Back

Precision stratification of risk for suicidal behavior in people with bipolar depression

de Lacy, N.; Lam, W. Y.; Virtosu, M.; Deshmukh, V.; Wilson, F. A.; Pescosolido, B.; Smith, K. R.

2026-02-25 psychiatry and clinical psychology
10.64898/2026.02.23.26346921
Show abstract

Patients with bipolar depression are at the highest risk for suicidal behavior, comprising [~]10% of all deaths. In the critical period preceding attempts, most are not in contact with mental health professionals to effect antisuicidal strategies. There is an urgent need for decision support tools to help nonspecialist providers identify those at elevated risk to facilitate prevention. However, we lack robust, performant predictive models to form the core of such tools. Here, we build a high-precision predictive model of 30-day risk for suicidal behavior using unique electronic health record data from >220,000 patients with bipolar depression. We show that optimized machine learning approaches offer very strong clinical utility, delivering high Standardized Net Benefit in the context of near-perfect calibration and smooth, threshold-robust decision curves. Our results break the longstanding performance ceiling in suicide risk prediction and highlight the importance of training models for clinical utility as well as discriminative skill.

Matching journals

The top 6 journals account for 50% of the predicted probability mass.

1
npj Digital Medicine
based on 85 papers
Top 1.0%
15.4%
2
Translational Psychiatry
based on 94 papers
Top 1%
12.7%
3
Scientific Reports
based on 701 papers
Top 24%
7.6%
4
Journal of Affective Disorders
based on 72 papers
Top 2%
7.6%
5
Biological Psychiatry
based on 36 papers
Top 1%
6.4%
6
Nature Medicine
based on 88 papers
Top 0.8%
5.3%
50% of probability mass above
7
Nature Communications
based on 483 papers
Top 18%
4.5%
8
Psychological Medicine
based on 52 papers
Top 3%
4.5%
9
PLOS ONE
based on 1737 papers
Top 78%
3.0%
10
Biological Psychiatry: Cognitive Neuroscience and Neuroimaging
based on 27 papers
Top 1%
2.4%
11
Proceedings of the National Academy of Sciences
based on 100 papers
Top 7%
1.6%
12
Biological Psychiatry Global Open Science
based on 23 papers
Top 2%
1.6%
13
JAMA Network Open
based on 125 papers
Top 14%
1.3%
14
Neuropsychopharmacology
based on 29 papers
Top 2%
1.3%
15
Schizophrenia Bulletin
based on 21 papers
Top 1%
1.3%
16
Molecular Psychiatry
based on 84 papers
Top 5%
1.2%
17
JAMA Psychiatry
based on 11 papers
Top 0.7%
1.2%
18
Frontiers in Psychiatry
based on 56 papers
Top 6%
1.2%
19
Journal of Medical Internet Research
based on 81 papers
Top 14%
0.8%
20
NeuroImage: Clinical
based on 77 papers
Top 7%
0.8%
21
Nature Human Behaviour
based on 18 papers
Top 2%
0.8%
22
The British Journal of Psychiatry
based on 21 papers
Top 4%
0.7%
23
Psychiatry Research
based on 33 papers
Top 5%
0.7%
24
American Journal of Psychiatry
based on 14 papers
Top 2%
0.7%
25
BJPsych Open
based on 24 papers
Top 3%
0.7%