{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T07:02:47Z","timestamp":1779692567803,"version":"3.53.1"},"reference-count":55,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T00:00:00Z","timestamp":1779667200000},"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. Immunol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Older adults are the high-risk group for COVID-19-related death. This study aimed to develop an accurate, efficient, clinically interpretable machine learning (ML) model for predicting mortality risk in this population, using only routine hematological indicators at admission to avoid extra medical costs and radiation exposure.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>2393 COVID-19 patients were enrolled in this retrospective study. Missing values were imputed via Random Forest. RandomOverSampler was utilized during model training to alleviate moderate class imbalance. Feature selection was conducted following the maximum relevance-minimum redundancy principle. Five ML algorithms\u2014Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF), XGBoost (XGB), Light Gradient Boosting Machine (LGBM) were optimized via bayesian optimization (BO). We performed 10 rounds of random stratified data splitting; models were fitted on the training set, with intermediate screening and hyperparameter optimization implemented on the validation set. The independent held-out test set was strictly reserved for final performance evaluation. Model performances were assessed using the ROC curve, accuracy, precision, recall, F1-score and brier score. Calibration curve evaluated concordance between predicted probabilities and actual outcomes, and decision curve analysis (DCA) quantified net clinical benefit in clinical practice. Shapley additive exPlanations (SHAP) values and partial dependence plots (PDPs) interpreted feature importance and their associations with mortality risk. A simplified model was further developed using the top 10 key features identified by SHAP analysis and a corresponding risk prediction system was constructed to facilitate clinical application by physicians.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The LGBM model achieved the best comprehensive performance: AUC of 0.973, recall of 0.924, accuracy of 0.918, F1-score of 0.918, NPV of 0.923, and Brier score of 0.064. It outperformed other algorithms in computational efficiency and cross-dataset stability. Top 10 key features identified included basophil percentage (BA%), C-reactive protein (CRP), procalcitonin (PCT), D-dimer (D-dimer), AST\/ALT ratio, cardiac troponin I (cTnI), standard bicarbonate (SB), age, aspartate transaminase (AST), and oxygen saturation (SaO\n                      <jats:sub>2<\/jats:sub>\n                      ) for predicting mortality risk in older adults. Non-linear associations and threshold effects were observed (e.g., risk surged when CRP &amp;gt; 100 mg\/L or D-dimer &amp;gt; 5\u201310 \u03bcg\/mL). The simplified model reduced training time by 58.31% without compromising performance, comparable accuracy and interpretability.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This study developed a TPE-LGBM model based on routine hematological indicators to predict mortality risk in older adults with COVID-19. The model demonstrated favorable accuracy, efficiency, and interpretability, suggesting the potential value of applying explainable machine learning to address unmet medical needs.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fimmu.2026.1789048","type":"journal-article","created":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T06:05:30Z","timestamp":1779689130000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Explainable machine learning-based mortality risk stratification for older adults with COVID-19: pinpointing core immunological biomarkers and revealing dose-threshold effects"],"prefix":"10.3389","volume":"17","author":[{"given":"Lin","family":"Luo","sequence":"first","affiliation":[{"name":"Clinical Laboratory, Second Affiliated Hospital of Dalian Medical University","place":["Dalian, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Statistics, Dongbei University of Finance and Economics","place":["Dalian, Liaoning, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Statistics, Dongbei University of Finance and Economics","place":["Dalian, Liaoning, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui","family":"Li","sequence":"additional","affiliation":[{"name":"School of Statistics, Dongbei University of Finance and Economics","place":["Dalian, Liaoning, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ting","family":"Liu","sequence":"additional","affiliation":[{"name":"Clinical Laboratory, Second Affiliated Hospital of Dalian Medical University","place":["Dalian, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sha","family":"Yu","sequence":"additional","affiliation":[{"name":"Clinical Laboratory, Second Affiliated Hospital of Dalian Medical University","place":["Dalian, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,5,25]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.virol.2020.08.011","article-title":"The novel coronavirus disease-2019 (COVID-19): mechanism of action, detection and recent therapeutic strategies","volume":"551","author":"Seyed Hosseini","year":"2020","journal-title":"Virology"},{"key":"B2","unstructured":""},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.m3862","article-title":"Virology, transmission, and pathogenesis of SARS-CoV-2","volume":"371","author":"Cevik","year":"2020","journal-title":"Bmj"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.3389\/fpubh.2023.1202216","article-title":"COVID-19 on the spectrum: a scoping review of hygienic standards","volume":"11","author":"Voidarou","year":"2023","journal-title":"Front Public Health"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1093\/cid\/ciaa443","article-title":"A tool for early prediction of severe coronavirus disease 2019 (COVID-19): a multicenter study using the risk nomogram in Wuhan and Guangdong, China","volume":"71","author":"Gong","year":"2020","journal-title":"Clin Infect Dis"},{"key":"B6","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1186\/s12967-022-03364-0","article-title":"Machine learning for the prediction of acute kidney injury in patients with sepsis","volume":"20","author":"Yue","year":"2022","journal-title":"J Transl Med"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1097\/dcr.0000000000003166","article-title":"Predicting colonic neoplasia surgical complications: a machine learning approach","volume":"67","author":"Nwaiwu","year":"2024","journal-title":"Dis Colon Rectum"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.3390\/cancers12102802","article-title":"Comparison of the tree-based machine learning algorithms to Cox regression in predicting the survival of oral and pharyngeal cancers: analyses based on SEER database","volume":"12","author":"Du","year":"2020","journal-title":"Cancers (Basel)"},{"key":"B9","doi-asserted-by":"publisher","first-page":"462","DOI":"10.1186\/s12967-020-02620-5","article-title":"Predicting 30-days mortality for MIMIC-III patients with sepsis-3: a machine learning approach using XGboost","volume":"18","author":"Hou","year":"2020","journal-title":"J\u00a0Transl Med"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.3389\/fimmu.2023.1286380","article-title":"A predictive model for disease severity among COVID-19 elderly patients based on IgG subtypes and machine learning","volume":"14","author":"Zhuang","year":"2023","journal-title":"Front Immunol"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0245157","article-title":"A comparison of machine learning models versus clinical evaluation for mortality prediction in patients with sepsis","volume":"16","author":"van Doorn","year":"2021","journal-title":"PloS One"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1136\/thoraxjnl-2020-216001","article-title":"Development and validation of a prediction model for 30-day mortality in hospitalised patients with COVID-19: the COVID-19 SEIMC score","volume":"76","author":"Berenguer","year":"2021","journal-title":"Thorax"},{"key":"B13","doi-asserted-by":"publisher","first-page":"24439","DOI":"10.1038\/s41598-021-03894-5","article-title":"Development of a prediction score for in-hospital mortality in COVID-19 patients with acute kidney injury: a machine learning approach","volume":"11","author":"Ponce","year":"2021","journal-title":"Sci Rep"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.18632\/aging.103980","article-title":"A predictive model for the severity of COVID-19 in elderly patients","volume":"12","author":"Zeng","year":"2020","journal-title":"Aging (Albany NY)"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1128\/msphere.00752-21","article-title":"Early prediction of severe COVID-19 in patients by a novel immune-related predictive model","volume":"6","author":"Sun","year":"2021","journal-title":"mSphere"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1016\/j.arr.2020.101205","article-title":"Aging in COVID-19: vulnerability, immunity and intervention","volume":"65","author":"Chen","year":"2021","journal-title":"Ageing Res Rev"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1016\/s0140-6736(20)30211-7","article-title":"Epidemiological and clinical characteristics of 99 cases of 2019 novel coronavirus pneumonia in Wuhan, China: a descriptive study","volume":"395","author":"Chen","year":"2020","journal-title":"Lancet"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1016\/j.lanwpc.2023.100919","article-title":"Factors associated with delayed diagnosis of symptomatic adult COVID-19 cases presenting to primary care: a population-wide study during transition from Delta to Omicron BA.1 in Singapore","volume":"41","author":"Tan","year":"2023","journal-title":"Lancet Reg Health West Pac"},{"key":"B19","unstructured":""},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3684447","article-title":"Assessing the age specificity of infection fatality rates for COVID-19: systematic review, meta-analysis, and public policy implications","volume":"35","author":"Levin","year":"2020","journal-title":"Eur J Epidemiol"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1086\/381165","article-title":"Development and validation of a clinical prediction rule for hospitalization due to pneumonia or influenza or death during influenza epidemics among community-dwelling elderly persons","volume":"189","author":"Hak","year":"2004","journal-title":"J Infect Dis"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1177\/09246479241292008","article-title":"Pharmaceutical product recall and educated hesitancy towards new drugs and novel vaccines","volume":"35","author":"Rhodes","year":"2024","journal-title":"Int J Risk Saf Med"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.3390\/ijerph17165974","article-title":"The age-related risk of severe outcomes due to COVID-19 infection: a rapid review, meta-analysis, and meta-regression","volume":"17","author":"Romero Starke","year":"2020","journal-title":"Int J Environ Res Public Health"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.3346\/jkms.2023.38.e217","article-title":"Clinical characteristics and risk factors for mortality in critical COVID-19 patients aged 50 years or younger during Omicron wave in Korea: comparison with patients older than 50 years of age","volume":"38","author":"Shi","year":"2023","journal-title":"J Kor Med Sci"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.2169\/internalmedicine.0086-22","article-title":"Mortality prediction of COVID-19 in hospitalized patients using the 2020 diagnosis procedure combination administrative database of Japan","volume":"62","author":"Nojiri","year":"2023","journal-title":"Intern Med"},{"key":"B26","doi-asserted-by":"publisher","first-page":"1778","DOI":"10.1007\/s12559-020-09812-7","article-title":"An early warning tool for predicting mortality risk of COVID-19 patients using machine learning","volume":"16","author":"Chowdhury","year":"2021","journal-title":"Cognit Comput"},{"key":"B27","doi-asserted-by":"publisher","first-page":"903","DOI":"10.1111\/j.1467-9868.2008.00674.x","article-title":"Discussion of \"Sure independence screening for ultra-high dimensional feature space","volume":"70","author":"Zhang","year":"2008","journal-title":"J R Stat Soc Ser B Stat Methodol"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1016\/j.engstruct.2020.110927","article-title":"Failure mode and effects analysis of RC members based on machine-learning-based SHapley additive explanations (SHAP) approach","volume":"219","author":"Mangalathu","year":"2020","journal-title":"Eng Struct"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1056\/nejm199701233360402","article-title":"A prediction rule to identify low-risk patients with community-acquired pneumonia","volume":"336","author":"Fine","year":"1997","journal-title":"N Engl J Med"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1136\/thorax.58.5.377","article-title":"Defining community acquired pneumonia severity on presentation to hospital: an international derivation and validation study","volume":"58","author":"Lim","year":"2003","journal-title":"Thorax"},{"key":"B31","doi-asserted-by":"publisher","first-page":"102824","DOI":"10.2139\/ssrn.4510948","article-title":"Machine learning algorithms to predict outcomes in children and adolescents with COVID-19: a systematic review","volume":"150","author":"Dos Santos","year":"2024","journal-title":"Artif Intell Med"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1021\/acs.est.2c05404","article-title":"Understanding and designing a high-performance ultrafiltration membrane using machine learning","volume":"57","author":"Gao","year":"2023","journal-title":"Environ Sci Technol"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1001\/jamaneurol.2020.1127","article-title":"Neurologic manifestations of hospitalized patients with coronavirus disease 2019 in Wuhan, China","volume":"77","author":"Mao","year":"2020","journal-title":"JAMA Neurol"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1016\/s2213-2600(20)30404-5","article-title":"Cytokine elevation in severe and critical COVID-19: a rapid systematic review, meta-analysis, and comparison with other inflammatory syndromes","volume":"8","author":"Leisman","year":"2020","journal-title":"Lancet Respir Med"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1111\/jth.14859","article-title":"D-dimer levels on admission to predict in-hospital mortality in patients with Covid-19","volume":"18","author":"Zhang","year":"2020","journal-title":"J Thromb Haemost"},{"key":"B36","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1093\/bmb\/ldac022","article-title":"COVID-19 and the heart","volume":"144","author":"Roy","year":"2022","journal-title":"Br Med Bull"},{"key":"B37","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1186\/s13045-020-00986-z","article-title":"Immunosenescence: a key player in cancer development","volume":"13","author":"Lian","year":"2020","journal-title":"J Hematol Oncol"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.3390\/cells11030359","article-title":"Interconnections between inflammageing and immunosenescence during ageing","volume":"11","author":"Teissier","year":"2022","journal-title":"Cells"},{"key":"B39","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1016\/j.jare.2020.12.013","article-title":"Recovery scenario and immunity in COVID-19 disease: a new strategy to predict the potential of reinfection","volume":"31","author":"Khoshkam","year":"2021","journal-title":"J Adv Res"},{"key":"B40","doi-asserted-by":"publisher","first-page":"18689","DOI":"10.1038\/s41598-020-75659-5","article-title":"IL-4\/IL-13 remodeling pathway of COVID-19 lung injury","volume":"10","author":"Vaz de Paula","year":"2020","journal-title":"Sci Rep"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.1016\/j.jinf.2020.06.061","article-title":"Distinct and early increase in circulating MMP-9 in COVID-19 patients with respiratory failure","volume":"81","author":"Ueland","year":"2020","journal-title":"J\u00a0Infect"},{"key":"B42","doi-asserted-by":"publisher","first-page":"295","DOI":"10.5114\/ait.2022.121091","article-title":"Respiratory mechanics in late COVID-19 ARDS - a restrictive pattern is strongly associated with death. A cohort study","volume":"54","author":"Pesta\u00f1a","year":"2022","journal-title":"Anaesthesiol Intensive Ther"},{"key":"B43","doi-asserted-by":"publisher","DOI":"10.1111\/imm.13623","article-title":"The role of HMGB1 in COVID-19-induced cytokine storm and its potential therapeutic targets: a review","volume":"169","author":"Wulandari","year":"2023","journal-title":"Immunology"},{"key":"B44","doi-asserted-by":"publisher","DOI":"10.3390\/cells10102754","article-title":"Basophils and mast cells in COVID-19 pathogenesis","volume":"10","author":"Murdaca","year":"2021","journal-title":"Cells"},{"key":"B45","doi-asserted-by":"publisher","DOI":"10.1016\/j.celrep.2021.109173","article-title":"Dynamics of B cell repertoires and emergence of cross-reactive responses in patients with different severities of COVID-19","volume":"35","author":"Montague","year":"2021","journal-title":"Cell Rep"},{"key":"B46","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1159\/000508647","article-title":"Heparin 2.0: a new approach to the infection crisis","volume":"50","author":"Seffer","year":"2021","journal-title":"Blood Purif"},{"key":"B47","doi-asserted-by":"publisher","DOI":"10.1002\/rth2.12582","article-title":"Severe COVID-19 is associated with endothelial activation and abnormal glycosylation of von Willebrand factor in patients undergoing hemodialysis","volume":"5","author":"Mobayen","year":"2021","journal-title":"Res Pract Thromb Haemost"},{"key":"B48","doi-asserted-by":"publisher","DOI":"10.1093\/cid\/ciaa248","article-title":"Dysregulation of immune response in patients with coronavirus 2019 (COVID-19) in Wuhan, China","volume":"71","author":"Qin","year":"2020","journal-title":"Clin Infect Dis"},{"key":"B49","doi-asserted-by":"publisher","DOI":"10.11613\/bm.2021.030501","article-title":"Complete blood count alterations in COVID-19 patients: a narrative review","volume":"31","author":"Palladino","year":"2021","journal-title":"Biochem Med (Zagreb)"},{"key":"B50","doi-asserted-by":"publisher","DOI":"10.3390\/medicina60060842","article-title":"Elevated cardiac troponin I as a mortality predictor in hospitalised COVID-19 patients","volume":"60","author":"Kubiliute","year":"2024","journal-title":"Med (Kaunas)"},{"key":"B51","doi-asserted-by":"publisher","DOI":"10.1007\/s44446-025-00030-6","article-title":"Clinical features and mortality risk in acute ischemic stroke with COVID-19: a multicenter-based comparative analysis of elderly and younger populations in Saudi Arabia","volume":"33","author":"Almarghalani","year":"2025","journal-title":"Saudi Pharm J"},{"key":"B52","unstructured":""},{"key":"B53","doi-asserted-by":"publisher","DOI":"10.7717\/peerj.9945","article-title":"A descriptive study of random forest algorithm for predicting COVID-19 patients outcome","volume":"8","author":"Wang","year":"2020","journal-title":"PeerJ"},{"key":"B54","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-020-05592-1","article-title":"Development and external evaluation of predictions models for mortality of COVID-19 patients using machine learning method","volume":"35","author":"Li","year":"2023","journal-title":"Neural Comput Appl"},{"key":"B55","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2020-041983","article-title":"Value of dynamic clinical and biomarker data for mortality risk prediction in COVID-19: a multicentre retrospective cohort study","volume":"10","author":"Berzuini","year":"2020","journal-title":"BMJ Open"}],"container-title":["Frontiers in Immunology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fimmu.2026.1789048\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T06:05:33Z","timestamp":1779689133000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fimmu.2026.1789048\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,25]]},"references-count":55,"alternative-id":["10.3389\/fimmu.2026.1789048"],"URL":"https:\/\/doi.org\/10.3389\/fimmu.2026.1789048","relation":{},"ISSN":["1664-3224"],"issn-type":[{"value":"1664-3224","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,25]]},"article-number":"1789048"}}