Examining the Role of Large Language Models in Orthopedics: Systematic Review

Journal of Medical Internet Research, Год журнала: 2024, Номер 26, С. e59607 - e59607

Опубликована: Ноя. 15, 2024

Background Large language models (LLMs) can understand natural and generate corresponding text, images, even videos based on prompts, which holds great potential in medical scenarios. Orthopedics is a significant branch of medicine, orthopedic diseases contribute to socioeconomic burden, could be alleviated by the application LLMs. Several pioneers orthopedics have conducted research LLMs across various subspecialties explore their performance addressing different issues. However, there are currently few reviews summaries these studies, systematic summary existing absent. Objective The objective this review was comprehensively summarize findings field opportunities challenges. Methods PubMed, Embase, Cochrane Library databases were searched from January 1, 2014, February 22, 2024, with limited English. terms, included variants “large model,” “generative artificial intelligence,” “ChatGPT,” “orthopaedics,” divided into 2 categories: large model orthopedics. After completing search, study selection process according inclusion exclusion criteria. quality studies assessed using revised risk-of-bias tool for randomized trials CONSORT-AI (Consolidated Standards Reporting Trials–Artificial Intelligence) guidance. Data extraction synthesis after assessment. Results A total 68 selected. involved fields clinical practice, education, research, management. Of 47 (69%) focused 12 (18%) addressed 8 (12%) related scientific 1 (1%) pertained only recruited patients, high-quality controlled trial. ChatGPT most commonly mentioned LLM tool. There considerable heterogeneity definition, measurement, evaluation LLMs’ studies. For diagnostic tasks alone, accuracy ranged 55% 93%. When performing disease classification tasks, GPT-4’s 2% 100%. With regard answering questions examinations, scores 45% 73.6% due differences test selections. Conclusions cannot replace professionals short term. as copilots approach effectively enhance work efficiency at present. More needed future, aiming identify optimal applications advance toward higher precision.

Язык: Английский

---

Ortopedi ve travmatoloji araştırmalarında yapay zekâ uygulamaları: Doğal dil işleme potansiyeli

Türk Ortopedi ve Travmatoloji Birliği Derneği, Год журнала: 2024, Номер 23(1), С. 79 - 90

Опубликована: Янв. 1, 2024

Yapay zekânın (YZ) sağlık araştırmalarına entegrasyonu, dönüştürücü bir devrime yol açmıştır.Bu yazıda gelişmiş dil işleme özelliğine sahip YZ sistemlerinin ortopedi ve travmatoloji alanında bilimsel yazım sürecine olan etkisini etik endişelerini kritik

---

What constitutes an obstructive ventilatory impairment in a pediatric population? A study design

La Tunisie Médicale, Год журнала: 2024, Номер 102(5)

Опубликована: Май 12, 2024

Introduction : There is no clear consensus as to what constitutes an obstructive ventilatory impairment (OVI) in pediatric populations. Aim To determine the percentage of children/adolescents having OVI among those addressed for spirometry after taking into account definitions advanced by some international scholarly societies [British Columbia (BC), British thoracic-society (BTS), Canadian thoracic society (CTS), European respiratory and American (ERS-ATS), global initiative asthma (GINA), Irish college general practitioners (ICGP), national council (NAC), institute clinical excellence (NICE), Société de pneumologie langue française et la société pédiatrique allergologie (SPLF-SP2A), South African (SATS)]. Methods This bi-centric cross-sectional study will involve two medical structures Sousse/Tunisia, encompass aged 6-18 years. A questionnaire be administered, anthropometric data collected, spirometric measured spirometers. The following six applied: i) GINA: Forced expiratory volume 1 second (FEV1) < 80% a FEV1/forced vital capacity (FVC) ≤ 0.90; ii) ICGP: FEV1/FVC 0.70; iii) ERS-ATS or BTS SATS SPLF-SP2A NAC: z-score -1.645; iv) NICE: 0.70 v) CTS: 0.80 vi) ERS: “FEV1 z-score” -1.645 FEV1/FVC” 0.80. Expected results ....( abstract truncated at 250 words)

Язык: Английский

---

Evaluating cognitive performance: Traditional methods vs. ChatGPT

Digital Health, Год журнала: 2024, Номер 10

Опубликована: Янв. 1, 2024

NLP models like ChatGPT promise to revolutionize text-based content delivery, particularly in medicine. Yet, doubts remain about ChatGPT's ability reliably support evaluations of cognitive performance, warranting further investigation into its accuracy and comprehensiveness this area.

Язык: Английский

---

Examining the Role of Large Language Models in Orthopedics: Systematic Review (Preprint)

Опубликована: Апрель 17, 2024

Large language models (LLMs) can understand natural and generate corresponding text, images, even videos based on prompts, which holds great potential in medical scenarios. Orthopedics is a significant branch of medicine, orthopedic diseases contribute to socioeconomic burden, could be alleviated by the application LLMs. Several pioneers orthopedics have conducted research LLMs across various subspecialties explore their performance addressing different issues. However, there are currently few reviews summaries these studies, systematic summary existing absent. The objective this review was comprehensively summarize findings field opportunities challenges. PubMed, Embase, Cochrane Library databases were searched from January 1, 2014, February 22, 2024, with limited English. terms, included variants “large model,” “generative artificial intelligence,” “ChatGPT,” “orthopaedics,” divided into 2 categories: <i>large model</i> <i>orthopedics</i>. After completing search, study selection process according inclusion exclusion criteria. quality studies assessed using revised risk-of-bias tool for randomized trials CONSORT-AI (Consolidated Standards Reporting Trials–Artificial Intelligence) guidance. Data extraction synthesis after assessment. A total 68 selected. involved fields clinical practice, education, research, management. Of 47 (69%) focused 12 (18%) addressed 8 (12%) related scientific 1 (1%) pertained only recruited patients, high-quality controlled trial. ChatGPT most commonly mentioned LLM tool. There considerable heterogeneity definition, measurement, evaluation LLMs’ studies. For diagnostic tasks alone, accuracy ranged 55% 93%. When performing disease classification tasks, GPT-4’s 2% 100%. With regard answering questions examinations, scores 45% 73.6% due differences test selections. cannot replace professionals short term. as copilots approach effectively enhance work efficiency at present. More needed future, aiming identify optimal applications advance toward higher precision.

Язык: Английский

---

Impact of Wet and Dry Cupping Therapy on Endurance, Perceived wellness, and Exertion in Recreational Male Runners

Sports Medicine and Health Science, Год журнала: 2024, Номер unknown

Опубликована: Ноя. 1, 2024

Язык: Английский

---