AI-ChatGPT/GPT-4: An Booster for the Development of Physical Medicine and Rehabilitation in the New Era!

Annals of Biomedical Engineering, Год журнала: 2023, Номер 52(3), С. 462 - 466

Опубликована: Июль 27, 2023

Abstract Artificial intelligence (AI) has been driving the continuous development of Physical Medicine and Rehabilitation (PM&R) fields. The latest release ChatGPT/GPT-4 shown us that AI can potentially transform healthcare industry. In this study, we propose various ways in which display its talents field PM&R future. is an essential tool for Physiatrists new era.

Язык: Английский

---

Image Analysis through the lens of ChatGPT-4

Journal of Applied Artificial Intelligence, Год журнала: 2023, Номер 4(2), С. 31 - 46

Опубликована: Дек. 28, 2023

Numerous studies have delved into the applications of ChatGPT across various domains such as medicine, sports, education, and business analysis. emerges a potential replacement for key contributors in these diverse fields, sparking an ongoing quest to validate this assertion. One focal point paper is examination GPT-4's, fourth generation Chat GPT, capacity handle spectrum visual elements like images, pictures, flowcharts, plots, diagrams. The inquiry extends assessing how gleaned information from visuals compares with human intuition, both inductive deductive. To investigate, GPT-4 was presented samples faces, diagrams, leading remarkably accurate error-free results within specified timeframe, surpassing capabilities. outcomes underscore GPT-4's impressive prowess image analysis, covering identification, recognition, contextual understanding content. Furthermore, proficiency identifying objects individual images opens door be utilized comprehensively field object detection. However, exhibits limitations recognizing due privacy considerations.

Язык: Английский

---

Application of ChatGPT for Orthopedic Surgeries and Patient Care

Clinics in Orthopedic Surgery, Год журнала: 2024, Номер 16(3), С. 347 - 347

Опубликована: Янв. 1, 2024

Artificial intelligence (AI) has rapidly transformed various aspects of life, and the launch chatbot "ChatGPT" by OpenAI in November 2022 garnered significant attention user appreciation. ChatGPT utilizes natural language processing based on a "generative pre-trained transfer" (GPT) model, specifically transformer architecture, to generate human-like responses wide range questions topics. Equipped with approximately 57 billion words 175 parameters from online data, potential applications medicine orthopedics. One its key strengths is personalized, easy-to-understand, adaptive response, which allows it learn continuously through interaction. This article discusses how AI, especially ChatGPT, presents numerous opportunities orthopedics, ranging preoperative planning surgical techniques patient education medical support. Although ChatGPT's user-friendly capabilities are laudable, limitations, including biased ethical concerns, necessitate cautious responsible use. Surgeons healthcare providers should leverage while recognizing current limitations verifying critical information independent research expert opinions. As AI technology continues evolve, may become valuable tool orthopedic care, leading improved outcomes efficiency delivery. The integration into orthopedics offers substantial benefits but requires careful consideration continuous improvement.

Язык: Английский

---

Diagnostic Applications of AI in Sports: A Comprehensive Review of Injury Risk Prediction Methods

Diagnostics, Год журнала: 2024, Номер 14(22), С. 2516 - 2516

Опубликована: Ноя. 10, 2024

This review provides a comprehensive analysis of the transformative role artificial intelligence (AI) in predicting and preventing sports injuries across various disciplines. By exploring application machine learning (ML) deep (DL) techniques, such as random forests (RFs), convolutional neural networks (CNNs), (ANNs), this highlights AI's ability to analyze complex datasets, detect patterns, generate predictive insights that enhance injury prevention strategies. AI models improve accuracy reliability risk assessments by tailoring strategies individual athlete profiles processing real-time data. A literature was conducted through searches PubMed, Google Scholar, Science Direct, Web Science, focusing on studies from 2014 2024 using keywords 'artificial intelligence', 'machine learning', 'sports injury', 'risk prediction'. While power supports both team sports, its effectiveness varies based unique data requirements risks each, with presenting additional complexity integration tracking multiple players. also addresses critical issues quality, ethical concerns, privacy, need for transparency applications. shifting focus reactive proactive management, technologies contribute enhanced safety, optimized performance, reduced human error medical decisions. As continues evolve, potential revolutionize prediction promises further advancements health performance while addressing current challenges.

Язык: Английский

---

Human-Written vs AI-Generated Texts in Orthopaedic Academic Literature, a Comparative Qualitative Analysis (Preprint)

JMIR Formative Research, Год журнала: 2023, Номер 8, С. e52164 - e52164

Опубликована: Дек. 13, 2023

Background As large language models (LLMs) are becoming increasingly integrated into different aspects of health care, questions about the implications for medical academic literature have begun to emerge. Key such as authenticity in writing at stake with artificial intelligence (AI) generating highly linguistically accurate and grammatically sound texts. Objective The objective this study is compare human-written AI-generated scientific orthopedics sports medicine. Methods Five original abstracts were selected from PubMed database. These subsequently rewritten assistance 2 LLMs degrees proficiency. Subsequently, researchers varying expertise areas specialization asked rank according linguistic methodological parameters. Finally, had classify articles AI generated or human written. Results Neither nor AI-detection software could successfully identify Furthermore, criteria previously suggested did not correlate whether deemed a text be they judged article correctly based on these Conclusions primary finding was that unable distinguish between LLM-generated However, due small sample size, it possible generalize results study. case any tool used research, potential cause harm can mitigated by relying transparency integrity researchers. With stake, further research similar design should conducted determine magnitude issue.

Язык: Английский

---

The application of artificial intelligence-based tools in the management of hepatocellular carcinoma: current status and future perspectives

Hepatoma Research, Год журнала: 2025, Номер unknown

Опубликована: Янв. 9, 2025

Artificial intelligence (AI) is rapidly advancing in hepatocellular carcinoma (HCC) management, offering promising applications across diagnosis, prognosis, and treatment. In histopathology, deep learning models have shown impressive accuracy differentiating liver lesions extracting prognostic information from tissue samples. For biomarker discovery, AI techniques applied to multi-omics data identified novel signatures predictors of immunotherapy response. radiology, convolutional neural networks demonstrated high performance classifying hepatic lesions, grading tumors, predicting microvascular invasion computed tomography (CT) magnetic resonance imaging (MRI) images. Multimodal integrating genomics, clinical are emerging as powerful tools for risk stratification. Large language (LLMs) show potential support decision making patient education, though concerns about remain. While holds immense promise, several challenges must be addressed, including algorithmic bias, privacy, regulatory compliance. The successful implementation HCC care will require ongoing collaboration between clinicians, scientists, ethicists. As technologies continue evolve, they expected enable more personalized approaches potentially improving treatment selection, outcomes. However, it crucial recognize that designed assist, not replace, expertise. Continuous validation diverse, real-world settings essential ensure the reliability generalizability care.

Язык: Английский

---

Enhancing Adverse Event Reporting With Clinical Language Models: Inpatient Falls

Journal of Advanced Nursing, Год журнала: 2025, Номер unknown

Опубликована: Фев. 13, 2025

ABSTRACT Aims To develop a method for computationally detecting fall events using clinical language models to complement existing self‐reporting mechanisms. Design Retrospective observational study. Methods Text data were collected from the unstructured nursing notes of three hospitals' electronic health records and Korean national patient safety reports, totalling 34,480 covering period January 2015 December 2019. Note‐level labelling was conducted by two researchers with 95% agreement. Preprocessing anonymisation English translation followed semantic validation. Five based on pretrained Bidirectional Encoder Representations Transformers (BERT) Generative Pretrained Transformer (GPT)‐4 prompt programming explored. Model performance assessed F measurements. Error analysis GPT‐4 results. Results Fine‐tuned BERT set outperformed GPT‐4, Bio+Clinical achieving highest F1 score 0.98. also reached an 0.98, while achieved competitive 0.94. showed much higher scores than standardised (0.85 vs. 0.39) (0.94 0.03). The error identified that common misclassification patterns included history homonyms, causing false positives implicit expressions missing contextual information, negatives. Conclusion model approach, if used alongside self‐reporting, promises increase chance identifying majority factual falls without need additional chart reviews. Impact Inpatient are often underreported, up 91% incidents missed in self‐reports. Using models, we significant portion these unreported falls, improving accuracy adverse event tracking reducing burden nurses. Patient or Public Contribution Not applicable.

Язык: Английский

---

Harnessing Generative Artificial Intelligence for Exercise and Training Prescription: Applications and Implications in Sports and Physical Activity—A Systematic Literature Review

Applied Sciences, Год журнала: 2025, Номер 15(7), С. 3497 - 3497

Опубликована: Март 22, 2025

Regular physical activity plays a critical role in health promotion and athletic performance, necessitating personalized exercise training prescriptions. While traditional methods rely on expert assessments, artificial intelligence (AI), particularly generative AI models such as ChatGPT Google Gemini, has emerged potential tool for enhancing personalization scalability recommendations. However, the applicability, reliability, adaptability of AI-generated prescriptions remain underexplored. A comprehensive search was performed using UnoPerTutto metadatabase, identifying 2891 records. After duplicate removal (1619 records) screening, 61 full-text reports were assessed eligibility, resulting inclusion 10 studies. The studies varied methodology, including qualitative mixed-methods approaches, quasi-experimental designs, randomized controlled trial (RCT). ChatGPT-4, ChatGPT-3.5, Gemini evaluated across different contexts, strength training, rehabilitation, cardiovascular exercise, general fitness programs. Findings indicate that programs generally adhere to established guidelines but often lack specificity, progression, real-time physiological feedback. recommendations found emphasize safety broad making them useful guidance less effective high-performance training. GPT-4 demonstrated superior performance generating structured resistance compared older models, yet limitations individualization contextual adaptation persisted. appraisal METRICS checklist revealed inconsistencies study quality, regarding prompt model transparency, evaluation frameworks. holds promise democratizing access prescriptions, its remains complementary rather than substitutive guidance. Future research should prioritize adaptability, integration with monitoring, improved AI-human collaboration enhance precision effectiveness AI-driven

Язык: Английский

---

Comparative evaluation of artificial intelligence models GPT-4 and GPT-3.5 in clinical decision-making in sports surgery and physiotherapy: a cross-sectional study

BMC Medical Informatics and Decision Making, Год журнала: 2025, Номер 25(1)

Опубликована: Апрель 14, 2025

The integration of artificial intelligence (AI) in healthcare has rapidly expanded, particularly clinical decision-making. Large language models (LLMs) such as GPT-4 and GPT-3.5 have shown potential various medical applications, including diagnostics treatment planning. However, their efficacy specialized fields like sports surgery physiotherapy remains underexplored. This study aims to compare the performance decision-making within these domains using a structured assessment approach. cross-sectional included 56 professionals specializing physiotherapy. Participants evaluated 10 standardized scenarios generated by 5-point Likert scale. encompassed common musculoskeletal conditions, assessments focused on diagnostic accuracy, appropriateness, surgical technique detailing, rehabilitation plan suitability. Data were collected anonymously via Google Forms. Statistical analysis paired t-tests for direct model comparisons, one-way ANOVA assess across multiple criteria, Cronbach's alpha evaluate inter-rater reliability. significantly outperformed all criteria. Paired t-test results (t(55) = 10.45, p < 0.001) demonstrated that provided more accurate diagnoses, superior plans, detailed recommendations. confirmed higher suitability planning (F(1, 55) 35.22, protocols 32.10, 0.001). values indicated internal consistency (α 0.478) compared 0.234), reflecting reliable performance. demonstrates These findings suggest advanced AI can aid planning, strategies. should function decision-support tool rather than substitute expert judgment. Future studies explore into real-world workflows, validate larger datasets, additional beyond GPT series.

Язык: Английский

---

Interdisciplinary Inquiry via PanelGPT: Application to Explore Chatbot Application in Sports Rehabilitation

medRxiv (Cold Spring Harbor Laboratory), Год журнала: 2023, Номер unknown

Опубликована: Июль 27, 2023

Abstract Background ChatGPT showcases exceptional conversational capabilities and extensive cross-disciplinary knowledge. In addition, it possesses the ability to perform multiple roles within a single chat session. This unique multi-role-playing feature positions as promising tool explore interdisciplinary subjects. Objective The study intended guide for exploration through simulated panel discussions. As proof-of-concept, we employed this method evaluate advantages challenges of using chatbots in sports rehabilitation. Methods We proposed model termed PanelGPT ChatGPTs’ knowledge graph on topics Applied “chatbots rehabilitation”, role-played both moderator panelists, which included physiotherapist, psychologist, nutritionist, AI expert, an athlete. act audience posed questions panel, with acting panelists responses hosting discussion. performed simulation ChatGPT-4 evaluated existing literature human expertise. Results Each mimicked real-life discussion: introduced opening/closing questions, all responded. experts engaged each other address inquiries from audience, primarily their respective fields By tackling related education, physiotherapy, physiology, nutrition, ethical consideration, discussion highlighted benefits such 24/7 support, personalized advice, automated tracking, reminders. It also emphasized importance user education identified limited interaction modes, inaccuracies emotion-related assurance data privacy security, transparency handling, fairness training. reached consensus that are designed assist, not replace, healthcare professionals rehabilitation process. Conclusions Compared typical conversation ChatGPT, multi-perspective approach facilitates comprehensive understanding topic by integrating insights complementary Beyond addressing exemplified rehabilitation, can be adapted tackle wide array educational, research, settings.

Язык: Английский

---