Recovery after extremity fracture is influenced by injury-related impairments, functional capacity, symptom severity and psychosocial well-being, emphasising the need for patient-reported outcome measures (PROMs). Despite increasing adoption of Patient-Reported Outcomes Measurement Information System (PROMIS) and legacy PROMs in orthopaedic research, substantial knowledge gaps remain regarding their measurement properties, comparability and clinical utility, particularly in fracture populations. Our aim is to develop meaningful guidance to clinicians regarding the use of PROMs in treating orthopaedic fracture patients.

A prospective cohort of 1500 patients across 14 centres presenting with isolated extremity fractures being treated operatively or non-operatively will be recruited prospectively. We will aim to recruit 300 patients for each of five fracture types: isolated hip, tibial shaft, ankle/pilon, proximal humerus and distal radius fracture. All procedures and management will be performed according to the site’s standard of care and treatment protocol. For patients treated non-operatively, the index visit (first study assessment) will be performed at the first orthopaedic treatment encounter (eg, emergency department visit or outpatient fracture clinic). Surgically treated patients will have PROMs collected anytime from the day of the surgery up to discharge from hospital for the index visit. Follow-up visits will be performed at 2–3 weeks, 6–8 weeks, 10–13 weeks, 6 months and 1 year after the index visit. At baseline, we will document injury data, demographic and sociodemographic data, and radiographic classification using the AO classification system. Patient-perceived functioning will be assessed with PROMIS Physical Function (PF), PROMIS Upper Extremity, PROMIS Global Health, Knee and Injury Osteoarthritis Outcome Score-12, Hip Disability and Osteoarthritis Outcome Score-12, Foot and Ankle Ability Measure and Quick Disabilities of the Arm, Shoulder and Hand. The following domains and PROMs will also be captured: symptoms of anxiety and depression (PROMIS Anxiety; PROMIS Depression), patient activation (Patient Activation Measures (PAM)-10) and a patient’s ability to fulfil social roles (PROMIS Social Roles).

The range and normative limits of the PROMs collected will be defined using standard descriptive statistics. We will crosswalk or validate PROMIS measures with legacy instruments for PF using an Item Response Theory (IRT)-based linking model and compare it to non-IRT models (such as equipercentile linking). Lastly, we will assess the PROM-based recovery trajectory after fracture, overall and after adjusting for relevant demographic, clinical or biopsychosocial factors.

Ethics approval for this study was granted from the local Ethics Committees or Institutional Review Board at each of the participating sites prior to patient enrolment. Austin: Institutional Review Board University of Texas at Austin, STUDY00000262; Boston: Mass General Brigham, 2019P000397; Los Angeles: Cedars-Sinai, Office of Research Compliance and Quality Improvement, STUDY00000081; Miami: University of Miami Human Subject Research Office, 20221353; Bogotá: Comité Corporativo de Ética en Investigación, CCEI-15607-2023; Berlin: GoFitFast: under Homburg approval; Recovery/Linking: Ethikkommission Charité Universitätsmedizin Berlin, EA2/026/21; Homburg: GoFitFast: Ethikkommission der Ärztekammer des Saarlandes, 232/19; Recovery/Linking: under Charité approval; Murnau: under umbrella from Homburg and Charité, GoFitFast: under Homburg approval, Recovery/Linking: under Charité approval; Tübingen: GoFitFast: Ethik-Kommission, Universitätsklinikum Tübingen, 393/2022BO2; Freiburg: Ethik-Kommission Albert-Ludwigs-Universität Freiburg, 21–1401; Rostock: Ethikkommission an der Universitätsmedizin Rostock, A 2024–0113; Innsbruck: Ethikkommission der Medizinischen Universität Innsbruck, 1258/2021; Oxford: HRA and Health and Care Research Wales, 20/EE/0051; London: HRA and Health and Care Research Wales, 20/EE/0051; Groningen: Medical Ethics Review Board University Medical Center Groningen, METc 2023/187 16882; Non-WMO waiver; Zwolle: Medical Ethics Review Board University Medical Center Groningen, METc 2023/187 16882; Non-WMO waiver. The results of this study will be published in peer-reviewed journals and presented at different conferences.

NCT04113044

To compare the quality and time efficiency of physician-written summaries with customised large language model (LLM)-generated medical summaries integrated into the electronic health record (EHR) in a non-English clinical environment.

Cross-sectional non-inferiority validation study.

Tertiary academic hospital.

52 physicians from 8 specialties at a large Dutch academic hospital participated, either in writing summaries (n=42) or evaluating them (n=10).

Physician writers wrote summaries of 50 patient records. LLM-generated summaries were created for the same records using an EHR-integrated LLM. An independent, blinded panel of physician evaluators compared physician-written summaries to LLM-generated summaries.

Primary outcome measures were completeness, correctness and conciseness (on a 5-point Likert scale). Secondary outcomes were preference and trust, and time to generate either the physician-written or LLM-generated summary.

The completeness and correctness of LLM-generated summaries did not differ significantly from physician-written summaries. However, LLM summaries were less concise (3.0 vs 3.5, p=0.001). Overall evaluation scores were similar (3.4 vs 3.3, p=0.373), with 57% of evaluators preferring LLM-generated summaries. Trust in both summary types was comparable, and interobserver variability showed excellent reliability (intraclass correlation coefficient 0.975). Physicians took an average of 7 min per summary, while LLMs completed the same task in just 15.7 s.

LLM-generated summaries are comparable to physician-written summaries in completeness and correctness, although slightly less concise. With a clear time-saving benefit, LLMs could help reduce clinicians’ administrative burden without compromising summary quality.