Predictive care: a protocol for a computational ethnographic approach to building fair models of inpatient violence in emergency psychiatry.

INTRODUCTION: Managing violence or aggression is an ongoing challenge in emergency psychiatry. Many patients identified as being at risk do not go on to become violent or aggressive. Efforts to automate the assessment of risk involve training machine learning (ML) models on data from electronic health records (EHRs) to predict these behaviours. However, no studies to date have examined which patient groups may be over-represented in false positive predictions, despite evidence of social and clinical biases that may lead to higher perceptions of risk in patients defined by intersecting features (eg, race, gender). Because risk assessment can impact psychiatric care (eg, via coercive measures, such as restraints), it is unclear which patients might be underserved or harmed by the application of ML. METHODS AND ANALYSIS: We pilot a computational ethnography to study how the integration of ML into risk assessment might impact acute psychiatric care, with a focus on how EHR data is compiled and used to predict a risk of violence or aggression. Our objectives include: (1) evaluating an ML model trained on psychiatric EHRs to predict violent or aggressive incidents for intersectional bias; and (2) completing participant observation and qualitative interviews in an emergency psychiatric setting to explore how social, clinical and structural biases are encoded in the training data. Our overall aim is to study the impact of ML applications in acute psychiatry on marginalised and underserved patient groups. ETHICS AND DISSEMINATION: The project was approved by the research ethics board at The Centre for Addiction and Mental Health (053/2021). Study findings will be presented in peer-reviewed journals, conferences and shared with service users and providers.

Operationalizing and Evaluating Synchronous Virtual Group Health Interventions: Wide-Scale Implementation at a Tertiary Care Academic Hospital.

Group-based health interventions are an important component of health promotion and management. To provide continuity of care throughout the COVID-19 pandemic, our institution undertook a rapid pivot to delivering group-based health interventions via a videoconferencing service which was securely embedded into both the electronic medical record and the patient portal to sustainably address immediate health service delivery needs during the pandemic and beyond. In this paper, we (1) describe the institutionally driven operationalization of a system to provide integrated synchronous video group visits across our hospital and (2) present a proposed strategy to comprehensively evaluate outcomes regarding their implementation, quality, and impact. Lessons for other institutions and the potential future role of synchronous video group visits to enhance how care can be scaled for delivery are discussed.

Information and communication technology-based interventions for suicide prevention implemented in clinical settings: a scoping review protocol.

INTRODUCTION: There is a surplus of information and communication technology (ICT)-based interventions for suicide prevention. However, it is unclear which of these ICT-based interventions for suicide prevention have been implemented in clinical settings. Furthermore, evidence shows that implementation strategies have often been mismatched to existing barriers. In response, the authors recognise the critical need for prospectively assessing the barriers and facilitators and then strategically developing implementation strategies. This review is part of a multiphase project to develop and test tailored implementation strategies for mobile app-based suicide prevention in clinical settings. The overall objective of this scoping review is to identify and characterise ICT-based interventions for all levels of suicide prevention in clinical settings. Additionally, this review will identify and characterise the barriers and facilitators to implementing these ICT-based interventions as well as reported measures and outcomes. The findings will directly inform the subsequent phase to maximise implementation and inform future efforts for implementing other types of ICT-based interventions related to suicide prevention in clinical settings. METHODS AND ANALYSIS: This review will adhere to the methods described by the Joanna Briggs Institute for conducting scoping reviews. The reporting will follow the Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for scoping review checklist. The following databases will be searched: Medline, PsycInfo, Embase, Cumulative Index to Nursing & Allied Health Literature (CINAHL), Web of Science and Library, Information Science & Technology Abstracts (LISTA). Two reviewers will independently screen the articles and extract data using a standardised data collection tool. Then, authors will characterise extracted data using frameworks, typology and taxonomies to address the proposed review questions. ETHICS AND DISSEMINATION: Ethics approval is not required for this scoping review. Authors will share the results in a peer-reviewed, open access publication and conference presentations. Furthermore, the findings will be shared with relevant health organisations through lay language summaries and informal presentations.