CoChat
Sign Up
Cited by 264Suicide and Self-Harm StudiesMachine Learning in HealthcareArtificial Intelligence in Healthcare

Predicting suicide attempts in adolescents with longitudinal clinical data and machine learning

Walsh, Colin G., Ribeiro, Jessica D., Franklin, Joseph C.·2018·Journal of Child Psychology and Psychiatry
DOI 10.1111/jcpp.12916
Open this paper in CoChat — free account

Abstract

Background: Adolescents have high rates of nonfatal suicide attempts, but clinically practical risk prediction remains a challenge. Screening can be time consuming to implement at scale, if it is done at all. Computational algorithms may predict suicide risk using only routinely collected clinical data. We used a machine learning approach validated on longitudinal clinical data in adults to address this challenge in adolescents. Methods: This is a retrospective, longitudinal cohort study. Data were collected from the Vanderbilt Synthetic Derivative from January 1998 to December 2015 and included 974 adolescents with nonfatal suicide attempts and multiple control comparisons: 496 adolescents with other self‐injury ( OSI ), 7,059 adolescents with depressive symptoms, and 25,081 adolescent general hospital controls. Candidate predictors included diagnostic, demographic, medication, and socioeconomic factors. Outcome was determined by multiexpert review of electronic health records. Random forests were validated with optimism adjustment at multiple time points (from 1 week to 2 years). Recalibration was done via isotonic regression. Evaluation metrics included discrimination ( AUC , sensitivity/specificity, precision/recall) and calibration (calibration plots, slope/intercept, Brier score). Results: Computational models performed well and did not require face‐to‐face screening. Performance improved as suicide attempts became more imminent. Discrimination was good in comparison with OSI controls ( AUC = 0.83 [0.82–0.84] at 720 days; AUC = 0.85 [0.84–0.87] at 7 days) and depressed controls ( AUC = 0.87 [95% CI 0.85–0.90] at 720 days; 0.90 [0.85–0.94] at 7 days) and best in comparison with general hospital controls ( AUC 0.94 [0.92–0.96] at 720 days; 0.97 [0.95–0.98] at 7 days). Random forests significantly outperformed logistic regression in every comparison. Recalibration improved performance as much as ninefold – clinical recommendations with poorly calibrated predictions can lead to decision errors. Conclusions: Machine learning on longitudinal clinical data may provide a scalable approach to broaden screening for risk of nonfatal suicide attempts in adolescents.

Integrity signals

Registry

Crossref · 10.1111/jcpp.12916

Cites

23 of 23 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Previously-used machine learning models in suicide research may not be appropriate for real-time monitoring data.

    “Finally, Kleiman and colleagues raised concerns about data overfitting in EMA studies (48); in this context, previously-used machine learning models in suicide research may not be appropriate for real-time monitoring data (38, 49).”

    From New methods for assessing rapid changes in suicide risk (2021) · cites this paper as [38]

Cites

Flagged first, then by citations

1 of the 24 references couldn’t be matched to a known paper.

Cited by

Sorted by citations

Related

Authors
Walsh, C. G., Ribeiro, J. D., & Franklin, J. C.
Affiliations
  • Vanderbilt University Medical Center (US)
  • Florida State University (US)
Corresponding author
Walsh, Colin G.
ORCID
Venue
Journal of Child Psychology and Psychiatry
Publisher
Wiley
Published
2018-04-30
Volume
59
Issue
12
Pages
1261-1270
ISSN
  • 0021-9630 (ISSN-L)
  • 1469-7610
DOI
10.1111/jcpp.12916
OpenAlex
W2801632865
Cited by
264
References
24
Citations by year
2026: 27 · 2025: 38 · 2024: 32 · 2023: 31 · 2022: 35 · 2021: 51 · 2020: 31 · 2019: 16 · 2018: 3
FWCI
29.67
Type
journal article
Language
en
Open access
closed
Licence
onlinelibrary.wiley.com/termsAndConditions#vor (vor)
Locations
  • Journal of Child Psychology and Psychiatry (publishedVersion)
  • PubMed (publishedVersion)
Funders
BioVU Synthetic Derivative (UL1 RR024975/RR/NCRR)
Topics
  • Social Sciences › Psychology › Clinical Psychology › Suicide and Self-Harm Studies
  • Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
Keywords
suicide attempts, adolescents, suicide risk prediction, machine learning, random forest, longitudinal clinical data, electronic health records, suicide risk screening, depressive symptoms
MeSH terms
Machine Learning, Adolescent, Depression, Female, Humans, Longitudinal Studies, Male, Retrospective Studies, Suicide, Attempted, Self-Injurious Behavior, Risk Assessment

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review