Machine-Learning for Prescription Patterns: Random Forest in the Prediction of Dose and Number of Antipsychotics Prescribed to People with Schizophrenia

Abstract

Objective: We aimed to predict antipsychotic prescription patterns for people with schizophrenia using machine learning (ML) algorithms. Methods: In a cross-sectional design, a sample of community mental health service users (SUs; n = 368) with a primary diagnosis of schizophrenia was randomly selected. Socio-demographic and clinical features, including the number, total dose, and route of administration of the antipsychotic treatment were recorded. Information about the number and the length of psychiatric hospitalization was retrieved. Ordinary Least Square (OLS) regression and ML algorithms (i.e., random forest [RF], supported vector machine, K-nearest neighborhood, and Naïve Bayes) were used to estimate the predictors of total antipsychotic dosage and prescription of antipsychotic polytherapy (APP). Results: The strongest predictor of the total dose was APP. The number of Community Mental Health Centers (CMHC) contacts was the most important predictor of APP and, with APP omitted, of dosage. Treatment with anticholinergics predicted APP, emphasizing the strong correlation between APP and higher antipsychotic dose. RF performed better than OLS regression and the other ML algorithms in predicting both antipsychotic dose (root square mean error = 0.70, R 2 = 0.31) and APP (area under the receiving operator curve = 0.66, true positive rate = 0.41, and true negative rate = 0.78). Conclusion: APP is associated with the prescription of higher total doses of antipsychotics. Frequent attenders at CMHCs, and SUs recently hospitalized are often treated with APP and higher doses of antipsychotics. Future prospective studies incorporating standardized clinical assessments for both psychopathological severity and treatment efficacy are needed to confirm these findings.

The effect of ketamine on cognition, anxiety, and social functioning in adults with psychiatric disorders: A systematic review and meta-analysis

“…It should be noted that ketamine treatment is now delivered to the most severe patients, such as treatment-resistant or suicidal, making the estimate of the effect size rather impressive for such a complex population. In addition, these patients usually suffer also from worst physical health (Chan et al, 2022 ; Marchi et al, 2022 ). Future trials should try to assess if ketamine treatment may be better tolerated by people without such complexity and high levels of physical frailty, also implementing lower doses arms to assess if similar outcomes may be obtained also at lower doses and with lower side effects.…”

Machine Learning Algorithms for the Prediction of Locomotor Activity by an Infrared Motion Detector on the Sleep-wake States in Mice

“…Many studies using machine learning have been performed to establish a diagnostic prediction model for treatment responses in the field of psychiatry [ 1 - 6 ]. Specially, the prediction of sleep-wake states using machine learning alogorithms have been performed recently [ 7 - 10 ], because machine learning techniques accomplish multivariate analysis to improve reliability and validity instead of univariate analysis [ 11 ].…”