Key result
Machine learning models effectively predicted suicidal ideation in stroke patients, with the CatBoost model achieving the highest total AUC of 0.900.
Why the study?
Identifying stroke patients with increased suicide risk currently relies primarily on self-report questionnaires, which lack objectivity.
Can machine learning models accurately predict suicidal ideation in stroke patients using clinical data?
Observational
Can machine learning models accurately predict suicidal ideation in stroke patients using clinical data?
Effect estimate: AUC 0.900
Machine learning models, particularly CatBoost, can effectively predict suicidal ideation in stroke patients using clinical data, potentially aiding in early intervention.
Should not yet change post-stroke suicide-risk screening; leaves open prospective validation of these prediction models.
Background: Currently, the identification of stroke patients with an increased suicide risk is mainly based on self‐report questionnaires, and this method suffers from a lack of objectivity. This study developed and validated a suicide ideation (SI) prediction model using clinical data and identified SI predictors. Method: Significant variables were selected through traditional statistical analysis based on retrospective data of 385 stroke patients; the data was collected from October 2012 to March 2014. The data was then applied to three boosting models (Xgboost, CatBoost, LGBM) to identify the comparative and best performing models. Results: Demographic variables that showed significant differences between the two groups were age, onset, type, socioeconomic, and education level. Additionally, functional variables also showed a significant difference with regard to ADL and emotion (p<0.05). The CatBoost model (0.900) showed higher performance than the other two models; and depression, anxiety, self-efficacy, and rehabilitation motivation (RM) were found to have high importance. Negative emotions such as depression and anxiety showed a positive relationship with SI and rehabilitation motivation and self-efficacy displayed an inverse relationship with SI. Conclusion: Machine learning-based SI models could augment SI prevention by helping rehabilitation and medical professionals identify high-risk stroke patients in need of SI prevention intervention.
No takes yet. Share an insight, caveat, or question.
Song et al. (2022) conducted an observational in Stroke with suicidal ideation. Machine learning prediction models (CatBoost, XGBoost, LGBM) was evaluated on Prediction of suicidal ideation (Total AUC) (AUC 0.900). Machine learning models effectively predicted suicidal ideation in stroke patients, with the CatBoost model achieving the highest total AUC of 0.900.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: