National trends and variation in nurse staffing on inpatient psychiatric units

Comprehensive Symptom Prediction in Inpatients With Acute Psychiatric Disorders Using Wearable-Based Deep Learning Models: Development and Validation Study

BACKGROUND

Assessing the complex and multifaceted symptoms of patients with acute psychiatric disorders proves to be significantly challenging for clinicians. Moreover, the staff in acute psychiatric wards face high work intensity and risk of burnout, yet research on the introduction of digital technologies in this field remains limited. The combination of continuous and objective wearable sensor data acquired from patients with deep learning techniques holds the potential to overcome the limitations of traditional psychiatric assessments and support clinical decision-making.

OBJECTIVE

This study aimed to develop and validate wearable-based deep learning models to comprehensively predict patient symptoms across various acute psychiatric wards in South Korea.

METHODS

Participants diagnosed with schizophrenia and mood disorders were recruited from 4 wards across 3 hospitals and prospectively observed using wrist-worn wearable devices during their admission period. Trained raters conducted periodic clinical assessments using the Brief Psychiatric Rating Scale, Hamilton Anxiety Rating Scale, Montgomery-Asberg Depression Rating Scale, and Young Mania Rating Scale. Wearable devices collected patients' heart rate, accelerometer, and location data. Deep learning models were developed to predict psychiatric symptoms using 2 distinct approaches: single symptoms individually (Single) and multiple symptoms simultaneously via multitask learning (Multi). These models further addressed 2 problems: within-subject relative changes (Deterioration) and between-subject absolute severity (Score). Four configurations were consequently developed for each scale: Single-Deterioration, Single-Score, Multi-Deterioration, and Multi-Score. Data of participants recruited before May 1, 2024, underwent cross-validation, and the resulting fine-tuned models were then externally validated using data from the remaining participants.

RESULTS

Of the 244 enrolled participants, 191 (78.3%; 3954 person-days) were included in the final analysis after applying the exclusion criteria. The demographic and clinical characteristics of participants, as well as the distribution of sensor data, showed considerable variations across wards and hospitals. Data of 139 participants were used for cross-validation, while data of 52 participants were used for external validation. The Single-Deterioration and Multi-Deterioration models achieved similar overall accuracy values of 0.75 in cross-validation and 0.73 in external validation. The Single-Score and Multi-Score models attained overall R² values of 0.78 and 0.83 in cross-validation and 0.66 and 0.74 in external validation, respectively, with the Multi-Score model demonstrating superior performance.

CONCLUSIONS

Deep learning models based on wearable sensor data effectively classified symptom deterioration and predicted symptom severity in participants in acute psychiatric wards. Despite lower computational costs, Multi models demonstrated equivalent or superior performance than Single models, suggesting that multitask learning is a promising approach for comprehensive symptom prediction. However, significant variations were observed across wards, which presents a key challenge for developing clinical decision support systems in acute psychiatric wards. Future studies may benefit from recurring local validation or federated learning to address generalizability issues.

American Psychiatric Nurses Association Position: Staffing Inpatient Psychiatric Units

OBJECTIVE

An American Psychiatric Nurses Association (APNA) task force reviewed current staffing research to revise and update the 2011 APNA "Staffing inpatient psychiatric units" position paper and provide recommendations to the APNA Board of Directors on how psychiatric mental health (PMH) nurses might champion the staffing needs of inpatient psychiatric units.

METHODS

Current research on staffing and nursing practice in inpatient psychiatric units was reviewed as well as variables believed to influence staffing and nursing practice, such as consumer needs and workplace culture. Since current nurse staffing principles emphasize nursing value and how that value is connected to outcomes, the literature search included a focus on staffing and related patient outcomes.

RESULTS

PMH nurses are critical to the safety and quality of care in inpatient psychiatric units. However, there are little existing data on the relationship between staffing levels and even common adverse events such as staff injury and restraint of patients. Furthermore, there is scant research conducted on inpatient psychiatric units that informs optimal staffing models or establishes links between staffing and patient outcomes.

CONCLUSIONS

Consistent with current evidence, the universal use of a single method or model of determining staffing needs (e.g., nursing hours per, case mix index, or mandatory ratios) is not recommended. PMH nurses should champion systematic evaluation of staffing on their inpatient units against select patient, nurse, and system outcomes. A data repository of PMH nurse-sensitive outcomes is necessary to benchmark unit performance and staffing.

Risk factors for coercion length at psychiatric hospitals in Israel: Relationship with staff

Background

Coercive interventions continue to be applied frequently in psychiatric care when patients are at imminent risk of harming themselves and/or others.

Aim

The purpose of this study was to demonstrate the relationship between the length of coercion and a variety of factors, including the sociodemographic background of patients, their diagnoses and the characteristics of hospital staff.

Methods

This is a one-year cross-sectional retrospective study, including records of 298 patients who underwent restraint and/or seclusion interventions in male acute, closed wards in two psychiatric hospitals in Israel.

Results

A higher proportion of academic nurses to nonacademic nurses on duty leads to a shorter coercion time (P < 0.000). The number of male staff on duty, without any relation to their level of education, also leads to the shortening of the coercion time.

Conclusion

The presence of registered, academic female nurses, male staff on duty and the administration of medication before coercive measures can reduce the length of restriction.