CoChat
Sign Up
Cited by 30Suicide and Self-Harm StudiesMental Health via WritingBipolar Disorder and Treatment

The role of suicide ideation in assessing near-term suicide risk: A machine learning approach

McMullen, Lauren, Parghi, Neelang, Rogers, Megan L., Yao, Heng, Bloch-Elkouby, Sarah, Galynker, Igor·2021·Psychiatry Research
DOI 10.1016/j.psychres.2021.114118
Open this paper in CoChat — free account

Abstract

Background The majority of suicide attempters do not disclose suicide ideation (SI) prior to making an attempt. When reported, SI is nevertheless associated with increased risk of suicide. This paper implemented machine learning (ML) approaches to assess the degree to which current and lifetime SI affect the predictive validity of the Suicide Crisis Syndrome (SCS), an acute condition indicative of imminent risk, for near-term suicidal behaviors (SB ). Methods In a sample of 591 high-risk inpatient participants, SCS and SI were respectively assessed using the Suicide Crisis Inventory (SCI) and the Columbia Suicide Severity Rating Scale (C-SSRS). Two ML predictive algorithms, Random Forest and XGBoost, were implemented and framed using optimism adjusted bootstrapping. Metrics collected included AUPRC, AUROC, classification accuracy, balanced accuracy, precision, recall, and brier score. AUROC metrics were compared by computing a z-score. Results The combination of current SI and SCI showed slightly higher predictive validity for near-term SB as evidenced by AUROC metrics than the SCI alone, but the difference was not significant (p Conclusion The addition of SI to the SCS does not materially improve the model's predictive validity for near-term SB, suggesting that patient self-reported SI should not be a requirement for the diagnosis of SCS.

Integrity signals

Registry

Crossref · 10.1016/j.psychres.2021.114118

Cites

63 of 63 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?

  • A combination of current suicidal ideation and SCI showed slightly higher predictive validity for near-term suicidal behavior than SCI alone (p < 0.05).

    “Combination of current SI and SCI showed slightly higher predictive validity for near-term SB than SCI alone (p < 0.05)”

    From Suicide Crisis Syndrome: A systematic review (2024) · cites this paper as McMullen, Parghi, Rogers, Yao, Bloch-Elkouby, Galynker 2021

  • Two studies found the combination of SCS and current suicide ideation to be of special predictive power for suicidal behavior at 1-month follow-up.

    “and two further studies found the combination of SCS and current suicide ideation to be of special predictive power for suicidal behavior at 1month follow-up (McMullen et al., 2021;Rogers, Bafna, & Galynker, 2022).”

    From Suicide Crisis Syndrome: A systematic review (2024) · cites this paper as McMullen et al., 2021

Cites

Flagged first, then by citations

Cited by

Sorted by citations

Related

Authors
McMullen, L., Parghi, N., Rogers, M. L., Yao, H., Bloch-Elkouby, S., & Galynker, I.
Affiliations
  • Icahn School of Medicine at Mount Sinai (US)
  • Courant Institute of Mathematical Sciences (US)
  • University of Florida (US)
Corresponding author
McMullen, Lauren
ORCID
Venue
Psychiatry Research
Publisher
Elsevier BV
Published
2021-10
Volume
304
Pages
114118
ISSN
0165-1781 (ISSN-L)
DOI
10.1016/j.psychres.2021.114118
OpenAlex
W3186062661
Cited by
30
References
63
Citations by year
2026: 2 · 2025: 7 · 2024: 10 · 2023: 3 · 2022: 8
FWCI
3.58
Type
journal article
Language
en
Open access
closed
Licence
Locations
  • Psychiatry Research (publishedVersion)
  • PubMed (publishedVersion)
Funders
  • National Institute of Mental Health (R34 MH119294-01)
  • American Foundation for Suicide Prevention (-1-015-14)
Topics
  • Social Sciences › Psychology › Clinical Psychology › Suicide and Self-Harm Studies
  • Social Sciences › Psychology › Social Psychology › Mental Health via Writing
  • Health Sciences › Medicine › Psychiatry and Mental health › Bipolar Disorder and Treatment
Keywords
suicidal ideation, suicide crisis syndrome, Columbia Suicide Severity Rating Scale, suicide attempters, predictive validity, random forest, XGBoost, suicide risk assessment
MeSH terms
Machine Learning, Humans, Risk Factors, Suicide, Attempted, Self Report, Suicidal Ideation

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