Translating promise into practice: a review of machine learning in suicide research and prevention

Mens, Kasper van; Hoogendoorn, Mark; Kapur, Navneet; Beurs, Derek de

doi:10.1016/s2215-0366(21)00254-6

Cited by 40 publications

(30 citation statements)

References 108 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We believe that clinicians can intuitively appreciate the value of PRS-SA when it is compared to this benchmark of clinical good practice. From a research perspective , considering skepticism in the field toward incorporating PRS in multivariable predictive algorithms in psychiatry ( 5 ), our findings provide support for incorporation of genetic scores, including that of suicide attempt, in suicide risk prediction ( 27 ). We suggest that this work serves as a proof of a concept for the potential utility of integrating polygenic risk as part of the comprehensive youth suicide risk assessment.…”

Section: Discussionmentioning

confidence: 60%

Genetic risk, parental history, and suicide attempts in a diverse sample of US adolescents

et al. 2022

View full text Add to dashboard Cite

BackgroundAdolescent suicide is a major health problem in the US marked by a recent increase in risk of suicidal behavior among Black/African American youth. While genetic factors partly account for familial transmission of suicidal behavior, it is not clear whether polygenic risk scores of suicide attempt can contribute to suicide risk classification.ObjectivesTo evaluate the contribution of a polygenic risk score for suicide attempt (PRS-SA) in explaining variance in suicide attempt by early adolescence.MethodsWe studied N = 5,214 non-related youth of African and European genetic ancestry from the Adolescent Brain Cognitive Development (ABCD) Study (ages 8.9–13.8 years) who were evaluated between 2016 and 2021. Regression models tested associations between PRS-SA and parental history of suicide attempt/death with youth-reported suicide attempt. Covariates included age and sex.ResultsOver three waves of assessments, 182 youth (3.5%) reported a past suicide attempt, with Black youth reporting significantly more suicide attempts than their White counterparts (6.1 vs. 2.8%, p < 0.001). PRS-SA was associated with suicide attempt [odds ratio (OR) = 1.3, 95% confidence interval (CI) 1.1–1.5, p = 0.001]. Parental history of suicide attempt/death was also associated with youth suicide attempt (OR = 3.1, 95% CI, 2.0–4.7, p < 0.001). PRS-SA remained significantly associated with suicide attempt even when accounting for parental history (OR = 1.29, 95% CI = 1.1–1.5, p = 0.002). In European ancestry youth (n = 4,128), inclusion of PRS-SA in models containing parental history explained more variance in suicide attempt compared to models that included only parental history (ΔR2 = 0.7%, p = 0.009).ConclusionsFindings suggest that PRS-SA may be useful for youth suicide risk classification in addition to established risk factors.

show abstract

Section: Discussionmentioning

confidence: 60%

Genetic risk, parental history, and suicide attempts in a diverse sample of US adolescents

et al. 2022

View full text Add to dashboard Cite

show abstract

“…We believe that clinicians can intuitively appreciate the value of PRS-SA when it is compared to this benchmark of clinical good practice. From a research perspective , considering skepticism in the field toward incorporating PRS in multivariable predictive algorithms in psychiatry (5), our findings provide support for incorporation of genetic scores, including that of suicide attempt, in suicide risk prediction (20).…”

Section: Discussionmentioning

confidence: 60%

Genetic risk, parental history, and suicide attempts in a diverse sample of US adolescents

Barzilay

Visoki

Schultz

et al. 2022

Preprint

View full text Add to dashboard Cite

Background: Adolescent suicide is a major health problem in the US marked by a recent increase in Black/African American youth suicide trends. While genetic factors partly account for familial transmission of suicidal behavior, it is not clear whether polygenic risk scores of suicide attempt have clinical utility in youth suicide risk classification. Objectives: To evaluate the contribution of a polygenic risk score for suicide attempt (PRS-SA) in explaining variance in suicide attempt by early adolescence. Methods: We studied N=5,214 non-related Black and White youth from the Adolescent Brain Cognitive Development (ABCD) Study (ages 8.9-13.8 years) who were evaluated between 2016 and 2021. Regression models tested associations between PRS-SA and parental history of suicide attempt/death with youth-reported suicide attempt. Covariates included age, sex, and race. Results: Over three waves of assessments, 182 youth (3.5%) reported a past suicide attempt, with Black youth reporting significantly more suicide attempts than their White counterparts (6.1% vs 2.8%, P<.001). PRS-SA was associated with suicide attempt (odds ratio [OR]=1.3, 95% confidence interval [CI] 1.1-1.5, P=.001). Inclusion of PRS-SA explained 2.7% of the variance in suicide attempts, significantly more than the base model including only age, sex and race, which explained 1.9% of the variance (P=.001). Parental history of suicide attempt/death was also associated with youth suicide attempt (OR=2.9, 95%CI 1.9-4.4, P<.001). Addition of PRS-SA to the model that included parental history significantly increased the variance explained from 3.3% to 4% (P=.002). Conclusions: Findings suggest that PRS-SA may be useful for suicide risk classification in diverse youth.

show abstract

“…However, it is reassuring to see that suicidal ideation at baseline was the highest-ranked predictor. We suggest that when the time comes for clinical translation, identification of strong clinical indicators at the top of the predictor list would bolster confidence in clinicians using prediction algorithms, which is critical for their implementation (39). We also emphasize that one should avoid interpretation of the cognitive predictors as causal because this was not the study aim.…”

Section: Discussionmentioning

confidence: 99%

Prediction of adolescent suicide attempt by integrating clinical, neurocognitive and geocoded neighborhood environment data

Visoki

Moore

Gur

et al. 2022

Preprint

View full text Add to dashboard Cite

Objective- The authors used multimodal data collected during pre/early-adolescence in research settings to predict self-report of past suicide attempt (SA) by mid-late adolescence in pediatric care settings. The study further aimed to determine types of data that contribute to the prediction; and to test generalizability of the prediction in an independent sample. Methods- The authors applied machine learning methods on clinical, neurocognitive and geocoded neighborhood environmental data from the Philadelphia Neurodevelopmental Cohort study (PNC, Mean age 11.1, SD=2.2, 52.3% female and 51.4% Black participants) to predict SA reported ~5 years later in a community pediatric clinic (n=922, 5.3% SA) or emergency department (n=497, 8.2% SA). The authors compared prediction performance when using all data versus individual data types, then used feature selection algorithms (Lasso, Relief and Random Forest) to identify important predictors and compared performance of models relying on feature subsets. Results- In the training dataset, SA prediction was good, reaching AUC=0.75, sensitivity/specificity 0.76/0.77 when relying on feature subsets identified using feature selection pipelines. Use of highest-ranking feature subsets from the training dataset yielded similar prediction in the testing dataset with AUC=0.74, sensitivity/specificity 0.66/0.70. Different algorithms showed different high-ranking features, but overall multiple data domains were represented among the highest-ranking predictors selected by each algorithm. Conclusions- These findings provide evidence for feasibility of predicting youth SA using data collected at a single timepoint early in life in a diverse cohort. Results encourage incorporation of multiple data types including neurocognitive and geocoded environmental measures in machine learning SA prediction pipelines.

show abstract

Translating promise into practice: a review of machine learning in suicide research and prevention

Cited by 40 publications

References 108 publications

Genetic risk, parental history, and suicide attempts in a diverse sample of US adolescents

Genetic risk, parental history, and suicide attempts in a diverse sample of US adolescents

Genetic risk, parental history, and suicide attempts in a diverse sample of US adolescents

Prediction of adolescent suicide attempt by integrating clinical, neurocognitive and geocoded neighborhood environment data

Contact Info

Product

Resources

About