{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T09:19:44Z","timestamp":1766222384309,"version":"3.48.0"},"reference-count":36,"publisher":"Walter de Gruyter GmbH","issue":"1","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,30]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    An accurate prediction of mortality in intensive care units (ICUs) is crucial to improving patient outcomes and optimizing resource allocation. However, existing methods often lack high-dimensional data and interpretability, rely on outdated equipment, or fail to integrate multifaceted clinical data effectively. This study aims to develop a hybrid predictive model integrating machine learning (ML), the fuzzy decision-by-opinion score method (FDOSM), and explainable artificial intelligence (XAI) to enhance the accuracy, transparency, and clinical applicability of the prediction of mortality forecasts. The dataset was used from Zigong Fourth People\u2019s Hospital and consisted of 1,210 patients and 182 attributes. Using Chi-square feature selection, we identified statistically significant features (e.g. vital signs, lab results) from ICU patient records, reducing dimensionality while preserving predictive power. We evaluated multiple ML models (including LightGBM, Extra Trees, Support Vector Machine,\n                    <jats:italic>K<\/jats:italic>\n                    -Nearest Neighbours, XGBoost, Random Forest, and Artificial Neural Network) using a comprehensive dataset of ICU patient records, which includes vital signs, laboratory results, and clinical interventions. The FDOSM was then integrated to assess model outputs against domain-specific criteria, enabling nuanced risk stratification and enhancing decision support in critical care. XAI techniques were used to interpret the outputs of the best-performing model, improving trust in the predictions. Our hybrid approach achieved superior performance, with the Extra Tree algorithm trained on the refined feature set obtaining the highest rank 1, with a weight of 0.14375, an AUC of 88.173%, a precision of 90.244%, and an accuracy of 88.167%. The results demonstrate that combining Chi-square-driven feature selection with ML-FDOSM and XAI integration significantly improves mortality prediction, offering a reliable and transparent tool for critical care settings.\n                  <\/jats:p>","DOI":"10.1515\/jisys-2025-0012","type":"journal-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T15:57:11Z","timestamp":1761839831000},"source":"Crossref","is-referenced-by-count":0,"title":["Predicting early mortality for patients in intensive care units using machine learning and FDOSM"],"prefix":"10.1515","volume":"34","author":[{"given":"Kareem Hameed","family":"Khalaf","sequence":"first","affiliation":[{"name":"Faculty of Electrical and Computer Engineering, University of Tabriz , 33169 , Tabriz , Iran"}]},{"given":"Abdolhamid","family":"Moallemi Khiavi","sequence":"additional","affiliation":[{"name":"Faculty of Electrical and Computer Engineering, University of Tabriz , 33169 , Tabriz , Iran"}]},{"given":"Dhafar Hamed","family":"Abd","sequence":"additional","affiliation":[{"name":"College of Computer Science and Information Technology, University of Anbar , Ramadi , 31001 , Iraq"}]}],"member":"374","published-online":{"date-parts":[[2025,10,30]]},"reference":[{"key":"2025122009032270529_j_jisys-2025-0012_ref_001","doi-asserted-by":"crossref","unstructured":"Khalaf KH, Khiavi AM, Abd DH. Adversarial ensemble learning for mortality prediction in intensive care units. 2024 17th International Conference on Development in eSystem Engineering (DeSE). IEEE; 2024. p. 405\u201310. 10.1109\/DeSE63988.2024.10912041.","DOI":"10.1109\/DeSE63988.2024.10912041"},{"key":"2025122009032270529_j_jisys-2025-0012_ref_002","doi-asserted-by":"crossref","unstructured":"Czapla M, Ju\u00e1rez-Vela R, Gea-Caballero V, Zieli\u0144ski S, Zieli\u0144ska M. The association between nutritional status and in-hospital mortality of COVID-19 in critically-ill patients in the ICU. Nutrients. 2021;13(10):3302. 10.3390\/nu13103302.","DOI":"10.3390\/nu13103302"},{"key":"2025122009032270529_j_jisys-2025-0012_ref_003","doi-asserted-by":"crossref","unstructured":"Hourmant Y, Mailloux A, Valade S, Lemiale V, Azoulay E, Darmon M. Impact of early ICU admission on outcome of critically ill and critically ill cancer patients: A systematic review and meta-analysis. J Crit Care. 2021;61:82\u20138. 10.1016\/j.jcrc.2020.10.008.","DOI":"10.1016\/j.jcrc.2020.10.008"},{"key":"2025122009032270529_j_jisys-2025-0012_ref_004","unstructured":"Churpek MM, Gupta S, Spicer AB, Parker WF, Fahrenbach J, Brenner SK, et al. Hospital-level variation in death for critically ill patients with COVID-19. Am J Respir Crit Care Med. 2021;204(4):403\u201311. 10.1164\/rccm.202012-4547OC."},{"key":"2025122009032270529_j_jisys-2025-0012_ref_005","doi-asserted-by":"crossref","unstructured":"Grasselli G, Scaravilli V, Mangioni D, Scudeller L, Alagna L, Bartoletti M, et al. Hospital-acquired infections in critically ill patients with COVID-19. Chest. 2021;160(2):454\u201365. 10.1016\/j.chest.2021.04.002.","DOI":"10.1016\/j.chest.2021.04.002"},{"key":"2025122009032270529_j_jisys-2025-0012_ref_006","doi-asserted-by":"crossref","unstructured":"Kiekkas P, Tzenalis A, Gklava V, Stefanopoulos N, Voyagis G, Aretha D. Delayed admission to the intensive care unit and mortality of critically ill adults: Systematic review and meta\u2010analysis. BioMed Res Int. 2022;2022(1):4083494. 10.1155\/2022\/4083494.","DOI":"10.1155\/2022\/4083494"},{"key":"2025122009032270529_j_jisys-2025-0012_ref_007","doi-asserted-by":"crossref","unstructured":"Silveira EC, Pretti SM, Santos BA, Corr\u00eaa CFS, Silva LM, de Melo FF. Prediction of hospital mortality in intensive care unit patients from clinical and laboratory data: A machine learning approach. World J Crit Care Med. 2022;11(5):317. 10.5492\/wjccm.v11.i5.317.","DOI":"10.5492\/wjccm.v11.i5.317"},{"key":"2025122009032270529_j_jisys-2025-0012_ref_008","doi-asserted-by":"crossref","unstructured":"Yun K, Oh J, Hong TH, Kim EY. Prediction of mortality in surgical intensive care unit patients using machine learning algorithms. Front Med. 2021;8:621861. 10.3389\/fmed.2021.621861.","DOI":"10.3389\/fmed.2021.621861"},{"key":"2025122009032270529_j_jisys-2025-0012_ref_009","doi-asserted-by":"crossref","unstructured":"Chiu C-C, Wu C-M, Chien T-N, Kao L-J, Qiu JT. Predicting the mortality of ICU patients by topic model with machine-learning techniques. Healthcare. 2022;10(6):1087. 10.3390\/healthcare10061087.","DOI":"10.3390\/healthcare10061087"},{"key":"2025122009032270529_j_jisys-2025-0012_ref_010","doi-asserted-by":"crossref","unstructured":"Quinto B. Introduction to machine learning. Next-generation machine learning with spark: Covers XGBoost, LightGBM, Spark NLP, distributed deep learning with keras, and more. Springer; 2020. p. 1\u201327. 10.1007\/978-1-4842-5669-5.","DOI":"10.1007\/978-1-4842-5669-5_1"},{"key":"2025122009032270529_j_jisys-2025-0012_ref_011","doi-asserted-by":"crossref","unstructured":"Shamout F, Zhu T, Clifton DA. Machine learning for clinical outcome prediction. IEEE Rev Biomed Eng. 2020;14:116\u201326. 10.1109\/RBME.2020.3007816.","DOI":"10.1109\/RBME.2020.3007816"},{"key":"2025122009032270529_j_jisys-2025-0012_ref_012","doi-asserted-by":"crossref","unstructured":"Mansouri A, Noei M, Saniee Abadeh M. A hybrid machine learning approach for early mortality prediction of ICU patients. Prog Artif Intell. 2022;11(4):333\u201347. 10.1007\/s13748-022-00288-0.","DOI":"10.1007\/s13748-022-00288-0"},{"key":"2025122009032270529_j_jisys-2025-0012_ref_013","doi-asserted-by":"crossref","unstructured":"Caicedo-Torres W, Gutierrez J. ISeeU: Visually interpretable deep learning for mortality prediction inside the ICU. J Biomed Inform. 2019;98:103269. 10.1016\/j.jbi.2019.103269.","DOI":"10.1016\/j.jbi.2019.103269"},{"key":"2025122009032270529_j_jisys-2025-0012_ref_014","doi-asserted-by":"crossref","unstructured":"Abd DH, Al-Mejibli IS. Monitoring system for sickle cell disease patients by using supervised machine learning. 2017 Second Al-Sadiq International Conference on Multidisciplinary in IT and Communication Science and Applications (AIC-MITCSA). IEEE; 2017. p. 119\u20134. 10.1109\/AIC-MITCSA.2017.8723006.","DOI":"10.1109\/AIC-MITCSA.2017.8723006"},{"key":"2025122009032270529_j_jisys-2025-0012_ref_015","doi-asserted-by":"crossref","unstructured":"Zilker S, Weinzierl S, Kraus M, Zschech P, Matzner M. A machine learning framework for interpretable predictions in patient pathways: The case of predicting ICU admission for patients with symptoms of sepsis. Health Care Manag Sci. 2024;27(2):136\u201367. 10.1007\/s10729-024-09673-8.","DOI":"10.1007\/s10729-024-09673-8"},{"key":"2025122009032270529_j_jisys-2025-0012_ref_016","doi-asserted-by":"crossref","unstructured":"Mukhlif DM, Abd DH, Ejbali R, Alimi AM, Mahdi MF. Enhancing comorbidity diagnosis with adversarial ensemble learning. 2024 17th International Conference on Development in eSystem Engineering (DeSE). IEEE; 2024. p. 381\u20136. 10.1109\/DeSE63988.2024.10912032.","DOI":"10.1109\/DeSE63988.2024.10912032"},{"key":"2025122009032270529_j_jisys-2025-0012_ref_017","doi-asserted-by":"crossref","unstructured":"Ghazi RF, Abd DH. Gene disease classification from biomedical text via ensemble machine learning. 2023 16th International Conference on Developments in eSystems Engineering (DeSE). IEEE; 2023. p. 593\u20138. 10.1109\/DeSE60595.2023.10469108.","DOI":"10.1109\/DeSE60595.2023.10469108"},{"key":"2025122009032270529_j_jisys-2025-0012_ref_018","doi-asserted-by":"crossref","unstructured":"Nsaif AA, Abd DH. Sentiment analysis of political post classification based on XGBoost. Proceedings of International Conference on Computing and Communication Networks: ICCCN 2021. Singapore: Springer Nature Singapore; 2022. p. 177\u201388. 10.1007\/978-981-19-0604-6_16.","DOI":"10.1007\/978-981-19-0604-6_16"},{"key":"2025122009032270529_j_jisys-2025-0012_ref_019","doi-asserted-by":"crossref","unstructured":"Jassim MA, Abd DH, Omri MN. Machine learning-based new approach to films review. Soc Netw Anal Min. 2023;13(1):40. 10.1007\/s13278-023-01042-7.","DOI":"10.1007\/s13278-023-01042-7"},{"key":"2025122009032270529_j_jisys-2025-0012_ref_020","doi-asserted-by":"crossref","unstructured":"Mukhlif DM, Abd DH, Ejbali R, Alimi AM, Mahdi MF, Hussain AJ. Comorbidity diagnosis using machine learning: Fuzzy decision-making approach. J Intell Syst. 2025;34(1):20240418. 10.1515\/jisys-2024-0418.","DOI":"10.1515\/jisys-2024-0418"},{"key":"2025122009032270529_j_jisys-2025-0012_ref_021","doi-asserted-by":"crossref","unstructured":"Si\u00f6land T, Rawshani A, Nellg\u00e5rd B, Malmgren J, Oras J, Dalla K, et al. ICURE: Intensive care unit (ICU) risk evaluation for 30\u2010day mortality. Developing and evaluating a multivariable machine learning prediction model for patients admitted to the general ICU in Sweden. Acta Anaesthesiol Scand. 2024;68(10):1379\u201389. 10.1111\/aas.14501.","DOI":"10.1111\/aas.14501"},{"key":"2025122009032270529_j_jisys-2025-0012_ref_022","doi-asserted-by":"crossref","unstructured":"Ko R-E, Cho J, Shin M-K, Oh SW, Seong Y, Jeon J, et al. Machine learning-based mortality prediction model for critically Ill Cancer patients admitted to the Intensive Care Unit (CanICU). Cancers. 2023;15(3):569. 10.3390\/cancers15030569.","DOI":"10.3390\/cancers15030569"},{"key":"2025122009032270529_j_jisys-2025-0012_ref_023","doi-asserted-by":"crossref","unstructured":"Razo M, Pishgar M, Galanter W, Darabi H. Deep-learning model for mortality prediction of ICU patients with paralytic ileus. Bioengineering. 2024;11(12):1214. 10.3390\/bioengineering11121214.","DOI":"10.3390\/bioengineering11121214"},{"key":"2025122009032270529_j_jisys-2025-0012_ref_024","doi-asserted-by":"crossref","unstructured":"Tu K-C, Tau ENT, Chen N-C, Chang M-C, Yu T-C, Wang C-C, et al. Machine learning algorithm predicts mortality risk in intensive care unit for patients with traumatic brain injury. Diagnostics. 2023;13(18):3016. 10.3390\/diagnostics13183016.","DOI":"10.3390\/diagnostics13183016"},{"key":"2025122009032270529_j_jisys-2025-0012_ref_025","doi-asserted-by":"crossref","unstructured":"Tasnim N, Al Mamun S, Shahidul Islam M, Kaiser MS, Mahmud M. Explainable mortality prediction model for congestive heart failure with nature-based feature selection method. Appl Sci. 2023;13(10):6138. 10.3390\/app13106138.","DOI":"10.3390\/app13106138"},{"key":"2025122009032270529_j_jisys-2025-0012_ref_026","doi-asserted-by":"crossref","unstructured":"Yu Z, Fang L, Ding Y. Explainable machine learning model for prediction of 28-day all-cause mortality in immunocompromised patients in the intensive care unit: a retrospective cohort study based on MIMIC-IV database. Eur J Med Res. 2025;30(1):358. 10.1186\/s40001-025-02622-3.","DOI":"10.1186\/s40001-025-02622-3"},{"key":"2025122009032270529_j_jisys-2025-0012_ref_027","doi-asserted-by":"crossref","unstructured":"Prithula J, Chowdhury ME, Khan MS, Al-Ansari K, Zughaier SM, Islam KR, et al. Improved pediatric ICU mortality prediction for respiratory diseases: Machine learning and data subdivision insights. Respir Res. 2024;25(1):216. 10.1186\/s12931-024-02753-x.","DOI":"10.1186\/s12931-024-02753-x"},{"key":"2025122009032270529_j_jisys-2025-0012_ref_028","doi-asserted-by":"crossref","unstructured":"Xu P, Chen L, Zhu Y, Yu S, Chen R, Huang W, et al. Critical care database comprising patients with infection. Front Public Health. 2022;10:852410. 10.3389\/fpubh.2022.852410.","DOI":"10.3389\/fpubh.2022.852410"},{"key":"2025122009032270529_j_jisys-2025-0012_ref_029","doi-asserted-by":"crossref","unstructured":"Ferreira FL, Bota DP, Bross A, M\u00e9lot C, Vincent J-L. Serial evaluation of the SOFA score to predict outcome in critically ill patients. JAMA. 2001;286(14):1754\u20138. 10.1001\/jama.286.14.1754.","DOI":"10.1001\/jama.286.14.1754"},{"key":"2025122009032270529_j_jisys-2025-0012_ref_030","doi-asserted-by":"crossref","unstructured":"Raouf ZT, Abd DH. Feature selection for binary dataset using dragonfly algorithm. 2023 16th International Conference on Developments in eSystems Engineering (DeSE). IEEE; 2023. p. 480\u20135. 10.1109\/DeSE60595.2023.10469222.","DOI":"10.1109\/DeSE60595.2023.10469222"},{"key":"2025122009032270529_j_jisys-2025-0012_ref_031","doi-asserted-by":"crossref","unstructured":"Mukhlif DM, Abd DH, Ejbali R, Alimi AM. Comorbidity diseases diagnosis using machine learning methods and chi-square feature selection technique. 2023 16th International Conference on Developments in eSystems Engineering (DeSE). IEEE; 2023. p. 144\u20139. 10.1109\/DeSE60595.2023.10469092.","DOI":"10.1109\/DeSE60595.2023.10469092"},{"key":"2025122009032270529_j_jisys-2025-0012_ref_032","doi-asserted-by":"crossref","unstructured":"Ahmed AA, Hasan MK, Jaber MM, Al-Ghuribi SM, Abd DH, Khan W, et al. Arabic text detection using rough set theory: Designing a novel approach. IEEE Access. 2023;11:68428\u201338. 10.1109\/ACCESS.2023.3278272.","DOI":"10.1109\/ACCESS.2023.3278272"},{"key":"2025122009032270529_j_jisys-2025-0012_ref_033","doi-asserted-by":"crossref","unstructured":"Abd DH, Khan W, Khan B, Alharbe N, Al-Jumeily D, Hussain A. Categorization of Arabic posts using Artificial Neural Network and hash features. J King Saud Univ-Sci. 2023;35(6):102733. 10.1016\/j.jksus.2023.102733.","DOI":"10.1016\/j.jksus.2023.102733"},{"key":"2025122009032270529_j_jisys-2025-0012_ref_034","doi-asserted-by":"crossref","unstructured":"Salih MM, Zaidan B, Zaidan A. Fuzzy decision by opinion score method. Appl Soft Comput. 2020;96:106595. 10.1016\/j.asoc.2020.106595.","DOI":"10.1016\/j.asoc.2020.106595"},{"key":"2025122009032270529_j_jisys-2025-0012_ref_035","doi-asserted-by":"crossref","unstructured":"Albahri OS, Zaidan AA, Salih MM, Zaidan BB, Khatari MA, Ahmed MA, et al. Multidimensional benchmarking of the active queue management methods of network congestion control based on extension of fuzzy decision by opinion score method. Int J Intell Syst. 2021;36(2):796\u2013831. 10.1002\/int.22322.","DOI":"10.1002\/int.22322"},{"key":"2025122009032270529_j_jisys-2025-0012_ref_036","doi-asserted-by":"crossref","unstructured":"Al-Qaysi Z, Albahri A, Ahmed M, SM, Mohammed. Development of hybrid feature learner model integrating FDOSM for golden subject identification in motor imagery. Phys Eng Sci Med. 2023;46(4):1519\u201334. 10.1007\/s13246-023-01316-6.","DOI":"10.1007\/s13246-023-01316-6"}],"container-title":["Journal of Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/jisys-2025-0012\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/jisys-2025-0012\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T09:15:48Z","timestamp":1766222148000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/jisys-2025-0012\/html"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,1]]},"references-count":36,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,3,7]]},"published-print":{"date-parts":[[2025,3,7]]}},"alternative-id":["10.1515\/jisys-2025-0012"],"URL":"https:\/\/doi.org\/10.1515\/jisys-2025-0012","relation":{},"ISSN":["2191-026X"],"issn-type":[{"type":"electronic","value":"2191-026X"}],"subject":[],"published":{"date-parts":[[2025,1,1]]},"article-number":"20250012"}}