{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T11:57:37Z","timestamp":1776513457098,"version":"3.51.2"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T00:00:00Z","timestamp":1771804800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T00:00:00Z","timestamp":1774569600000},"content-version":"vor","delay-in-days":32,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Timely identification of COVID-19 outpatients who are at risk of hospitalization is critical for preventing clinical deterioration and optimizing healthcare resources. Although machine-learning models have demonstrated high predictive accuracy, their limited interpretability often hinders clinical adoption. This study aims to develop a hybrid explainable framework that combines the predictive strength of XGBoost with clinically interpretable rule-based explanations to support decision-making in real clinical settings. A retrospective dataset of 1278 COVID-19 patients was analyzed after applying strict inclusion and exclusion criteria. Twenty-seven clinical, laboratory, and demographic variables were preprocessed using outlier detection, multiple imputation by chained equations, and stratified train\u2013test splitting validated through a Kolmogorov\u2013Smirnov test. XGBoost was trained and benchmarked against logistic regression, random forest, LightGBM, and a neural network. For interpretability, candidate rules were extracted from a constrained Random Forest and optimized via a genetic algorithm (GA) using accuracy\u2013support multi-objective fitness. Clinical validation of rules was performed by ten physicians using the Content Validity Index (CVI; threshold\u2009\u2265\u20090.85). XGBoost achieved superior predictive performance with an AUC of 0.85, sensitivity of 73.5%, specificity of 88.7%, AUPRC of 0.72, and a Brier Score of 0.085. Baseline models demonstrated lower discrimination and calibration. Fairness evaluation indicated stable model behavior across demographic and comorbidity subgroups. Sensitivity analysis identified SpO\n                    <jats:sub>2<\/jats:sub>\n                    , CRP, age, D-dimer, ferritin, and lymphocyte percentage as the most influential predictors. From 400 initial rules, 80 were selected and refined, and 40 clinically valid rules were finalized through expert review. The explainability framework expands upon the classical Decision Tree Surrogate method, producing global IF\u2013THEN rules that outperform local attribution tools such as SHAP and LIME in practical interpretability. The proposed hybrid system successfully integrates high-accuracy machine-learning predictions with clinically validated, interpretable rules, offering a transparent decision-support tool for hospitalization risk assessment in COVID-19 outpatients. Its modular design enables rapid adaptation to future infectious disease outbreaks, supporting broader clinical deployment and improved triage decision-making.\n                  <\/jats:p>","DOI":"10.1038\/s41598-026-40120-6","type":"journal-article","created":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T19:47:20Z","timestamp":1771876040000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Designing an explainable algorithm based on XGBoost and genetic algorithm for predicting hospitalization needs of COVID-19 patients"],"prefix":"10.1038","volume":"16","author":[{"given":"Azadeh","family":"Abkar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mahdi","family":"Mehrabi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amin","family":"Golabpour","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohammad Amin","family":"Shayegan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,2,23]]},"reference":[{"key":"40120_CR1","doi-asserted-by":"publisher","first-page":"1786","DOI":"10.1136\/bmj.n1786","volume":"373","author":"O Dyer","year":"2021","unstructured":"Dyer, O. Covid-19: Study claims real global deaths are twice official figures. BMJ Br. Med. J. 373, 1786\u20131789 (2021).","journal-title":"BMJ Br. Med. J."},{"key":"40120_CR2","unstructured":"Prevention (CDC) CfDCa. Hospitalization Rates and Characteristics of Patients Hospitalized with COVID-19 (2023). Available from: https:\/\/covid.cdc.gov\/covid-data-tracker."},{"issue":"1","key":"40120_CR3","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1016\/S1473-3099(21)00475-8","volume":"22","author":"KA Twohig","year":"2022","unstructured":"Twohig, K. A. et al. Hospital admission and emergency care attendance risk for SARS-CoV-2 delta (B.1.617.2) compared with alpha (B.1.1.7) variants of concern: A cohort study. Lancet Infect. Dis. 22(1), 35\u201342 (2022).","journal-title":"Lancet Infect. Dis."},{"key":"40120_CR4","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1016\/j.ijid.2021.03.066","volume":"106","author":"D Dennison","year":"2021","unstructured":"Dennison, D. et al. Circulating activated neutrophils in COVID-19: An independent predictor for mechanical ventilation and death. Int. J. Infect. Dis. 106, 155\u2013159 (2021).","journal-title":"Int. J. Infect. Dis."},{"key":"40120_CR5","doi-asserted-by":"crossref","unstructured":"Essafi, F., Talik, I., Ismail, K. B., Kharrat, M., Slimene, N. B., Bayoudh, A., et al. Delay of Intensive Care Admission of Severe COVID-19 Patients: What Impact on Mortality? (European Respiratory Society, 2022).","DOI":"10.1183\/13993003.congress-2022.4051"},{"issue":"4","key":"40120_CR6","doi-asserted-by":"publisher","first-page":"321","DOI":"10.34172\/jcvtr.2020.51","volume":"12","author":"G G\u00f6k","year":"2020","unstructured":"G\u00f6k, G., Karada\u011f, M., \u00c7inar, T., Nurkalem, Z. & Duman, D. In-hospital and short-term predictors of mortality in patients with intermediate-high risk pulmonary embolism. J. Cardiovasc. Thorac. Res. 12(4), 321 (2020).","journal-title":"J. Cardiovasc. Thorac. Res."},{"key":"40120_CR7","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1007\/s00134-016-4638-3","volume":"43","author":"R Zhang","year":"2017","unstructured":"Zhang, R. et al. Late-onset moderate to severe acute respiratory distress syndrome is associated with shorter survival and higher mortality: A two-stage association study. Intensive Care Med. 43, 399\u2013407 (2017).","journal-title":"Intensive Care Med."},{"issue":"16","key":"40120_CR8","doi-asserted-by":"publisher","first-page":"1574","DOI":"10.1001\/jama.2020.5394","volume":"323","author":"G Grasselli","year":"2020","unstructured":"Grasselli, G. et al. Baseline characteristics and outcomes of 1591 patients infected with SARS-CoV-2 admitted to ICUs of the Lombardy Region, Italy. JAMA 323(16), 1574\u20131581 (2020).","journal-title":"JAMA"},{"issue":"1","key":"40120_CR9","doi-asserted-by":"publisher","DOI":"10.1186\/s12879-021-06179-4","volume":"21","author":"M-R Sohrabi","year":"2021","unstructured":"Sohrabi, M.-R. et al. Sociodemographic determinants and clinical risk factors associated with COVID-19 severity: A cross-sectional analysis of over 200,000 patients in Tehran, Iran. BMC Infect. Dis. 21(1), 474 (2021).","journal-title":"BMC Infect. Dis."},{"key":"40120_CR10","doi-asserted-by":"crossref","unstructured":"Yekollu, R. K., Ghuge, T. B., Biradar, S. S., Haldikar, S. V., Kader, O. F. M. A. (eds.) Explainable AI in healthcare: Enhancing transparency and trust in predictive models. In 2024 5th International Conference on Electronics and Sustainable Communication Systems (ICESC) 7\u20139 Aug. 2024 (2024).","DOI":"10.1109\/ICESC60852.2024.10690121"},{"key":"40120_CR11","doi-asserted-by":"publisher","first-page":"1978","DOI":"10.47392\/IRJAEH.2024.0270","volume":"2","author":"I Mishra","year":"2024","unstructured":"Mishra, I., Kashyap, V., Yadav, N. & Pahwa, D. R. Harmonizing intelligence: A holistic approach to bias mitigation in artificial intelligence (AI). Int. Res. J. Adv. Eng. Hub. 2, 1978\u20131985 (2024).","journal-title":"Int. Res. J. Adv. Eng. Hub."},{"issue":"9","key":"40120_CR12","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1108\/03684929410075011","volume":"23","author":"G Plenert","year":"1994","unstructured":"Plenert, G. Improved decision support systems help to build better artificial intelligence systems. Kybernetes 23(9), 48\u201354 (1994).","journal-title":"Kybernetes"},{"key":"40120_CR13","doi-asserted-by":"publisher","first-page":"152","DOI":"10.30699\/fhi.v12i0.473","volume":"12","author":"Z Salehnasab","year":"2023","unstructured":"Salehnasab, Z., Mousavizadeh, A., Ghalamfarsa, G., Garavand, A. & Salehnasab, C. Predictive modeling of COVID-19 hospitalization using twenty machine learning classification Algorithms on cohort data. Front. Health Inform. 12, 152 (2023).","journal-title":"Front. Health Inform."},{"issue":"1","key":"40120_CR14","volume":"5","author":"M Mass\u00f3-Muratel","year":"2023","unstructured":"Mass\u00f3-Muratel, M. et al. Predictive factors for hospitalization in a cohort of primary healthcare patients with suspected COVID-19. Aten. Prim. Pr\u00e1ct. 5(1), 100168 (2023).","journal-title":"Aten. Prim. Pr\u00e1ct."},{"issue":"1","key":"40120_CR15","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-22547-9","volume":"12","author":"A Cisterna-Garc\u00eda","year":"2022","unstructured":"Cisterna-Garc\u00eda, A. et al. A predictive model for hospitalization and survival to COVID-19 in a retrospective population-based study. Sci. Rep. 12(1), 18126 (2022).","journal-title":"Sci. Rep."},{"key":"40120_CR16","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1016\/j.clnesp.2021.08.027","volume":"45","author":"F Mart\u00edn-Del-Campo","year":"2021","unstructured":"Mart\u00edn-Del-Campo, F. et al. Morbid obesity is associated with mortality and acute kidney injury in hospitalized patients with COVID-19. Clin. Nutr. ESPEN 45, 200\u2013205 (2021).","journal-title":"Clin. Nutr. ESPEN"},{"issue":"7","key":"40120_CR17","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2021-056685","volume":"12","author":"ZG Fang","year":"2022","unstructured":"Fang, Z. G., Yang, S. Q., Lv, C. X., An, S. Y. & Wu, W. Application of a data-driven XGBoost model for the prediction of COVID-19 in the USA: A time-series study. BMJ Open 12(7), e056685 (2022).","journal-title":"BMJ Open"},{"key":"40120_CR18","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.60519","volume":"9","author":"B Hao","year":"2020","unstructured":"Hao, B. et al. Early prediction of level-of-care requirements in patients with COVID-19. Elife 9, e60519 (2020).","journal-title":"Elife"},{"key":"40120_CR19","unstructured":"Brownlee, J. Ensemble Learning Algorithms With Python: Make Better Predictions with Bagging, Boosting, and Stacking: Machine Learning Mastery (2021)."},{"key":"40120_CR20","volume-title":"Random Forests","author":"YL Pavlov","year":"2019","unstructured":"Pavlov, Y. L. Random Forests (De Gruyter, 2019)."},{"key":"40120_CR21","volume-title":"Genetic Algorithms: Concepts and Designs","author":"KF Man","year":"2012","unstructured":"Man, K. F., Tang, K. S. & Kwong, S. Genetic Algorithms: Concepts and Designs (Springer, 2012)."},{"issue":"5","key":"40120_CR22","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1002\/nur.20147","volume":"29","author":"DF Polit","year":"2006","unstructured":"Polit, D. F. & Beck, C. T. The content validity index: Are you sure you know what\u2019s being reported? Critique and recommendations. Res. Nurs. Health 29(5), 489\u2013497 (2006).","journal-title":"Res. Nurs. Health"},{"issue":"1","key":"40120_CR23","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-85420-5","volume":"15","author":"S Lee","year":"2025","unstructured":"Lee, S. et al. External validation of an artificial intelligence model using clinical variables, including ICD-10 codes, for predicting in-hospital mortality among trauma patients: A multicenter retrospective cohort study. Sci. Rep. 15(1), 1100 (2025).","journal-title":"Sci. Rep."},{"key":"40120_CR24","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2024.1397388","volume":"7","author":"L Aissaoui Ferhi","year":"2024","unstructured":"Aissaoui Ferhi, L., Ben Amar, M., Choubani, F. & Bouallegue, R. Enhancing diagnostic accuracy in symptom-based health checkers: A comprehensive machine learning approach with clinical vignettes and benchmarking. Front. Artif. Intell. 7, 1397388 (2024).","journal-title":"Front. Artif. Intell."},{"key":"40120_CR25","doi-asserted-by":"publisher","first-page":"5333","DOI":"10.3934\/mbe.2023247","volume":"20","author":"Q Shen","year":"2023","unstructured":"Shen, Q. Research of mortality risk prediction based on hospital admission data for COVID-19 patients. Math. Biosci. Eng. 20, 5333\u20135351 (2023).","journal-title":"Math. Biosci. Eng."},{"issue":"1","key":"40120_CR26","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-02370-4","volume":"11","author":"L Jia","year":"2021","unstructured":"Jia, L. et al. An interpretable machine learning model based on a quick pre-screening system enables accurate deterioration risk prediction for COVID-19. Sci. Rep. 11(1), 23127 (2021).","journal-title":"Sci. Rep."},{"issue":"1","key":"40120_CR27","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-023-02192-6","volume":"23","author":"F Ma","year":"2023","unstructured":"Ma, F. et al. Interpretable machine-learning model for predicting the convalescent COVID-19 patients with pulmonary diffusing capacity impairment. BMC Med. Inform. Decis. Mak. 23(1), 169 (2023).","journal-title":"BMC Med. Inform. Decis. Mak."},{"issue":"6","key":"40120_CR28","doi-asserted-by":"publisher","first-page":"1270","DOI":"10.1007\/s10900-020-00920-x","volume":"45","author":"FM Noor","year":"2020","unstructured":"Noor, F. M. & Islam, M. M. Prevalence and associated risk factors of mortality among COVID-19 patients: A meta-analysis. J. Community Health 45(6), 1270\u20131282 (2020).","journal-title":"J. Community Health"},{"issue":"10229","key":"40120_CR29","doi-asserted-by":"publisher","first-page":"1054","DOI":"10.1016\/S0140-6736(20)30566-3","volume":"395","author":"F Zhou","year":"2020","unstructured":"Zhou, F. et al. Clinical course and risk factors for mortality of adult inpatients with COVID-19 in Wuhan, China: A retrospective cohort study. Lancet (London, Engl.) 395(10229), 1054\u20131062 (2020).","journal-title":"Lancet (London, Engl.)"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-40120-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-40120-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-40120-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T09:31:04Z","timestamp":1774603864000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-40120-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,23]]},"references-count":29,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["40120"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-40120-6","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,23]]},"assertion":[{"value":"26 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 February 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"10210"}}