{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T21:05:46Z","timestamp":1790370346650,"version":"4.1.0"},"reference-count":54,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T00:00:00Z","timestamp":1752624000000},"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. Med."],"abstract":"<jats:sec><jats:title>Background<\/jats:title><jats:p>Early identification of Type 1 Diabetes Mellitus (T1DM) in pediatric populations is crucial for implementing timely interventions and improving long-term outcomes. Peripheral blood transcriptomic analysis provides a minimally invasive approach for identifying predictive biomarkers prior to clinical manifestation. This study aimed to develop and validate machine learning algorithms utilizing transcriptomic signatures to predict T1DM onset in children up to 46\u202fmonths before clinical diagnosis.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>We analyzed 247 peripheral blood RNA-sequencing samples from pre-diabetic children and age-matched healthy controls. Differential gene expression analysis was performed using established bioinformatics pipelines to identify significantly dysregulated transcripts. Five feature selection methods (Lasso, Elastic Net, Random Forest, Support Vector Machine, and Gradient Boosting Machine) were employed to optimize gene sets. Nine machine learning algorithms (Decision Tree, Gradient Boosting Machine, K-Nearest Neighbors, Linear Discriminant Analysis, Logistic Regression, Multilayer Perceptron, Naive Bayes, Random Forest, and Support Vector Machine) were combined with selected features, generating 45 unique model combinations. Performance was evaluated using accuracy, precision, recall, and F1-score metrics. Model validation was conducted using quantitative polymerase chain reaction (qPCR) in an independent cohort of six children (three healthy, three diabetic).<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Transcriptomic analysis revealed significant differential expression patterns between pre-diabetic and control groups. Four model combinations demonstrated superior predictive performance: Lasso+K-Nearest Neighbors, Elastic Net\u202f+\u202fK-Nearest Neighbors, Elastic Net\u202f+\u202fRandom Forest, and Support Vector Machine+K-Nearest Neighbors. These models achieved high accuracy in predicting diabetes onset up to 46\u202fmonths before clinical diagnosis. Both Elastic Net-based models achieved perfect classification performance in the validation cohort, demonstrating their potential as clinically viable diagnostic tools.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>This study establishes the feasibility of integrating peripheral blood transcriptomic profiling with machine learning for early pediatric T1DM prediction. The identified transcriptomic signatures and validated predictive models provide a foundation for developing clinically translatable, non-invasive diagnostic tools. These findings support the implementation of precision medicine approaches for childhood diabetes prevention and warrant validation in larger, multi-center cohorts to assess generalizability and clinical utility.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fmed.2025.1636214","type":"journal-article","created":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T13:18:38Z","timestamp":1752671918000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Development and validation of machine learning-based diagnostic models using blood transcriptomics for early childhood diabetes prediction"],"prefix":"10.3389","volume":"12","author":[{"given":"Xin","family":"Huang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Di","family":"Ouyang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiming","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huawei","family":"Zhuang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siyu","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lizhong","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,7,16]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12951-023-02253-y","article-title":"Polymeric nanoparticles (PNPs) for oral delivery of insulin","volume":"22","author":"Wang","year":"2024","journal-title":"J Nanobiotechnol"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"1631","DOI":"10.7150\/thno.92463","article-title":"Emerging role of extracellular vesicles in diabetic retinopathy","volume":"14","author":"Zhu","year":"2024","journal-title":"Theranostics"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1007\/s13300-023-01515-0","article-title":"Efficacy and safety of once-weekly Semaglutide versus once-daily Sitagliptin as metformin add-on in a Korean population with type 2 diabetes","volume":"15","author":"Lee","year":"2024","journal-title":"Diabetes Ther"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41522-023-00475-4","article-title":"Dietary emulsifier consumption accelerates type 1 diabetes development in NOD mice","volume":"10","author":"Delaroque","year":"2024","journal-title":"NPJ Biofilms Microbiomes"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"11980","DOI":"10.3390\/ijms241511980","article-title":"Pediatric type 1 diabetes: mechanisms and impact of technologies on comorbidities and life expectancy","volume":"24","author":"Urbano","year":"2023","journal-title":"Int J Mol Sci"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"433","DOI":"10.1111\/pedi.12302","article-title":"Cardiovascular medication use and cardiovascular disease in children and adolescents with type 1 diabetes: a population-based cohort study","volume":"17","author":"Ahmadizar","year":"2016","journal-title":"Pediatr Diabetes"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1186\/s12902-022-01107-2","article-title":"The sonographic quantitative assessment of the deltoid muscle to detect type 2 diabetes mellitus: a potential noninvasive and sensitive screening method?","volume":"22","author":"Rosen","year":"2022","journal-title":"BMC Endocr Disord"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"e24656","DOI":"10.1016\/j.heliyon.2024.e24656","article-title":"Mechanism of damage of HIF-1 signaling in chronic diabetic foot ulcers and its related therapeutic perspectives","volume":"10","author":"Zhu","year":"2024","journal-title":"Heliyon"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1007\/s13300-023-01513-2","article-title":"A systematic literature review of psychological interventions for adults with type 1 diabetes","volume":"15","author":"Diribe","year":"2024","journal-title":"Diabetes Ther"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"e1009926","DOI":"10.1371\/journal.pcbi.1009926","article-title":"The ability to classify patients based on gene-expression data varies by algorithm and performance metric","volume":"18","author":"Piccolo","year":"2022","journal-title":"PLoS Comput Biol"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"2136","DOI":"10.3390\/ijerph19042136","article-title":"Stability risk assessment of underground rock pillars using logistic model trees","volume":"19","author":"Li","year":"2022","journal-title":"Int J Environ Res Public Health"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"342","DOI":"10.1186\/s12916-023-03045-9","article-title":"Detection of diabetic patients in people with normal fasting glucose using machine learning","volume":"21","author":"Lv","year":"2023","journal-title":"BMC Med"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"150674","DOI":"10.1016\/j.scitotenv.2021.150674","article-title":"Environmental chemical exposure dynamics and machine learning-based prediction of diabetes mellitus","volume":"806","author":"Wei","year":"2022","journal-title":"Sci Total Environ"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1007\/s00125-017-4460-7","article-title":"Enterovirus-associated changes in blood transcriptomic profiles of children with genetic susceptibility to type 1 diabetes","volume":"61","author":"Lietzen","year":"2018","journal-title":"Diabetologia"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"2402","DOI":"10.2337\/db13-1775","article-title":"Innate immune activity is detected prior to seroconversion in children with HLA-conferred type 1 diabetes susceptibility","volume":"63","author":"Kallionp\u00e4\u00e4","year":"2014","journal-title":"Diabetes"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1152\/physrev.00003.2010","article-title":"Type 1 diabetes: etiology, immunology, and therapeutic strategies","volume":"91","author":"van Belle","year":"2011","journal-title":"Physiol Rev"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"973","DOI":"10.3390\/cancers15030973","article-title":"Intestinal epithelial cells adapt to chronic inflammation through partial genetic reprogramming","volume":"15","author":"Collin","year":"2023","journal-title":"Cancers (Basel)"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"8169981","DOI":"10.1155\/2022\/8169981","article-title":"Down-regulation of insulin like growth factor 1 involved in Alzheimer\u2019s disease via MAPK, Ras, and FoxO signaling pathways","volume":"2022","author":"Kang","year":"2022","journal-title":"Oxidative Med Cell Longev"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"9962397","DOI":"10.1155\/2022\/9962397","article-title":"Neoadjuvant chemotherapy improves the immunosuppressive microenvironment of bladder cancer and increases the sensitivity to immune checkpoint blockade","volume":"2022","author":"Luo","year":"2022","journal-title":"J Immunol Res"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"e1010050","DOI":"10.1371\/journal.pcbi.1010050","article-title":"Microbiome-based disease prediction with multimodal variational information bottlenecks","volume":"18","author":"Grazioli","year":"2022","journal-title":"PLoS Comput Biol"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"5847242","DOI":"10.1155\/2022\/5847242","article-title":"Comparative analysis on alignment-based and pretrained feature representations for the identification of DNA-binding proteins","volume":"2022","author":"Chen","year":"2022","journal-title":"Comput Math Methods Med"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"103319","DOI":"10.1016\/j.nicl.2023.103319","article-title":"Age-level bias correction in brain age prediction","volume":"37","author":"Zhang","year":"2023","journal-title":"Neuroimage Clin"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"1007","DOI":"10.1038\/s42255-022-00620-x","article-title":"BMP4 and gremlin 1 regulate hepatic cell senescence during clinical progression of NAFLD\/NASH","volume":"4","author":"Baboota","year":"2022","journal-title":"Nat Metab"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"21052","DOI":"10.1021\/acsomega.2c01839","article-title":"Machine learning-assisted Design of Yttria-Stabilized Zirconia Thermal Barrier Coatings with high bonding strength","volume":"7","author":"Xu","year":"2022","journal-title":"ACS Omega"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1007\/s11250-022-03073-2","article-title":"Assessing machine learning techniques in forecasting lumpy skin disease occurrence based on meteorological and geospatial features","volume":"54","author":"Afshari Safavi","year":"2022","journal-title":"Trop Anim Health Prod"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"311","DOI":"10.21037\/jtd-23-1430","article-title":"Prediction of postoperative final degree and recurrence of pectus excavatum using machine learning algorithms","volume":"16","author":"Hyun","year":"2024","journal-title":"J Thorac Dis"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1167\/tvst.9.2.12","article-title":"A 3D deep learning system for detecting referable Glaucoma using full OCT macular cube scans","volume":"9","author":"Russakoff","year":"2020","journal-title":"Transl Vis Sci Technol"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1016\/j.ajhg.2020.05.017","article-title":"De novo variants in CNOT1, a central component of the CCR4-NOT complex involved in gene expression and RNA and protein stability, cause neurodevelopmental delay","volume":"107","author":"Vissers","year":"2020","journal-title":"Am J Hum Genet"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"758","DOI":"10.1002\/pro.4262","article-title":"Structure of the human Ccr4-not nuclease module using X-ray crystallography and electron paramagnetic resonance spectroscopy distance measurements","volume":"31","author":"Zhang","year":"2022","journal-title":"Protein Sci"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1016\/j.immuni.2019.12.015","article-title":"Clec2d joins the cell death sensor ranks","volume":"52","author":"Del Fresno","year":"2020","journal-title":"Immunity"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"5482","DOI":"10.3390\/cancers13215482","article-title":"GCC2 as a new early diagnostic biomarker for non-small cell lung Cancer","volume":"13","author":"Jeong","year":"2021","journal-title":"Cancers (Basel)"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"7356297","DOI":"10.1155\/2022\/7356297","article-title":"Prognostic value of an integrin-based signature in hepatocellular carcinoma and the identification of immunological role of LIMS2","volume":"2022","author":"Ye","year":"2022","journal-title":"Dis Markers"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1186\/s12911-022-02092-1","article-title":"Machine learning based efficient prediction of positive cases of waterborne diseases","volume":"23","author":"Hussain","year":"2023","journal-title":"BMC Med Inform Decis Mak"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"510","DOI":"10.1126\/science.abh1654","article-title":"Immunotherapy: building a bridge to a cure for type 1 diabetes","volume":"373","author":"Bluestone","year":"2021","journal-title":"Science"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1038\/s41556-024-01368-0","article-title":"Redox regulation of m6A methyltransferase METTL3 in \u03b2-cells controls the innate immune response in type 1 diabetes","volume":"26","author":"De Jesus","year":"2024","journal-title":"Nat Cell Biol"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"91","DOI":"10.4049\/jimmunol.1501061","article-title":"The expression of BAFF is controlled by IRF transcription factors","volume":"196","author":"Sj\u00f6strand","year":"2016","journal-title":"J Immunol"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1146\/annurev-immunol-101921-044122","article-title":"Designing Cancer immunotherapies that engage T cells and NK cells","volume":"41","author":"Kyrysyuk","year":"2023","journal-title":"Annu Rev Immunol"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"3151","DOI":"10.1080\/15548627.2023.2239633","article-title":"Starvation-inactivated MTOR triggers cell migration via a ULK1-SH3PXD2A\/TKS5-MMP14 pathway in ovarian carcinoma","volume":"19","author":"Lin","year":"2023","journal-title":"Autophagy"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"1228","DOI":"10.1002\/eji.202149560","article-title":"ICAP-1 loss impairs CD8+ thymocyte development and leads to reduced marginal zone B cells in mice","volume":"52","author":"Sevilla-Movilla","year":"2022","journal-title":"Eur J Immunol"},{"key":"ref40","doi-asserted-by":"publisher","first-page":"15879","DOI":"10.1007\/s00432-023-05360-3","article-title":"Integrative analysis reveals that SLC38A1 promotes hepatocellular carcinoma development via PI3K\/AKT\/mTOR signaling via glutamine mediated energy metabolism","volume":"149","author":"Feng","year":"2023","journal-title":"J Cancer Res Clin Oncol"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1631\/jzus.B2300457","article-title":"Roles of THEM4 in the Akt pathway: a double-edged sword","volume":"25","author":"Xie","year":"2024","journal-title":"J Zhejiang Univ Sci B"},{"key":"ref42","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1016\/j.envres.2016.11.019","article-title":"Modulation of blood pressure in response to low ambient temperature: the role of DNA methylation of zinc finger genes","volume":"153","author":"Lim","year":"2017","journal-title":"Environ Res"},{"key":"ref43","doi-asserted-by":"publisher","first-page":"1515","DOI":"10.1093\/jleuko\/qiae151","article-title":"MT1E in AML: a gateway to understanding regulatory cell death and immunotherapeutic responses","volume":"116","author":"Zhuang","year":"2024","journal-title":"J Leukoc Biol"},{"key":"ref44","doi-asserted-by":"publisher","first-page":"2877","DOI":"10.1038\/s41467-025-57996-z","article-title":"Foxk1 and Foxk2 promote cardiomyocyte proliferation and heart regeneration","volume":"16","author":"Cai","year":"2025","journal-title":"Nat Commun"},{"key":"ref45","doi-asserted-by":"publisher","first-page":"941","DOI":"10.1016\/j.gendis.2021.03.009","article-title":"The pseudogenes of eukaryotic translation elongation factors (EEFs): role in cancer and other human diseases","volume":"9","author":"Cristiano","year":"2022","journal-title":"Genes Dis"},{"key":"ref46","doi-asserted-by":"publisher","first-page":"1527","DOI":"10.1016\/j.molcel.2023.03.030","article-title":"Chaperone-directed ribosome repair after oxidative damage","volume":"83","author":"Yang","year":"2023","journal-title":"Mol Cell"},{"key":"ref47","doi-asserted-by":"publisher","first-page":"680","DOI":"10.1007\/s13238-021-00839-6","article-title":"Higher-order assemblies in immune signaling: supramolecular complexes and phase separation","volume":"12","author":"Xia","year":"2021","journal-title":"Protein Cell"},{"key":"ref48","doi-asserted-by":"publisher","first-page":"e70362","DOI":"10.1371\/journal.pone.0070362","article-title":"Different genetic associations of the IgE production among fetus, infancy and childhood","volume":"8","author":"Chang","year":"2013","journal-title":"PLoS One"},{"key":"ref49","doi-asserted-by":"publisher","first-page":"947","DOI":"10.1016\/j.stemcr.2017.02.018","article-title":"Identification of three early phases of cell-fate determination during osteogenic and Adipogenic differentiation by transcription factor dynamics","volume":"8","author":"van de Peppel","year":"2017","journal-title":"Stem Cell Rep"},{"key":"ref50","doi-asserted-by":"publisher","first-page":"e70332","DOI":"10.1111\/jcmm.70332","article-title":"Foxk2 enhances Adipogenic differentiation by relying on the transcriptional activation of peroxisome proliferator-activated receptor gamma","volume":"29","author":"Zhang","year":"2025","journal-title":"J Cell Mol Med"},{"key":"ref51","doi-asserted-by":"publisher","first-page":"e63836","DOI":"10.1002\/ajmg.a.63836","article-title":"CNOT1 p.Arg535Cys variant in holoprosencephaly with late onset diabetes mellitus","volume":"194","author":"de Queiroz J\u00fanior","year":"2024","journal-title":"Am J Med Genet A"},{"key":"ref52","doi-asserted-by":"publisher","first-page":"102962","DOI":"10.1016\/j.artmed.2024.102962","article-title":"Multiomics and eXplainable artificial intelligence for decision support in insulin resistance early diagnosis: a pediatric population-based longitudinal study","volume":"156","author":"Torres-Martos","year":"2024","journal-title":"Artif Intell Med"},{"key":"ref53","doi-asserted-by":"publisher","first-page":"103133","DOI":"10.1016\/j.inffus.2025.103133","article-title":"Reflections and attentiveness on eXplainable artificial intelligence (XAI). The journey ahead from criticisms to human\u2013AI collaboration","volume":"121","author":"Herrera","year":"2025","journal-title":"Inf Fusion"},{"key":"ref54","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/j.inffus.2019.12.012","article-title":"Explainable artificial intelligence (XAI): concepts, taxonomies, opportunities and challenges toward responsible AI","volume":"58","author":"Barredo Arrieta","year":"2020","journal-title":"Informat Fusion"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1636214\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T13:18:39Z","timestamp":1752671919000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1636214\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,16]]},"references-count":54,"alternative-id":["10.3389\/fmed.2025.1636214"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2025.1636214","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,16]]},"article-number":"1636214"}}