AI Science Tracker
EN

University of Vic–Central University of Catalonia

1 discovery from 2022

Discoveries

A Machine Learning Approach for Predicting Non-Suicidal Self-Injury in Young Adults

Source check: Source checked. Not independent scientific confirmation.

Finding: In a 15-day ecological momentary assessment of 64 young adults, classification trees identified self-harm thoughts, sadness and frustration as informative predictors of non-suicidal self-injury thoughts or behaviors. The per-person averaged model achieved 84.78% accuracy but 14.48% positive predictive value, limiting any clinical-use interpretation.

Technology: CART classification of repeated app-based self-report features

Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.

AI contribution
CART models classified repeated self-report features to predict non-suicidal self-injury thoughts or behaviors.
Test and result
Leave-one-subject-out evaluation reported 84.78% accuracy, 64.84% sensitivity, 85.53% specificity, 14.48% positive predictive value and 98.47% negative predictive value.
Limitation / still unknown
Small retrospective EMA cohort and low positive predictive value; no deployment or clinical-benefit validation.
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/PMC9269418/

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 full-text Methods, Results and Discussion; date and exact-result catalog comparison checked..

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.

Open the interactive profile for the timeline, or browse all organizations and model families.