Assessing the predictive ability of the Suicide Crisis Inventory for near‐term suicidal behavior using machine learning approaches

Abstract

Objective: This study explores the prediction of near-term suicidal behavior using machine learning (ML) analyses of the Suicide Crisis Inventory (SCI), which measures the Suicide Crisis Syndrome, a presuicidal mental state. Methods: SCI data were collected from high-risk psychiatric inpatients (N = 591) grouped based on their short-term suicidal behavior, that is, those who attempted suicide between intake and 1-month follow-up dates (N = 20) and those who did not (N = 571). Data were analyzed using three predictive algorithms (logistic regression, random forest, and gradient boosting) and three sampling approaches (split sample, Synthetic minority oversampling technique, and enhanced bootstrap). Results: The enhanced bootstrap approach considerably outperformed the other sampling approaches, with random forest (98.0% precision; 33.9% recall; 71.0% Area under the precision-recall curve [AUPRC]; and 87.8% Area under the receiver operating characteristic [AUROC]) and gradient boosting (94.0% precision; 48.9% recall; 70.5% AUPRC; and 89.4% AUROC) algorithms performing best in predicting positive cases of near-term suicidal behavior using this dataset. Conclusions: ML can be useful in analyzing data from psychometric scales, such as the SCI, and for predicting near-term suicidal behavior. However, in cases such as the current analysis where the data are highly imbalanced, the optimal method of measuring performance must be carefully considered and selected.

Suicide plan prevalence, recurrence, and longitudinal association with nonfatal suicide attempt

“…Studies should also examine whether combining the symptoms highlighted by the proposed SCS and ASAD diagnoses (e.g., overarousal; social withdrawal) with measures of detailed suicide planning results in improved ability to predict imminent suicide attempts. Further testing of modeling paradigms adept at handling complexity may also help improve our ability to detect imminent suicide risk (Parghi et al, 2021). If these modeling paradigms are found to be helpful, suicide risk assessment guidelines should be updated to incorporate these novel approaches.…”

A review and meta-analysis of machine intelligence approaches for mental health issues and depression detection

“…In 2021, Parghi et al [79] determined, which machine learning algorithm can better predict suicidal behavior. They compared the predictive power of various machine learning algorithms such as GB, LR, and RF.…”

Az öngyilkossági rizikó becslése a klinikai gyakorlatban.

“…Ennek során a Pub-Med adatbázis a "suicidal crisis syndrome" kifejezésre 18 találatot adott. Ebből a 18-ből 13 empirikus kutatás [8,[44][45][46][47][48][49][51][52][53][54][55][56]. (Szerk.…”

“…A fentiek miatt egyre több kutatás tűzi ki célul a szuicid viselkedés hátterének és az öngyilkossági cselekmény kialakulásának megértését elősegítő komplex szuicidrizikó-és jóslómodellek kidolgozását, melyek alapján számos módszert, kérdőívet és becslőskálát dolgoztak ki. Előtérbe került például az úgynevezett "machine-learning" módszer alkalmazása, melynek segítségével különböző matematikai algoritmusok (például "random tree") segítségével az egészségügyi adatbázisokban óriási, akár több százezres esetszámot használva kereshetnek új összefüggéseket [7,8]. Napjainkban azonban még nem áll rendelkezésre olyan megbízható módszer, mellyel a szuicid cselekmény egyértelműen megjósolható lenne, mert az aktuális modellek prediktív értéke és gyakorlati hasznosíthatósága egyelőre csekélynek bizonyul [9].…”