Suicide rates have increased over the last couple of decades globally, particularly in the United States and among populations with lower economic status who present at safety-net healthcare systems. Recently, predictive models for suicide risk have shown promise; however, a model for this specific population does not exist.

To develop a predictive risk model of suicide and intentional self-harm (ISH) for patients presenting at the psychiatric emergency department (ED) of JPS Health Network, a safety net medical and mental healthcare system in Texas.

The study used structured and unstructured electronic medical record (EMR) data (2015–2019) and local medical examiner data (2015–2020) to create predictors and outcome variables. All psychiatric ED notes during calendar years 2018 and 2019 were reviewed using natural language processing to identify presentations for any level of self-harm and subsequent manual review of identified visits to accurately classify ED presentations for treatment of an act of intentional self-harm meeting study criteria. Data from 15 987 patients were used to develop and validate a machine learning-based predictive model that leverages rolling window methodology to predict risk repeatedly across a patient’s trajectory. Feature engineering played a prominent role in defining new predictors.

The best model (XGBoost) achieved the area under the receiver operating characteristic curve of 0.81 for 30-day predictions and demonstrated concentration of ISH and suicide attempt events in high-risk quantiles of risk (65% had events in top 0.1% quantile). The predicted risk can be translated into a propensity of events (80% at the highest predicted risk) to facilitate clinical interpretation.

Machine learning-based models can be used with standard EMRs to identify patients presenting at the psychiatric ED with a high risk of ISH and suicide attempts within the next 30 days.

Integration of a predictive model can significantly aid clinical decision-making in safety-net psychiatric EDs.

Case reports (CRs) are essential in physiotherapy, yet reporting remains heterogeneous and insufficiently standardised. The 2013 CAse REport (CARE) guideline improves transparency but lacks physiotherapy-specific detail. This study aimed to develop a consensus-driven extension of the CARE reporting guideline to support structured reporting of physiotherapy CRs, encompassing physiotherapy-specific assessments and interventions.

An e-Delphi consensus process study following the ACcurate COnsensus Reporting Document (ACCORD) guidelines.

Online.

Forty-four international experts in physiotherapy practice, research and education, along with six core committee members.

Experts objectively scored items for relevance (5-point Likert scale) and provided open-ended responses for each item of the drafts. Scores and responses were analysed to facilitate iterative refinement of the Physiotherapy CAse REport (PhyCARE) reporting guidelines. Consensus was predetermined at over 70% agreement.

Round 1 had the majority of items achieving ≥70% agreement, except two items that did not meet the threshold were revised and replaced with an alternative. Five new items addressing physiotherapy-specific reporting needs were added, and 10 items were relocated. In round 2, all 35 items across 13 domains achieved 84%–100% agreement. The nomenclature of one domain was revised to ‘Outcomes and Follow-up’. Following two e-Delphi rounds, consensus was achieved, and suggestions from online meeting, piloting led to item rephrasing, after which the PhyCARE guidelines were finalised.

The PhyCARE guidelines have the potential to provide a physiotherapy-specific extension of CARE to support structured, transparent and reproducible reporting of physiotherapy CRs.