Background: Burnout among clinicians, including physicians, is a growing concern in healthcare. An overwhelming burden of clinical documentation is a significant contributor. While medical scribes have been employed to mitigate this burden, they have limitations such as cost, training needs, and high turnover rates. Artificial intelligence (AI) scribe systems can transcribe, summarize, and even interpret clinical conversations, offering a potential solution for improving clinician well-being. We aimed to evaluate the effectiveness of AI scribes in streamlining clinical documentation, with a focus on clinician experience, healthcare system efficiency, and patient engagement. Methods: We conducted a systematic review following Cochrane methods and PRISMA guidelines. Two reviewers conducted the selection process independently. Eligible intervention studies included quantitative and mixed-methods studies evaluating AI scribe systems. We summarized the data narratively. Results: Eight studies were included. AI scribes demonstrated positive effects on healthcare provider engagement, with users reporting increased involvement in their workflows. The documentation burden showed signs of improvement, as AI scribes helped alleviate the workload for some participants. Many clinicians have found AI systems to be user-friendly and intuitive, although some have expressed concerns about scribe training and documentation quality. A limited impact on reducing burnout was found, although documentation time improved in some studies. Conclusions: Most of the studies reported in this review involved small sample sizes and specific healthcare settings, limiting the generalizability of the findings to other contexts. Accuracy and consistency can vary significantly depending on the specific technology, model training data, and implementation approach. AI scribes show promise in improving documentation efficiency and clinician workflow, although the evidence remains limited and heterogeneous. Broader and real-world evaluations are needed to confirm their effectiveness and inform responsible implementations.

: In health care, clinical decision making is typically based on diagnostic findings. Rehabilitation clinicians commonly rely on pathoanatomical diagnoses to guide treatment and define prognosis. Targeting prognostic factors is a promising way for rehabilitation clinicians to enhance treatment decision-making processes, personalize rehabilitation approaches, and ultimately improve patient outcomes. This can be achieved by using prognostic tools that provide accurate estimates of the probability of future outcomes for a patient in clinical practice. Most literature reviews of prognostic tools in rehabilitation have focused on prescriptive clinical prediction rules. These studies highlight notable methodological issues and conclude that these tools are neither valid nor useful for clinical practice. This has raised the need to open the scope of research to understand what makes a quality prognostic tool that can be used in clinical practice. Methodological guidance in prognosis research has emerged in the last decade, encompassing exploratory studies on the development of prognosis and prognostic models. Methodological rigor is essential to develop prognostic tools, because only prognostic models developed and validated through a rigorous methodological process should guide clinical decision making. This Perspective argues that rehabilitation clinicians need to master the identification and use of prognostic tools to enhance their capacity to provide personalized rehabilitation. It is time for prognosis research to look for prognostic models that were developed and validated following a comprehensive process before being simplified into suitable tools for clinical practice. New models, or rigorous validation of current models, are needed. The approach discussed in this Perspective offers a promising way to overcome the limitations of most models and provide clinicians with quality tools for personalized rehabilitation approaches. Impact: Prognostic research can be applied to clinical rehabilitation; this Perspective proposes solutions to develop high-quality prognostic models to optimize patient outcomes.

Introduction: Self-reported levels of disability in individuals with low back pain (LBP) have not improved in the last decade. A broader perspective and a more comprehensive management framework may improve disability outcomes. We recently developed and validated the Low Back Pain and Disability Drivers Management (PDDM) model, which aims to identify the domains driving pain and disability to guide clinical decisions. The objectives of this study were to determine the applicability of the PDDM model to a LBP population and the feasibility of conducting a pragmatic trial, as well as to explore clinicians’ perceived acceptability of the PDDM model’s use in clinical settings. Methods: This study was an one-arm prospective feasibility trial. Participants included physiotherapists working with a population suffering from LBP and their patients aged 18 years or older presenting with a primary complaint of LBP that sought a new referral and deemed fit for rehabilitation from private and public clinical settings. Clinicians participated in a one-day workshop on the integration of the PDDM model into their clinical practice, and were asked to report various LBP-related outcomes via self-reported questionnaires (i.e., impact of pain on physical function, nervous system dysfunctions, cognitive-emotional factors, work disabilities) at baseline and at six-week follow-up. Physiotherapists’ acceptability of the use of the PDDM model and appreciation of the training were assessed via semi-structured phone interviews. Analyses focused on a description of the model’s applicability to a LBP population, feasibility outcomes and acceptability measures. Results: Applicablity of the PDDM model was confirmed since it successfully established the profile of patients according to the elements of each categories, and each of the 5 domains of the model was represented among the study sample. Trial was deemed feasible contingent upon few modifications as our predefined success criteria for the feasibility outcomes were met but feasibility issues pertaining to data collection were highlighted. Twenty-four (24) clinicians and 61 patients were recruited within the study’s timeframe. Patient’s attrition rate (29%) and clinicians’ compliance to the study protocol were adequate. Clinicians’ perceived acceptability of the use of the model in clinical settings and their appreciation of the training and online resources were both positive. Recommendations to improve the model’s integration in clinical practice, content of the workshop and feasibility of data collection methods were identified for future studies. A positive effect for all patients’ reported outcome measures were also observed. All outcome measures except for the PainDetect questionnaire showed a statistically significant reduction post-intervention (p<0.05). Conclusion: These findings provide preliminary evidence of the potential of the PDDM model to optimize LBP management as well as conducting a future larger-scale pragmatic trial to determine its effectiveness. Trial registration: Clinicaltrial.gov: NCT03949179.

Background: Chronic diseases represent a significant global burden of mortality, exacerbated by behavioral risk factors. Artificial intelligence (AI) has transformed health promotion and disease reduction through improved early detection, encouraging healthy lifestyle modifications, and mitigating the economic strain on health systems. Objective: The aim of this study is to investigate how AI contributes to health promotion and disease reduction among Organization for Economic Co-operation and Development countries. Methods: We conducted a rapid review of the literature to identify the latest evidence on how AI is used in health promotion and disease reduction. We applied comprehensive search strategies formulated for MEDLINE (OVID) and CINAHL to locate studies published between 2019 and 2024. A pair of reviewers independently applied the inclusion and exclusion criteria to screen the titles and abstracts, assess the full texts, and extract the data. We synthesized extracted data from the study characteristics, intervention characteristics, and intervention purpose using structured narrative summaries of main themes, giving a portrait of the current scope of available AI initiatives used in promoting healthy activities and preventing disease. Results: We included 22 studies in this review (out of 3442 publications screened), most of which were conducted in the United States (10/22, 45%) and focused on health promotion by targeting lifestyle dimensions, such as dietary behavior (10/22, 45%), smoking cessation (6/22, 27%), physical activity (4/22, 18%), and mental health (3/22, 14%). Three studies targeted disease reduction related to metabolic health (eg, obesity, diabetes, hypertension). Most AI initiatives were AI-powered mobile apps. Overall, positive results were reported for process outcomes (eg, acceptability, engagement), cognitive and behavioral outcomes (eg, confidence, step count), and health outcomes (eg, glycemia, blood pressure). We categorized the challenges, benefits, and suggestions identified in the studies using a Strengths, Weaknesses, Opportunities, and Threats analysis to inform future developments. Key recommendations include conducting further investigations, taking into account the needs of end users, improving the technical aspect of the technology, and allocating resources. Conclusions: These findings offer critical insights into the effective implementation of AI for health promotion and disease prevention, potentially guiding policymakers and health care practitioners in optimizing the use of AI technologies in supporting health promotion and disease reduction.

Introduction: The 2021 Action Plan for Pain from the Canadian Pain Task Force advocates for patient-centred pain care at all levels of healthcare across provinces. Shared decision-making is the crux of patient-centred care. Implementing the action plan will require innovative shared decision-making interventions, specifically following the disruption of chronic pain care during the COVID-19 pandemic. The first step in this endeavour is to assess current decisional needs (ie, decisions most important to them) of Canadians with chronic pain across their care pathways. Methods and analysis: Design Grounded in patient-oriented research approaches, we will perform an online population-based survey across the ten Canadian provinces. We will report methods and data following the CROSS reporting guidelines. Sampling The Léger Marketing company will administer the online population-based survey to its representative panel of 500 000 Canadians to recruit 1646 adults (age ≥18 years old) with chronic pain according to the definition by the International Association for the Study of Pain (eg, pain ≥12 weeks). Content Based on the Ottawa Decision Support Framework, the self-administered survey has been codesigned with patients and contain six core domains: (1) healthcare services, consultation and postpandemic needs, (2) difficult decisions experienced, (3) decisional conflict, (4) decisional regret, (5) decisional needs and (6) sociodemographic characteristics. We will use several strategies such as random sampling to improve survey quality. Analysis We will perform descriptive statistical analysis. We will identify factors associated with clinically significant decisional conflict and decision regret using multivariate analyses. Ethics and dissemination: Ethics was approved by the Research Ethics Board at the Research Centre of the Centre Hospitalier Universitaire de Sherbrooke (project #2022-4645). We will codesign knowledge mobilisation products with research patient partners (eg, graphical summaries and videos). Results will be disseminated via peer-reviewed journals and national and international conferences to inform the development of innovative shared decision-making interventions for Canadians with chronic pain.

Background: Neck pain is a prevalent and disabling condition. Conservative management of this condition has shown only moderate effects. A solution to improve treatment effectiveness is to sub‐group patients into a classification system (CS) that allows for more personalised care. However, current stratification methods have only shown short‐term efficacy for pain. Given the limitations of these tools, it is pertinent to understand how these CSs are composed to be able to propose alternative patient management solutions.Objective: To identify and examine the different components of classification systems specific to patients with neck‐related conditions.Method: A systematic literature search was performed on 3 databases (PubMed, Scopus and CINAHL). Only systematic reviews, with or without meta‐analysis, and scoping reviews reporting CS with associated treatment for neck pain were included. Bias evaluation was performed through risk of bias in systematic review tools.Results: From the search strategy, 741 citations were retrieved, and seven studies were included. From these studies, 37 CS with associated treatments were extracted. Mobilisations showed that 64% were constructed using physical findings, 61% of CS were guided by symptom modulation, 25% used results of self‐reported questionnaire, 14% used individual characteristics, 14% incorporated cognitive findings, 8% used neurological findings, 3% used results of medical diagnostic test, and 3% incorporated environmental findings. Fear‐avoidance beliefs was the only cognitive parameter considered among CS.Conclusion: This study shows that existing classification systems for neck pain are limited and lack coverage of all potential drivers of pain and disability. The lack of recognition of psychosocial and pain neuroscience parameters may partly explain the limited effectiveness of these tools.