 105 hospitalized adolescents followed longitudinally, 18 developed bipolar-spectrum disorder; the model identified mania-like symptom variables associated with onset and reported estimated risk through four years, with discrimination peaking around month 20.
- Limitation / still unknown
- Leave-one-out cross-validation (AUC 0.72 at month 20) and bootstrap out-of-bag validation (AUC up to 0.86). This is internal validation in a small cohort with 18 transitions; external and outpatient validation are absent, and attrition limits generalizability.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC12916283/
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
Review date: 22 Nov 2026. Review scope: Primary source full text Methods and Results; version/date checked against bibliographic record..
No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.
Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.