ABSTRACT
Introduction: Bipolar disorder (BD) is a chronically progressive mental condition, associated with a reduced quality of life and greater disability. Patient admissions are preventable events with a considerable impact on global functioning and social adjustment. While machine learning (ML) approaches have proven prediction ability in other diseases, little is known about their utility to predict patient admissions in this pathology. Aim: To develop prediction models for hospital admission/readmission within 5 years of diagnosis in patients with BD using ML techniques. Methods: The study utilized data from patients diagnosed with BD in a major healthcare organization in Colombia. Candidate predictors were selected from Electronic Health Records (EHRs) and included sociodemographic and clinical variables. ML algorithms, including Decision Trees, Random Forests, Logistic Regressions, and Support Vector Machines, were used to predict patient admission or readmission. Survival models, including a penalized Cox Model and Random Survival Forest, were used to predict time to admission and first readmission. Model performance was evaluated using accuracy, precision, recall, F1 score, area under the receiver operating characteristic curve (AUC) and concordance index. Results: The admission dataset included 2,726 BD patients, with 354 admissions, while the readmission dataset included 352 patients, with almost half being readmitted. The best-performing model for predicting admission was the Random Forest, with an accuracy score of 0.951 and an AUC of 0.98. The variables with the greatest predictive power in the Recursive Feature Elimination (RFE) importance analysis were the number of psychiatric emergency visits, the number of outpatient follow-up appointments and age. Survival models showed similar results, with the Random Survival Forest performing best, achieving an AUC of 0.95. However, the prediction models for patient readmission had poorer performance, with the Random Forest model being again the best performer but with an AUC below 0.70. Conclusion: ML models, particularly the Random Forest model, outperformed traditional statistical techniques for admission prediction. However, readmission prediction models had poorer performance. This study demonstrates the potential of ML techniques in improving prediction accuracy for BD patient admissions.
ABSTRACT
Indices of classification accuracy of the Substance Use/Abuse scale of a Spanish-language version of the Problem Oriented Screening Instrument for Teenagers (POSIT) were evaluated among school-based youth in Mexico. Participants were 1203 youth attending one middle school (N = 619) and one high school (N = 584) in the third largest city of Coahuila, a northern border state in Mexico in May 1998. More than 94% of youth enrolled in the participating middle school and 89% of youth enrolled in the participating high school completed the International Longitudinal Survey of Adolescent Health. Indices of classification accuracy of the POSIT Substance Use/Abuse scale were evaluated against a "drug abuse" problem severity criterion that combined youth meeting DSM-IV criteria for alcohol abuse/dependence disorders with youth having used other illicit drugs five or more times in their lifetime. The present study findings suggest that using a cut score of one or two on the POSIT Substance Use/Abuse scale generally yields optimal classification accuracy indices that vary somewhat by gender and school subgroups. Further, classification accuracy indices of the POSIT Substance Use/Abuse scale are slightly better when used among high school males due, in part, to the higher base rate of serious involvement among this group compared to others.
