ROAD2H: Development and evaluation of an open-source explainable artificial intelligence approach for managing co-morbidity and clinical guidelines.

Introduction: Clinical decision support (CDS) systems (CDSSs) that integrate clinical guidelines need to reflect real-world co-morbidity. In patient-specific clinical contexts, transparent recommendations that allow for contraindications and other conflicts arising from co-morbidity are a requirement. In this work, we develop and evaluate a non-proprietary, standards-based approach to the deployment of computable guidelines with explainable argumentation, integrated with a commercial electronic health record (EHR) system in Serbia, a middle-income country in West Balkans. Methods: We used an ontological framework, the Transition-based Medical Recommendation (TMR) model, to represent, and reason about, guideline concepts, and chose the 2017 International global initiative for chronic obstructive lung disease (GOLD) guideline and a Serbian hospital as the deployment and evaluation site, respectively. To mitigate potential guideline conflicts, we used a TMR-based implementation of the Assumptions-Based Argumentation framework extended with preferences and Goals (ABA+G). Remote EHR integration of computable guidelines was via a microservice architecture based on HL7 FHIR and CDS Hooks. A prototype integration was developed to manage chronic obstructive pulmonary disease (COPD) with comorbid cardiovascular or chronic kidney diseases, and a mixed-methods evaluation was conducted with 20 simulated cases and five pulmonologists. Results: Pulmonologists agreed 97% of the time with the GOLD-based COPD symptom severity assessment assigned to each patient by the CDSS, and 98% of the time with one of the proposed COPD care plans. Comments were favourable on the principles of explainable argumentation; inclusion of additional co-morbidities was suggested in the future along with customisation of the level of explanation with expertise. Conclusion: An ontological model provided a flexible means of providing argumentation and explainable artificial intelligence for a long-term condition. Extension to other guidelines and multiple co-morbidities is needed to test the approach further.

Remote COVID-19 Assessment in Primary Care (RECAP) risk prediction tool: derivation and real-world validation studies.

BACKGROUND: Accurate assessment of COVID-19 severity in the community is essential for patient care and requires COVID-19-specific risk prediction scores adequately validated in a community setting. Following a qualitative phase to identify signs, symptoms, and risk factors, we aimed to develop and validate two COVID-19-specific risk prediction scores. Remote COVID-19 Assessment in Primary Care-General Practice score (RECAP-GP; without peripheral oxygen saturation [SpO2]) and RECAP-oxygen saturation score (RECAP-O2; with SpO2). METHODS: RECAP was a prospective cohort study that used multivariable logistic regression. Data on signs and symptoms (predictors) of disease were collected from community-based patients with suspected COVID-19 via primary care electronic health records and linked with secondary data on hospital admission (outcome) within 28 days of symptom onset. Data sources for RECAP-GP were Oxford-Royal College of General Practitioners Research and Surveillance Centre (RCGP-RSC) primary care practices (development set), northwest London primary care practices (validation set), and the NHS COVID-19 Clinical Assessment Service (CCAS; validation set). The data source for RECAP-O2 was the Doctaly Assist platform (development set and validation set in subsequent sample). The two probabilistic risk prediction models were built by backwards elimination using the development sets and validated by application to the validation datasets. Estimated sample size per model, including the development and validation sets was 2880 people. FINDINGS: Data were available from 8311 individuals. Observations, such as SpO2, were mostly missing in the northwest London, RCGP-RSC, and CCAS data; however, SpO2 was available for 1364 (70·0%) of 1948 patients who used Doctaly. In the final predictive models, RECAP-GP (n=1863) included sex (male and female), age (years), degree of breathlessness (three point scale), temperature symptoms (two point scale), and presence of hypertension (yes or no); the area under the curve was 0·80 (95% CI 0·76-0·85) and on validation the negative predictive value of a low risk designation was 99% (95% CI 98·1-99·2; 1435 of 1453). RECAP-O2 included age (years), degree of breathlessness (two point scale), fatigue (two point scale), and SpO2 at rest (as a percentage); the area under the curve was 0·84 (0·78-0·90) and on validation the negative predictive value of low risk designation was 99% (95% CI 98·9-99·7; 1176 of 1183). INTERPRETATION: Both RECAP models are valid tools to assess COVID-19 patients in the community. RECAP-GP can be used initially, without need for observations, to identify patients who require monitoring. If the patient is monitored and SpO2 is available, RECAP-O2 is useful to assess the need for treatment escalation. FUNDING: Community Jameel and the Imperial College President's Excellence Fund, the Economic and Social Research Council, UK Research and Innovation, and Health Data Research UK.

Barriers and facilitators to incident reporting in mental healthcare settings: A qualitative study.

WHAT IS KNOWN ON THE SUBJECT?: The barriers and facilitators to incident reporting are becoming well known in general healthcare settings due to a large body of research in this area. At present, it is unknown if these factors also affect incident reporting in mental healthcare settings as the same amount of research has not been conducted in these settings. WHAT THE PAPER ADDS TO EXISTING KNOWLEDGE: Some of the barriers and facilitators to incident reporting in mental healthcare settings are the same as general healthcare settings (i.e., learning and improvement, time and fear). Other factors appear to be specific to mental healthcare settings (i.e., the role of patient diagnosis and how incidents involving assault are dealt with). WHAT ARE THE IMPLICATIONS FOR PRACTICE?: Interventions to improve incident reporting in mental healthcare settings may be adapted from general healthcare settings in some cases. Bespoke interventions for mental healthcare settings that focus specifically on violence and aggression should be co-designed with patients and staff. Thresholds for incident reporting (i.e., what types of incidents will not be tolerated) need to be set, communicated and adopted Trust wide to ensure parity across staff groups and services. ABSTRACT: Introduction Barriers and facilitators to incident reporting have been widely researched in general health care. However, it is unclear if the findings are applicable to mental health care where care is increasingly complex. Aim To investigate if barriers and facilitators affecting incident reporting in mental health care are consistent with factors identified in other healthcare settings. Method Data were collected from focus groups (n = 8) with 52 members of staff from across West London NHS Trust and analysed with thematic analysis. Results Five themes were identified during the analysis. Three themes (a) learning and improvement, (b) time and (c) fear were consistent with the existing wider literature on barriers and facilitators to incident reporting. Two further themes (d) interaction between patient diagnosis and incidents and (e) aftermath of an incident-prosecution specifically linked to the provision of mental health care. Conclusions Whilst some barriers and facilitators to incident reporting identified in other settings are also prevalent in the mental healthcare setting, the increased incidence of violent and aggressive behaviour within mental health care presents a unique challenge for incident reporting. Clinical implications Although interventions to improve incident reporting may be adapted/adopted from other settings, there is a need to develop specific interventions to improve reporting of violent and aggressive incidents.