{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T15:04:55Z","timestamp":1790262295909,"version":"4.1.0"},"reference-count":30,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T00:00:00Z","timestamp":1753315200000},"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. Neurol."],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>An analysis of the prognostic ability of the large language model (LLM) Generative Pre-trained Transformer (GPT) to predict short-term survival and functional outcomes in patients with malignant middle cerebral artery (MCA) infarction following decompressive hemicraniectomy.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>This retrospective study included 100 patients with malignant MCA infarction who underwent decompressive craniectomy (DC). GPT-4 and GPT-4 Omni were used to predict patient outcomes based on 20 patient-specific factors. Each version of GPT was tested with and without context enrichment (CE). CE versions were provided with the current AHA\/ASA 2019 guidelines and meta-analyses of RCTs to inform decision-making. The real-life outcome of the patients, measured by the modified Rankin Scale (mRS), served as a reference. The following endpoints were evaluated: survival during inpatient stay, achievement of a functional status of mRS 0\u20134 at discharge, and at 3-, 6-, and 12-months post-discharge. We analyzed the prognostic prediction of GPT by calculating the area under the curve (AUC) and determining the optimal cutoff using the Youden index for divergent prediction outcomes. After dichotomization according to the cutoff set, a chi-squared test (two-sided) was performed.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>GPT-4 and GPT-4 Omni demonstrated the ability to estimate survival during in-hospital stay. In both versions, the CE GPT outperformed the non-CE versions. GPT-4 Omni (CE) achieved an AUC of 0.67 (95% CI: 0.54\u20130.79; <jats:italic>p<\/jats:italic> = 0.002), while GPT-4 (CE) reached an AUC of 0.70 (95% CI: 0.57\u20130.82; <jats:italic>p<\/jats:italic> = 0.018). GPT-4 also achieved statistical significance even without CE (AUC of 0.66; 95% CI: 0.53\u20130.78; <jats:italic>p<\/jats:italic> = 0.018). In contrast, the non-CE version of GPT-4 Omni did not reach significance in predicting the survival of hospitalization (AUC of 0.60; 95% CI: 0.48\u20130.73; <jats:italic>p<\/jats:italic> = 0.07). For questions regarding the functional outcome of patients, neither version of GPT was able to make a sufficient prognostic prediction. However, when provided with the pre-stroke mRS, GPT-4 Omni was able to predict the mRS at discharge (<jats:italic>p<\/jats:italic> = 0.01; Pearson's correlation coefficient = 0.696).<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>The study shows the already existing high potential of AI in predicting short-term outcomes. It also shows the existing limitations for the evaluation of more complex questions, such as functional outcomes.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fneur.2025.1603536","type":"journal-article","created":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T08:51:53Z","timestamp":1753347113000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["GPT-based prediction of short-term survival following decompressive hemicraniectomy in malignant middle cerebral artery infarction"],"prefix":"10.3389","volume":"16","author":[{"given":"Sebastian","family":"Lehmann","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martin","family":"Vychopen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erdem","family":"G\u00fcresir","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Johannes","family":"Wach","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,7,24]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"2023","DOI":"10.1101\/2023.01.30.23285067","article-title":"The diagnostic and triage accuracy of the GPT-3 artificial intelligence model","volume":"1","author":"Levine","year":"2023","journal-title":"medRxiv."},{"key":"B2","doi-asserted-by":"publisher","first-page":"635","DOI":"10.1016\/j.nicl.2014.02.003","article-title":"Prediction of stroke thrombolysis outcome using CT brain machine learning","volume":"4","author":"Bentley","year":"2014","journal-title":"Neuroimage Clin."},{"key":"B3","doi-asserted-by":"publisher","first-page":"e88225","DOI":"10.1371\/journal.pone.0088225","article-title":"Machine learning for outcome prediction of acute ischemic stroke post intra-arterial therapy","volume":"9","author":"Asadi","year":"2014","journal-title":"PLoS ONE."},{"key":"B4","doi-asserted-by":"publisher","first-page":"942","DOI":"10.1097\/CCM.0000000000006236","article-title":"Evaluation of ChatGPT in predicting 6-month outcomes after traumatic brain injury","volume":"52","author":"Gakuba","year":"2024","journal-title":"Crit Care Med."},{"key":"B5","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1007\/s10143-025-03194-w","article-title":"Beyond traditional prognostics: integrating RAG-enhanced AtlasGPT and ChatGPT 4.0 into aneurysmal subarachnoid hemorrhage outcome prediction","volume":"48","author":"Basaran","year":"2024","journal-title":"Neurosurg Rev."},{"key":"B6","doi-asserted-by":"publisher","first-page":"3331","DOI":"10.1161\/STROKEAHA.119.027708","article-title":"Guidelines for the early management of patients with acute ischemic stroke: 2019 update to the 2018 guidelines for the early management of acute ischemic stroke","volume":"50","author":"Warner","year":"2019","journal-title":"Stroke."},{"key":"B7","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.neunet.2014.09.003","article-title":"Deep learning in neural networks: an overview","volume":"61","author":"Schmidhuber","year":"2015","journal-title":"Neural Netw."},{"key":"B8","doi-asserted-by":"publisher","first-page":"1346","DOI":"10.1007\/s12262-023-03727-x","article-title":"ChatGPT in surgical practice\u2014a new kid on the block","volume":"85","author":"Bhattacharya","year":"2023","journal-title":"Indian J Surg."},{"key":"B9","doi-asserted-by":"publisher","first-page":"e1216","DOI":"10.1002\/ctm2.1216","article-title":"The potential impact of ChatGPT in clinical and translational medicine","volume":"13","author":"Xue","year":"2023","journal-title":"Clin Transl Med."},{"key":"B10","doi-asserted-by":"publisher","first-page":"693","DOI":"10.3171\/jns.2001.94.5.0693","article-title":"Suboptimum hemicraniectomy as a cause of additional cerebral lesions in patients with malignant infarction of the middle cerebral artery","volume":"94","author":"Wagner","year":"2001","journal-title":"J Neurosurg."},{"key":"B11","doi-asserted-by":"publisher","first-page":"17","DOI":"10.3892\/br.2023.1599","article-title":"CRP as a potential predictor of outcome in acute ischemic stroke","volume":"18","author":"Bian","year":"2023","journal-title":"Biomed Rep."},{"key":"B12","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1016\/j.jcrc.2013.11.008","article-title":"The impact of low hemoglobin levels and transfusion on critical care patients with severe ischemic stroke: STroke: RelevAnt impact of HemoGlobin, Hematocrit and Transfusion (STRAIGHT)\u2013an observational study","volume":"29","author":"Kellert","year":"2014","journal-title":"J Crit Care."},{"key":"B13","doi-asserted-by":"publisher","first-page":"1096","DOI":"10.1177\/0271678X17718693","article-title":"Infarct volume predicts outcome after decompressive hemicraniectomy for malignant hemispheric stroke","volume":"38","author":"Hecht","year":"2018","journal-title":"J Cereb Blood Flow Metab."},{"key":"B14","doi-asserted-by":"publisher","first-page":"201","DOI":"10.3389\/fneur.2020.00201","article-title":"Leukocyte counts and ratios are predictive of stroke outcome and hemorrhagic complications independently of infections","volume":"11","author":"Semerano","year":"2020","journal-title":"Front Neurol."},{"key":"B15","doi-asserted-by":"publisher","first-page":"731","DOI":"10.1080\/09537104.2019.1680826","article-title":"Platelet count and mean volume in acute stroke: a systematic review and meta-analysis","volume":"31","author":"Sadeghi","year":"2020","journal-title":"Platelets."},{"key":"B16","unstructured":"2025"},{"key":"B17","doi-asserted-by":"publisher","first-page":"5237693","DOI":"10.1155\/2018\/5237693","article-title":"Estimation of the craniectomy surface area by using postoperative images","volume":"2018","author":"Ho","year":"2018","journal-title":"Int J Biomed Imaging."},{"key":"B18","doi-asserted-by":"publisher","first-page":"3054","DOI":"10.1161\/STROKEAHA.121.034480","article-title":"Standardized nomenclature for modified rankin scale global disability outcomes: consensus recommendations from stroke therapy academic industry roundtable XI","volume":"52","author":"Saver","year":"2021","journal-title":"Stroke."},{"key":"B19","doi-asserted-by":"publisher","first-page":"2506","DOI":"10.1161\/STROKEAHA.107.485235","article-title":"Sequential-design, multicenter, randomized, controlled trial of early decompressive craniectomy in malignant middle cerebral artery infarction (DECIMAL Trial)","volume":"38","author":"Vahedi","year":"2007","journal-title":"Stroke."},{"key":"B20","doi-asserted-by":"publisher","first-page":"326","DOI":"10.1016\/S1474-4422(09)70047-X","article-title":"Surgical decompression for space-occupying cerebral infarction (the hemicraniectomy after middle cerebral artery infarction with life-threatening edema trial HAMLET): a multicentre, open, randomised trial","volume":"8","author":"Hofmeijer","year":"2009","journal-title":"Lancet Neurol."},{"key":"B21","doi-asserted-by":"publisher","first-page":"2518","DOI":"10.1161\/STROKEAHA.107.485649","article-title":"Decompressive surgery for the treatment of malignant infarction of the middle cerebral artery (DESTINY): a randomized, controlled trial","volume":"38","author":"J\u00fcttler","year":"2007","journal-title":"Stroke."},{"key":"B22","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1111\/j.1747-4949.2010.00544.x","article-title":"DESTINY II: DEcompressive surgery for the treatment of malignant INfarction of the middle cerebral arterY II","volume":"6","author":"J\u00fcttler","year":"2011","journal-title":"Int J Stroke."},{"key":"B23","doi-asserted-by":"publisher","first-page":"14119","DOI":"10.1038\/s41598-025-98949-2","article-title":"Evaluating the performance of GPT-3.5, GPT-4, and GPT-4o in the Chinese national medical licensing examination","volume":"15","author":"Luo","year":"2025","journal-title":"Sci Rep"},{"key":"B24","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1016\/S1474-4422(07)70036-4","article-title":"Early decompressive surgery in malignant infarction of the middle cerebral artery: a pooled analysis of three randomised controlled trials","volume":"6","author":"Vahedi","year":"2007","journal-title":"Lancet Neurol."},{"key":"B25","doi-asserted-by":"publisher","first-page":"77","DOI":"10.14797\/mdcvj.1290","article-title":"ChatGPT and artificial intelligence in hospital level research: potential, precautions, and prospects","volume":"19","author":"Arshad","year":"2023","journal-title":"Methodist Debakey Cardiovasc J."},{"key":"B26","doi-asserted-by":"publisher","first-page":"e37432","DOI":"10.7759\/cureus.37432","article-title":"Exploring the boundaries of reality: investigating the phenomenon of artificial intelligence hallucination in scientific writing through ChatGPT references","volume":"15","author":"Athaluri","year":"2023","journal-title":"Cureus."},{"key":"B27","first-page":"282","article-title":"Investigating the perception of the future in GPT-3,\u22123.5 and GPT-4","author":"Kozachek","year":"2023"},{"key":"B28","doi-asserted-by":"publisher","first-page":"4041","DOI":"10.3390\/cancers14164041","article-title":"An artificial intelligence-based tool for data analysis and prognosis in cancer patients: results from the clarify study","volume":"14","author":"Torrente","year":"2022","journal-title":"Cancers"},{"key":"B29","doi-asserted-by":"publisher","first-page":"85","DOI":"10.3171\/2023.8.PEDS2352","article-title":"An online calculator using machine learning for predicting survival in pediatric patients with medulloblastoma","volume":"33","author":"Kuo","year":"2024","journal-title":"J Neurosurg Pediatr."},{"key":"B30","unstructured":"2025"}],"container-title":["Frontiers in Neurology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2025.1603536\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T08:51:54Z","timestamp":1753347114000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2025.1603536\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,24]]},"references-count":30,"alternative-id":["10.3389\/fneur.2025.1603536"],"URL":"https:\/\/doi.org\/10.3389\/fneur.2025.1603536","relation":{},"ISSN":["1664-2295"],"issn-type":[{"value":"1664-2295","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,24]]},"article-number":"1603536"}}