Integrating Retrieval-Augmented Generation with Large Language Models in Nephrology: Advancing Practical Applications

Medicina, Год журнала: 2024, Номер 60(3), С. 445 - 445

Опубликована: Март 8, 2024

The integration of large language models (LLMs) into healthcare, particularly in nephrology, represents a significant advancement applying advanced technology to patient care, medical research, and education. These have progressed from simple text processors tools capable deep understanding, offering innovative ways handle health-related data, thus improving practice efficiency effectiveness. A challenge applications LLMs is their imperfect accuracy and/or tendency produce hallucinations—outputs that are factually incorrect or irrelevant. This issue critical where precision essential, as inaccuracies can undermine the reliability these crucial decision-making processes. To overcome challenges, various strategies been developed. One such strategy prompt engineering, like chain-of-thought approach, which directs towards more accurate responses by breaking down problem intermediate steps reasoning sequences. Another one retrieval-augmented generation (RAG) strategy, helps address hallucinations integrating external enhancing output relevance. Hence, RAG favored for tasks requiring up-to-date, comprehensive information, clinical decision making educational applications. In this article, we showcase creation specialized ChatGPT model integrated with system, tailored align KDIGO 2023 guidelines chronic kidney disease. example demonstrates its potential providing specialized, advice, marking step reliable efficient nephrology practices.

Язык: Английский

---

Chain of Thought Utilization in Large Language Models and Application in Nephrology

Medicina, Год журнала: 2024, Номер 60(1), С. 148 - 148

Опубликована: Янв. 13, 2024

Chain-of-thought prompting enhances the abilities of large language models (LLMs) significantly. It not only makes these more specific and context-aware but also impacts wider field artificial intelligence (AI). This approach broadens usability AI, increases its efficiency, aligns it closely with human thinking decision-making processes. As we improve this method, is set to become a key element in future adding purpose, precision, ethical consideration technologies. In medicine, chain-of-thought especially beneficial. Its capacity handle complex information, logical sequential reasoning, suitability for ethically context-sensitive situations make an invaluable tool healthcare professionals. role enhancing medical care research expected grow as further develop use technique. bridges gap between AI’s traditionally obscure process clear, accountable standards required healthcare. does by emulating reasoning style familiar professionals, fitting well into their existing practices codes. While solving AI transparency challenge, significant step toward making comprehensible trustworthy medicine. review focuses on understanding workings LLMs, particularly how can be adapted nephrology’s unique requirements. aims thoroughly examine aspects, clarity, possibilities, offering in-depth view exciting convergence areas.

Язык: Английский

---

Evaluation of ChatGPT and Gemini large language models for pharmacometrics with NONMEM

Journal of Pharmacokinetics and Pharmacodynamics, Год журнала: 2024, Номер 51(3), С. 187 - 197

Опубликована: Апрель 24, 2024

Язык: Английский

---

Open Science at the Generative AI Turn: An Exploratory Analysis of Challenges and Opportunities

Опубликована: Май 24, 2024

Technology influences Open Science (OS) practices, because conducting science in transparent, accessible, and participatory ways requires tools/platforms for collaborative research sharing results. Due to this direct relationship, characteristics of employed technologies directly impact OS objectives. Generative Artificial Intelligence (GenAI) models are increasingly used by researchers tasks such as text refining, code generation/editing, reviewing literature, data curation/analysis. GenAI promises substantial efficiency gains but is currently fraught with limitations that could negatively core values fairness, transparency integrity, harm various social actors.In paper, we explore possible positive negative impacts on OS. We use the taxonomy within UNESCO Recommendation systematically intersection conclude using advance key objectives further broadening meaningful access knowledge, enabling efficient infrastructure, improving engagement societal actors, enhancing dialogue among knowledge systems. However, due limitations, it also compromise equity, reproducibility, reliability research, while having potential implications political economy its infrastructure. Hence, sufficient checks, validation critical assessments essential when incorporating into workflows.

Язык: Английский

---

Characterizing patients at higher cardiovascular risk for prescribed stimulants: Learning from health records data with predictive analytics and data mining techniques

Computers in Biology and Medicine, Год журнала: 2025, Номер 188, С. 109870 - 109870

Опубликована: Фев. 20, 2025

Язык: Английский

---

Leveraging Large Language Models in Pharmacometrics: Evaluation of NONMEM Output Interpretation and Simulation Capabilities

Research Square (Research Square), Год журнала: 2025, Номер unknown

Опубликована: Апрель 28, 2025

Advancements in large language models (LLMs) have suggested their potential utility for diverse pharmacometrics tasks. This study investigated the performance of LLM generating structure diagrams, publication-ready tables, analysis reports, and conducting simulations using output files from models. Forty-four NONMEM were obtained GitHub software repository. The Claude 3.5 Sonnet (Claude) ChatGPT 4o was compared with two other candidate LLMs: Gemini 1.5 Pro Llama 3.2. Prompt engineering conducted tasks such as model parameter reports. Simulations ChatGPT. Artifacts used to visualize A Shiny R application implemented. selected investigation following comparisons 4o, Pro, on diagram table generation successfully generated diagrams 40 (90.9%) 44 initial prompts, remaining resolved an additional prompt. consistently accurate summary tables succinct Modest variability replicate prompts identified. demonstrated simulation capabilities but revealed limitations complex PK/PD LLMs enhance key modeling However, expert review results is essential.

Язык: Английский

---

Leveraging large language models in pharmacometrics: evaluation of NONMEM output interpretation and simulation capabilities

Journal of Pharmacokinetics and Pharmacodynamics, Год журнала: 2025, Номер 52(3)

Опубликована: Июнь 1, 2025

Язык: Английский

---

Performance of the ChatGPT large language model for decision support in community pharmacy

British Journal of Clinical Pharmacology, Год журнала: 2024, Номер 90(12), С. 3320 - 3333

Опубликована: Авг. 27, 2024

Abstract Aims The aim of this study was to assess the ChatGPT‐4 (ChatGPT) large language model (LLM) on tasks relevant community pharmacy. Methods ChatGPT assessed with pharmacy‐relevant test cases involving drug information retrieval, identifying labelling errors, prescription interpretation, decision‐making under uncertainty and multidisciplinary consults. Drug rituximab, warfarin, St. John's wort queried. decision‐support scenarios consisted a subject swollen eyelids maculopapular rash in lisinopril ferrous sulfate. required integration medication management recommendations for healthy eating physical activity/exercise. Results responses from were satisfactory cited databases drug‐specific monographs. identified labeling errors related incorrect strength, form, route administration, unit conversion, directions. For patient inflamed eyelids, course action developed by comparable pharmacist's approach. rash, both pharmacist placed reaction either or sulfate at top differential. provided customized vaccination requirements travel Brazil, guidance allergies recovery knee injury. wellness diabetic metformin semaglutide. Conclusions LLMs have potential become powerful tool However, rigorous validation studies across diverse queries, classes populations, engineering secure privacy will be needed enhance LLM utility.

Язык: Английский

---

Open Science at the Generative AI Turn: An Exploratory Analysis of Challenges and Opportunities

Quantitative Science Studies, Год журнала: 2024, Номер 6, С. 22 - 45

Опубликована: Ноя. 5, 2024

Abstract Technology influences Open Science (OS) practices, because conducting science in transparent, accessible, and participatory ways requires tools platforms for collaboration sharing results. Due to this relationship, the characteristics of employed technologies directly impact OS objectives. Generative Artificial Intelligence (GenAI) is increasingly used by researchers tasks such as text refining, code generation/editing, reviewing literature, data curation/analysis. Nevertheless, concerns about openness, transparency, bias suggest that GenAI may benefit from greater engagement with OS. promises substantial efficiency gains but currently fraught limitations could negatively core values, fairness, integrity, harm various social actors. In paper, we explore possible positive negative impacts on We use taxonomy within UNESCO Recommendation systematically intersection conclude using advance key objectives broadening meaningful access knowledge, enabling efficient infrastructure, improving societal actors, enhancing dialogue among knowledge systems. However, due GenAI’s limitations, it also compromise equity, reproducibility, reliability research. Hence, sufficient checks, validation, critical assessments are essential when incorporating into research workflows.

Язык: Английский

---

Prompt-engineering enabled LLM or MLLM and instigative bioinformatics pave the way to identify and characterize the significant SARS-CoV-2 antibody escape mutations

International Journal of Biological Macromolecules, Год журнала: 2024, Номер unknown, С. 138547 - 138547

Опубликована: Дек. 1, 2024

Язык: Английский

---