{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T04:30:36Z","timestamp":1786595436616,"version":"build-2736575974"},"reference-count":30,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T00:00:00Z","timestamp":1786579200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>This study aimed to evaluate the performance of ChatGPT in identifying hemodialysis (HD) indications from authentic nephrology consultation notes and to compare its recommendations with both real-world clinical decisions and expert nephrologist consensus.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This exploratory observational study included 22 anonymized nephrology consultation notes from routine inpatient care at a tertiary care university hospital. Each note was independently evaluated by ChatGPT 5.4 using a standardized zero-shot prompt. The same notes were independently reviewed by three blinded senior academic nephrologists. The majority-vote consensus among these nephrologists was defined as the primary reference standard. Real-world decisions documented by nephrology fellows were evaluated as a secondary comparator. Agreement was assessed using Cohen\u2019s kappa coefficient, and inter-rater reliability among nephrologists was evaluated using Fleiss\u2019 kappa.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Expert consensus classified eight of 22 cases (40.9%) as requiring hemodialysis and 13 (59.1%) as not requiring HD. Inter-rater agreement among the nephrologists was excellent (Fleiss\u2019\n                      <jats:italic>\u03ba<\/jats:italic>\n                      \u202f=\u202f0.814,\n                      <jats:italic>p<\/jats:italic>\n                      \u202f&amp;lt;\u202f0.001). ChatGPT and real-world clinical decisions agreed in 18 of 22 cases (81.8%;\n                      <jats:italic>\u03ba<\/jats:italic>\n                      \u202f=\u202f0.633,\n                      <jats:italic>p<\/jats:italic>\n                      \u202f=\u202f0.003), whereas ChatGPT and expert consensus agreed in 15 of 22 cases (68.2%;\n                      <jats:italic>\u03ba<\/jats:italic>\n                      \u202f=\u202f0.374,\n                      <jats:italic>p<\/jats:italic>\n                      \u202f=\u202f0.069). Expert consensus and real-world clinical decisions agreed in 17 of 22 cases (77.3%;\n                      <jats:italic>\u03ba<\/jats:italic>\n                      \u202f=\u202f0.553,\n                      <jats:italic>p<\/jats:italic>\n                      \u202f=\u202f0.007). Among the nine expert-defined HD cases, ChatGPT agreed in seven cases and demonstrated exact indication-level agreement in four cases. Among the 10 cases classified as HD by both ChatGPT and real-world clinical decisions, exact indication-level agreement was observed in four cases. Discrepancies were most commonly observed in cases involving metabolic acidosis, volume overload, and oliguria\/anuria.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>These exploratory findings suggest that ChatGPT may align more closely with nephrology fellows\u2019 decision-making than with senior nephrologists\u2019 judgments. The observed discrepancies may reflect differences in how clinical findings were interpreted and incorporated into the overall clinical context. Although ChatGPT cannot replace expert clinical judgment, it may have potential as an educational tool for trainees, encouraging systematic evaluation of HD indications and structured clinical reasoning. Larger, prospective, multicenter studies are needed to confirm these findings and evaluate ChatGPT\u2019s educational impact in nephrology training.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1909864","type":"journal-article","created":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T04:23:43Z","timestamp":1786595023000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Evaluating the potential of ChatGPT as an educational decision-support tool for hemodialysis decision-making in nephrology training"],"prefix":"10.3389","volume":"13","author":[{"given":"Esin","family":"Avsar Kucukkurt","sequence":"first","affiliation":[{"name":"Department of Internal Medicine, Faculty of Medicine, Akdeniz University","place":["Antalya, T\u00fcrkiye"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feyza","family":"Bora","sequence":"additional","affiliation":[{"name":"Division of Nephrology, Department of Internal Medicine, Faculty of Medicine, Akdeniz University","place":["Antalya, T\u00fcrkiye"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hasan","family":"Sozel","sequence":"additional","affiliation":[{"name":"Department of Internal Medicine, Faculty of Medicine, Akdeniz University","place":["Antalya, T\u00fcrkiye"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dilek","family":"Yapar","sequence":"additional","affiliation":[{"name":"Institute of Health Sciences, Department of Medical Informatics, Akdeniz University","place":["Antalya, T\u00fcrkiye"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,13]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"1087","DOI":"10.1007\/s40620-022-01529-0","article-title":"Toward generalizing the use of artificial intelligence in nephrology and kidney transplantation","volume":"36","author":"Badrouchi","year":"2023","journal-title":"J Nephrol"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"452","DOI":"10.1038\/s41581-022-00562-3","article-title":"Artificial intelligence-enabled decision support in nephrology","volume":"18","author":"Loftus","year":"2022","journal-title":"Nat Rev Nephrol"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1097\/MNH.0000000000000787","article-title":"Role of artificial intelligence in the diagnosis and management of kidney disease: applications to chronic kidney disease and acute kidney injury","volume":"31","author":"Tangri","year":"2022","journal-title":"Curr Opin Nephrol Hypertens"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"3455","DOI":"10.1038\/s41598-025-88074-5","article-title":"Evaluating AI performance in nephrology triage and subspecialty referrals","volume":"15","author":"Koirala","year":"2025","journal-title":"Sci Rep"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"sfaf243","DOI":"10.1093\/ckj\/sfaf243","article-title":"Clinical applications and limitations of large language models in nephrology: a systematic review","volume":"18","author":"Unger","year":"2025","journal-title":"Clin Kidney J"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1038\/s41746-025-01550-0","article-title":"Enhancing diagnostic capability with multi-agents conversational large language models","volume":"8","author":"Chen","year":"2025","journal-title":"NPJ Digit Med"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"169","DOI":"10.52312\/jdrs.2023.1402","article-title":"Chatgpt's potential to support home care for patients in the early period after orthopedic interventions and enhance public health","volume":"35","author":"Yapar","year":"2024","journal-title":"Jt Dis Relat Surg"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"gfaf116.0712","DOI":"10.1093\/ndt\/gfaf116.0712","article-title":"#786 large language models for algorithm-based management of bone mineral disorders in patients with hemodialysis","volume":"40","author":"Bergling","year":"2025","journal-title":"Nephrol Dial Transplant"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"3211","DOI":"10.1007\/s00467-025-06819-w","article-title":"Performance evaluation of large language models in pediatric nephrology clinical decision support: a comprehensive assessment","volume":"40","author":"Niel","year":"2025","journal-title":"Pediatr Nephrol"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"223","DOI":"10.4274\/bmb.galenos.2025.78941","article-title":"Evaluation of ChatGPT\u2019s performance in making-decision of dialysis in acute kidney injury","volume":"10","author":"Can","year":"2025","journal-title":"Bagcilar Med Bull"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"e951942","DOI":"10.12659\/msm.951942","article-title":"AI-assisted dialysis decision-making: assessing agreement between ChatGPT and nephrologist in initial dialysis indication and prescription in emergency and ICU settings","volume":"32","author":"Kara","year":"2026","journal-title":"Med Sci Monit"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"sfag004","DOI":"10.1093\/ckj\/sfag004","article-title":"Transforming nephrology through artificial intelligence: a state-of-the-art roadmap for clinical integration","volume":"19","author":"Cheungpasitporn","year":"2026","journal-title":"Clin Kidney J"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"e0000198","DOI":"10.1371\/journal.pdig.0000198","article-title":"Performance of ChatGPT on USMLE: potential for AI-assisted medical education using large language models","volume":"2","author":"Kung","year":"2023","journal-title":"PLoS Digit Health"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"399","DOI":"10.3325\/cmj.2025.66.399","article-title":"ChatGPT and Gemini in warfarin counseling","volume":"66","author":"Erkan","year":"2026","journal-title":"Croat Med J"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"366","DOI":"10.1186\/s12911-024-02709-7","article-title":"Analyzing evaluation methods for large language models in the medical field: a scoping review","volume":"24","author":"Lee","year":"2024","journal-title":"BMC Med Inform Decis Mak"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1016\/s0031-9406(05)61417-4","article-title":"Clinical reasoning of expert and novice physiotherapists in an outpatient orthopaedic setting","volume":"88","author":"Doody","year":"2002","journal-title":"Physiotherapy"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"5890","DOI":"10.3402\/meo.v16i0.5890","article-title":"An analysis of clinical reasoning through a recent and comprehensive approach: the dual-process theory","volume":"16","author":"Pelaccia","year":"2011","journal-title":"Med Educ Online"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1038\/s41586-023-06291-2","article-title":"Large language models encode clinical knowledge","volume":"620","author":"Singhal","year":"2023","journal-title":"Nature"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"2309","DOI":"10.1056\/NEJMra1309483","article-title":"Lactic acidosis","volume":"371","author":"Kraut","year":"2014","journal-title":"N Engl J Med"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"839","DOI":"10.1016\/j.ccc.2015.06.015","article-title":"Renal replacement therapy","volume":"31","author":"Villa","year":"2015","journal-title":"Crit Care Clin"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"1496","DOI":"10.3390\/ph15121496","article-title":"Lactic acidosis related to pharmacotherapy and human diseases","volume":"15","author":"Zanza","year":"2022","journal-title":"Pharmaceuticals"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"c179","DOI":"10.1159\/000339789","article-title":"KDIGO clinical practice guidelines for acute kidney injury","volume":"120","author":"Khwaja","year":"2012","journal-title":"Nephron Clin Pract"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"664","DOI":"10.34067\/KID.0000001037","article-title":"Artificial intelligence in critical care nephrology: current applications, emerging techniques, and challenges to clinical integration","volume":"7","author":"Cheungpasitporn","year":"2026","journal-title":"Kidney360"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1186\/s12912-026-04348-x","article-title":"How do dialysis nurses and AI reason clinically? A scenario-based comparative study","volume":"25","author":"Orkaby","year":"2026","journal-title":"BMC Nurs"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1016\/j.kint.2019.01.017","article-title":"Dialysis initiation, modality choice, access, and prescription: conclusions from a kidney disease: improving global outcomes (KDIGO) controversies conference","volume":"96","author":"Chan","year":"2019","journal-title":"Kidney Int"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"477","DOI":"10.1038\/s41746-026-02724-0","article-title":"Multi expert integrated algorithm for kidney biopsy triage","volume":"9","author":"Yun","year":"2026","journal-title":"npj Digit Med"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"797","DOI":"10.1016\/j.jclinepi.2009.02.005","article-title":"A review of solutions for diagnostic accuracy studies with an imperfect or missing reference standard","volume":"62","author":"Reitsma","year":"2009","journal-title":"J Clin Epidemiol"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"iii","DOI":"10.3310\/hta11500","article-title":"Evaluation of diagnostic tests when there is no gold standard. A review of methods","volume":"11","author":"Rutjes","year":"2007","journal-title":"Health Technol Assess"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"1391","DOI":"10.1186\/s12909-024-06399-7","article-title":"Large language models improve clinical decision making of medical students through patient simulation and structured feedback: a randomized controlled trial","volume":"24","author":"Br\u00fcgge","year":"2024","journal-title":"BMC Med Educ"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"458","DOI":"10.1093\/postmj\/qgae170","article-title":"ChatGPT versus expert feedback on clinical reasoning questions and their effect on learning: a randomized controlled trial","volume":"101","author":"\u00c7i\u00e7ek","year":"2025","journal-title":"Postgrad Med J"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1909864\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T04:23:44Z","timestamp":1786595024000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1909864\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,13]]},"references-count":30,"alternative-id":["10.3389\/fmed.2026.1909864"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1909864","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,13]]},"article-number":"1909864"}}