Predicting involuntary hospitalization in psychiatry: A machine learning investigation

The Future of Artificial Intelligence in Mental Health Nursing Practice: An Integrative Review

Artificial intelligence (AI) has been increasingly used in delivering mental healthcare worldwide. Within this context, the traditional role of mental health nurses has been changed and challenged by AI-powered cutting-edge technologies emerging in clinical practice. The aim of this integrative review is to identify and synthesise the evidence of AI-based applications with relevance for, and potential to enhance, mental health nursing practice. Five electronic databases (CINAHL, PubMed, PsycINFO, Web of Science and Scopus) were systematically searched. Seventy-eight studies were identified, critically appraised and synthesised following a comprehensive integrative approach. We found that AI applications with potential use in mental health nursing vary widely from machine learning algorithms to natural language processing, digital phenotyping, computer vision and conversational agents for assessing, diagnosing and treating mental health challenges. Five overarching themes were identified: assessment, identification, prediction, optimisation and perception reflecting the multiple levels of embedding AI-driven technologies in mental health nursing practice, and how patients and staff perceive the use of AI in clinical settings. We concluded that AI-driven technologies hold great potential for enhancing mental health nursing practice. However, humanistic approaches to mental healthcare may pose some challenges to effectively incorporating AI into mental health nursing. Meaningful conversations between mental health nurses, service users and AI developers should take place to shaping the co-creation of AI technologies to enhance care in a way that promotes person-centredness, empowerment and active participation.

Predicting involuntary admission following inpatient psychiatric treatment using machine learning trained on electronic health record data

BACKGROUND

Involuntary admissions to psychiatric hospitals are on the rise. If patients at elevated risk of involuntary admission could be identified, prevention may be possible. Our aim was to develop and validate a prediction model for involuntary admission of patients receiving care within a psychiatric service system using machine learning trained on routine clinical data from electronic health records (EHRs).

METHODS

EHR data from all adult patients who had been in contact with the Psychiatric Services of the Central Denmark Region between 2013 and 2021 were retrieved. We derived 694 patient predictors (covering e.g. diagnoses, medication, and coercive measures) and 1134 predictors from free text using term frequency-inverse document frequency and sentence transformers. At every voluntary inpatient discharge (prediction time), without an involuntary admission in the 2 years prior, we predicted involuntary admission 180 days ahead. XGBoost and elastic net models were trained on 85% of the dataset. The models with the highest area under the receiver operating characteristic curve (AUROC) were tested on the remaining 15% of the data.

RESULTS

The model was trained on 50 634 voluntary inpatient discharges among 17 968 patients. The cohort comprised of 1672 voluntary inpatient discharges followed by an involuntary admission. The best XGBoost and elastic net model from the training phase obtained an AUROC of 0.84 and 0.83, respectively, in the test phase.

CONCLUSION

A machine learning model using routine clinical EHR data can accurately predict involuntary admission. If implemented as a clinical decision support tool, this model may guide interventions aimed at reducing the risk of involuntary admission.

Compulsory treatment in Portuguese-speaking countries: An analysis and comparison of the legal framework

BACKGROUND

Compulsory treatment involves the hospital admission of individuals with mental disorders in appropriate facilities through judicial decisions. However, limited information is available regarding the similarities and differences in compulsory treatment legislation in Portuguese-speaking countries.

AIMS

To analyse the commonalities and differences in compulsory treatment legislation in Portuguese-speaking countries, where Portuguese is the primary official language, including Angola, Brazil, Cape Verde, East Timor, Guinea-Bissau, Mozambique, Portugal, and São Tomé and Príncipe.

METHODS

A comparative analysis of the specific legislation on compulsory treatment in Portuguese-speaking countries was conducted. National development plans were analysed in countries lacking legislation. A purposive sampling of mental health professionals was contacted to gather information on the countries under study.

RESULTS

Among the eight Portuguese-speaking countries examined, specific legislation regarding compulsory treatment was found only in Brazil, Cape Verde, and Portugal. These countries, with the lowest poverty rates, exhibited a notable degree of homogeneity in the criteria supporting compulsory treatment, ensuring the protection of individual rights. In contrast, in Angola, East Timor, Guinea-Bissau, Mozambique, and São Tomé and Príncipe, compulsory treatment primarily relies on mental health development plans, resulting in significant variations in the presented criteria.

CONCLUSIONS

The significant disparities in compulsory treatment policies among Portuguese-speaking countries, with only Brazil, Cape Verde, and Portugal having specific legislation, underscore the need for a collective effort to establish more consistent procedures and safeguard individual rights.

[Cantonal Differences in The Implementation of Involuntary Admission in Switzerland]

OBJECTIVE

To examine sociodemographic and clinical characteristics of persons hospitalized in five psychiatric hospitals from regions with different structural characteristics compared with persons hospitalized voluntarily.

METHODS

Descriptive analyses of routine data on approximately 57000 cases of 33000 patients treated for a primary ICD-10 psychiatric diagnosis at one of the participating hospitals from 2016 to 2019.

RESULTS

Admission rates, length of stay, rates of further coercive measures, sociodemographic and clinical characteristics of the affected persons differ between the different regions.

CONCLUSION

There are considerable regional differences between regulations and implementation of the admission procedures and the sample. Causal relationships between regional specifics and the results cannot be inferred.

Diagnosis and Treatment of Bipolar Disorder: A Review

Importance

Bipolar disorder affects approximately 8 million adults in the US and approximately 40 million individuals worldwide.

Observations

Bipolar disorder is characterized by recurrent episodes of depression and mania or hypomania. Bipolar depressive episodes are similar to major depressive episodes. Manic and hypomanic episodes are characterized by a distinct change in mood and behavior during discrete time periods. The age of onset is usually between 15 and 25 years, and depression is the most frequent initial presentation. Approximately 75% of symptomatic time consists of depressive episodes or symptoms. Early diagnosis and treatment are associated with a more favorable prognosis. Diagnosis and optimal treatment are often delayed by a mean of approximately 9 years following an initial depressive episode. Long-term treatment consists of mood stabilizers, such as lithium, valproate, and lamotrigine. Antipsychotic agents, such as quetiapine, aripiprazole, asenapine, lurasidone, and cariprazine, are recommended, but some are associated with weight gain. Antidepressants are not recommended as monotherapy. More than 50% of patients with bipolar disorder are not adherent to treatment. Life expectancy is reduced by approximately 12 to 14 years in people with bipolar disorder, with a 1.6-fold to 2-fold increase in cardiovascular mortality occurring a mean of 17 years earlier compared with the general population. Prevalence rates of metabolic syndrome (37%), obesity (21%), cigarette smoking (45%), and type 2 diabetes (14%) are higher among people with bipolar disorder, contributing to the risk of early mortality. The annual suicide rate is approximately 0.9% among individuals with bipolar disorder, compared with 0.014% in the general population. Approximately 15% to 20% of people with bipolar disorder die by suicide.

Conclusions and Relevance

Bipolar disorder affects approximately 8 million adults in the US. First-line therapy includes mood stabilizers, such as lithium, anticonvulsants, such as valproate and lamotrigine, and atypical antipsychotic drugs, such as quetiapine, aripiprazole, asenapine, lurasidone, and cariprazine.

Satisfaction and Perceived Coercion in Voluntary Hospitalisations: Impact of Past Coercive Experiences

Coercion in psychiatry is associated with several detrimental effects, including in the long term. The effect of past experience of coercion on the perception of subsequent hospitalisations remains less studied. The present study aimed to assess the impact of past experience of coercion on the perception of coercion and satisfaction with subsequent voluntary hospitalisations. A total of 140 patients who were hospitalised on a voluntary basis were included. Fifty-three patients experienced coercion before this hospitalisation and 87 did not. Patients were assessed for treatment satisfaction and perceived coercion. Health status was also evaluated by both patients and carers. Past experience of coercion was the independent variable. Perceived coercion and satisfaction scores were used as different dependent variables in a series of regression models. Results suggested a long-term detrimental impact of past experience of coercion on some aspects of satisfaction and perceived coercion in subsequent voluntary hospitalisations even when controlling for self and carers-rated health status. Overall, this study suggests that special attention should be paid to patients who are voluntarily admitted to hospital but have a history of coercion, as they may still be impacted by their past coercive experiences. Ways to increase satisfaction and reduce perceived coercion of these patients are discussed.

Impact of Compulsory Admission on Treatment and Outcome: A Propensity Score Matched Analysis

Background

Despite multiple ethical issues and little evidence of their efficacy, compulsory admission and treatment are still common psychiatric practice. Therefore, we aimed to assess potential differences in treatment and outcome between voluntarily and compulsorily admitted patients.

Methods

We extracted clinical data from inpatients treated in an academic hospital in Zurich, Switzerland between January 1, 2013 and December 31, 2019. Observation time started upon the first admission and ended after a one-year follow-up after the last discharge. Several sociodemographic and clinical characteristics, including Health of the Nation Outcome Scales (HoNOS) scores, were retrospectively obtained. We then identified risk factors of compulsory admission using logistic regression in order to perform a widely balanced propensity score matching. Altogether, we compared 4,570 compulsorily and 4,570 voluntarily admitted propensity score-matched patients. Multiple differences between these groups concerning received treatment, coercive measures, clinical parameters, and service use outcomes were detected.

Results

Upon discharge, compulsorily admitted patients reached a similar HoNOS sum score in a significantly shorter duration of treatment. They were more often admitted for crisis interventions, were prescribed less pharmacologic treatment, and received fewer therapies. During the follow-up, voluntarily admitted patients were readmitted more often, while the time to readmission did not differ.

Conclusions

Under narrowly set circumstances, compulsory admissions might be helpful to avert and relieve exacerbations of severe psychiatric disorders.

Relationship Between Time of Admission, Help-Seeking Behavior, and Psychiatric Outcomes: "From Dusk Till Dawn"

INTRODUCTION

Day and time of admission influence treatment outcomes and prognosis in several medical specialties; this seems related to resources' ability. It is largely unknown whether this also applies to mental health services. We investigate the relationship between time of admission, patients' demographic and clinical profile, and treatment outcomes.

METHODS

Demographic and clinical profiles of admitted and discharged patients to a general psychiatric ward between January 1st, 2013 and December 31st, 2020, were analyzed. In addition, we used the last year (i.e., 2020) to monitor rehospitalization. Time of admission was defined as weekdays (working day, weekend) and dayshifts (daytime, dusk, and dawn).

RESULTS

During the study period, 12,449 patient admissions occurred. The mean age of the sample was 48.05 ± 20.90 years, with 49.32% (n = 6,140) females. Most admissions (n = 10,542, 84%) occurred on working days. Two-fifths of admissions (39.7%, n = 4,950) were compulsory, with a higher rate outside daytime hours. Patients had slight differences in the clinical profile, resulting from evaluating the different items of the Health of Nation Outcome Scale (HoNOS). Patients admitted on night shifts, weekends, and holidays showed a shorter length of stay; patients compulsorily admitted during daytime (disregarding the day of the week) had a longer length of stay. All patient groups achieved a robust clinical improvement (i.e., an HoNOS score reduction of around 50%), with similar readmission rates.

DISCUSSION

The main finding of our study is the relationship between "daytime hours" and fewer compulsory admissions, a result of the interplay between demographics, clinical characteristics, and out-of-clinic service availability (such as ambulatory psychiatric- psychological praxis; day-clinic; home-treatment). The differing clinical profile, in turn, determines differences in treatment selection, with patients admitted after office hours experiencing a higher rate of coercive measures. The shorter length of stay for out-of-office admissions might result from the hospitalization as an intervention. These results should encourage the implementation of outpatient crisis-intervention services, available from dusk till dawn.