{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T05:54:10Z","timestamp":1783662850942,"version":"3.55.0"},"reference-count":33,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Med Inform"],"abstract":"\n Background<\/jats:title>\n Predicting enterocutaneous fistula (ECF)\u2013associated sepsis and mortality poses significant challenges in digital health care due to the disease\u2019s complexity and heterogeneous clinical manifestations. Current approaches that rely on single-modal data or traditional scoring systems often fail to capture the intricate immune-inflammatory dynamics and multisystem involvement in patients with ECF.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aims to develop an artificial intelligence (AI)\u2013driven multimodal fusion model integrating clinical, imaging, and transcriptomic data for early prediction of ECF-associated sepsis and 28-day mortality, addressing the limitations of conventional single-dimensional models.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n This study leveraged publicly available datasets (Medical Information Mart for Intensive Care III [MIMIC-III], electronic Intensive Care Unit [eICU], and The Cancer Genome Atlas) to construct a multimodal framework. Clinical parameters were processed using Extreme Gradient Boosting, abdominal imaging features were extracted via convolutional neural networks, and transcriptomic profiles were analyzed with variational autoencoders. A Transformer-based fusion network was employed for joint prediction and validated through cross-validation and external testing. Key features were identified using Shapley Additive Explanations and Local Interpretable Model-Agnostic Explanations interpretability algorithms, while immune regulatory mechanisms were explored via weighted gene co-expression network analysis.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n The multimodal model achieved an area under the curve (AUC) of 0.89 for predicting sepsis and 28-day mortality, outperforming unimodal models (clinical-only model, AUC 0.72, and imaging-only model, AUC 0.78). Critical predictors included Sequential Organ Failure Assessment score, lactate levels, intra-abdominal free fluid on imaging, and immunoregulatory genes (programmed death-ligand 1 [PD-L1] and indoleamine 2,3-dioxygenase 1 [IDO1]). Mechanistic analysis revealed distinct immune reprogramming in patients with sepsis, characterized by increased regulatory T cells and M2 macrophages, along with downregulated cluster of differentiation 8+ (CD8+) T cells.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n This multimodal AI model offers an innovative digital solution in medical informatics, enabling precise early risk stratification for ECF-associated sepsis. By integrating multisource data and providing interpretable insights into immune-inflammatory pathways, the model enhances health care quality for patients with ECF and paves the way for personalized intervention strategies.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/79985","type":"journal-article","created":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:50:06Z","timestamp":1777571406000},"page":"e79985","source":"Crossref","is-referenced-by-count":2,"title":["Enterocutaneous Fistula\u2013Associated Sepsis and Mortality: Development and Validation of a Multimodal Artificial Intelligence Prediction Model"],"prefix":"10.2196","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-6192-0519","authenticated-orcid":false,"given":"Hui","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5225-1169","authenticated-orcid":false,"given":"Jing","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4688-2332","authenticated-orcid":false,"given":"Peijun","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5436-9650","authenticated-orcid":false,"given":"Youmei","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1906-6681","authenticated-orcid":false,"given":"Yawen","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1736-9993","authenticated-orcid":false,"given":"Wenfeng","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,4,30]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.4240\/wjgs.v2.i7.242"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10151-022-02656-3"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.7789"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.31729\/jnma.5780"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1097\/md.0000000000030963"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2021.628302"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s00134-019-05872-y"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.amsu.2021.102413"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.stem.2013.11.008"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3390\/microorganisms7120583"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10753-020-01396-6"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.intimp.2020.107272"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1172\/jci84431"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ad6d28"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/tmi.2021.3057635"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1038\/s41419-024-06598-6"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1186\/s13040-024-00391-z"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3389\/fpubh.2021.754348"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocab236"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/jbhi.2022.3171673"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3389\/fimmu.2023.1152117"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1186\/s12879-023-08614-0"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.aucc.2018.02.005"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1097\/CCM.0000000000004550"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1111\/iwj.13254"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3346\/jkms.2019.34.e110"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2020.100196"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.2119\/molmed.2016.00150"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1097\/mog.0b013e32835c9cb3"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s10753-024-02135-x"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1038\/labinvest.2010.208"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1038\/s41385-021-00450-2"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1186\/cc13902"}],"container-title":["JMIR Medical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/medinform.jmir.org\/2026\/1\/e79985","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T20:32:20Z","timestamp":1783629140000},"score":1,"resource":{"primary":{"URL":"https:\/\/medinform.jmir.org\/2026\/1\/e79985"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,30]]},"references-count":33,"URL":"https:\/\/doi.org\/10.2196\/79985","relation":{"has-preprint":[{"id-type":"doi","id":"10.2196\/preprints.79985","asserted-by":"object"}]},"ISSN":["2291-9694"],"issn-type":[{"value":"2291-9694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,30]]}}}