{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T05:55:47Z","timestamp":1776318947190,"version":"3.50.1"},"reference-count":28,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T00:00:00Z","timestamp":1776297600000},"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>\n                      Accurate prediction of long-term CD4\n                      <jats:sup>+<\/jats:sup>\n                      T-cell recovery trajectories in people living with HIV on antiretroviral therapy (ART) is a crucial unmet need for personalized monitoring and treatment optimization. Traditional statistical models have limited ability to capture the complex, non-linear relationships inherent in longitudinal clinical data.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      We developed a heterogeneous stacking ensemble framework to predict longitudinal CD4\n                      <jats:sup>+<\/jats:sup>\n                      count, CD8\n                      <jats:sup>+<\/jats:sup>\n                      count, and CD4\/CD8 ratio. The model integrates four tree-based algorithms\u2014XGBoost, LightGBM, Random Forest, and Gradient Boosting\u2014with a Ridge regression meta-learner. It was trained and tested on a retrospective cohort of 5,436 patients who initiated ART between 2016 and 2025, using only demographic and clinical features while explicitly excluding baseline CD4\n                      <jats:sup>+<\/jats:sup>\n                      \/CD8\n                      <jats:sup>+<\/jats:sup>\n                      counts to prevent data leakage.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      On an independent test set (n=1,088), the ensemble achieved an R\n                      <jats:sup>2<\/jats:sup>\n                      of 0.768 (MAE: 74.8 cells\/\u03bcL) for CD4\n                      <jats:sup>+<\/jats:sup>\n                      count, 0.636 (MAE: 300.5 cells\/\u03bcL) for CD8\n                      <jats:sup>+<\/jats:sup>\n                      count, and 0.131 (MAE: 0.137) for the CD4\/CD8 ratio. This represents a relative improvement in R\n                      <jats:sup>2<\/jats:sup>\n                      of 66.4% for CD4\n                      <jats:sup>+<\/jats:sup>\n                      and 128.6% for CD8\n                      <jats:sup>+<\/jats:sup>\n                      predictions compared to a baseline Robust Transformer model. The model accurately replicated the statistical distributions of observed outcomes and demonstrated stable learning dynamics without overfitting.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Our ensemble learning framework provides a robust and clinically applicable tool for forecasting multi-dimensional immune reconstitution in HIV care. By synthesizing diverse algorithmic perspectives without relying on baseline immunology, it offers a foundation for data-driven clinical decision support to personalize long-term treatment monitoring.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fimmu.2026.1805202","type":"journal-article","created":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T05:25:45Z","timestamp":1776317145000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Predicting immune reconstitution after antiretroviral therapy in HIV\/AIDS using ensemble machine learning: a real-world study"],"prefix":"10.3389","volume":"17","author":[{"given":"Juan","family":"Jin","sequence":"first","affiliation":[{"name":"Department of Infectious Diseases, The Eighth\u2019s Hospital of Xi\u2019an","place":["Xi\u2019an, Shaanxi, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tingting","family":"Li","sequence":"additional","affiliation":[{"name":"Drug Clinical Trial Institution Office, Xi\u2019an Chest Hospital","place":["Xi\u2019an, Shaanxi, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Infectious Diseases, The Eighth\u2019s Hospital of Xi\u2019an","place":["Xi\u2019an, Shaanxi, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huanhuan","family":"Ba","sequence":"additional","affiliation":[{"name":"Department of Infectious Diseases, The Eighth\u2019s Hospital of Xi\u2019an","place":["Xi\u2019an, Shaanxi, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Infectious Diseases, The Eighth\u2019s Hospital of Xi\u2019an","place":["Xi\u2019an, Shaanxi, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiajia","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Infectious Diseases, The Eighth\u2019s Hospital of Xi\u2019an","place":["Xi\u2019an, Shaanxi, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinling","family":"Yin","sequence":"additional","affiliation":[{"name":"Department of Infectious Diseases, The Eighth\u2019s Hospital of Xi\u2019an","place":["Xi\u2019an, Shaanxi, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huanqing","family":"Liu","sequence":"additional","affiliation":[{"name":"Information Management Office, Northwestern Polytechnical University","place":["Xi\u2019an, Shaanxi, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kangxiao","family":"Ma","sequence":"additional","affiliation":[{"name":"Department of Infectious Diseases, The Eighth\u2019s Hospital of Xi\u2019an","place":["Xi\u2019an, Shaanxi, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,4,16]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1016\/S2352-3018(21)00152-1","article-title":"Global, regional, and national sex-specific burden and control of the HIV epidemic, 1990-2019, for 204 countries and territories: the Global Burden of Diseases Study 2019","volume":"8","year":"2021","journal-title":"Lancet HIV"},{"key":"B2","doi-asserted-by":"publisher","first-page":"15035","DOI":"10.1038\/nrdp.2015.35","article-title":"HIV infection","volume":"1","author":"Deeks","year":"2015","journal-title":"Nat Rev Dis Primers"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1097\/QAD.0000000000000049","article-title":"A systematic review of definitions of extreme phenotypes of HIV control and progression","volume":"28","author":"Gurdasani","year":"2014","journal-title":"AIDS"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1093\/cid\/cix731","article-title":"Machine learning for healthcare: On the verge of a major shift in healthcare epidemiology","volume":"66","author":"Wiens","year":"2018","journal-title":"Clin Infect Dis"},{"key":"B5","doi-asserted-by":"publisher","first-page":"474","DOI":"10.1186\/s12879-024-09368-z","article-title":"The predictive accuracy of machine learning for the risk of death in HIV patients: a systematic review and meta-analysis","volume":"24","author":"Li","year":"2024","journal-title":"BMC Infect Dis"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1086\/595851","article-title":"The absence of CD4+ T cell count recovery despite receipt of virologically suppressive highly active antiretroviral therapy: clinical risk, immunological gaps, and therapeutic options","volume":"48","author":"Gazzola","year":"2009","journal-title":"Clin Infect Dis"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0097482","article-title":"Efficacy of initial antiretroviral therapy for HIV-1 infection in adults: a systematic review and meta-analysis of 114 studies with up to 144 weeks' follow-up","volume":"9","author":"Lee","year":"2014","journal-title":"PLoS One"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1097\/00126334-200406010-00007","article-title":"Long-term CD4+ T-cell response to highly active antiretroviral therapy according to baseline CD4+ T-cell count","volume":"36","author":"Garc\u00eda","year":"2004","journal-title":"J Acquir Immune Defic Syndr"},{"key":"B9","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1097\/QAD.0000000000000033","article-title":"Common clinical conditions - age, low BMI, ritonavir use, mild renal impairment - affect tenofovir pharmacokinetics in a large cohort of HIV-infected women","volume":"28","author":"Baxi","year":"2014","journal-title":"AIDS"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1097\/inf.0000000000001478","article-title":"Modelling CD4 T cell recovery in hepatitis C and HIV co-infected children receiving antiretroviral therapy","volume":"36","author":"Majekodunmi","year":"2017","journal-title":"Pediatr Infect Dis J"},{"key":"B11","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1186\/s12874-019-0681-4","article-title":"Machine learning in medicine: a practical introduction","volume":"19","author":"Sidey-Gibbons","year":"2019","journal-title":"BMC Med Res Methodol"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.3389\/fcimb.2025.1542707","article-title":"Predictive survival modelings for HIV-related cryptococcosis: comparing machine learning approaches","volume":"15","author":"Fu","year":"2025","journal-title":"Front Cell Infect Microbiol"},{"key":"B13","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1186\/s12874-018-0482-1","article-title":"DeepSurv: personalized treatment recommender system using a Cox proportional hazards deep neural network","volume":"18","author":"Katzman","year":"2018","journal-title":"BMC Med Res Methodol"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2018.06.011","article-title":"A study of generalizability of recurrent neural network-based predictive models for heart failure onset risk using a large and heterogeneous EHR data set","volume":"84","author":"Rasmy","year":"2018","journal-title":"J BioMed Inform"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2023.3348436","article-title":"Is attention all you need in medical image analysis? A review","volume":"28","author":"Papanastasiou","year":"2024","journal-title":"IEEE J BioMed Health Inform"},{"key":"B16","first-page":"14794","article-title":"Rethinking attention with performers","author":"Choromanski","year":"2020","journal-title":"arXiv preprint arXiv:2009"},{"key":"B17","doi-asserted-by":"publisher","first-page":"7155","DOI":"10.1038\/s41598-020-62922-y","article-title":"BEHRT: transformer for electronic health records","volume":"10","author":"Li","year":"2020","journal-title":"Sci Rep"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2021.3070203","article-title":"A survey on multi-task learning","volume":"34","author":"Zhang","year":"2021","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1371\/journal.ppat.1004078","article-title":"HIV-infected individuals with low CD4\/CD8 ratio despite effective antiretroviral therapy exhibit altered T cell subsets, heightened CD8+ T cell activation, and increased risk of non-AIDS morbidity and mortality","volume":"10","author":"Serrano-Villar","year":"2014","journal-title":"PLoS Pathog"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2025.104823","article-title":"Multi-modal fusion model for time-varying medical data: Addressing long-term dependencies and memory challenges in sequence fusion","volume":"165","author":"Ma","year":"2025","journal-title":"J BioMed Inf"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1001\/jamainternmed.2021.2626","article-title":"External validation of a widely implemented proprietary sepsis prediction model in hospitalized patients","volume":"181","author":"Wong","year":"2021","journal-title":"JAMA Intern Med"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.3389\/fcimb.2022.867737","article-title":"Construction of machine learning models to predict changes in immune function using clinical monitoring indices in HIV\/AIDS patients after 9.9-years of antiretroviral therapy in Yunnan, China","volume":"12","author":"Li","year":"2022","journal-title":"Front Cell Infect Microbiol"},{"key":"B23","doi-asserted-by":"publisher","first-page":"432","DOI":"10.1186\/s12967-024-05147-1","article-title":"Predicting humoral responses to primary and booster SARS-CoV-2 mRNA vaccination in people living with HIV: a machine learning approach","volume":"22","author":"Montesi","year":"2024","journal-title":"J Transl Med"},{"key":"B24","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1038\/s43856-025-00987-4","article-title":"Machine learning approaches to dissect hybrid and vaccine-induced immunity","volume":"5","author":"Montesi","year":"2025","journal-title":"Commun Med (Lond)"},{"key":"B25","doi-asserted-by":"publisher","first-page":"12715","DOI":"10.1038\/s41598-022-16062-0","article-title":"Applying machine learning and predictive modeling to retention and viral suppression in South African HIV treatment cohorts","volume":"12","author":"Maskew","year":"2022","journal-title":"Sci Rep"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1093\/ofid\/ofx262","article-title":"Systemic inflammation, coagulation, and clinical risk in the START trial","volume":"4","author":"Baker","year":"2017","journal-title":"Open Forum Infect Dis"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2017.1307116","article-title":"Distribution-free predictive inference for regression","volume":"113","author":"Lei","year":"2018","journal-title":"J Am Stat Assoc"},{"key":"B28","article-title":"Interpretable machine learning in healthcare","author":"Ahmad","year":"2018"}],"container-title":["Frontiers in Immunology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fimmu.2026.1805202\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T05:25:46Z","timestamp":1776317146000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fimmu.2026.1805202\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,16]]},"references-count":28,"alternative-id":["10.3389\/fimmu.2026.1805202"],"URL":"https:\/\/doi.org\/10.3389\/fimmu.2026.1805202","relation":{},"ISSN":["1664-3224"],"issn-type":[{"value":"1664-3224","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,16]]},"article-number":"1805202"}}