A future role for health applications of large language models depends on regulators enforcing safety standards

The Lancet Digital Health, Journal Year: 2024, Volume and Issue: 6(9), P. e662 - e672

Published: Aug. 23, 2024

Among the rapid integration of artificial intelligence in clinical settings, large language models (LLMs), such as Generative Pre-trained Transformer-4, have emerged multifaceted tools that potential for health-care delivery, diagnosis, and patient care. However, deployment LLMs raises substantial regulatory safety concerns. Due to their high output variability, poor inherent explainability, risk so-called AI hallucinations, LLM-based applications serve a medical purpose face challenges approval devices under US EU laws, including recently passed Artificial Intelligence Act. Despite unaddressed risks patients, misdiagnosis unverified advice, are available on market. The ambiguity surrounding these creates an urgent need frameworks accommodate unique capabilities limitations. Alongside development frameworks, existing regulations should be enforced. If regulators fear enforcing market dominated by supply or technology companies, consequences layperson harm will force belated action, damaging potentiality advice.

Language: Английский

---

Understanding natural language: Potential application of large language models to ophthalmology

Asia-Pacific Journal of Ophthalmology, Journal Year: 2024, Volume and Issue: 13(4), P. 100085 - 100085

Published: July 1, 2024

Large language models (LLMs), a natural processing technology based on deep learning, are currently in the spotlight. These closely mimic comprehension and generation. Their evolution has undergone several waves of innovation similar to convolutional neural networks. The transformer architecture advancement generative artificial intelligence marks monumental leap beyond early-stage pattern recognition via supervised learning. With expansion parameters training data (terabytes), LLMs unveil remarkable human interactivity, encompassing capabilities such as memory retention comprehension. advances make particularly well-suited for roles healthcare communication between medical practitioners patients. In this comprehensive review, we discuss trajectory their potential implications clinicians For clinicians, can be used automated documentation, given better inputs extensive validation, may able autonomously diagnose treat future. patient care, triage suggestions, summarization documents, explanation patient's condition, customizing education materials tailored level. limitations possible solutions real-world use also presented. Given rapid advancements area, review attempts briefly cover many that play ophthalmic space, with focus improving quality delivery.

Language: Английский

---

Evaluation of a context-aware chatbot using retrieval-augmented generation for answering clinical questions on medication-related osteonecrosis of the jaw

Journal of Cranio-Maxillofacial Surgery, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 1, 2025

The potential of large language models (LLMs) in medical applications is significant, and Retrieval-augmented generation (RAG) can address the weaknesses these terms data transparency scientific accuracy by incorporating current knowledge into responses. In this study, RAG GPT-4 OpenAI were applied to develop GuideGPT, a context aware chatbot integrated with database from 449 publications designed provide answers on prevention, diagnosis, treatment medication-related osteonecrosis jaw (MRONJ). A comparison was made generic LLM ("PureGPT") across 30 MRONJ-related questions. Ten international experts MRONJ evaluated responses based content, language, explanation, agreement using 5-point Likert scales. Statistical analysis Mann-Whitney U test showed significantly better ratings for GuideGPT than PureGPT regarding content (p = 0.006), explanation 0.032), 0.008), though not 0.407). Thus, study demonstrates be promising tool improve response quality reliability LLMs domain-specific knowledge. This approach addresses limitations chatbots traceable up-to-date essential clinical practice.

Language: Английский

---

Retrieval-augmented generation for generative artificial intelligence in health care

Published: Jan. 25, 2025

Abstract Generative artificial intelligence has brought disruptive innovations in health care but faces certain challenges. Retrieval-augmented generation (RAG) enables models to generate more reliable content by leveraging the retrieval of external knowledge. In this perspective, we analyze possible contributions that RAG could bring equity, reliability, and personalization. Additionally, discuss current limitations challenges implementing medical scenarios.

Language: Английский

---

A knowledge-graph enhanced large language model-based fault diagnostic reasoning and maintenance decision support pipeline towards industry 5.0

International Journal of Production Research, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 22

Published: Feb. 28, 2025

Language: Английский

---

Retrieval-Augmented-Generation large language models outperform junior clinicians in guideline-concordant PSA testing

Research Square (Research Square), Journal Year: 2025, Volume and Issue: unknown

Published: March 31, 2025

Background and Objective Society guidelines for prostate cancer screening via PSA testing serve to standardize patient care, are often utilized by trainees, junior staff, or generalist medical practitioners guide decision-making. Adherence is a time-consuming challenging task rates of inappropriate high. This study evaluates retrieval-augmented generation (RAG) enhanced large language model (LLM), grounded in current EAU AUA guidelines, assess its effectiveness providing guideline-concordant recommendations compared clinicians. Methods A pipeline was developed used process series 44 fictional case scenarios. Five clinicians were tasked provide the same scenarios, closed-book open-book formats. Answers accuracy binomial fashion. Key Findings Limitations The RAG-LLM tool provided 95.5% clinicians, who correct 62.3% scenarios format, 74.1% an open book format. difference statistically significant both (p < 0.001) Conclusions Clinical Implications Use RAG techniques allows LLMs integrate complex into day-to-day tools Urology have capability enhance clinical decision-making testing, potentially improving consistency healthcare delivery, reducing cognitive load on unnecessary investigations costs.

Language: Английский

---

Systematic analysis of large language models for automating document-to-smart contract transformation

Automation in Construction, Journal Year: 2025, Volume and Issue: 175, P. 106209 - 106209

Published: April 15, 2025

Language: Английский

---

ChatGPT and neurosurgical education: A crossroads of innovation and opportunity

Journal of Clinical Neuroscience, Journal Year: 2024, Volume and Issue: 129, P. 110815 - 110815

Published: Sept. 4, 2024

Language: Английский

---

The path forward for large language models in medicine is open

npj Digital Medicine, Journal Year: 2024, Volume and Issue: 7(1)

Published: Nov. 27, 2024

Large language models (LLMs) are increasingly applied in medical documentation and have been proposed for clinical decision support. We argue that the future LLMs medicine must be based on transparent controllable open-source models. Openness enables tool developers to control safety quality of underlying AI models, while also allowing healthcare professionals hold these accountable. For reasons, is open.

Language: Английский

---

Multimodal Large Language Model Passes Specialty Board Examination and Surpasses Human Test-Taker Scores: A Comparative Analysis Examining the Stepwise Impact of Model Prompting Strategies on Performance

medRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: July 29, 2024

ABSTRACT Background Large language models (LLMs) have shown promise in answering medical licensing examination-style questions. However, there is limited research on the performance of multimodal LLMs subspecialty examinations. Our study benchmarks LLM’s enhanced by model prompting strategies gastroenterology subspeciality questions and examines how these incrementally improve overall performance. Methods We used 2022 American College Gastroenterology (ACG) self-assessment examination (N=300). This test typically completed fellows established gastroenterologists preparing for board examination. employed a sequential implementation strategies: prompt engineering, retrieval augmented generation (RAG), five-shot learning, an LLM-powered answer validation revision (AVRM). GPT-4 Gemini Pro were tested. Results Implementing all improved score from 60.3% to 80.7% Pro’s 48.0% 54.3%. GPT-4’s surpassed 70% passing threshold 75% average human test-taker scores unlike Pro. Stratification difficulty showed accuracy both mirrored that examinees, demonstrating higher as increased. The addition AVRM prompt, RAG 5-shot increased 4.4%. incremental non-image (57.2% 80.4%) image-based (63.0% 80.9%) GPT-4, but not Conclusions results underscore value improving LLM subspecialty-level exam also present novel reviewer context medicine which further when combined with other strategies. findings highlight potential future role LLMs, particularly multiple strategies, clinical decision support systems care healthcare providers.

Language: Английский

---