001047199 001__ 1047199
001047199 005__ 20251129202118.0
001047199 0247_ $$2doi$$a10.1186/s12911-025-03224-z
001047199 0247_ $$2datacite_doi$$a10.34734/FZJ-2025-04148
001047199 037__ $$aFZJ-2025-04148
001047199 082__ $$a610
001047199 1001_ $$00000-0002-3916-1085$$aE. Samadi, Moein$$b0
001047199 245__ $$aGPT-4o and the quest for machine learning interpretability in ICU risk of death prediction
001047199 260__ $$aLondon$$bBioMed Central$$c2025
001047199 3367_ $$2DRIVER$$aarticle
001047199 3367_ $$2DataCite$$aOutput Types/Journal article
001047199 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1764422013_29733
001047199 3367_ $$2BibTeX$$aARTICLE
001047199 3367_ $$2ORCID$$aJOURNAL_ARTICLE
001047199 3367_ $$00$$2EndNote$$aJournal Article
001047199 520__ $$aBackground:Clinical utilization of machine learning is hampered by the lack of interpretability inherent in most non-linear black box modeling approaches, reducing trust among clinicians and regulators. Advanced large language models offer a potential framework for integrating medical knowledge into these models, potentially enhancing their interpretability.Methods:A hybrid mechanistic/data-driven modeling framework is presented for developing an ICU risk of death prediction model for mechanically ventilated patients. In the mechanistic modeling part, GPT-4o is used to generate detailed medical feature descriptions, which are then aggregated into a comprehensive corpus and processed with TF-I DF vectorization. Fuzzy C-means clustering is subsequently applied to these vectorized features to identify significant mortality cause-specific feature clusters, and a physician reviewed the resulting clusters to validate their relevance to actionable insights for clinical decision support. In the data-driven part, the identified clusters inform the creation of XGBoost-based weak classifiers, whose outcomes are combined into a single XGBoost-based strong classifier through a hierarchically structured feed-forward network. This process results in a novel GPT hybrid model for ICU risk of death prediction.Results:This study enrolled 16,018 mechanically ventilated ICU patients, divided into derivation (12,758) and validation (3,260) cohorts, to develop and evaluate a GPT hybrid model for predicting in-ICU death. Leveraging GPT-4o, we implemented an automated process for clustering mortality cause-specific features, resulting in six feature clusters: Liver Failure, Infection, Renal Failure, Hypoxia, Cardiac Failure, and Mechanical Ventilation. This approach significantly improved upon previous manual methods, automating the reconstruction of structured hybrid models. While the GPT hybrid model showed similar predictive accuracy to a Global XGBoost model, it demonstrated superior interpretability and clinical relevance by incorporating a wider array of features and providing a hierarchical structure of feature importance aligned with medical knowledge.Conclusion:We introduce a novel approach to predicting in-ICU risk of death for mechanically ventilated patients using a GPT hybrid model. Our methodology demonstrates the potential of integrating large language models with traditional machine learning techniques to create interpretable and clinically relevant predictive models.
001047199 536__ $$0G:(DE-HGF)POF4-5112$$a5112 - Cross-Domain Algorithms, Tools, Methods Labs (ATMLs) and Research Groups (POF4-511)$$cPOF4-511$$fPOF IV$$x0
001047199 536__ $$0G:(DE-HGF)POF4-5111$$a5111 - Domain-Specific Simulation & Data Life Cycle Labs (SDLs) and Research Groups (POF4-511)$$cPOF4-511$$fPOF IV$$x1
001047199 536__ $$0G:(BMBF)01IS22095D$$aSDI-S - SDI-S: Smart Data Innovation Services - Experimentelle Erprobung und Entwicklung von KI-Dienstverbünden für Innovationen auf industriellen Daten (01IS22095D)$$c01IS22095D$$x2
001047199 588__ $$aDataset connected to CrossRef, Journals: juser.fz-juelich.de
001047199 7001_ $$0P:(DE-HGF)0$$aNikulina, Kateryna$$b1
001047199 7001_ $$0P:(DE-Juel1)185651$$aFritsch, Sebastian Johannes$$b2
001047199 7001_ $$00000-0003-3783-6605$$aSchuppert, Andreas$$b3$$eCorresponding author
001047199 773__ $$0PERI:(DE-600)2046490-3$$a10.1186/s12911-025-03224-z$$gVol. 25, no. 1, p. 373$$n1$$p373$$tBMC medical informatics and decision making$$v25$$x1472-6947$$y2025
001047199 8564_ $$uhttps://juser.fz-juelich.de/record/1047199/files/GPT-4o%20and%20the%20quest%20for%20machine%20learning%20interpretability%20in%20ICU%20risk%20of%20death%20prediction.pdf$$yOpenAccess
001047199 909CO $$ooai:juser.fz-juelich.de:1047199$$popenaire$$popen_access$$pVDB$$pdriver$$pdnbdelivery
001047199 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)185651$$aForschungszentrum Jülich$$b2$$kFZJ
001047199 9131_ $$0G:(DE-HGF)POF4-511$$1G:(DE-HGF)POF4-510$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5112$$aDE-HGF$$bKey Technologies$$lEngineering Digital Futures – Supercomputing, Data Management and Information Security for Knowledge and Action$$vEnabling Computational- & Data-Intensive Science and Engineering$$x0
001047199 9131_ $$0G:(DE-HGF)POF4-511$$1G:(DE-HGF)POF4-510$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5111$$aDE-HGF$$bKey Technologies$$lEngineering Digital Futures – Supercomputing, Data Management and Information Security for Knowledge and Action$$vEnabling Computational- & Data-Intensive Science and Engineering$$x1
001047199 9141_ $$y2025
001047199 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2024-12-11
001047199 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2024-12-11
001047199 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
001047199 915__ $$0StatID:(DE-HGF)0600$$2StatID$$aDBCoverage$$bEbsco Academic Search$$d2024-12-11
001047199 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bBMC MED INFORM DECIS : 2022$$d2024-12-11
001047199 915__ $$0StatID:(DE-HGF)0501$$2StatID$$aDBCoverage$$bDOAJ Seal$$d2024-04-10T15:34:47Z
001047199 915__ $$0StatID:(DE-HGF)0500$$2StatID$$aDBCoverage$$bDOAJ$$d2024-04-10T15:34:47Z
001047199 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2024-12-11
001047199 915__ $$0StatID:(DE-HGF)0700$$2StatID$$aFees$$d2024-12-11
001047199 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2024-12-11
001047199 915__ $$0StatID:(DE-HGF)9900$$2StatID$$aIF < 5$$d2024-12-11
001047199 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001047199 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bASC$$d2024-12-11
001047199 915__ $$0StatID:(DE-HGF)0561$$2StatID$$aArticle Processing Charges$$d2024-12-11
001047199 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2024-12-11
001047199 915__ $$0StatID:(DE-HGF)1110$$2StatID$$aDBCoverage$$bCurrent Contents - Clinical Medicine$$d2024-12-11
001047199 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2024-12-11
001047199 920__ $$lno
001047199 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x0
001047199 9201_ $$0I:(DE-Juel1)CASA-20230315$$kCASA$$lCenter for Advanced Simulation and Analytics$$x1
001047199 980__ $$ajournal
001047199 980__ $$aVDB
001047199 980__ $$aUNRESTRICTED
001047199 980__ $$aI:(DE-Juel1)JSC-20090406
001047199 980__ $$aI:(DE-Juel1)CASA-20230315
001047199 9801_ $$aFullTexts