Jeffrey S. Upperman

Background: Clinical documentation demands a significant share of surgeons’ time and can contribute to documentation-related burden and burnout. While electronic health records (EHRs) offer accessibility and completeness, they also impose a substantial documentation burden. Ambient AI scribe solutions aim to reduce this burden by capturing patient-clinician dialogue in real time to automate clinical documentation. However, their specific impact on surgical practice remains under-studied. Objective: We aimed to evaluate surgeons’ perceptions of documentation efficiency, documentation timeliness, and burnout following implementation of an ambient AI documentation tool within the EHR during outpatient clinical encounters. Methods: We conducted a single-center cross-sectional survey of all surgical faculty members at a tertiary care academic institution 3 months after institutional implementation of the ambient AI-powered clinical documentation tool Dragon Ambient Experience (DAX) Copilot. A total of 368 faculty surgeons representing 12 surgical subspecialties were invited to participate. Participants were asked to retrospectively assess their baseline perceptions of documentation burden and subsequently report perceived changes following DAX Copilot implementation using standardized Likert-scale survey items. Descriptive analyses were performed among active DAX Copilot users. Open-ended responses were analyzed using practical thematic analysis. Results: The survey was completed by 28.5% (105/368) of the invited surgeons, with 38.1% (40/105) of participants reporting active DAX Copilot use. Overall, 77.5% (31/40) of users reported some or significant improvement in perceived documentation efficiency. Of those who reported a negative or neutral baseline perception of documentation time, 75.8% (25/33) reported an improved perception of efficiency following implementation of the ambient AI tool, whereas 85.7% (6/7) of surgeons with positive baseline perceptions of documentation time also reported further improvement. Improvements in perceived documentation timeliness were reported by 70.4% (19/27) of surgeons who previously reported negative or neutral baseline perceptions of timeliness and 76.9% (10/13) of surgeons with positive baseline perceptions. Additionally, 72.5% (29/40) of respondents reported enhanced documentation accuracy, detail, and consistency after DAX Copilot implementation. Improvements in self-reported burnout levels were reported less frequently, with 59.0% (23/39) of respondents reporting some or significant improvement, including 63.0% (17/27) with negative or neutral baseline perceptions of burnout. Qualitative feedback highlighted perceived improvements in documentation quality while also identifying current limitations of the technology, including challenges related to EHR integration, device compatibility, and customization. Conclusions: In this single-center survey of surgeons using DAX Copilot in their outpatient clinical practice, use of ambient AI scribe technology was associated with improved perceptions of documentation efficiency and timeliness. These findings suggest that ambient AI tools may improve surgeons’ perceived documentation experience in outpatient surgical care.

Introduction: Large language models (LLMs) deliver real-time, conversational guidance, yet their reliability for time-critical first aid remains unclear. Materials and methods: Five standardized vignettes (drowning, animal bite, opioid overdose, lightning strike, and frostbite) were presented three times each to GPT-4o (OpenAI, San Francisco, CA, USA) and Claude 3.5 Sonnet (Anthropic, San Francisco, CA, USA). Outputs were scored (0 = incorrect/unsafe, 1 = incomplete, 2 = entirely correct) across six domains: diagnostic accuracy, first-aid advice, triage accuracy, comprehensiveness, safety, and consistency. Scores were averaged within and across vignettes. Results: Both LLMs achieved perfect diagnostic (2.0) and triage (2.0) scores. Claude 3.5 outperformed GPT-4o in first-aid accuracy (2.0 vs 1.5), comprehensiveness (1.5 vs 1.3), and consistency (2.0 vs 1.6). Safety ratings were comparable (1.9-2.0). Key GPT-4 omissions included naloxone administration for opioid overdose and immediate sheltering guidance after a lightning strike. Conclusions: Claude 3.5 provided more complete and stable first-aid guidance than GPT-4, although both models reliably identified emergencies and advised on the appropriate escalation of care. Wider implementation warrants larger vignette sets, real-user simulations, and continuous monitoring for guideline concordance.

Prevention of surgical site infection (SSI) is a key charge for surgeons. The use of perioperative antibiotics is based on evidence. Still, other elements

The recent randomized clinical trial by Mueller et al assessing the effectiveness of polyhexanide 0.04% solution in surgical site infection (SSI) prevention fol

Background: Traumatic brain injuries (TBIs) and intra-abdominal injuries (IAIs) are 2 leading causes of traumatic death and disability in children. To avoid missed or delayed diagnoses leading to increased morbidity, computed tomography (CT) is used liberally. However, the overuse of CT leads to inefficient care and radiation-induced malignancies. Therefore, to maximize precision and minimize the overuse of CT, the Pediatric Emergency Care Applied Research Network (PECARN) previously derived clinical prediction rules for identifying children at high risk and very low risk for IAIs undergoing acute intervention and clinically important TBIs after blunt trauma in large cohorts of children who are injured. Objective: This study aimed to validate the IAI and age-based TBI clinical prediction rules for identifying children at high risk and very low risk for IAIs undergoing acute intervention and clinically important TBIs after blunt trauma. Methods: This was a prospective 6-center observational study of children aged 24 hours for TBI, or hospital admission of ≥2 nights due to a TBI on CT). Prediction rule accuracy was assessed by measuring rule classification performance, using standard point and 95% CI estimates of the operational characteristics of each prediction rule (sensitivity, specificity, positive and negative predictive values, and diagnostic likelihood ratios). Results: The project was funded in 2016, and enrollment was completed on September 1, 2021. Data analyses are expected to be completed by December 2022, and the primary study results are expected to be submitted for publication in 2023. Conclusions: This study will attempt to validate previously derived clinical prediction rules to accurately identify children at high and very low risk for clinically important IAIs and TBIs. Assuming successful validation, widespread implementation is then indicated, which will optimize the care of children who are injured by better aligning CT use with need. International Registered Report Identifier (IRRID): RR1-10.2196/43027

In this brief review, I suggest a framework for the ideal pediatric trauma program. I provide a trauma program construct devised by the American College of Surgeons. I expand on this design by offering some concepts around how trauma programs can maximize their effectiveness in care, education, and research. This review was a preamble for a minisymposium focused on pediatric hemorrhagic shock and resuscitation. Level of Evidence: IV