The impact of court-ordered psychiatric treatment on hospital length of stay: balancing legal and clinical concerns.

Purpose: Psychiatric hospital length of stay (LOS) is not affected solely by socio-clinical factors but also by legal procedures. This study examined the associations between legal procedures and LOS. Methods: Data from 521 patients with psychiatric illnesses hospitalized over 2013-2015 were analyzed. Logistic regression was used to evaluate the predictors of longer (> 14 days) or prolonged (> 30) LOS with socio-clinical factors and legal procedures including court-ordered interventions (assisted outpatient treatment, medication over objection, and retention). Results: Longer LOS occurred in 246 patients and 99 had prolonged LOS. Legal procedures affected 57 patients, with 11 assisted outpatient treatments, 39 cases of medication over objection, and 16 retentions. Longer LOS was significantly associated with six factors including older age, unmarried status, non-Hispanic race, risk of violence, schizophrenia, and legal procedures. Legal procedures had the strongest association. Longer/prolonged LOS yielded qualitatively similar associations. Conclusion: Among 521 psychiatric inpatients, approximately 11% were mandated to receive interventions/procedures by the courts. Court-ordered legal procedures were strongly associated with longer LOS. Mental health providers may consider legal procedures for patients at high treatment/medication noncompliance risk as early as patient admission to inpatient units to prevent, intervene or prepare for a longer or prolonged LOS.

Osteoporosis Pre-Screening Using Ensemble Machine Learning in Postmenopausal Korean Women.

As osteoporosis is a degenerative disease related to postmenopausal aging, early diagnosis is vital. This study used data from the Korea National Health and Nutrition Examination Surveys to predict a patient's risk of osteoporosis using machine learning algorithms. Data from 1431 postmenopausal women aged 40-69 years were used, including 20 features affecting osteoporosis, chosen by feature importance and recursive feature elimination. Random Forest (RF), AdaBoost, and Gradient Boosting (GBM) machine learning algorithms were each used to train three models: A, checkup features; B, survey features; and C, both checkup and survey features, respectively. Of the three models, Model C generated the best outcomes with an accuracy of 0.832 for RF, 0.849 for AdaBoost, and 0.829 for GBM. Its area under the receiver operating characteristic curve (AUROC) was 0.919 for RF, 0.921 for AdaBoost, and 0.908 for GBM. By utilizing multiple feature selection methods, the ensemble models of this study achieved excellent results with an AUROC score of 0.921 with AdaBoost, which is 0.1-0.2 higher than those of the best performing models from recent studies. Our model can be further improved as a practical medical tool for the early diagnosis of osteoporosis after menopause.