A machine learning approach for predicting suicidal ideation in post stroke patients

Abstract

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. Significant variables were selected through traditional statistical analysis based on retrospective data of 385 stroke patients; the data were collected from October 2012 to March 2014. The data were then applied to three boosting models (Xgboost, CatBoost, and LGBM) to identify the comparative and best performing models. 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 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. 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.

Explainable artificial intelligence models for predicting risk of suicide using health administrative data in Quebec

“…It enhances the classification tree by considering a random subspace of predictors when building a tree and by creating a diverse set of trees that contribute to classification performance [ 50 ]. The XGBoost method is a variant of the gradient boosting algorithm, which minimizes errors by applying the gradient descent method in a Boosting algorithm combining several weak learners [ 51 ]. MLP is a neural network classifier consisting of feedforward networks with dense, all-to-all connections between layers.…”

Testing a Psychological Tool to Enhance Hope in People With Stroke; Qualitative Study

“…This provides a brief (within a 10-minute interaction) way to document essential psychological constructs in stroke. For instance, acceptance has been identified as negatively associated with depression and anxiety [13] and low acceptance can be identified as a risk for developing mental health disorder [14]. As a result of this relationship, acceptance should be examined early during rehabilitation for people with stroke [15].…”

Explainable Artificial Intelligence in the Early Diagnosis of Gastrointestinal Disease

“…Moreover, the notion of explainable artificial intelligence is enjoying immense popularity now. Explainable artificial intelligence can be defined as “artificial intelligence to identify major predictors of the dependent variable”, and there are four approaches of explainable artificial intelligence at this point, i.e., random forest impurity importance, random forest permutation importance [ 20 , 21 ], machine learning accuracy importance, and Shapley additive explanations (SHAP) [ 15 , 22 , 23 , 24 , 25 , 26 , 27 , 28 , 29 , 30 , 31 , 32 ]. Random forest impurity importance calculates the node impurity decrease from the creation of a branch on a certain predictor.…”

“…Machine learning accuracy importance (an extension of random forest permutation importance) calculates the accuracy decrease from the exclusion of data on the predictor. The SHAP value of a predictor for a participant measures the difference between what machine learning predicts for the probability of GID with and without the predictor [ 15 , 22 , 23 , 24 , 25 , 26 , 27 , 28 , 29 , 30 , 31 , 32 ]. For example, let us assume in a hypothetical figure ( Figure 1 ) that the SHAP values of diabetes (x033) for GERD have the range of (−0.05, 0.30).…”