Clinical documentation is essential for safe and effective patient care but places a substantial clerical burden on doctors, particularly those early in training. Ambient artificial intelligence (AI) systems, which passively capture clinical conversations and generate structured notes, have demonstrated promise in outpatient and primary care settings. However, their use in inpatient ward rounds remains largely unexplored. Semi-structured interviews were conducted with ten postgraduate year one doctors following participation in simulated orthopaedic ward rounds incorporating an ambient AI scribe (Heidi Health, Melbourne, Australia). The topic guide was informed by Normalisation Process Theory (NPT) to explore participants' understanding of AI-assisted documentation workflows, the work they anticipated would be required at individual, team, and system levels for implementation, and their appraisal of the potential benefits, risks, and practical challenges of future use. Data were analysed collaboratively by two researchers using reflexive thematic analysis with a hybrid inductive-deductive approach. Seven themes were identified and mapped across the four NPT constructs. Coherence was reflected in participants' understanding of ambient AI as a way to reduce documentation burden, support patient-centred records, and improve accessibility. Cognitive participation was evident in their recognition that implementation would require individual engagement, including review and approval of AI-generated outputs. Collective action captured the practical work required to adapt ward round behaviours, redistribute documentation tasks, manage consent, and address infrastructure, access, and governance requirements. Reflexive monitoring was demonstrated through participants' appraisal of anticipated benefits, including potential for improved clinical engagement, multidisciplinary communication, and real-time capture of complex conversations, balanced against risks of clinical misrepresentation, cultural resistance, and privacy concerns. Through simulated exposure, participants made sense of ambient AI scribes as a potentially valuable addition to inpatient documentation workflows, anticipating effects on efficiency, communication, and patient-centred documentation. However, they also identified individual, team, and organisational work required for implementation, including workflow adaptation, consent processes, data privacy, access controls, infrastructure, and real-world appraisal in clinical settings.

Artificial Intelligence (AI) driven documentation systems are positioned to enhance documentation efficiency and reduce documentation burden in the healthcare setting. The administrative burden associated with clinical documentation has been identified as a major contributor to health care professional (HCP) burnout. The current systematic review aims to evaluate the efficiency, quality, and stakeholder opinion regarding the use of AI-driven documentation systems. Using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines a comprehensive search was conducted across PubMed, Embase and Cochrane library. Two independent reviewers applied inclusion and exclusion criteria to identify eligible studies. Details of AI technology, document type, document quality and stakeholder experience were extracted. The review included 11 studies. All included studies utilised Chat generated pretrained transformer (Chat GPT, Open AI, CA, USA) or an ambient AI technology. Both forms of AI demonstrated significant potential to improve documentation efficiency. Despite efficiency gains, the quality of AI-generated documentation varied across studies. The heterogeneity of methods utilised to assess document quality influenced interpretation of results. HCP opinion was generally positive, users highlighted ease of use and reduced task load as primary benefits. However, HCPs also expressed concerns about the reliability and validity of AI-generated documentation. Chat GPT and ambient AI show promise in enhancing the efficiency and quality of clinical documentation. While the efficiency benefits are clear, the challenges associated with accuracy and consistency need to be addressed. HCP experiences indicate a cautious optimism towards AI integration, however reliability will depend on continued refinement and validation of the technology.

OBJECTIVES:We conduct a systematic review and meta-analysis of the published literature regarding the impact of performing lumbar decompression for cauda equina syndrome (CES) out of hours compared to regular operating hours. METHODS:A search of databases including Medline, EMBASE and Cochrane Library was performed with two independent reviewers per the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. A senior author arbitrated in event of disagreement. MeSH terms [((cauda equina) OR (CES)) AND ((hours) OR OOH)] were used. Filters including date range (from January 01, 1990 to November 01, 2022) and the English language were applied. Inclusion criteria consisted of retrospective or prospective cohort studies, English or full translation available, surgical complication as primary or secondary outcome and out of hours surgery as an independent variable. Case reports and studies without complication frequency were excluded. There were no additional studies identified through a snowballing secondary search through references of identified articles. Operative metrics were compiled into ad-hoc tables. Statistical analysis was performed using RevMan 5.4. A difference in complication rates with a P value of < .05 was deemed statistically significant. Heterogeneity was reported using I2. Study quality was assessed using the Newcastle Ottawa Score (NOS). RESULTS:The search strategy yielded 363 articles. After duplicate removal and application of inclusion/exclusion criteria, 15 studies were sought for retrieval and full text review. Of these, 5 studies were included for qualitative synthesis. Of these, 4 studies underwent quantitative analysis with 581 datasets. Meta-analysis was undertaken on 3 studies comprising 495 datasets. A dichotomous outcome was modelled using the Mantel-Haenszel statistical method with fixed effect which demonstrated an odds ratio (OR) of 2.38 (95 % CI 1.39-4.07) for sustaining an adverse event from out of hours surgery compared to routine operative hours. I2 = 12 %, suggesting homogeneity between studies analysed. CONCLUSIONS:This study provides clinical evidence that out of hours surgery for lumbar decompression for CES is associated with a higher rate of surgical complications. The spinal surgeon should appropriately counsel the patient with CES that while it is important to do the surgery as soon as possible, operating out of hours carries a higher risk of surgical complications.

Generative artificial intelligence (AI) models are increasingly used to create patient education materials (PEM), offering on-demand health information. These tools hold the potential to democratise access to medical information, but concerns remain regarding the quality, readability, and reliability of AI-generated PEM. Spinal fusion surgery, a complex procedure, necessitates clear, accurate educational materials to support informed decision-making. Despite their promise, the capacity of AI models to meet health literacy needs remains underexplored. This study aimed to evaluate and compare the readability and quality of PEM on spinal fusion surgery sourced from institution and society websites and those generated by three AI models (ChatGPT, Gemini, and Co-Pilot). Patient information on spinal fusion surgery was sourced from the British Association of Spinal Surgeons (BASS), American Academy of Orthopaedic Surgeons (AAOS), Cleveland Clinic, Mayo Clinic, and John Hopkins websites, and generated by AI models (Chat GPT, Co-Pilot Gemini) using a standard prompt on 15/12/24. Patient Education Materials Assessment Tool (PEMAT), JAMA benchmark criteria, and the DISCERN tool assessed quality. Readability was evaluated with the Flesch-Kincaid Grade Level (FKGL), Reading Ease (FKRE), and Gunning Fog Index (GFI). Mean quality and readability outcome measures of AI generated and institution or society sourced PEM were compared. Post Bonferroni correction, statistical significance was set at P < .0125 for quality and follow-up prompting assessments, and P < .0167 for readability assessments. Society and institution sourced PEM outperformed AI-generated content in readability and quality. Website-sourced materials scored significantly higher PEMAT (77.1

SPECT/CT combines scintigraphy with a CT scan forming a 3-dimensional reconstruction of bone-tracer uptake patterns. It has become a fundamental component of the work-up of a painful total knee arthroplasty (TKA). The addition of an arthrogram is purported to improve its diagnostic yield. The aim of this study was to assess whether the addition of a concurrent arthrogram to a SPECT/CT enhances its sensitivity and specificity for diagnosing aseptic loosening in a painful total knee replacement. Methods: PubMed, Embase, and Scopus were searched in accordance with Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Included studies compared the results of SPECT/CT with or without an arthrogram against an appropriate reference standard for diagnosing TKA aseptic loosening. The quality of included studies was independently assessed using the QUADAS-2 tool. Results: In total, 160 abstracts were identified by our search strategy. Of these, 6 studies comprising 472 patients met our inclusion criteria. All included studies used operative findings or a period of clinical and radiologic observation as reference standards. The SPECT/CT arthrogram was more sensitive in identifying aseptic loosening of knee prostheses, and it also provided greater specificity for excluding its diagnosis. Conclusion: The amalgamated results of included studies of the use of SPECT/CT demonstrate it is the best test in helping determine aseptic loosening in patients with painful TKAs (specificity, 97% vs. 85%). It is also a more sensitive test (sensitivity, 78% vs. 75%). Considering the potential morbidity of injection of contrast into the prosthetic joint, addition of an arthrogram to SPECT/CT is not beneficial and is potentially harmful.

Fractures of the distal radius and of the ankle are two of the most common injuries requiring fixation in orthopaedic trauma services. Guidelines recommend post-operative follow up for these injuries at two-week and six-weeks after surgery. To assess the frequency and utility of orthopaedic OPD attendances for surgically-managed distal radius and ankle fractures in an Irish Trauma Unit. Weidentified distal radius and ankle fractures needing surgery over 18 months using our electronic health records. To understand outpatient attendance reasons, we reviewed outpatient letters via the Integrated Patient Management System. From September 2022 to March 2024, 463 distal radius and ankle operative cases were included; 248 distal radius and 215 ankle fracture. 227 distal radius patients (92

BACKGROUND:Artificial intelligence (AI) and machine-learning (ML) technologies are increasingly being incorporated into orthopaedic medical devices, offering the potential to enhance surgical planning, intraoperative precision, and personalized care. The incorporation of AI into medical devices introduces unique risks and challenges that traditional regulatory pathways in the United States and European Union (EU) were not designed to address. Although the EU Artificial Intelligence Act is currently being implemented to provide a specific framework for AI medical device assessment, no equivalent directive exists in the United States. QUESTIONS/PURPOSES:In consideration of these evolving regulatory contexts, this study sought to address the following questions related to FDA-approved, AI/ML-enabled orthopaedic devices: (1) How often are FDA-approved, AI/ML-enabled orthopaedic devices also approved under the EU Medical Device Regulation (MDR)? (2) How often are AI/ML-enabled orthopaedic devices approved through the FDA 510(k) pathway using non-AI predicate devices? (3) How often do approved AI/ML-enabled orthopaedic devices have independent, peer-reviewed evidence supporting their use? (4) How often are the details of the training and validation datasets of these devices disclosed in publicly available regulatory documents? METHODS:A total of 37 AI/ML-enabled orthopaedic device approvals were identified from the FDA's list of 1017 AI/ML-enabled medical devices as of May 2025. Regulatory documents were analyzed to identify training and validation data sets and predicate devices. A predicate device is an existing legally marketed device that the FDA has previously approved; a manufacturer may claim that a new device is "substantially equivalent" to this approved device to obtain clearance through the 510(k) pathway. The availability of devices in the EU was assessed through the publicly available European Database on Medical Devices (EUDAMED) database and manufacturer websites. A systematic review of PubMed and manufacturer websites identified peer-reviewed evidence for each device. RESULTS:Our results showed that 38% (14 of 37) of AI/ML-enabled orthopaedic devices were approved for use in the EU, and devices were more frequently available in the United States first. All AI/ML-enabled orthopaedic devices approved by the FDA received regulatory clearance through the 510(k) pathway; most devices (62% [23 of 37]) were approved based on substantial equivalence to non-AI enabled devices. Independent peer-reviewed evidence was identified for 30% (11 of 37) of devices, with 67% (34 of 51) of published studies reporting manufacturer involvement. Information on training and validation datasets was disclosed in 57% (21 of 37) of 510(k) summaries, with dataset sizes ranging from 21 to 150,000 for training and 20 to 29,991 for validation. CONCLUSION:AI/ML-enabled orthopaedic devices have entered the market under existing regulatory frameworks in the United States and, at a slower pace, in the EU. Reliance on non-AI comparators and limited postmarket evaluation raises concerns regarding their long-term clinical reliability. CLINICAL RELEVANCE:As the level of patient risk under the current regulatory pathways remains uncertain, future research should compare AI/ML-enabled device recall rates across jurisdictions to assess whether AI-specific regulatory frameworks improve patient safety and device reliability.

BACKGROUND:Clinical documentation is essential for safe and effective patient care but places a considerable clerical burden on clinicians. Ambient artificial intelligence (AI) systems, which capture clinical conversations and generate structured notes in real time, have shown promise in primary and outpatient care but remain underexplored in the inpatient setting. This study examined the impact of an ambient AI scribe on documentation timing, quality, and workload in a simulated orthopaedic inpatient setting. METHODS:Seven postgraduate year one junior doctors participated in simulated orthopaedic ward rounds incorporating an ambient AI scribe (Heidi Health, Melbourne, Australia). A total of 150 clinical documents were generated: 120 progress notes (60 manual, written retrospectively, and 60 produced in real time using ambient AI) and 30 discharge summaries (15 manual and 15 AI-generated). Documentation time was recorded, and quality was assessed using the Physician Documentation Quality Instrument-9 (PDQI-9) for each clinical document. Workload was evaluated using the NASA-TLX instrument. RESULTS:Ambient AI significantly reduced documentation time for both progress notes (median 27s vs. 128s; P < .0001) and discharge summaries (median 114s vs. 459s; P < .0001). Time savings persisted across all complexity levels. AI-generated progress notes achieved higher overall PDQI-9 scores than manual notes (median 43.5 vs. 41; P = .002), with significant gains in thoroughness, currency, and usefulness, without compromising accuracy. Similarly, AI-generated discharge summaries scored higher (median 40 vs. 33; P < .0001), with improvements in comprehensibility, organisation, internal consistency, and synthesis. Junior doctors reported reduced workload across all NASA-TLX domains, with the largest improvements in frustration (-79 %) and effort (-81 %). CONCLUSION:In simulated orthopaedic ward rounds, ambient AI substantially reduced documentation time, improved document quality, and alleviated workload for junior doctors.

Background: Visual pedagogy is an intrinsic component of surgical education and training. Conventional surgical training dictated intraoperative experiential learning was required to familiarise trainees with procedural steps. Recognition of the value of online videos to reinforce remote learning is now well documented. However, issues remain. Variations in surgeon preference exist such that non-specific videos may have limited utility to trainees rotating through units, with live videos also often limited due to the nature of the procedure. The aim of this study was to coordinate an animated video-based library of procedural approaches and techniques carried out by consultants within a hospital group available to rotating non-consultant hospital doctors (NCHDs) to optimise surgical preparation. Methods: Identification of key procedures for NCHDs transitioning between units in a hospital group was carried out. Consensus on high-yield procedures through stages of surgical training was achieved, with procedural approaches within specialties impacting NCHDS outlined for incorporation into the library. Results: Steps of a procedural approach preferred by the senior author were broken for animated reconstruction, with detailed instructions on instrument angles, key anatomy to be visualised, to optimise focus within each procedural step. Following completion of this, consultant specific step-related discussion was provided over the video to enhance the viewer experience and help garner an understanding on techniques used for NCHDs preparing for surgery. Conclusions: Consultant specific-procedural animated videos made available NCHDs rotating through surgical units can enhance surgical preparation and optimise learning outcomes. Opportunities for the development of technical skills in this manner should also be considered.

Study design: Retrospective Observational Study. Introduction: Lumbar radicular pain has a prevalence of 3-5%. Level 1 evidence has demonstrated equivalence between surgical and injection treatment. We assess the outcomes from a transforaminal epidural steroid injection clinic in a tertiary neuroscience referral centre. Methods: We performed an analysis of data from consecutive patients entered into a new internal referral database between August 2018 to May 2021. Radicular pain was classified as one of "first presentation" or "recurrence". Outcomes were obtained from follow up clinic letters and recorded in a binary manner of "positive result" or "negative result". Spinal pathology was documented from radiology reports and MRI images. Results: We analysed 208 patients referred to the clinic. Excluding those who improved to a point of not requiring treatment, and those who underwent surgical intervention, 119 patients undergoing injection were included, of which 14 were lost to follow-up. 68 % of patients had a positive result from injection. Subgroup analysis demonstrated good outcomes for both hyperacute (<6 weeks) and chronic (>12 months). Contained disk pathologies had better outcomes than uncontained. There was no difference in outcomes across grades of compression, but previous same level surgery was associated with poorer response rates. Conclusions: There is a high rate of natural resolution of symptoms in patients with LSRP. In those where pain persists, TFESI is a valuable first line treatment modality. This study suggests the efficacy of TFESI is potentially independent of grade of stenosis and chronicity of symptoms. Contained disc pathologies respond better than uncontained. (c) 2023 Royal College of Surgeons of Edinburgh (Scottish charity number SC005317) and Royal College of Surgeons in Ireland. Published by Elsevier Ltd. All rights reserved.

OBJECTIVES: Despite efforts to mitigate challenges to advance underrepresented groups (URG) groups' representation in medical education, diversity remains underwhelming. In response to this several mentoring programs to increase diversification within medical education have been implemented. However, the impact of these programs on URG representation across disciplines is unknown. The aim of this review is to evaluate the impact of structured mentoring programs on URGs in undergraduate medical education. DESIGN: Systematic review. METHODS: A comprehensive search strategy was performed of electronic databases including PubMed, Ovid Medline, and EMBASE between January and September 2022 in accordance with Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Both qualitative and quantitative outcomes including characteristics of the mentoring structure explored within each study were collected, and differences in study outcomes analyzed. RESULTS: In total 17 studies were included for analysis. Mentoring within URGs resulted in an increase in research opportunities, exam performance, medical specialty applications, and residency matching. Structured feedback yielded positive experiences by both mentors and mentees participating in programs, with both emotional and cultural competence issues explored across studies included for analysis. CONCLUSIONS: Mentoring for medical students underrepresented in medicine across mentoring relationships including peer, senior, formal, and informal structures yield positive outcomes within research, academic modules, and career pathways. Future applications of mentoring programs should consider the use of tandem mentoring from both senior and peer mentors to optimize benefits URG students derive from each mentoring relationship. (J Surg Ed 81:353-366. (c) 2023 Association of Program Directors in Surgery. Published by Elsevier Inc. All rights reserved.)

Abstract Aim The aim of this review is to evaluate the impact of structured mentoring programs on underrepresented minorities in undergraduate medical education. Method A comprehensive search strategy was performed of electronic databases including PubMed, Ovid Medline, and EMBASE between January- September 2022 in accordance with PRISMA guidelines. Both qualitative and quantitative outcomes including characteristics of the mentoring structure explored within each study were collected, and differences in study outcomes analysed. Results In total 17 studies were included for analysis. Mentoring within underrepresented minorities resulted in an increase in research opportunities, exam performance, medical specialty applications and residency matching. Structured feedback yielded positive experiences by both mentors and mentees participating in programs, with both emotional and cultural competence issues explored across studies included for analysis. Conclusions Mentoring for medical students underrepresented in medicine across mentoring relationships including peer, senior, formal, and informal structures yield positive outcomes within research, academic modules, and career pathways. Future applications of mentoring programs should consider the use of tandem mentoring from both senior and peer mentors to optimise benefits URM students derive from each mentoring relationship.

Background: Surgeons have been reported to practice performance-based medicine. Comparisons between surgery and surgeons to elite sports and athletes have often been made in recognition of similarities in the performance science entrenched across these professions. The incorporation of practices between careers has been noted; the use of preparatory mental techniques prior to performance is well recognised in the literature. The use of simulation as a tool to hone mental focus, and dexterity in surgery has been limited to minimally invasive and laparoscopic procedures to date. The aim of this study was to evaluate the impact of a surgical warm-up using a virtual reality simulator on operative performance. Methods: A single-blinded cross-over randomised control trial in a single tertiary Orthopaedic training centre was carried out. Orthopaedic trainees were recruited, and each morning participants rostered to theatre were randomised to either undergo a simulated surgical procedure on a virtual reality simulation system prior to their first case as primary operator (priming arm), or to perform their usual preparatory routine for surgery (control arm). Results: Over three study periods a total of 151 datapoints were collected, with 49 matched datapoints across priming status and procedural level of difficulty. Subjective assessment tools consistently demonstrated improved operative performance by participants following surgical priming (P=0.001). Conclusions: This study highlights that introduction of preoperative priming to improve operative preparation, and optimizes operative performance. This has not only implications for improved resident training, but also signals towards beneficial downstream effects on patient outcomes, and theatre list planning.

IntroductionThere has been widespread international implementation of duration-hour restrictions to prevent surgical resident burnout and promote patient safety and wellbeing of doctors. A variety of Extended-Duration Work Shifts (EDWS) have been implemented, with a variety of studies examining the effect of shift systems on both surgical performance and the stress response unestablished in the literature.MethodsThis was a systematic review evaluating the impact of extended working hours on surgical performance, cognitive impairment, and physiological stress responses. The review used PubMed, Ovid Medline, Embase, and Google Scholar search engines between September and October 2021 in accordance with Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Filters including studies carried out after 2002 and published in the English language were applied.ResultsIn total, 30 studies were included for analysis. General surgery was the most commonly studied rotation, with Neurosurgical, Orthopedic, and ear, nose and throat specialties also included. The majority of studies found no difference or a significant improvement in post-EDWS on simulated performance. EDWS appeared to have the greatest impact on physiological stress markers in junior surgical trainees.ConclusionsExperience appears to confer a protective element in the postcall period, with preservation of skill demonstrated. More experienced clinicians yielded lower levels of physiological markers of stress, although variability in hierarchical workload should be considered. Heterogeneity of findings across physiological, cognitive, and psychomotor assessments highlights the need for robust research on the optimum shift pattern prevents worker burnout and promotes patient safety. Future research to evaluate correlation between stress, on-call workload, and performance in the postcall period is warranted.

BackgroundPreoperative warm-up regimens are increasingly utilised in the surgical field, however no consensus on benefits of priming across surgical experience has been realised. The aim of this study was to evaluate the impact of simulation preoperative priming on operative performance across levels of resident experience.MethodsA single-blinded randomised control trial was carried out in a regional surgical training centre. Volunteers were randomised to undergo simulated surgical warm-up procedure prior to their first case as primary operator or proceed directly to surgery.ResultsPerformances of 147 operative procedures were collected over an 18 month period, experience ranging from PGY2-PGY 7. Senior participants consistently outperformed junior residents in unprimed operative cases (p = 0.005). In primed operative performances no significant difference in aggregate performance scores was found (p = 0.07).ConclusionPriming confers a greater advantage to junior residents with particular regard to generic surgical skills. Senior residents demonstrate improved self-efficacy scores measured following priming.

•Use of non-absorbable sutures in Achilles Tendon rupture repair is associated with higher rates of postoperative infections.•Neither braided or monofilament sutures were associated with higher rates of infections post TA rupture repair.•Type of suture material was not associated with re-rupture rates following Achilles tendon rupture repair.

The aim of this study was to identify if experience in arthroscopy confers ambidexterity to the operator and the role of baseline characteristics in arthroscopic simulator performance. A prospective comparative study was carried out across four regional Orthopaedic training centres. Participants were divided into novice, intermediate or experienced groups based on arthroscopic experience. Baseline demographics including age, sex, handedness, and gaming history were also collected. Following familiarisation with the procedure, participants were asked to complete a simulated task requiring bimanual control consisting of visualisation with camera control and manipulation of highlighted objects using a grasping instrument. One attempt using camera control and grasping accuracy per hand was performed by each participant, with scores for each hand collected for analysis. Performance scores for camera alignment, camera path length, grasper path length and grasping efficiency were collected. Time taken to completion was also noted for each attempt. Fifty-six participants were recruited to the study. A significant difference in grasping efficiency between groups in the dominant hand was demonstrated (p = 0.013). Novices demonstrated laterality with superior performance in grasping efficiency in the dominant hand (p = 0.001). No significant difference was noted between dominant and non-dominant hand performance in the experienced group. Arthroscopic simulation-based training is a valuable learning tool for orthopaedic training. This study demonstrated that experienced orthopaedic surgeons have a greater degree of ambidexterity than intermediate or novice groups, hypothesised by authors to be conferred through conventional orthopaedic training. Dedicated bimanual control tasks to reduce laterality in trainees should be incorporated in simulated surgical curricula. III.

BACKGROUND:Preoperative warm-up in preparation for surgery is a technique used in recognition of similarities between surgeons and performance based professionals. The aim of this review was to evaluate the use of simulation-based preoperative warm-up on surgical performance in the operating room and its impact on both clinical and patient outcomes.MATERIALS AND METHODS:A systematic review of the literature was carried out in accordance with PRISMA guidelines between August-September 2021. In total 15 studies were retrieved.RESULTS:Seven studies across general surgery, urology, and vascular surgery used a procedure specific warm-up, with significant improvement in operative performance, rate of errors, radiological and patient-based outcomes. Variables including level of experience and specialty appeared to have no impact on the merits of preoperative warm-up demonstrated.CONCLUSIONS:While heterogeneity in the benefit of generic warm-up procedures was noted, procedure specific warm-up methods consistently resulted in significantly better operative outcomes.