Health Care Management Models for the Evolution of Hospitalization in Acute Inpatient Psychiatry Units: Comparative Quantitative Study

Long-term mental health care in Portugal: A portrait of the first years of activity

INTRODUCTION

In Portugal, a reform to implement Long-term mental health care (LTMHC) started in 2017 allowing patients with severe mental illness receiving psychosocial rehabilitation to regain their autonomy and be reintegrated into their communities.

AIM

To describe the first steps of the Portuguese LTMHC implementation and to assess the relationship between the LTMHC's demand (referrals) and supply (vacancies and occupancy).

METHODS

We conducted a national retrospective observational study to analyse the LTMHC referrals, vacancies and occupancy between mid-2017 (LTMHC establishment) and December 2022. We described and analysed the associated indicators through time and geography, as well as performed a simultaneous regression model to evaluate the relationship between supply and demand.

RESULTS

There were 1,192 referrals to the LTMHC, of which 99 (8.3%) were made for childhood and adolescence structures. The maximum support residence (RAMa, 'Residência de apoio máximo'), designed for patients with higher disabilities, had the highest number of referrals. Additionally, since the opening of vacancies in different institutions, residential structures became quickly saturated. On the other hand, domiciliary services were those with the lowest occupancy. Our estimates support that the vacancies (supply) are induced by the referrals (demand), and referrals are also related to the location of LTMHC facilities.

CONCLUSION

LTMHC is still in the initial stage of development in Portugal, and it is expected to receive financial support through the Recovery and Resilience Programme. According to the occupancy rates and referrals made, residential structures seem to be a priority, being also important to explore the partial use of domiciliary services. The geographical distribution of vacancies can also be a concern, considering the important proximity to the community in LTMHC.

Comparison of Machine Learning Algorithms in the Prediction of Hospitalized Patients with Schizophrenia

New computational methods have emerged through science and technology to support the diagnosis of mental health disorders. Predictive models developed from machine learning algorithms can identify disorders such as schizophrenia and support clinical decision making. This research aims to compare the performance of machine learning algorithms: Decision Tree, AdaBoost, Random Forest, Naïve Bayes, Support Vector Machine, and k-Nearest Neighbor in the prediction of hospitalized patients with schizophrenia. The data set used in the study contains a total of 11,884 electronic admission records corresponding to 6933 patients with various mental health disorders; these records belong to the acute units of 11 public hospitals in a region of Spain. Of the total, 5968 records correspond to patients diagnosed with schizophrenia (3002 patients) and 5916 records correspond to patients with other mental health disorders (3931 patients). The results recommend Random Forest with the best accuracy of 72.7%. Furthermore, this algorithm presents 79.6%, 72.8%, 72.7%, and 72.7% for AUC, precision, F1-Score, and recall, respectively. The results obtained suggest that the use of machine learning algorithms can classify hospitalized patients with schizophrenia in this population and help in the hospital management of this type of disorder, to reduce the costs associated with hospitalization.