{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,22]],"date-time":"2026-03-22T07:33:15Z","timestamp":1774164795631,"version":"3.50.1"},"reference-count":48,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,8,5]],"date-time":"2025-08-05T00:00:00Z","timestamp":1754352000000},"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. Digit. Health"],"abstract":"<jats:p>When a patient survives the first 24\u2009h in intensive care, outcome prediction is crucial for further treatment decisions. As recent advances have shown that Artificial Intelligence (AI) outperforms clinicians in prognostication, and especially generative AI has developed rapidly in the past ten years, this scoping review aimed to explore the use of generative AI models for outcome prediction in intensive care medicine. Of the 481 records found in the search, 119 studies were subjected to abstract screening and, when necessary, full-text review for eligibility assessment. Twenty-two studies and two review articles were finally included. The studies were categorized into three prototypical use cases for generative AI in outcome prediction in intensive care: (i) data augmentation, (ii) feature generation from unstructured data, and (iii) prediction by the generative model. In the first two use cases, the generative models worked together with downstream predictive models. In the third use case, the generative models made the predictions themselves. The studies within data augmentation either fell into the area of compensation for class imbalances by producing additional synthetic cases or imputation of missing values. Overall, Generative Adversarial Network (GAN) was the most frequently used technology (8\/22 studies; 36%), followed by Generative Pretrained Transformer (GPT) (7\/22 studies; 32%). All publications except one were from the last four years. This review shows that generative AI has immense potential in the future, and continuous monitoring of new technologies is necessary to ensure that patients receive the best possible care.<\/jats:p>","DOI":"10.3389\/fdgth.2025.1633458","type":"journal-article","created":{"date-parts":[[2025,8,5]],"date-time":"2025-08-05T05:24:25Z","timestamp":1754371465000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Applications of generative artificial intelligence in outcome prediction in intensive care medicine\u2014a scoping review"],"prefix":"10.3389","volume":"7","author":[{"given":"Tanja","family":"Stamm","sequence":"first","affiliation":[]},{"given":"Mohamed","family":"Bader-El-Den","sequence":"additional","affiliation":[]},{"given":"James","family":"McNicholas","sequence":"additional","affiliation":[]},{"given":"Jim","family":"Briggs","sequence":"additional","affiliation":[]},{"given":"Peng","family":"Zhao","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2025,8,5]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1186\/s13054-024-04937-9","article-title":"Past, present, and future of sustainable intensive care: narrative review and a large hospital system experience","volume":"28","author":"Masud","year":"2024","journal-title":"Crit Care"},{"key":"B2","doi-asserted-by":"publisher","first-page":"1871","DOI":"10.1097\/CCM.0000000000004659","article-title":"Prediction models for physical, cognitive, and mental health impairments after critical illness: a systematic review and critical appraisal","volume":"48","author":"Haines","year":"2020","journal-title":"Crit Care Med"},{"key":"B3","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1016\/j.ijmedinf.2017.10.002","article-title":"Early hospital mortality prediction of intensive care unit patients using an ensemble learning approach","volume":"108","author":"Awad","year":"2017","journal-title":"Int J Med Inform"},{"key":"B4","doi-asserted-by":"publisher","first-page":"1043","DOI":"10.1177\/1460458219850323","article-title":"Predicting hospital mortality for intensive care unit patients: time-series analysis","volume":"26","author":"Awad","year":"2020","journal-title":"Health Informatics J"},{"key":"B5","doi-asserted-by":"publisher","first-page":"12912","DOI":"10.1038\/s41598-022-17091-5","article-title":"Prediction algorithm for ICU mortality and length of stay using machine learning","volume":"12","author":"Iwase","year":"2022","journal-title":"Sci Rep"},{"key":"B6","doi-asserted-by":"publisher","first-page":"109834","DOI":"10.1016\/j.compbiomed.2025.109834","article-title":"Generative AI for synthetic data across multiple medical modalities: a systematic review of recent developments and challenges","volume":"189","author":"Ibrahim","year":"2025","journal-title":"Comput Biol Med"},{"key":"B7","article-title":"Large language models (LLMs) on tabular data: prediction, generation, and understanding\u2013a survey","author":"Fang","year":""},{"key":"B8","article-title":"Generative adversarial nets","author":"Goodfellow","year":"2014","journal-title":"arXiv"},{"key":"B9","article-title":"Auto-encoding variational bayes","author":"Kingma","year":""},{"key":"B10","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":""},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1706.03762","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"arXiv"},{"key":"B12","article-title":"Stochastic parrots or ICU experts? Large language models in critical care medicine: a scoping review","author":"Shi","year":""},{"key":"B13","doi-asserted-by":"publisher","first-page":"55","DOI":"10.3390\/nursrep15020055","article-title":"Exploring applications of artificial intelligence in critical care nursing: a systematic review","volume":"15","author":"Porcellato","year":"2025","journal-title":"Nurs Rep"},{"key":"B14","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1080\/1364557032000119616","article-title":"Scoping studies: towards a methodological framework","volume":"8","author":"Arksey","year":"2005","journal-title":"Int J Soc Res Methodol"},{"key":"B15","doi-asserted-by":"publisher","first-page":"9744","DOI":"10.1182\/blood-2022-168646","article-title":"Synthetic data generation by artificial intelligence to accelerate translational research and precision medicine in hematological malignancies","volume":"140","author":"D\u2019Amico","year":"2022","journal-title":"Blood"},{"key":"B16","doi-asserted-by":"publisher","first-page":"e082505","DOI":"10.1136\/bmj-2024-082505","article-title":"Probast+ AI: an updated quality, risk of bias, and applicability assessment tool for prediction models using regression or artificial intelligence methods","volume":"388","author":"Moons","year":"2025","journal-title":"BMJ"},{"key":"B17","doi-asserted-by":"publisher","first-page":"n160","DOI":"10.1136\/bmj.n160","article-title":"Prisma 2020 explanation and elaboration: updated guidance and exemplars for reporting systematic reviews","volume":"372","author":"Page","year":"2021","journal-title":"BMJ"},{"key":"B18","doi-asserted-by":"crossref","DOI":"10.1109\/ICTAI59109.2023.00109","article-title":"MedCT-BERT: multimodal mortality prediction using medical ConvTransformer-BERT model","author":"Zhang","year":""},{"key":"B19","doi-asserted-by":"publisher","first-page":"76403","DOI":"10.1109\/ACCESS.2023.3296147","article-title":"Predicting ICU mortality based on generative adversarial nets and ensemble methods","volume":"11","author":"Wei","year":"2023","journal-title":"IEEE Access"},{"key":"B20","doi-asserted-by":"publisher","first-page":"e13200","DOI":"10.1016\/j.heliyon.2023.e13200","article-title":"Mortality prediction among ICU inpatients based on MIMIC-III database results from the conditional medical generative adversarial network","volume":"9","author":"Yang","year":"2023","journal-title":"Heliyon"},{"key":"B21","doi-asserted-by":"crossref","DOI":"10.1109\/ICWR61162.2024.10533368","article-title":"Prediction of neonatal infections using machine learning techniques.","author":"Shariat","year":""},{"key":"B22","doi-asserted-by":"crossref","DOI":"10.1109\/ICBEA62825.2024.00017","article-title":"A generative adversarial network-based approach for facial pain assessment.","author":"Wang","year":""},{"key":"B23","doi-asserted-by":"publisher","first-page":"122702","DOI":"10.1109\/ACCESS.2024.3417176","article-title":"Alleviation of health data poverty for skin lesions using ACGAN: systematic review","volume":"12","author":"Ravikumar","year":"2024","journal-title":"IEEE Access"},{"key":"B24","doi-asserted-by":"crossref","DOI":"10.1109\/BSEC.2013.6618491","article-title":"Prediction of ICU in-hospital mortality using a deep boltzmann machine and dropout neural net","author":"Ryan","year":""},{"key":"B25","doi-asserted-by":"publisher","first-page":"134466","DOI":"10.1109\/ACCESS.2022.3230324","article-title":"Improving sepsis prediction performance using conditional recurrent adversarial networks","volume":"10","author":"Apalak","year":"2022","journal-title":"IEEE Access"},{"key":"B26","doi-asserted-by":"crossref","DOI":"10.1109\/ICPR48806.2021.9412112","article-title":"End-to-end multi-task learning of missing value imputation and forecasting in time-series data","author":"Kim","year":""},{"key":"B27","doi-asserted-by":"publisher","first-page":"ocae271","DOI":"10.1093\/jamia\/ocae271","article-title":"DySurv: dynamic deep learning model for survival analysis with conditional variational inference","author":"Mesinovic","year":"2024","journal-title":"J Am Med Inform Assoc"},{"key":"B28","doi-asserted-by":"crossref","DOI":"10.1109\/EMBC46164.2021.9629559","article-title":"Unsupervised learning approach for predicting sepsis onset in ICU patients","author":"Ramos","year":""},{"key":"B29","doi-asserted-by":"crossref","DOI":"10.1109\/IAICT62357.2024.10617530","article-title":"Anomaly detection in wireless body area networks using generative adversarial networks","author":"Rao","year":""},{"key":"B30","article-title":"Reliability in AI-assisted critical care: assessing large language model robustness and instruction following for cardiac arrest identification","author":"Vurgun","year":""},{"key":"B31","doi-asserted-by":"publisher","first-page":"1455","DOI":"10.1109\/JBHI.2024.3502575","article-title":"RespBERT: a multi-site validation of a natural language processing algorithm, of radiology notes to identify Acute Respiratory Distress Syndrome (ARDS)","volume":"29","author":"Pathak","year":"2025","journal-title":"IEEE J Biomed Health Inf"},{"key":"B32","doi-asserted-by":"publisher","first-page":"1018","DOI":"10.1007\/s00134-023-07128-2","article-title":"Assessing the usefulness of a large language model to query and summarize unstructured medical notes in intensive care","volume":"49","author":"Madden","year":"2023","journal-title":"Intensive Care Med"},{"key":"B33","doi-asserted-by":"publisher","first-page":"ooae137","DOI":"10.1093\/jamiaopen\/ooae137","article-title":"An empirical study of using radiology reports and images to improve intensive care unit mortality prediction","volume":"8","author":"Lin","year":"2024","journal-title":"JAMIA open"},{"key":"B34","doi-asserted-by":"publisher","first-page":"2532","DOI":"10.1002\/ejhf.3410","article-title":"In-hospital course of patients with heart failure with improved ejection fraction in the DELIVER trial","volume":"26","author":"Pabon","year":"2024","journal-title":"Eur J Heart Fail"},{"key":"B35","doi-asserted-by":"crossref","DOI":"10.1109\/ISCMI63661.2024.10851557","article-title":"A generative frailty index based explainable approach for hospital readmission prediction","author":"Parizad","year":""},{"key":"B36","doi-asserted-by":"publisher","first-page":"928","DOI":"10.1001\/jamasurg.2024.1621","article-title":"Large language model capabilities in perioperative risk prediction and prognostication","volume":"159","author":"Chung","year":"2024","journal-title":"JAMA Surg"},{"key":"B37","doi-asserted-by":"publisher","first-page":"100587","DOI":"10.1016\/j.resplu.2024.100587","article-title":"Prediction of outcomes after cardiac arrest by a generative artificial intelligence model","volume":"18","author":"Amacher","year":"2024","journal-title":"Resusc Plus"},{"key":"B38","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1093\/jamia\/ocae287","article-title":"LCD benchmark: long clinical document benchmark on mortality prediction for language models","volume":"32","author":"Yoon","year":"2025","journal-title":"J Am Med Inform Assoc"},{"key":"B39","article-title":"DeLLiriuM: a large language model for delirium prediction in the ICU using structured EHR","author":"Contreras","year":""},{"key":"B40","doi-asserted-by":"crossref","DOI":"10.1109\/ICAIT61638.2024.10690733","article-title":"A real-time medical report analysis and AI-powered diagnosis: a cloud-based solution for improved patient care","author":"Mahalakshmi","year":""},{"key":"B41","doi-asserted-by":"publisher","first-page":"108060","DOI":"10.1016\/j.cmpb.2024.108060","article-title":"A transformer-based diffusion probabilistic model for heart rate and blood pressure forecasting in intensive care unit","volume":"246","author":"Chang","year":"2024","journal-title":"Comput Methods Programs Biomed"},{"key":"B42","doi-asserted-by":"publisher","first-page":"102287","DOI":"10.1016\/j.outlook.2024.102287","article-title":"Unlocking ChatGPT\u2019s potential and challenges in intensive care nursing education and practice: a systematic review with narrative synthesis","volume":"72","author":"Kucukkaya","year":"2024","journal-title":"Nurs Outlook"},{"key":"B43","doi-asserted-by":"publisher","first-page":"366","DOI":"10.1093\/ehjdh\/ztad043","article-title":"Chatgpt fails the test of evidence-based medicine","volume":"4","author":"Haverkamp","year":"2023","journal-title":"Eur Heart J Digit Health"},{"key":"B44","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1038\/s41746-024-01079-8","article-title":"A critical assessment of using chatgpt for extracting structured data from clinical notes","volume":"7","author":"Huang","year":"2024","journal-title":"npj Digit Med"},{"key":"B45","doi-asserted-by":"crossref","DOI":"10.1109\/EMBC40787.2023.10340232","article-title":"Unlocking the power of EHRs: harnessing unstructured data for machine learning-based outcome predictions","author":"Noaeen","year":""},{"key":"B46","doi-asserted-by":"publisher","first-page":"101640","DOI":"10.1016\/j.jocs.2022.101640","article-title":"From missing data imputation to data generation","volume":"61","author":"Neves","year":"2022","journal-title":"J Comput Sci"},{"key":"B47","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41746-025-01671-6","article-title":"Patient perceptions of empathy in physician and artificial intelligence chatbot responses to patient questions about cancer","volume":"8","author":"Chen","year":"2025","journal-title":"npj Digit Med"},{"key":"B48","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12874-016-0116-4","article-title":"A scoping review on the conduct and reporting of scoping reviews","volume":"16","author":"Tricco","year":"2016","journal-title":"BMC Med Res Methodol"}],"container-title":["Frontiers in Digital Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2025.1633458\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,5]],"date-time":"2025-08-05T05:24:27Z","timestamp":1754371467000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2025.1633458\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,5]]},"references-count":48,"alternative-id":["10.3389\/fdgth.2025.1633458"],"URL":"https:\/\/doi.org\/10.3389\/fdgth.2025.1633458","relation":{},"ISSN":["2673-253X"],"issn-type":[{"value":"2673-253X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,5]]},"article-number":"1633458"}}