RESUMO
STUDY OBJECTIVE: The workload of clinical documentation contributes to health care costs and professional burnout. The advent of generative artificial intelligence language models presents a promising solution. The perspective of clinicians may contribute to effective and responsible implementation of such tools. This study sought to evaluate 3 uses for generative artificial intelligence for clinical documentation in pediatric emergency medicine, measuring time savings, effort reduction, and physician attitudes and identifying potential risks and barriers. METHODS: This mixed-methods study was performed with 10 pediatric emergency medicine attending physicians from a single pediatric emergency department. Participants were asked to write a supervisory note for 4 clinical scenarios, with varying levels of complexity, twice without any assistance and twice with the assistance of ChatGPT Version 4.0. Participants evaluated 2 additional ChatGPT-generated clinical summaries: a structured handoff and a visit summary for a family written at an 8th grade reading level. Finally, a semistructured interview was performed to assess physicians' perspective on the use of ChatGPT in pediatric emergency medicine. Main outcomes and measures included between subjects' comparisons of the effort and time taken to complete the supervisory note with and without ChatGPT assistance. Effort was measured using a self-reported Likert scale of 0 to 10. Physicians' scoring of and attitude toward the ChatGPT-generated summaries were measured using a 0 to 10 Likert scale and open-ended questions. Summaries were scored for completeness, accuracy, efficiency, readability, and overall satisfaction. A thematic analysis was performed to analyze the content of the open-ended questions and to identify key themes. RESULTS: ChatGPT yielded a 40% reduction in time and a 33% decrease in effort for supervisory notes in intricate cases, with no discernible effect on simpler notes. ChatGPT-generated summaries for structured handoffs and family letters were highly rated, ranging from 7.0 to 9.0 out of 10, and most participants favored their inclusion in clinical practice. However, there were several critical reservations, out of which a set of general recommendations for applying ChatGPT to clinical summaries was formulated. CONCLUSION: Pediatric emergency medicine attendings in our study perceived that ChatGPT can deliver high-quality summaries while saving time and effort in many scenarios, but not all.
Assuntos
Inteligência Artificial , Serviço Hospitalar de Emergência , Humanos , Médicos/psicologia , Feminino , Masculino , Atitude do Pessoal de Saúde , Medicina de Emergência Pediátrica , Documentação/métodos , Documentação/normas , Medicina de Emergência , Registros Eletrônicos de Saúde , AdultoRESUMO
BACKGROUND: While patient and family engagement in research has become a widespread practice, meaningful and authentic engagement remains a challenge. In the READYorNot™ Brain-Based Disabilities Study, we developed the MyREADY Transition™ Brain-Based Disabilities App to promote education, empowerment, and navigation for the transition from pediatric to adult care among youth with brain-based disabilities, aged 15-17 years old. Our research team created a Patient and Family Advisory Council (PFAC) to engage adolescents, young adults, and parent caregivers as partners throughout our multi-year and multi-stage project. MAIN BODY: This commentary, initiated and co-authored by members of our PFAC, researchers, staff, and a trainee, describes how we corrected the course of our partnership in response to critical feedback from partners. We begin by highlighting an email testimonial from a young adult PFAC member, which constituted a "critical turning point," that unveiled feelings of unclear expectations, lack of appreciation, and imbalanced relationships among PFAC members. As a team, we reflected on our partnership experiences and reviewed documentation of PFAC activities. This process allowed us to set three intentions to create a collective goal of authentic and meaningful engagement and to chart the course to get us there: (1) offering clarity and flexibility around participation; (2) valuing and acknowledging partners and their contributions; and (3) providing choice and leveraging individual interests and strengths. Our key recommendations include: (1) charting the course with a plan to guide our work; (2) learning the ropes by developing capacity for patient-oriented research; (3) all hands on deck by building a community of engagement; and (4) making course corrections and being prepared to weather the storms by remaining open to reflection, re-evaluation, and adjustment as necessary. CONCLUSIONS: We share key recommendations and lessons learned from our experiences alongside examples from the literature to offer guidance for multi-stage research projects partnering with adolescents, young adults, and family partners. We hope that by sharing challenges and lessons learned, we can help advance patient and family engagement in research.
RESUMO
Background: Despite restrictive opioid management guidelines, opioid use disorder (OUD) remains a major public health concern. Machine learning (ML) offers a promising avenue for identifying and alerting clinicians about OUD, thus supporting better clinical decision-making regarding treatment. Objective: This study aimed to assess the clinical validity of an ML application designed to identify and alert clinicians of different levels of OUD risk by comparing it to a structured review of medical records by clinicians. Methods: The ML application generated OUD risk alerts on outpatient data for 649,504 patients from 2 medical centers between 2010 and 2013. A random sample of 60 patients was selected from 3 OUD risk level categories (n=180). An OUD risk classification scheme and standardized data extraction tool were developed to evaluate the validity of the alerts. Clinicians independently conducted a systematic and structured review of medical records and reached a consensus on a patient's OUD risk level, which was then compared to the ML application's risk assignments. Results: A total of 78,587 patients without cancer with at least 1 opioid prescription were identified as follows: not high risk (n=50,405, 64.1%), high risk (n=16,636, 21.2%), and suspected OUD or OUD (n=11,546, 14.7%). The sample of 180 patients was representative of the total population in terms of age, sex, and race. The interrater reliability between the ML application and clinicians had a weighted kappa coefficient of 0.62 (95% CI 0.53-0.71), indicating good agreement. Combining the high risk and suspected OUD or OUD categories and using the review of medical records as a gold standard, the ML application had a corrected sensitivity of 56.6% (95% CI 48.7%-64.5%) and a corrected specificity of 94.2% (95% CI 90.3%-98.1%). The positive and negative predictive values were 93.3% (95% CI 88.2%-96.3%) and 60.0% (95% CI 50.4%-68.9%), respectively. Key themes for disagreements between the ML application and clinician reviews were identified. Conclusions: A systematic comparison was conducted between an ML application and clinicians for identifying OUD risk. The ML application generated clinically valid and useful alerts about patients' different OUD risk levels. ML applications hold promise for identifying patients at differing levels of OUD risk and will likely complement traditional rule-based approaches to generating alerts about opioid safety issues.
RESUMO
INTRODUCTION: There is an urgent need for scalable strategies for treating overweight and obesity in clinical settings. PROPS 2.0 (Partnerships for Reducing Overweight and Obesity with Patient-Centered Strategies 2.0) aims to adapt and implement the combined intervention from the PROPS Study at scale, in a diverse cross-section of patients and providers. METHODS AND ANALYSIS: We are implementing PROPS 2.0 across a variety of clinics at Brigham and Women's Hospital, targeting enrolment of 5000 patients. Providers can refer patients or patients can self-refer. Eligible patients must be ≥20 years old and have a body mass index (BMI) of ≥30 kg/m2 or a BMI of 25-29.9 kg/m2 plus another cardiovascular risk factor or obesity-related condition. After enrolment, patients register for the RestoreHealth online programme/app (HealthFleet Inc.) and participate for 12 months. Patients can engage with the programme and receive personalized feedback from a coach. Patient navigators help to enrol patients, enter updates in the electronic health record, and refer patients to additional resources. The RE-AIM (Reach, Effectiveness, Adoption, Implementation, and Maintenance) framework is guiding the evaluation. ETHICS AND DISSEMINATION: The Mass General Brigham Human Research Committee approved this protocol. An implementation guide will be created and disseminated, to help other sites adopt the intervention in the future. TRIAL REGISTRATION NUMBER: NCT0555925.