Vnitr Lek 2025, 71(5):284-288
Artificial intelligence in primary care: From dimensionality reduction to clinical decision‑making and time efficiency
- Všeobecný praktický lékař, Medikatze, s. r. o., Litovel
This review summarizes the principles of applying artificial intelligence (in primary care, focusing on dimensionality reduction and the integration of large language models in clinical decision-making. The article demonstrates how modern algorithms based on latent representations and deep learning contribute to more efficient diagnostics, refined diagnosis, and streamlined administrative processes, all while complementing the clinical expertise of practicing physicians.
Keywords: artificial intelligence, language models, LLM, prompt, transformer, primary care.
Accepted: August 25, 2025; Published: September 18, 2025 Show citation
References
- Lee P, Goldberg HS, Kohane IS. Integrating artificial intelligence into primary care: perspectives, challenges, and opportunities. NPJ Digit Med. 2023;6(1):45.
- Silver D, Schrittwieser J, Simonyan K, et al. Mastering the game of Go without human knowledge. Nature. 2017;550(7676):354-359.
Go to original source...
Go to PubMed...
- Mikolov T, Sutskever I, Chen K, Corrado GS, Dean J. Efficient Estimation of Word Representations in Vector Space. arXiv preprint. 2013; arXiv:1301.3781.
- Friston K. The free-energy principle: a unified brain theory? Nat Rev Neurosci. 2010;11(2):127-138.
Go to original source...
Go to PubMed...
- Beam AL, Kohane IS. Big Data and Machine Learning in Health Care. JAMA. 2018;319(13):1317-1318.
Go to original source...
Go to PubMed...
- Goh E, Gallo R, Hom J, et al. Large Language Model Influence on Diagnostic Reasoning: A Randomized Clinical Trial. JAMA Netw Open. 2024;7(10):e2440969.
Go to original source...
Go to PubMed...
- Mahale N. GPT-4.5 vs GPT-4o: Testing The AI Models Using Seven Prompts. Writesonic Blog. 2025 Mar 11. Dostupné z: https://writesonic.com/blog/gpt-4-5-vs-gpt-4o.
- Rajpurkar P, Chen E, Banerjee O, Topol EJ. AI in health and medicine. Nat Med. 2022;28(1):31-38.
Go to original source...
Go to PubMed...
- HL7 Czech Republic. HL7 Czech Base & Core Implementation Guide. Version 0.3.0ballot, Continuous build. HL7 Czech Republic 2025. [cit. 20250802]. Available from: https://build.fhir.org/ig/HL7-cz/czcore.
- European Parliament and Council of the European Union. Regulation (EU) 2017/745 of the European Parliament and of the Council on medical devices. Official Journal of the European Union. 2017;60(L 117):1-175. [cit. 2024-08-02]. Available from: https://eur-lex.europa.eu/legal-content/EN/TXT/?uri=CELEX%3A32017R0745.
- OpenAI. ChatGPT General FAQ: Is ChatGPT suitable for medical use? OpenAI Support. [cit. 2024-08-02]. Available from: https://help.openai.com/en/articles/6783459-chatgpt-general-faq.
- Ministerstvo zdravotnictví ČR. Metodický pokyn pro poskytovatele zdravotních služeb k využívání umělé inteligence. Věstník Ministerstva zdravotnictví ČR. 2025;(9):1-12. [cit. 2024-08-02]. Available from: https://mzd.gov.cz/wp-content/uploads/2025/06/Vestnik-MZD-09-2025.pdf.
- Davenport T, Kalakota R. The potential for artificial intelligence in healthcare. Future Healthc J. 2019;6(2):94-98.
Go to original source...
Go to PubMed...
- Hannun AY, Rajpurkar P, Haghpanahi M, et al. Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network. Nat Med. 2019;25(1):65-69.
Go to original source...
Go to PubMed...
- Esteva A, Robicquet A, Ramsundar B, et al. A guide to deep learning in healthcare. Nat Med. 2019;25(1):24-29.
Go to original source...
Go to PubMed...