How do explicit, implicit, and sociodemographic measures relate to concurrent suicidal ideation? A comparative machine learning approach

Abstract

IntroductionSuicide is a leading cause of death, and decades of research have identified a range of risk factors, including demographics, past self‐injury and suicide attempts, and explicit suicide cognitions. More recently, implicit self‐harm and suicide cognitions have been proposed as risk factors for the prospective prediction of suicidal behavior. However, most studies have examined these implicit and explicit risk factors in isolation, and little is known about their combined effects and interactions in the prediction of concurrent suicidal ideation.MethodsIn an online community sample of 6855 participants, we used different machine learning techniques to evaluate the utility of measuring implicit self‐harm and suicide cognitions to predict concurrent desire to self‐harm or die.ResultsDesire to self‐harm was best predicted using gradient boosting, achieving 83% accuracy. However, the most important predictors were mood, explicit associations, and past suicidal thoughts and behaviors; implicit measures provided little to no gain in predictive accuracy.ConclusionConsidering our focus on the concurrent prediction of explicit suicidal ideation, we discuss the need for future studies to assess the utility of implicit suicide cognitions in the prospective prediction of suicidal behavior using machine learning approaches.

Reproducibility of Health Claims in Meta-Analysis Studies of COVID Quarantine (Stay-at-Home) Orders

“…Specifically, the Attitude IAT−behavior intention and Stereotype IAT−behavior intention p-values were 0.172 and 0.739, respectively. Finally, Freichel et al (2023) employed several machine learning methods to access the usefulness of implicit suicide cognitions, self-harm IATs, to predict concurrent desire to self-harm or die with an online community sample of 6,855 participants. Specifically, they assessed whether self-harm IATs add to the prediction capability of (explicit) concurrent self-reported suicidality (thoughts or ideas about the possibility of ending one's life) and desire to self-harm, over and above more easily collected measures -such as sociodemographic factors, self-reported history of self-harm and suicide, and explicit momentary self-harm and suicide cognitions.…”

“…Specifically, they assessed whether self-harm IATs add to the prediction capability of (explicit) concurrent self-reported suicidality (thoughts or ideas about the possibility of ending one's life) and desire to self-harm, over and above more easily collected measures -such as sociodemographic factors, self-reported history of self-harm and suicide, and explicit momentary self-harm and suicide cognitions. Freichel et al (2023) observed that, in their best-performing model, self-harm, suicide, and death IATs offered very little (<2%) and often no predictive value on top of explicit measures that are much easier to collect to explain concurrent self-reported suicidality. Mood, explicit associations, and past suicidal thoughts and behaviors were the most important predictors of concurrent self-reported suicidality.…”

Reproducibility of Implicit Association Test (IAT) – Case Study of Meta-Analysis of Racial Bias Research Claims

“…They assessed whether self-harm IATs add to the prediction capability of (explicit) concurrent self-reported suicidality (thoughts or ideas about the possibility of ending one's life) and desire to self-harm, over and above more easily collected measuressuch as sociodemographic factors, self-reported history of self-harm and suicide, and explicit momentary self-harm and suicide cognitions. Freichel et al (2023) observed that, in their best-performing model, self-harm, suicide, and death IATs offered very little (less than 2%) and often no predictive value on top of explicit measures that are much easier to collect to explain concurrent self-reported suicidality. Mood, explicit associations, and past suicidal thoughts and behaviors were the most important predictors of concurrent self-reported suicidality.…”