Predicting Inpatient Aggression in Forensic Services Using Remote Monitoring Technology: Qualitative Study of Staff Perspectives

Health Care Professionals' Views on the Use of Passive Sensing, AI, and Machine Learning in Mental Health Care: Systematic Review With Meta-Synthesis

BACKGROUND

Mental health difficulties are highly prevalent worldwide. Passive sensing technologies and applied artificial intelligence (AI) methods can provide an innovative means of supporting the management of mental health problems and enhancing the quality of care. However, the views of stakeholders are important in understanding the potential barriers to and facilitators of their implementation.

OBJECTIVE

This study aims to review, critically appraise, and synthesize qualitative findings relating to the views of mental health care professionals on the use of passive sensing and AI in mental health care.

METHODS

A systematic search of qualitative studies was performed using 4 databases. A meta-synthesis approach was used, whereby studies were analyzed using an inductive thematic analysis approach within a critical realist epistemological framework.

RESULTS

Overall, 10 studies met the eligibility criteria. The 3 main themes were uses of passive sensing and AI in clinical practice, barriers to and facilitators of use in practice, and consequences for service users. A total of 5 subthemes were identified: barriers, facilitators, empowerment, risk to well-being, and data privacy and protection issues.

CONCLUSIONS

Although clinicians are open-minded about the use of passive sensing and AI in mental health care, important factors to consider are service user well-being, clinician workloads, and therapeutic relationships. Service users and clinicians must be involved in the development of digital technologies and systems to ensure ease of use. The development of, and training in, clear policies and guidelines on the use of passive sensing and AI in mental health care, including risk management and data security procedures, will also be key to facilitating clinician engagement. The means for clinicians and service users to provide feedback on how the use of passive sensing and AI in practice is being received should also be considered.

TRIAL REGISTRATION

PROSPERO International Prospective Register of Systematic Reviews CRD42022331698; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=331698.

A service evaluation of passive remote monitoring technology for patients in a high-secure forensic psychiatric hospital: a qualitative study

BACKGROUND

Technology has the potential to remotely monitor patient safety in real-time that helps staff and without disturbing the patient. However, staff and patients' perspectives on using passive remote monitoring within an inpatient setting is lacking. The study aim was to explore stakeholders' perspectives about using Oxehealth passive monitoring technology within a high-secure forensic psychiatric hospital in the UK as part of a wider mixed-methods service evaluation.

METHODS

Semi-structured interviews were conducted with staff and patients with experience of using Oxehealth technology face-to-face within a private room in Broadmoor Hospital. We applied thematic analysis to the data of each participant group separately. Themes and sub-themes were integrated, finalised, and presented in a thematic map. Design, management, and analysis was meaningfully informed by both staff and patients.

RESULTS

Twenty-four participants were interviewed (n = 12 staff, n = 12 patients). There were seven main themes: detecting deterioration and improving health and safety, "big brother syndrome", privacy and dignity, knowledge and understanding, acceptance, barriers to use and practice issues and future changes needed. Oxehealth technology was considered acceptable to both staff and patients if the technology was used to detect deterioration and improve patient's safety providing patient's privacy was not invaded. However, overall acceptance was lower when knowledge and understanding of the technology and its camera was limited. Most patients could not understand why both physical checks through bedroom windows, and Oxehealth was needed to monitor patients, whilst staff felt Oxehealth should not replace physical checks of patients as reassures staff on patient safety.

CONCLUSIONS

Oxehealth technology is considered viable and acceptable by most staff and patients but there is still some concern about its possible intrusive nature. However, more support and education for new patients and staff to better understand how Oxehealth works in the short- and long-term could be introduced to further improve acceptability. A feasibility study or pilot trial to compare the impact of Oxehealth with and without physical checks may be needed.

Utilization and effects of security technologies in mental health: A scoping review

Violence in healthcare is an urgent and increasing issue. Mental health settings are particularly affected, with severe negative impacts on staff, patients, and organizations. Security technologies could help maintain and improve safety in this field. However, knowledge of their utilization and effectiveness in mental health is lacking. A scoping review was conducted using the methodology recommended by the Joanna Briggs Institute to map research on the utilization and effects of security technologies in mental health, identify how research is currently performed, and highlight gaps in the existing knowledge. Literature search for peer-reviewed publications was performed on PubMed, CINAHL, PsycInfo, Embase, and Scopus. Following the screening process and the eligibility criteria, 22 articles were included in this review. The publication range was 2002-2020, many studies were surveys, and European countries were the most investigated, especially the United Kingdom. Overall, the use of 10 different technologies was reported 46 times. The most represented category was alarms, followed by video cameras, other technologies (such as wearable sensors), and metal detectors. More than half of the included papers reported positive effects of these measures on safety. This review indicates that several security technologies are available in mental health settings, with encouraging positive safety outcomes for both patients and healthcare professionals, especially nurses. However, research on the topic is still emerging, with a limited number of sources and a few high-quality designed studies. Therefore, future research should focus on producing evidence on the availability and effectiveness of these measures in mental health settings across countries.

mHealth technology to assess, monitor and treat daily functioning difficulties in people with severe mental illness: A systematic review

Severe mental illness (SMI) is associated with poor daily functioning; however available interventions currently under-deliver on their recovery prospect. Mobile digital health (mHealth) interventions are increasingly being developed and evaluated, and have the potential to support recovery. This review evaluates the use of mHealth technology to assess, monitor and reduce functioning difficulties in people with SMI. Studies were systematically searched on multiple databases. Study quality was assessed and double-rated independently. Findings were organised using a narrative synthesis and results were summarised according to the mHealth device purpose, i.e., assessment and monitoring or intervention. Thirty-eight studies comprised of 2262 participants met the inclusion criteria. Smartphones were the most popular mHealth device; personal digital assistants, wearables and tablets were also used. mHealth was widely found to be acceptable and feasible, with preliminary findings suggesting it can support functional recovery by augmenting an intervention, simplifying the assessment, increasing monitoring frequency and/or providing more detailed information. Considerations for overcoming barriers to implementation, recommendations for future research to establish effectiveness, personalisation and specification of mHealth devices and methodologies are discussed. The value of mHealth for remote delivery of recovery based interventions is also considered.

Heart Rate and Skin Conductance Associations with Physical Aggression, Psychopathy, Antisocial Personality Disorder and Conduct Disorder: An Updated Meta-Analysis

The associations between physiological measures (i.e., heart rate and skin conductance) of autonomic nervous system (ANS) activity and severe antisocial spectrum behavior (AB) were meta-analyzed. We used an exhaustive partitioning of variables relevant to the ANS-AB association and investigated four highly relevant questions (on declining effect sizes, psychopathy subscales, moderators, and ANS measures) that are thought to be transformative for future research on AB. We investigated a broad spectrum of physiological measures (e.g., heart rate (variability), pre-ejection period) in relation to AB. The search date for the current meta-analysis was on January 1^st, 2020, includes 101 studies and 769 effect sizes. Results indicate that effect sizes are heterogeneous and bidirectional. The careful partitioning of variables sheds light on the complex associations that were obscured in previous meta-analyses. Effects are largest for the most violent offenders and for psychopathy and are dependent on the experimental tasks used, parameters calculated, and analyses run. Understanding the specificity of physiological reactions may be expedient for differentiating between (and within) types of AB.

How to make study documents clear and relevant: the impact of patient involvement

Background

Patient and public involvement can improve study outcomes, but little data have been collected on why this might be. We investigated the impact of the Feasibility and Support to Timely Recruitment for Research (FAST-R) service, made up of trained patients and carers who review research documents at the beginning of the research pipeline.

Aims

To investigate the impact of the FAST-R service, and to provide researchers with guidelines to improve study documents.

Method

A mixed-methods design assessing changes and suggestions in documents submitted to the FAST-R service from 2011 to 2020. Quantitative measures were readability, word count, jargon words before and after review, the effects over time and if changes were implemented. We also asked eight reviewers to blindly select a pre- or post-review participant information sheet as their preferred version. Reviewers’ comments were analysed qualitatively via thematic analysis.

Results

After review, documents were longer and contained less jargon, but did not improve readability. Jargon and the number of suggested changes increased over time. Participant information sheets had the most suggested changes. Reviewers wanted clarity, better presentation and felt that documents lacked key information such as remuneration, risks involved and data management. Six out of eight reviewers preferred the post-review participant information sheet. FAST-R reviewers provided jargon words and phrases with alternatives for researchers to use.

Conclusions

Longer documents are acceptable if they are clear, with jargon explained or substituted. The highlighted barriers to true informed consent are not decreasing, although this study has suggestions for improving research document accessibility.

Physiological Measurements of Stress Preceding Incidents of Challenging Behavior in People With Severe to Profound Intellectual Disabilities: Longitudinal Study Protocol of Single-Case Studies

Background

Clients with severe to profound intellectual disabilities (SPID) and challenging behavior (CB) and the professional caregivers that support them are vulnerable to high stress levels, which negatively impact their well-being and the quality of care. CB is thought to result from an increase in the intensity and frequency of clients’ stress experiences. In turn, staff members experience stress in dealing with this behavior, and stressed staff members might behave in ways that increase clients’ stress levels, contributing to the origin and maintenance of CB. Research into these dyadic interactions between clients and staff is scarce for people with SPID, especially in real-life situations. The barriers of studying stress in this population include clients’ difficulties in communicating stress experiences and the lack of an objective continuous measure of stress.

Objective

This paper presents a protocol for studying patterns of physiological stress in 15 client-caregiver dyads in the 30 minutes preceding incidents of CB compared to control periods without CB and the interplay between the stress levels of clients and professional caregivers.

Methods

We will conduct 15 single-case studies to assess patterns of physiological stress in dyads of clients with SPID and professional caregivers prior to CB in several Dutch residential institutes. Client-caregiver dyads will wear the Empatica E4 wristband for 20 sessions of 3 to 8 hours without interruptions of daily routines while caregivers report clients’ CB. The physiological measures obtained will be electrodermal activity (microsiemens) and heart rate (beats per minute). A multilevel model with repeated measures at the incident level nested within the person level will be applied, employing separate models for electrodermal activity and heart rate to compare stress levels in the 30 minutes prior to incidents with control epochs. Covariates in the models include movement, temperature, and gender. In addition, cross-recurrence quantification analyses will be performed to study the synchronization between the stress levels of clients and professional caregivers.

Results

The Ethics Committee of the Radboud University (NL-number: NL71683.091.19) approved the study on February 12, 2020. In total, 15 organizations have declared their commitment to participate in the study. The first result is expected in the spring of 2022.

Conclusions

Study results will demonstrate whether changes in patterns of electrodermal activity and heart rate are apparent in the 30 minutes preceding an incident of CB compared to baseline levels when the client does not engage in CB. The synchronization between caregivers’ and clients’ physiological stress levels will be explored with cross-recurrence quantification analyses. Insights into the physiological stress levels of clients and caregivers may contribute to a reduction of CB and an improvement of both clients’ and caregivers’ safety and well-being.

International Registered Report Identifier (IRRID)

DERR1-10.2196/24911

An observational study of a cross platform risk assessment mobile application in a forensic inpatient setting

Consumer-focused healthcare mobile applications have seen widespread adoption in recent years. Enterprise mobile applications in hospital settings have been slower to gain traction. In this study we examine the Dynamic Appraisal of Situational Aggression: Inpatient version (DASA), a short-term risk assessment tool which is well validated and widely used in the prediction of violent incidents, within an inpatient forensic setting. The application was piloted over a period of three months, collecting 847 total DASA scores on 21 different patients. Time stamping allowed for accurate correlation between risk assessment scoring and the violent risk incidents. The internal validity of the app was measured using Cronbach's alpha and was calculated at 0.798 indicating good internal validity. Using violent incidents as the dependent factor and the total DASA score as the independent factor, predictive validity of the app was calculated at 0.85, p = 0.007. The use of this application in a forensic setting was successful with good internal and predictive validity. A major benefit of this form of data collection was the electronic time stamping so that the correlation between risk estimation and events could be more closely correlated. Deployment of such an application in a general hospital setting would bring its own challenges but would be useful in other types of risk assessment and screening tools.

The path of compassion in forensic psychiatry

We aimed to deepen our understanding of the concept of compassion in caring for patients with mental illness in forensic psychiatric inpatient care settings. Qualitative analysis was used to illuminate themes from interviews conducted with 13 nurses in a prior study. The audiotaped interviews, which had been transcribed verbatim, were analyzed following a hermeneutic approach. Results revealed the main theme of "being compassionate in forensic psychiatry is an emotional journey" and three themes. Overall, compassion was seen as a changeable asset, but also an obstacle when absent; sensitivity to one's own vulnerability is necessary to overcome that obstacle.