52426 research outputs found
Sort by
Assessing the Accuracy of Artificial Intelligence-Generated Clinical Summaries From Ambulatory Glaucoma Subspecialty Clinical Encounters.
No full textPURPOSE: The purpose of this study was to evaluate the accuracy of large language model (LLM) LLaMA 2-70B in summarizing glaucoma clinic notes into patient-friendly language and generating educational material.
METHODS: A random sample of 147 clinic notes from unique patients who visited Glaucoma Service at a tertiary center was analyzed. LLaMA 2 generated paragraph and bullet-point summaries in five subjects: (1) glaucoma diagnosis and type, (2) disease progression, (3) treatment plan, (4) treatment changes, and (5) surgical/laser interventions. Two ophthalmologists reviewed responses for accuracy and categorized them as correct, partially correct, or incorrect. Discrepancies were adjudicated by a glaucoma specialist. A comparison using identical prompts was performed on a subset (n = 50) with ChatGPT-4.
RESULTS: LLaMA 2 correctly summarized 97 notes (66%) in paragraph and 103 (70%) in bullet format. Another 44 (30%) and 41 (28%) were partially correct, respectively. Paragraph summaries were more accurate and complete for glaucoma suspects than diagnosed patients (82% vs. 53%, P \u3c 0.001). For targeted clinical questions, LLaMA 2 accurately identified glaucoma diagnosis in 118 notes (80%), disease stability/progression in 129 (88%), treatment plans in 127 (87%), treatment changes in 134 (91%), and surgical/laser interventions in 124 (84%). ChatGPT-4 achieved 46% correct paragraph summaries, 50% correct bullet summaries, and accuracies of 96%, 88%, 64%, 78%, and 82%, respectively, for targeted questions.
CONCLUSIONS: Although LLaMA 2 is not yet reliable as a standalone clinical tool, it shows promise to improve clinical communication.
TRANSLATION RELEVANCE: LLMs may enhance patient experience and health literacy by standardizing patient-friendly language in clinical care
Implementation of a Color-Coded Hall Pass System to Aid in the Reduction of Specimen Transportation Errors
No full textEditorial. Introducing the VPS Reporting Guideline as a framework to improve evidence in hydrocephalus care.
No full textDelay in hip reductions due to the advent of rapid CT scans in the trauma setting.
No full textINTRODUCTION: With increasing reliance on computed tomography (CT) in trauma care, the use of anteroposterior (AP) pelvis radiographs has declined. This study examined whether omitting an initial AP pelvis film affected time to hip reduction and the need for additional CT imaging in patients with traumatic hip dislocations.
METHODS: We conducted a retrospective review at a Level I trauma center (2005-2016). Eligible patients were adults (\u3e 17 years) with native hip dislocations evaluated under the Advanced Trauma Life Support (ATLS) protocol. Patients with incomplete records or irreducible hips requiring operative reduction were excluded. Data collected included patient demographics, AP pelvis use, CT imaging, time to reduction, and presence of acetabular or proximal femur fractures.
RESULTS: The study cohort consisted of 50 patients, 76% male (n = 38), with a mean age of 33 years (range, 18-68). High-energy motor vehicle accident or motorcycle crash accounted for 90% (n = 45) of injuries, and 94% (n = 47) were posterior dislocations. Associated fractures were present in 76% (n = 38). Patients were divided into those who had no AP pelvis radiograph prior to CT scan (N-APP group, n = 8; 16%) and those who obtained an initial AP pelvis radiograph on presentation (APP group, n = 42; 84%). All patients in the N-APP group received an additional CT pelvis scan, while none in the APP group did. Average time to reduction was significantly shorter in the APP group compared with the N-APP group (69 vs. 216 min, p \u3c 0.05).
CONCLUSIONS: Obtaining an initial AP pelvis radiograph provided a rapid and reliable means of diagnosing hip dislocations. Adherence to ATLS guidelines by performing a pelvic film before CT shortened time to reduction and prevented unnecessary repeat CT imaging in adult patients with traumatic native hip dislocations
Abstract DP395: A Diagnostic Dilemma: A Case of Amyloid Beta-Related Angiitis Mimicking Posterior Reversible Encephalopathy Syndrome
No full text
