{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T11:07:12Z","timestamp":1792062432988,"version":"4.4.0"},"reference-count":47,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Med Inform"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Severe COVID-19 is a global health concern despite continuous vaccination campaigns because current therapies, such as dexamethasone and remdesivir, do not considerably improve immune function, especially in high-risk individuals. SARS-CoV-2\u2013specific T cells (CoV-2-STs) from vaccinated or convalescent donors are a promising new treatment that can enhance clinical outcomes and viral-specific immunity. CoV-2-STs improve T cell proliferation and recovery without raising safety concerns, according to randomized studies. Targeting patients for immunotherapy is made more difficult by the variability in COVID-19 progression brought on by variables like age and comorbidities. In order to further enable precision medicine and patient care, machine learning techniques are being used to analyze clinical data, predict disease severity, and optimize treatment. However, their use in guiding the treatment of novel therapies like CoV-2-STs using early cellular immunology data is limited and requires improvement.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n The purpose of this research was to stratify high-risk individuals using early immunological and clinical indicators, and to develop a prediction tool to enable individualized treatment decisions, either with standard of care (SoC) or with a combination of CoV-2-STs and SoC.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n \n A randomized phase 1\u20102 trial enrolled 87 patients with severe COVID-19 (CoV-2-STs+SoC: n=57; SoC only: n=30). We performed a post hoc machine learning analysis. Clinical and biomarker data from days 0 and 5 were analyzed longitudinally. Shrinkage linear discriminant analysis was used to create arm-specific prognostic models, and stratified cross-validation assessed performance (area under the receiver operating characteristic curve, area under the precision-recall curve, sensitivity, specificity,\n F<\/jats:italic>\n 1<\/jats:sub>\n -score, and Brier score). To investigate arm-swap scenarios, Monte Carlo simulations (4 variance models) generated hypothetical early-treatment trajectories.\n <\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n Day 5 analysis revealed a significant difference in CD3+, CD8+, CD56+, and CoV-2-STs between the 2 treatment groups (CoV-2-STs+SoC vs SoC). At Day 60, 64.9% (37\/57) of patients with CoV-2-STs+SoC survived, compared with 40% (12\/30) of patients with only SoC, resulting in a crude odds ratio of 2.8 (95% CI 1.1\u20106.9) for recovery. SoC-only models had an area under the curve between 0.72 and 0.76, while CoV-2-STs+SoC models had an area under the curve between 0.86 and 0.88. Area under the precision-recall curve values for CoV-2-STs+SOC models were 0.74\u20100.78, with sensitivity ranging from 0.89 to 0.91 and specificity from 0.83 to 0.87, compared with SoC-only models with a sensitivity of approximately 0.95 and a specificity of 0.58\u20100.62. Simulation studies indicate that CoV-2-STs+SoC may benefit up to 30% (approximately 9\/30) of patients receiving SoC alone. Misclassifying candidates with CoV-2-STs+SoC as SoC-only could increase critical outcomes by up to approximately 22%.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n A robust computational tool for severe COVID-19 risk stratification and treatment selection is presented. Precision medicine and early treatment outcome prediction are supported by clinical and immunological data integration. Prospective studies are needed to confirm its clinical utility.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/78471","type":"journal-article","created":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T20:44:46Z","timestamp":1780605886000},"page":"e78471-e78471","source":"Crossref","is-referenced-by-count":1,"title":["Early Immunological Biomarkers for Personalized Treatment Selection in Severe COVID-19: Post Hoc Machine Learning Analysis of a Randomized Clinical Trial"],"prefix":"10.2196","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2092-7041","authenticated-orcid":false,"given":"Symeon","family":"Savvopoulos","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5385-8738","authenticated-orcid":false,"given":"Anastasia","family":"Papadopoulou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3119-5720","authenticated-orcid":false,"given":"Georgios","family":"Karavalakis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4325-8856","authenticated-orcid":false,"given":"Ioanna","family":"Sakellari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9906-4797","authenticated-orcid":false,"given":"Grigorios","family":"Georgolopoulos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2090-2162","authenticated-orcid":false,"given":"Christos","family":"Argyropoulos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9849-1279","authenticated-orcid":false,"given":"Evangelia","family":"Yannaki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1270-7885","authenticated-orcid":false,"given":"Haralampos","family":"Hatzikirou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,6,4]]},"reference":[{"issue":"2","key":"R1","doi-asserted-by":"publisher","first-page":"186","DOI":"10.1038\/s41590-021-01122-w","article-title":"The T cell immune response against SARS-CoV-2","volume":"23","author":"Moss","journal-title":"Nat Immunol"},{"issue":"7","key":"R2","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2022.e09863","article-title":"Robust SARS-COV-2-specific T-cell immune memory persists long-term in immunocompetent individuals post BNT162b2 double shot","volume":"8","author":"Papadopoulou","journal-title":"Heliyon"},{"issue":"7","key":"R3","doi-asserted-by":"publisher","first-page":"1183","DOI":"10.1038\/s41409-022-01675-w","article-title":"Neutralizing antibody and T cell responses to SARS-CoV-2 vaccination in hematopoietic cell transplant recipients","volume":"57","author":"Gavriilaki","journal-title":"Bone Marrow Transplant"},{"issue":"7821","key":"R4","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1038\/s41586-020-2550-z","article-title":"SARS-CoV-2-specific T cell immunity in cases of COVID-19 and SARS, and uninfected controls","volume":"584","author":"Le Bert","journal-title":"Nature New Biol"},{"issue":"11","key":"R5","doi-asserted-by":"publisher","first-page":"2073","DOI":"10.1093\/cid\/ciab371","article-title":"Vaccinated and convalescent donor-derived severe acute respiratory syndrome coronavirus 2-specific T cells as adoptive immunotherapy for high-risk coronavirus disease 2019 patients","volume":"73","author":"Papayanni","journal-title":"Clin Infect Dis"},{"key":"R6","doi-asserted-by":"publisher","DOI":"10.3389\/fimmu.2021.751869","article-title":"Off-the-shelf partial HLA matching SARS-CoV-2 antigen specific T cell therapy: a new possibility for COVID-19 treatment","volume":"12","author":"Kim","journal-title":"Front Immunol"},{"issue":"25","key":"R7","doi-asserted-by":"publisher","first-page":"2905","DOI":"10.1182\/blood.2020008488","article-title":"SARS-CoV-2-specific T cells are rapidly expanded for therapeutic use and target conserved regions of the membrane protein","volume":"136","author":"Keller","journal-title":"Blood"},{"issue":"3","key":"R8","doi-asserted-by":"publisher","DOI":"10.1016\/j.xcrm.2022.100562","article-title":"Count on us: T cells in SARS-CoV-2 infection and vaccination","volume":"3","author":"Kedzierska","journal-title":"Cell Rep Med"},{"key":"R9","doi-asserted-by":"publisher","DOI":"10.3389\/fcell.2021.620730","article-title":"SARS-CoV-2-specific memory T lymphocytes from COVID-19 convalescent donors: identification, biobanking, and large-scale production for adoptive cell therapy","volume":"9","author":"Ferreras","journal-title":"Front Cell Dev Biol"},{"key":"R10","doi-asserted-by":"publisher","DOI":"10.3389\/fimmu.2020.598402","article-title":"Rapid GMP-compliant expansion of SARS-CoV-2-specific T cells from convalescent donors for use as an allogeneic cell therapy for COVID-19","volume":"11","author":"Cooper","journal-title":"Front Immunol"},{"issue":"4","key":"R11","doi-asserted-by":"publisher","DOI":"10.1002\/acg2.101","article-title":"Rapid production of clinical-grade SARS-CoV-2 specific T cells","volume":"3","author":"Leung","journal-title":"Adv Cell Gene Ther"},{"issue":"8","key":"R12","doi-asserted-by":"publisher","first-page":"2019","DOI":"10.1038\/s41591-023-02480-8","article-title":"SARS-CoV-2-specific T cell therapy for severe COVID-19: a randomized phase 1\/2 trial","volume":"29","author":"Papadopoulou","journal-title":"Nat Med"},{"key":"R13","doi-asserted-by":"publisher","DOI":"10.1016\/j.csbj.2014.11.005","article-title":"Machine learning applications in cancer prognosis and prediction","volume":"13","author":"Kourou","journal-title":"Comput Struct Biotechnol J"},{"key":"R14","doi-asserted-by":"publisher","DOI":"10.1038\/s43856-021-00020-4","article-title":"Improving personalized tumor growth predictions using a Bayesian combination of mechanistic modeling and machine learning","volume":"1","author":"Mascheroni","journal-title":"Commun Med (Lond)"},{"issue":"11","key":"R15","doi-asserted-by":"publisher","DOI":"10.3390\/jcm7110428","article-title":"Prediction of acute kidney injury after liver transplantation: machine learning approaches vs. logistic regression model","volume":"7","author":"Lee","journal-title":"J Clin Med"},{"issue":"3","key":"R16","doi-asserted-by":"publisher","first-page":"165","DOI":"10.21037\/jtd.2020.02.64","article-title":"Modified SEIR and AI prediction of the epidemics trend of COVID-19 in China under public health interventions","volume":"12","author":"Yang","journal-title":"J Thorac Dis"},{"issue":"8","key":"R17","doi-asserted-by":"publisher","first-page":"1435","DOI":"10.1007\/s11739-020-02475-0","article-title":"Utilization of machine-learning models to accurately predict the risk for critical COVID-19","volume":"15","author":"Assaf","journal-title":"Intern Emerg Med"},{"issue":"1","key":"R18","doi-asserted-by":"publisher","DOI":"10.2196\/24207","article-title":"Federated learning of electronic health records to improve mortality prediction in hospitalized patients with COVID-19: machine learning approach","volume":"9","author":"Vaid","journal-title":"JMIR Med Inform"},{"issue":"2","key":"R19","doi-asserted-by":"publisher","DOI":"10.21037\/atm-20-5328","article-title":"Deep learning for differentiating novel coronavirus pneumonia and influenza pneumonia","volume":"9","author":"Zhou","journal-title":"Ann Transl Med"},{"issue":"3","key":"R20","doi-asserted-by":"publisher","first-page":"E156","DOI":"10.1148\/radiol.2020201491","article-title":"Artificial intelligence augmentation of radiologist performance in distinguishing COVID-19 from pneumonia of other origin at chest CT","volume":"296","author":"Bai","journal-title":"Radiology"},{"issue":"17","key":"R21","doi-asserted-by":"publisher","DOI":"10.3390\/healthcare13172154","article-title":"Explainable AI in clinical decision support systems: a meta-analysis of methods, applications, and usability challenges","volume":"13","author":"Abbas","journal-title":"Healthcare (Basel)"},{"issue":"14","key":"R22","doi-asserted-by":"publisher","DOI":"10.3390\/healthcare13141642","article-title":"Exploring the role of artificial intelligence in smart healthcare: a capability and function-oriented review","volume":"13","author":"Abbas","journal-title":"Healthcare (Basel)"},{"issue":"1","key":"R23","doi-asserted-by":"publisher","first-page":"5033","DOI":"10.1038\/s41467-020-18684-2","article-title":"Machine learning based early warning system enables accurate mortality risk prediction for COVID-19","volume":"11","author":"Gao","journal-title":"Nat Commun"},{"key":"R24","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.m1328","article-title":"Prediction models for diagnosis and prognosis of COVID-19: systematic review and critical appraisal","volume":"369","author":"Wynants","journal-title":"BMJ"},{"key":"R25","unstructured":"Abyu GY . WHO R&D blueprint novel coronavirus COVID-19 therapeutic trial synopsis. 2020. URL: https:\/\/www.researchgate.net\/publication\/347549790_WHO_RD_Blueprint_novel_Coronavirus_COVID-19_Therapeutic_Trial_Synopsis [Accessed 27-05-2026]"},{"key":"R26","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-7-91","article-title":"Bias in error estimation when using cross-validation for model selection","volume":"7","author":"Varma","journal-title":"BMC Bioinformatics"},{"key":"R27","unstructured":"Kohavi R . A study of cross-validation and bootstrap for accuracy estimation and model selection. Presented at: IJCAI\u201995: Proceedings of the 14th International Joint Conference on Artificial Intelligence; Aug 20-25, 1995:1137-1143; Montreal, Cananda."},{"issue":"4","key":"R28","doi-asserted-by":"publisher","first-page":"316","DOI":"10.1080\/00031305.1990.10475751","article-title":"A suggestion for using powerful and informative tests of normality","volume":"44","author":"D\u2019agostino","journal-title":"Am Stat"},{"key":"R29","doi-asserted-by":"publisher","DOI":"10.2202\/1544-6115.1175","article-title":"A shrinkage approach to large-scale covariance matrix estimation and implications for functional genomics","volume":"4","author":"Sch\u00e4fer","journal-title":"Stat Appl Genet Mol Biol"},{"key":"R30","volume":"20","author":"Fisher","journal-title":"J Mach Learn Res"},{"issue":"260","key":"R31","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1080\/01621459.1952.10483441","article-title":"Use of ranks in one-criterion variance analysis","volume":"47","author":"Kruskal","journal-title":"J Am Stat Assoc"},{"issue":"302","key":"R32","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1080\/14786440009463897","article-title":"X. On the criterion that a given system of deviations from the probable in the case of a correlated system of variables is such that it can be reasonably supposed to have arisen from random sampling","volume":"50","author":"Pearson","journal-title":"The London, Edinburgh, and Dublin Philosophical Magazine and Journal of Science"},{"key":"R33","unstructured":"Bishop CM . Pattern Recognition and Machine Learning. Springer; 2006. ISBN: 978-1493938438"},{"issue":"1","key":"R34","doi-asserted-by":"publisher","first-page":"87","DOI":"10.2307\/2340521","article-title":"On the interpretation of \u03c7 2 from contingency tables, and the calculation of P","volume":"85","author":"Fisher","journal-title":"J R Stat Soc"},{"issue":"620","key":"R35","doi-asserted-by":"publisher","first-page":"7790","DOI":"10.1126\/scitranslmed.abj7790","article-title":"Lung epithelial and endothelial damage, loss of tissue repair, inhibition of fibrinolysis, and cellular senescence in fatal COVID-19","volume":"13","author":"D\u2019Agnillo","journal-title":"Sci Transl Med"},{"issue":"1","key":"R36","doi-asserted-by":"publisher","DOI":"10.1038\/s41392-023-01580-8","article-title":"The role of cell death in SARS-CoV-2 infection","volume":"8","author":"Yuan","journal-title":"Signal Transduct Target Ther"},{"key":"R37","doi-asserted-by":"publisher","DOI":"10.3389\/fnut.2022.825629","article-title":"Unraveling muscle impairment associated with COVID-19 and the role of 3D culture in Its investigation","volume":"9","author":"Seixas","journal-title":"Front Nutr"},{"issue":"4","key":"R38","doi-asserted-by":"publisher","first-page":"861","DOI":"10.1016\/j.cell.2021.01.007","article-title":"Adaptive immunity to SARS-CoV-2 and COVID-19","volume":"184","author":"Sette","journal-title":"Cell"},{"issue":"4","key":"R39","doi-asserted-by":"publisher","first-page":"996","DOI":"10.1016\/j.cell.2020.09.038","article-title":"Antigen-specific adaptive immunity to SARS-CoV-2 in acute COVID-19 and associations with age and disease severity","volume":"183","author":"Rydyznski Moderbacher","journal-title":"Cell"},{"issue":"2","key":"R40","doi-asserted-by":"publisher","DOI":"10.2196\/26773","article-title":"Rapid response to drive COVID-19 research in a learning health care system: rationale and design of the Houston methodist COVID-19 surveillance and outcomes registry (CURATOR)","volume":"9","author":"Vahidy","journal-title":"JMIR Med Inform"},{"key":"R41","doi-asserted-by":"publisher","DOI":"10.2196\/65590","article-title":"Data interoperability in COVID-19 vaccine trials: methodological approach in the VACCELERATE project","volume":"13","author":"Malik","journal-title":"JMIR Med Inform"},{"issue":"2","key":"R42","doi-asserted-by":"publisher","DOI":"10.1183\/13993003.01104-2020","article-title":"Development of a clinical decision support system for severity risk prediction and triage of COVID-19 patients at hospital admission: an international multicentre study","volume":"56","author":"Wu","journal-title":"Eur Respir J"},{"key":"R43","doi-asserted-by":"crossref","unstructured":"Izenman AJ . Linear Discriminant Analysis Modern Multivariate Statistical Techniques Regression, Classification, and Manifold Learning. Springer-Verlag New York Inc; 2013:237-280. URL: https:\/\/doi.org\/10.1007\/978-0-387-78189-1 [doi: 10.1007\/978-0-387-78189-1]","DOI":"10.1007\/978-0-387-78189-1"},{"issue":"2","key":"R44","doi-asserted-by":"publisher","first-page":"1","DOI":"10.4236\/oalib.1108414","article-title":"Comparison between common statistical modeling techniques used in research, including: discriminant analysis vs logistic regression, ridge regression vs LASSO, and decision tree vs random forest","volume":"09","author":"Abdulhafedh","journal-title":"Open Access Library Journal"},{"issue":"13","key":"R45","doi-asserted-by":"publisher","first-page":"2194","DOI":"10.3390\/math13132194","article-title":"A novel approach utilizing bagging, histogram gradient boosting, and advanced feature selection for predicting the onset of cardiovascular diseases","volume":"13","author":"Fitriyani","journal-title":"Mathematics"},{"issue":"5","key":"R46","doi-asserted-by":"publisher","DOI":"10.3390\/healthcare13050507","article-title":"HeartEnsembleNet: an innovative hybrid ensemble learning approach for cardiovascular risk prediction","volume":"13","author":"Zaidi","journal-title":"Healthcare (Basel)"},{"key":"R47","unstructured":"Savvopoulos S Papadopoulou A Karavalakis G et al. Cov-2-STs+SoC data. Zenodo. 2026. URL: https:\/\/doi.org\/10.5281\/zenodo.20155800 [Accessed 27-05-2026]"}],"container-title":["JMIR Medical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/medinform.jmir.org\/2026\/1\/e78471","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T22:26:53Z","timestamp":1785536813000},"score":1,"resource":{"primary":{"URL":"https:\/\/medinform.jmir.org\/2026\/1\/e78471"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,4]]},"references-count":47,"URL":"https:\/\/doi.org\/10.2196\/78471","relation":{},"ISSN":["2291-9694"],"issn-type":[{"value":"2291-9694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,4]]},"article-number":"v14i2e78471"}}