{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T06:17:46Z","timestamp":1787811466206,"version":"build-2784847793"},"reference-count":43,"publisher":"Wiley","license":[{"start":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T00:00:00Z","timestamp":1787702400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"},{"start":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T00:00:00Z","timestamp":1787702400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Clinical Anatomy"],"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>Generative artificial intelligence (GenAI) can perform strongly on written anatomy examinations, but whether such scores represent anatomical competence remains uncertain because results vary with the model, assessment, protocol, modality, scoring, and comparator. We synthesized studies evaluating GenAI as the examinee in university\u2010level human anatomy assessments and proposed MATRIX\u2010Anatomy, a reporting and interpretive framework not yet externally validated. PubMed, Scopus, and Web of Science Core Collection were searched for records published from January 2022 to 11 July 2026. Eligible studies used university examinations, course item banks, or curriculum\u2010aligned undergraduate benchmarks and reported quantitative performance. Three reviewers completed study selection, data extraction, and narrative synthesis by consensus. Of 115 records, 51 duplicates were removed, 64 were screened, and 15 studies were included. Leading systems scored 76% to 98% on text\u2010based multiple\u2010choice assessments. On a fixed 120\u2010item set, accuracy increased from 45.8% with ChatGPT\u20103.5 to 86.7% with ChatGPT\u20105. Human comparisons were mixed. Visuospatial performance was weaker: ChatGPT\u20104o identified 22.26% of cadaveric structures after up to three attempts; ChatGPT\u20104.0 achieved 17.3% end\u2010to\u2010end accuracy on image\u2010based anatomy; and ChatGPT\u20105.1 reached 74.4% on a surgical\u2010anatomy subset. Repeated runs revealed volatility and consistently incorrect responses. The findings support supervised formative use with authoritative verification and retention of secure supervised, oral, constructed\u2010response, visuospatial, and practical assessments. MATRIX\u2010Anatomy specifies six domains (Model, Assessment, Testing protocol, Reference standard, Input, and eXternal validity) for reproducible reporting and defensible interpretation, but requires formal external validation.<\/jats:p>","DOI":"10.1002\/ca.70218","type":"journal-article","created":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T05:29:22Z","timestamp":1787808562000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Generative Artificial Intelligence Performance on University\u2010Level Human Anatomy Examinations: A Structured Narrative Review and Proposed\n                    <scp>MATRIX<\/scp>\n                    \u2010Anatomy Framework"],"prefix":"10.1002","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2599-8474","authenticated-orcid":false,"given":"Juan A.","family":"Sanchis\u2010Gimeno","sequence":"first","affiliation":[{"name":"GIAVAL Research Group, Faculty of Medicine University of Valencia  Valencia Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7634-012X","authenticated-orcid":false,"given":"Juan Jos\u00e9","family":"Valenzuela\u2010Fuenzalida","sequence":"additional","affiliation":[{"name":"Departamento de Morfolog\u00eda, Facultad de Medicina Universidad Andr\u00e9s Bello  Vi\u00f1a del Mar Chile"},{"name":"Departamento de Ciencias Qu\u00edmicas y Biol\u00f3gicas, Facultad de Ciencias de la Salud Universidad Bernardo O'Higgins  Santiago Chile"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7697-419X","authenticated-orcid":false,"given":"Alejandro","family":"Bruna\u2010Mej\u00edas","sequence":"additional","affiliation":[{"name":"Departamento de Morfolog\u00eda, Facultad de Medicina Universidad Andr\u00e9s Bello  Vi\u00f1a del Mar Chile"},{"name":"Departamento de Ciencias y Geograf\u00eda, Facultad de Ciencias Naturales y Exactas Universidad de Playa Ancha  Valpara\u00edso Chile"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1781-062X","authenticated-orcid":false,"given":"Mathias","family":"Orellana\u2010Donoso","sequence":"additional","affiliation":[{"name":"Escuela de Medicina Universidad Finis Terrae  Santiago Chile"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3519-9625","authenticated-orcid":false,"given":"Glen J.","family":"Paton","sequence":"additional","affiliation":[{"name":"Department of Chiropractic, Faculty of Health Sciences University of Johannesburg  Johannesburg South Africa"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0957-1067","authenticated-orcid":false,"given":"Shahed","family":"Nalla","sequence":"additional","affiliation":[{"name":"Department of Human Anatomy and Physiology, Faculty of Health Sciences University of Johannesburg  Johannesburg South Africa"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,8,26]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.1002\/ca.24243"},{"key":"e_1_2_10_3_1","volume-title":"Standards for Educational and Psychological Testing","author":"American Educational Research Association","year":"2014"},{"key":"e_1_2_10_4_1","doi-asserted-by":"publisher","DOI":"10.1186\/s41073\u2010019\u20100064\u20108"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598\u2010025\u201022437\u2010w"},{"key":"e_1_2_10_6_1","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.l6890"},{"key":"e_1_2_10_7_1","doi-asserted-by":"publisher","DOI":"10.1002\/ca.70076"},{"key":"e_1_2_10_8_1","doi-asserted-by":"publisher","DOI":"10.1002\/ca.22835"},{"key":"e_1_2_10_9_1","doi-asserted-by":"publisher","DOI":"10.1111\/joa.12782"},{"key":"e_1_2_10_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2013.12.002"},{"key":"e_1_2_10_11_1","doi-asserted-by":"publisher","DOI":"10.1152\/advan.00191.2024"},{"key":"e_1_2_10_12_1","doi-asserted-by":"publisher","DOI":"10.1080\/08998280.2026.2612683"},{"key":"e_1_2_10_13_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591\u2010024\u201003425\u20105"},{"key":"e_1_2_10_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s40670\u2010025\u201002303\u20100"},{"key":"e_1_2_10_15_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12909\u2010026\u201008656\u20103"},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.1111\/jedm.12000"},{"key":"e_1_2_10_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.lindif.2023.102274"},{"key":"e_1_2_10_18_1","doi-asserted-by":"publisher","DOI":"10.12669\/pjms.41.12.12855"},{"key":"e_1_2_10_19_1","doi-asserted-by":"crossref","first-page":"528","DOI":"10.18653\/v1\/2024.findings-emnlp.30","volume-title":"Findings of the Association for Computational Linguistics: EMNLP 2024","author":"Li Y.","year":"2024"},{"key":"e_1_2_10_20_1","volume-title":"Assessment Reform for the Age of Artificial Intelligence","author":"Lodge J. M.","year":"2023"},{"key":"e_1_2_10_21_1","doi-asserted-by":"publisher","DOI":"10.1002\/ase.70256"},{"key":"e_1_2_10_22_1","doi-asserted-by":"publisher","DOI":"10.1111\/joa.13133"},{"key":"e_1_2_10_23_1","doi-asserted-by":"publisher","DOI":"10.1002\/ca.24244"},{"key":"e_1_2_10_24_1","doi-asserted-by":"publisher","DOI":"10.11613\/BM.2012.031"},{"key":"e_1_2_10_25_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41415\u2010023\u20106286\u20107"},{"key":"e_1_2_10_26_1","doi-asserted-by":"publisher","DOI":"10.1002\/ca.70115"},{"key":"e_1_2_10_27_1","volume-title":"Guidance for Generative AI in Education and Research","author":"Miao F.","year":"2023"},{"key":"e_1_2_10_28_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pmed.1000217"},{"key":"e_1_2_10_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00276\u2010025\u201003769\u20108"},{"key":"e_1_2_10_30_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1708274114"},{"key":"e_1_2_10_31_1","doi-asserted-by":"publisher","DOI":"10.1002\/ase.70255"},{"key":"e_1_2_10_32_1","doi-asserted-by":"publisher","DOI":"10.53761\/q3azde36"},{"key":"e_1_2_10_33_1","doi-asserted-by":"publisher","DOI":"10.1002\/nur.20147"},{"key":"e_1_2_10_34_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13643\u2010020\u201001542\u2010z"},{"key":"e_1_2_10_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00276\u2010010\u20100748\u20108"},{"key":"e_1_2_10_36_1","doi-asserted-by":"publisher","DOI":"10.1097\/ACM.0000000000005769"},{"key":"e_1_2_10_37_1","doi-asserted-by":"publisher","DOI":"10.1177\/23821205261449387"},{"key":"e_1_2_10_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00276\u2010025\u201003707\u20108"},{"key":"e_1_2_10_39_1","doi-asserted-by":"publisher","DOI":"10.1111\/joa.12405"},{"key":"e_1_2_10_40_1","doi-asserted-by":"publisher","DOI":"10.1055\/s\u20100045\u20101808254"},{"key":"e_1_2_10_41_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1365\u20102929.2005.02094.x"},{"key":"e_1_2_10_42_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13104\u2010015\u20101603\u20100"},{"key":"e_1_2_10_43_1","doi-asserted-by":"publisher","DOI":"10.1002\/ca.23953"},{"key":"e_1_2_10_44_1","first-page":"23650","article-title":"Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs","volume":"2024","author":"Xiong M.","year":"2024","journal-title":"International Conference on Learning Representations"}],"container-title":["Clinical Anatomy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/ca.70218","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/ca.70218","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/ca.70218","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T05:29:24Z","timestamp":1787808564000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/ca.70218"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,26]]},"references-count":43,"alternative-id":["10.1002\/ca.70218"],"URL":"https:\/\/doi.org\/10.1002\/ca.70218","archive":["Portico"],"relation":{},"ISSN":["0897-3806","1098-2353"],"issn-type":[{"value":"0897-3806","type":"print"},{"value":"1098-2353","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,26]]},"assertion":[{"value":"2026-07-14","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-08-20","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-08-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"ca.70218"}}