{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T14:10:18Z","timestamp":1789999818272,"version":"4.0.1"},"reference-count":24,"publisher":"MDPI AG","issue":"18","license":[{"start":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T00:00:00Z","timestamp":1789689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background\/Objective: Large language models (LLMs) have shown exam-level performance, yet their reliability and safety in laboratory medicine\u2014where quantitative data interpretation is central\u2014remain insufficiently validated. This study compared the accuracy, interpretive quality, and safety of ChatGPT-5.2, Gemini 3 Pro, and DeepSeek-V3.2 using a standardized, text-based educational benchmark of clinical pathology and laboratory medicine vignettes. Methods: For each case, the original open-ended questions were answered by each model and scored by two blinded expert raters across four domains\u2014diagnostic accuracy, interpretation, management\/investigations, and safety\u2014using a six-point Likert scale, yielding a composite score ranging from 4 to 24. Investigators developed five single-best-answer MCQs per case (500 MCQs total) with consensus answer keys; models selected one option per item. Results: Inter-rater agreement was high (\u03ba = 0.80 for diagnostic concordance; \u03ba = 0.78 for safety flags). Mean composite open-ended scores were 22.5 \u00b1 2 for ChatGPT-5.2, 21.1 \u00b1 2.5 for Gemini, and 20.6 \u00b1 2.6 for DeepSeek (p &lt; 0.001). Fully concordant primary diagnoses were observed in 88%, 84% and 82% of cases, respectively. Unsafe or guideline-discordant recommendations were uncommon but present (2%, 4%, 5%). MCQ accuracy was high: 96% (480\/500) for ChatGPT-5.2, 95% (475\/500) for Gemini, and 94% (470\/500) for DeepSeek. Conclusions: All three LLMs achieved high performance in this standardized text-based benchmark. ChatGPT-5.2 had the highest observed performance across several predefined outcomes, although absolute differences were modest for some measures, particularly MCQ accuracy. These findings should not be interpreted as evidence of clinical superiority or real-world effectiveness.<\/jats:p>","DOI":"10.3390\/diagnostics16183030","type":"journal-article","created":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T12:50:03Z","timestamp":1789995003000},"page":"3030","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Laboratory Medicine Decision Support\u2014Beyond Exam Passing: A Blinded 100-Case Text-Based Benchmark of Diagnostic Accuracy, Management Quality, and Safety for ChatGPT, Gemini, and DeepSeek\u2014LLM Decision Support in Laboratory Medicine"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2852-0449","authenticated-orcid":false,"given":"Kemal Turker","family":"Uluta\u015f","sequence":"first","affiliation":[{"name":"Department of Medical Biochemistry and Laboratory Medicine, Reyhanl\u0131 State Hospital, 31500 Hatay, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adnan","family":"Pekmezci","sequence":"additional","affiliation":[{"name":"Department of Internal Medicine, Reyhanl\u0131 State Hospital, 31500 Hatay, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,9,18]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1930","DOI":"10.1038\/s41591-023-02448-8","article-title":"Large language models in medicine","volume":"29","author":"Thirunavukarasu","year":"2023","journal-title":"Nat. Med."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"794","DOI":"10.1007\/s12020-024-03750-2","article-title":"Assessment of ChatGPT\u2019s adherence to ETA-thyroid nodule management guideline over two different time intervals 14 days apart: In binary and multiple-choice queries","volume":"85","author":"Deniz","year":"2024","journal-title":"Endocrine"},{"key":"ref_3","unstructured":"Nori, H., King, N., McKinney, S.M., Carignan, D., and Horvitz, E. (2023). Capabilities of GPT-4 on Medical Challenge Problems. arXiv."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Kung, T.H., Cheatham, M., Medenilla, A., Sillos, C., De Leon, L., and Elepano, C. (2023). Performance of ChatGPT on USMLE: Potential for AI-assisted medical education using large language models. PLoS Digit. Health, 2.","DOI":"10.1371\/journal.pdig.0000198"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1122","DOI":"10.1093\/clinchem\/hvae093","article-title":"ChatGPT vs Medical Professional: Analyzing Responses to Laboratory Medicine Questions on Social Media","volume":"70","author":"Girton","year":"2024","journal-title":"Clin. Chem."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1233","DOI":"10.1056\/NEJMsr2214184","article-title":"Benefits, Limits, and Risks of GPT-4 as an AI Chatbot for Medicine","volume":"388","author":"Lee","year":"2023","journal-title":"N. Engl. J. Med."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"107028","DOI":"10.1016\/j.ssci.2025.107028","article-title":"Artificial intelligence adoption challenges from healthcare providers\u2019 perspectives: A comprehensive review and future directions","volume":"193","author":"Abdelwanis","year":"2026","journal-title":"Saf. Sci."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"4712","DOI":"10.1007\/s00266-024-04157-0","article-title":"Can AI Answer My Questions? Utilizing Artificial Intelligence in the Perioperative Assessment for Abdominoplasty Patients","volume":"48","author":"Lim","year":"2024","journal-title":"Aesthet. Plast. Surg."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Shamil, E., Ravi, P., and Chandra, A. (2023). 100 Cases in Clinical Pathology and Laboratory Medicine, CRC Press. [2nd ed.].","DOI":"10.1201\/9781003242697"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"3283","DOI":"10.1038\/s41591-025-03953-8","article-title":"The STARD-AI reporting guideline for diagnostic accuracy studies using artificial intelligence","volume":"31","author":"Sounderajah","year":"2025","journal-title":"Nat. Med."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1038\/s41591-024-03425-5","article-title":"The TRIPOD-LLM reporting guideline for studies using large language models","volume":"31","author":"Gallifant","year":"2025","journal-title":"Nat. Med."},{"key":"ref_12","unstructured":"OpenAI (ChatGPT, 2025). ChatGPT, version 5.2; A Smarter, More Conversational ChatGPT."},{"key":"ref_13","unstructured":"Google DeepMind (Gemini, 2025). Gemini, version 3 Pro; Model Card and Technical Overview."},{"key":"ref_14","unstructured":"DeepSeek, A.I. (DeepSeek, 2025). DeepSeek, version V3.2; Release: Reasoning-First Models Built for Agents."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"528","DOI":"10.1152\/advan.00076.2023","article-title":"Assessing the performance of ChatGPT to solve biochemistry question papers of university examination","volume":"47","author":"Mahat","year":"2023","journal-title":"Adv. Physiol. Educ."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"e47191","DOI":"10.2196\/47191","article-title":"Assessing the Performance of ChatGPT in Medical Biochemistry Using Clinical Case Vignettes: Observational Study","volume":"9","author":"Surapaneni","year":"2023","journal-title":"JMIR Med. Educ."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1002\/bmb.21808","article-title":"Evaluating ChatGPT as a self-learning tool in medical biochemistry: A performance assessment in undergraduate medical university examination","volume":"52","author":"Surapaneni","year":"2024","journal-title":"Biochem. Mol. Biol. Educ."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1089","DOI":"10.1093\/clinchem\/hvae100","article-title":"ChatGPT: A Reliable Laboratory Medicine Consult?","volume":"70","year":"2024","journal-title":"Clin. Chem."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"315","DOI":"10.1007\/s12020-024-04121-7","article-title":"Comparative evaluation of ChatGPT-4, ChatGPT-3.5 and Google Gemini on PCOS assessment and management based on recommendations from the 2023 guideline","volume":"88","author":"Gunesli","year":"2025","journal-title":"Endocrine"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"e53297","DOI":"10.2196\/53297","article-title":"Triage Performance Across Large Language Models, ChatGPT, and Untrained Doctors in Emergency Medicine: Comparative Study","volume":"26","author":"Masanneck","year":"2024","journal-title":"J. Med. Internet Res."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"294","DOI":"10.15388\/Amed.2024.31.2.18","article-title":"Emergency Medicine Assistants in the Field of Toxicology, Comparison of ChatGPT-3.5 and GEMINI Artificial Intelligence Systems","volume":"31","author":"Bedel","year":"2024","journal-title":"Acta Medica Litu."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1186\/s12245-025-00949-6","article-title":"Comparative performance of ChatGPT, Gemini, and final-year emergency medicine clerkship students in answering multiple-choice questions: Implications for the use of AI in medical education","volume":"18","author":"Anjum","year":"2025","journal-title":"Int. J. Emerg. Med."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Tangsrivimol, J.A., Darzidehkalani, E., Virk, H.U.H., Wang, Z., Egger, J., Wang, M., Hacking, S., Glicksberg, B.S., Strauss, M., and Krittanawong, C. (2025). Benefits, limits, and risks of ChatGPT in medicine. Front. Artif. Intell., 8.","DOI":"10.3389\/frai.2025.1518049"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"e41780","DOI":"10.1097\/MD.0000000000041780","article-title":"Readability, reliability and quality of responses generated by ChatGPT, gemini, and perplexity for the most frequently asked questions about pain","volume":"104","author":"Ozduran","year":"2025","journal-title":"Medicine"}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/18\/3030\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T13:19:48Z","timestamp":1789996788000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/18\/3030"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,18]]},"references-count":24,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["diagnostics16183030"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics16183030","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,18]]}}}