Clinical documentation is a significant driver of burnout among physicians. Ambient artificial intelligence (AI) scribes, which leverage generative large language models to automate the creation of clinical notes from patient–physician conversations, are rapidly emerging as a potential solution. While these tools promise to enhance efficiency and reduce administrative tasks, concerns about the quality, accuracy and potential biases persist. There is now a need for a systematic synthesis of evidence to evaluate the impact of these technologies in clinical practice. To assess the effects of ambient AI scribes on physicians’ clinical documentation, the specific objectives are to: (1) evaluate the effectiveness of these tools on documentation, including accuracy and completeness; (2) synthesise evidence on the impact on physician efficiency after adoption, including time spent on documentation and (3) examine physicians’ satisfaction with these tools, including physicians’ perceived burden.

A systematic review of quantitative or mixed-method studies as well as preprints will be conducted. We will perform a comprehensive search of four electronic databases (PubMed, IEEE Xplore, APA PsycInfo and Web of Science, along with medRix and ClinicalTrials.gov for preprints) for empirical studies published between January 2023 and March 2026. The review will synthesise studies comparing physicians’ use of ambient AI scribes with traditional documentation approaches. Given the anticipated heterogeneity of the studies, a narrative synthesis will be employed to summarise the findings. Where common quantitative outcomes exist, effect sizes will be calculated using Hedges’ g, mean differences or risk ratios/odds ratios as appropriate. The overall quality of evidence will be assessed using the Grading of Recommendations Assessment, Development and Evaluation (GRADE) framework.

As no patient data are involved in the data collection, no ethical approval is acquired. Results will be disseminated in a peer-reviewed, open-access journal, and presented at relevant academic conferences.

CRD420251149086.

Acute low back pain (LBP) is a prevalent condition with various non-surgical treatment options, yet no comprehensive network meta-analysis has systematically compared their relative efficacy for pain and disability. This study aims to fill that gap by synthesising available evidence on the efficacy of different types of non-surgical interventions for acute LBP, such as various medications, manual therapies and education-based therapies. Our coprimary objectives are to (1) compare each active treatment to an inert reference for measures of LBP and related disability and (2) rank the efficacy of treatments.

We will conduct a systematic search across multiple databases, including grey literature, to identify randomised controlled trials evaluating non-surgical treatments for acute LBP. Eligible studies must report on pain and/or disability outcomes in adults. The risk of bias will be assessed using the Risk of Bias tool, and the certainty of evidence will be graded using CINeMA (Confidence in Network Meta-Analysis). We will use a frequentist network meta-analysis to pool standardised mean differences in pain and disability, employing random-effects models to account for heterogeneity. A qualitative analysis will assess study characteristics and transitivity, while a quantitative analysis will evaluate efficacy and inconsistency. Results will be presented using network geometry, p-scores, forest plots, funnel plots, Egger’s test, Q-statistics and league tables to visualise both direct and indirect evidence and to identify potential biases.

This review protocol does not involve any primary research with human participants, animal subjects or medical record review. Consequently, this work did not require approval from an institutional review board or ethics committee. Results will be submitted to a peer-reviewed journal and presented at conference(s). De-identified data will be made available in a public repository.