{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T09:17:37Z","timestamp":1785403057857,"version":"3.56.0"},"reference-count":20,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T00:00:00Z","timestamp":1774396800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"German Diabetes Center"},{"id":[{"id":"https:\/\/ror.org\/04ews3245","id-type":"ROR","asserted-by":"publisher"}]},{"name":"Ministry of Culture and Science of the State of North Rhine-Westphalia"},{"name":"German Federal Ministry of Education and Research (BMBF) to the German Center for Diabetes Research"},{"name":"European Community","award":["HORIZON-HLTH-2022STAYHLTH-02\u201301: Panel A"],"award-info":[{"award-number":["HORIZON-HLTH-2022STAYHLTH-02\u201301: Panel A"]}]},{"DOI":"10.13039\/501100001659","name":"German Research Foundation","doi-asserted-by":"crossref","award":["GRK 2576"],"award-info":[{"award-number":["GRK 2576"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"crossref"}]},{"award":["GRK 2576"],"award-info":[{"award-number":["GRK 2576"]}],"id":[{"id":"https:\/\/ror.org\/018mejw64","id-type":"ROR","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021371","name":"Schmutzler Stiftung","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100021371","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Ministry of Culture and Science of the State of Northrhine Westphalia"},{"name":"Ministry of Education and Science of Poland"},{"name":"Ministry of Health of Poland"},{"DOI":"10.13039\/501100023181","name":"Medical Research Agency","doi-asserted-by":"crossref","award":["2023\/ABM\/02\/00008"],"award-info":[{"award-number":["2023\/ABM\/02\/00008"]}],"id":[{"id":"10.13039\/501100023181","id-type":"DOI","asserted-by":"crossref"}]},{"name":"BreakthroughT1D","award":["2-SRA-2025-1653-S-B"],"award-info":[{"award-number":["2-SRA-2025-1653-S-B"]}]},{"DOI":"10.13039\/501100004587","name":"Instituto de Salud Carlos III","doi-asserted-by":"publisher","award":["PMP21\/00063"],"award-info":[{"award-number":["PMP21\/00063"]}],"id":[{"id":"10.13039\/501100004587","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004587","name":"Instituto de Salud Carlos III","doi-asserted-by":"publisher","award":["PMP22\/00049"],"award-info":[{"award-number":["PMP22\/00049"]}],"id":[{"id":"10.13039\/501100004587","id-type":"DOI","asserted-by":"publisher"}]},{"award":["PMP21\/00063"],"award-info":[{"award-number":["PMP21\/00063"]}],"id":[{"id":"https:\/\/ror.org\/00ca2c886","id-type":"ROR","asserted-by":"publisher"}]},{"award":["PMP22\/00049"],"award-info":[{"award-number":["PMP22\/00049"]}],"id":[{"id":"https:\/\/ror.org\/00ca2c886","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IJMS"],"abstract":"<jats:p>Type 1 diabetes (T1D) is an autoimmune disease with a strong genetic component (~70% heritability). Early identification of individuals at risk is crucial for early intervention or risk assessment. Although polygenic risk scores (PRS) have shown promise in risk assessment, most current approaches remain constrained by linear assumptions and limited generalizability. We aimed to develop a neural network-driven classifier using T1D-associated single nucleotide polymorphisms (SNPs). In addition, we explored the inclusion of an entropy-derived feature as a complementary variable, representing the degree of genetic variability within an individual\u2019s genotype profile across the 67 T1D-associated SNPs, to evaluate its potential additive contribution to the model performance. We analyzed genotype data from 11,909 individuals in the UK BioBank (546 T1D cases and 11,363 controls). Sixty-seven well-known SNPs associated with T1D were utilized as inputs to the model, using two distinct allele-encoding strategies. A feed-forward neural network was evaluated under varying case\u2013control ratios through five-fold cross-validation. Performance was assessed using the area under the receiver operating characteristic curve (AUC) on a held-out test set and on an external European cohort as a validation cohort. Across five-fold cross-validation, the best configuration achieved a median AUC of 0.903. On the held-out UK Biobank test set, the model generalized well, with an AUC of 0.8889 (95% CI: 0.8516\u20130.9262). A probability-based risk framework, constructed using five risk groups (\u201cvery low\u201d, \u201clow\u201d, \u201cintermediate\u201d, \u201chigh\u201d, and \u201cvery high\u201d risk), yielded a negative predictive value (NPV) of 98.9% for the \u201cvery low\u201d risk group and a Positive Predicted Value (PPV) of 61.9% with a specificity of 97.3% for the \u201cvery high\u201d risk group, assuming a 10% T1D prevalence. External validation in the German Diabetes Study reproduced clear case\u2013control separation; for individuals with recent onset diabetes and glutamic acid decarboxylase antibodies (GADA+) vs. controls, specificity reached 91.9% in the \u201chigh\u201d risk group (PPV of 94.3%) and 97.6% in the \u201cvery high\u201d risk group (PPV of 95.7%). The proposed neural network reliably predicts T1D genetic risk using a compact SNP panel of 67 SNPs and maintains accuracy in both internal and external European cohorts. Its probabilistic output enables clinically interpretable risk thresholds, while entropy features contributed modestly to performance. These results demonstrate that a neural network-based approach achieves discriminative performance that is comparable to established T1D genetic risk models, while offering flexible probability-based risk stratification and architectural extensibility for future integration of additional features.<\/jats:p>","DOI":"10.3390\/ijms27072966","type":"journal-article","created":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T09:11:14Z","timestamp":1774429874000},"page":"2966","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Type 1 Diabetes Polygenic Risk Prediction Through Neural Networks and Entropy-Derived Insights"],"prefix":"10.3390","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-1782-3433","authenticated-orcid":false,"given":"Antonio","family":"Nadal-Mart\u00ednez","sequence":"first","affiliation":[{"name":"Soft Computing, Image Processing and Aggregation (SCOPIA) Research Group, University of the Balearic Islands (UIB), 07122 Palma, Spain"},{"name":"Health Research Institute of the Balearic Islands (IdISBa), 07010 Palma, Spain"},{"name":"Artificial Intelligence Research Institute of the UIB (IAIB), University of the Balearic Islands, 07122 Palma, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guillermo","family":"P\u00e9rez-Solero","sequence":"additional","affiliation":[{"name":"Research Department Unit, N-GENE, Carretera Betlem, s\/n, Colonia de Sant Pere, 07579 Arta, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9303-0515","authenticated-orcid":false,"given":"Sandra","family":"Ferreiro L\u00f3pez","sequence":"additional","affiliation":[{"name":"Research Department Unit, N-GENE, Carretera Betlem, s\/n, Colonia de Sant Pere, 07579 Arta, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7065-0802","authenticated-orcid":false,"given":"Jorge","family":"Blom-Dahl","sequence":"additional","affiliation":[{"name":"Research Department Unit, N-GENE, Carretera Betlem, s\/n, Colonia de Sant Pere, 07579 Arta, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2518-9076","authenticated-orcid":false,"given":"Eduard","family":"Montanya","sequence":"additional","affiliation":[{"name":"Bellvitge Biomedical Research Institute (IDIBELL), Hospital Universitari de Bellvitge, University of Barcelona, 08907 Barcelona, Spain"},{"name":"Centro de Investigaci\u00f3n Biom\u00e9dica en Red de Diabetes y Enfermedades Metab\u00f3licas Asociadas (CIBERDEM), Instituto de Salud Carlos III, 28029 Madrid, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marta","family":"Alonso-Bern\u00e1ldez","sequence":"additional","affiliation":[{"name":"Research Department Unit, N-GENE, Carretera Betlem, s\/n, Colonia de Sant Pere, 07579 Arta, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0007-591X","authenticated-orcid":false,"given":"Moises","family":"Shabot","sequence":"additional","affiliation":[{"name":"Research Department Unit, N-GENE, Carretera Betlem, s\/n, Colonia de Sant Pere, 07579 Arta, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christian","family":"Binsch","sequence":"additional","affiliation":[{"name":"Department of Endocrinology and Diabetology, Medical Faculty and University Hospital, Heinrich Heine University, 40225 D\u00fcsseldorf, Germany"},{"name":"Institute for Clinical Diabetology, German Diabetes Center (DDZ), Leibniz Institute for Diabetes Research at Heinrich Heine University, 40225 D\u00fcsseldorf, Germany"},{"name":"German Center for Diabetes Research, M\u00fcnchen-Neuherberg, 85764 Neuherberg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6201-0605","authenticated-orcid":false,"given":"Lukasz","family":"Szczerbinski","sequence":"additional","affiliation":[{"name":"Center for Genomic Medicine, Massachusetts General Hospital, Boston, MA 02114, USA"},{"name":"Diabetes Unit, Department of Medicine, Massachusetts General Hospital, Boston, MA 02114, USA"},{"name":"Programs in Metabolism and Medical & Population Genetics, Broad Institute, Cambridge, MA 02142, USA"},{"name":"Department of Endocrinology, Diabetology and Internal Medicine, Medical University of Bialystok, 15-174 Bialystok, Poland"},{"name":"Clinical Research Centre, Medical University of Bialystok, 15-174 Bialystok, Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adam","family":"Kretowski","sequence":"additional","affiliation":[{"name":"Department of Endocrinology, Diabetology and Internal Medicine, Medical University of Bialystok, 15-174 Bialystok, Poland"},{"name":"Clinical Research Centre, Medical University of Bialystok, 15-174 Bialystok, Poland"},{"name":"Centre for Digital Medicine, Medical University of Bialystok, 15-174 Bialystok, Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juli\u00e1n","family":"Nevado","sequence":"additional","affiliation":[{"name":"Instituto de Gen\u00e9tica M\u00e9dica y Molecular (INGEMM), Instituto de Investigaci\u00f3n del Hospital Universitario La Paz (IdiPaz), Hospital Universitario La Paz, 28046 Madrid, Spain"},{"name":"CIBERER, Centro de Investigaci\u00f3n Biom\u00e9dica en Red de Enfermedades Raras, Instituto de Salud Carlos III, 28029 Madrid, Spain"},{"name":"ERN-ITHACA, European Reference Network on Rare Malformations Syndromes, Intellectual and Other Neuro-Developmental Disorders, 75019 Paris, France"},{"name":"Centro Universitario HM Hospitales de Ciencias de la Salud (CUHMED), Universidad Camilo Jos\u00e9 Cela, 28660 Madrid, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6324-4825","authenticated-orcid":false,"given":"Pablo","family":"Lapunzina","sequence":"additional","affiliation":[{"name":"Instituto de Gen\u00e9tica M\u00e9dica y Molecular (INGEMM), Instituto de Investigaci\u00f3n del Hospital Universitario La Paz (IdiPaz), Hospital Universitario La Paz, 28046 Madrid, Spain"},{"name":"CIBERER, Centro de Investigaci\u00f3n Biom\u00e9dica en Red de Enfermedades Raras, Instituto de Salud Carlos III, 28029 Madrid, Spain"},{"name":"ERN-ITHACA, European Reference Network on Rare Malformations Syndromes, Intellectual and Other Neuro-Developmental Disorders, 75019 Paris, France"},{"name":"Centro Universitario HM Hospitales de Ciencias de la Salud (CUHMED), Universidad Camilo Jos\u00e9 Cela, 28660 Madrid, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert","family":"Wagner","sequence":"additional","affiliation":[{"name":"Department of Endocrinology and Diabetology, Medical Faculty and University Hospital, Heinrich Heine University, 40225 D\u00fcsseldorf, Germany"},{"name":"Institute for Clinical Diabetology, German Diabetes Center (DDZ), Leibniz Institute for Diabetes Research at Heinrich Heine University, 40225 D\u00fcsseldorf, Germany"},{"name":"German Center for Diabetes Research, M\u00fcnchen-Neuherberg, 85764 Neuherberg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5308-2316","authenticated-orcid":false,"given":"Jair","family":"Tenorio-Castano","sequence":"additional","affiliation":[{"name":"Research Department Unit, N-GENE, Carretera Betlem, s\/n, Colonia de Sant Pere, 07579 Arta, Spain"},{"name":"Instituto de Gen\u00e9tica M\u00e9dica y Molecular (INGEMM), Instituto de Investigaci\u00f3n del Hospital Universitario La Paz (IdiPaz), Hospital Universitario La Paz, 28046 Madrid, Spain"},{"name":"CIBERER, Centro de Investigaci\u00f3n Biom\u00e9dica en Red de Enfermedades Raras, Instituto de Salud Carlos III, 28029 Madrid, Spain"},{"name":"ERN-ITHACA, European Reference Network on Rare Malformations Syndromes, Intellectual and Other Neuro-Developmental Disorders, 75019 Paris, France"},{"name":"Centro Universitario HM Hospitales de Ciencias de la Salud (CUHMED), Universidad Camilo Jos\u00e9 Cela, 28660 Madrid, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,3,25]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1016\/S2213-8587(17)30362-5","article-title":"Frequency and phenotype of type 1 diabetes in the first six decades of life: A cross-sectional, genetically stratified survival analysis from UK Biobank","volume":"6","author":"Thomas","year":"2018","journal-title":"Lancet Diabetes Endocrinol."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"2473","DOI":"10.1001\/jama.2013.6285","article-title":"Seroconversion to Multiple Islet Autoantibodies and Risk of Progression to Diabetes in Children","volume":"309","author":"Ziegler","year":"2013","journal-title":"JAMA"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"2331","DOI":"10.1016\/S0140-6736(16)30582-7","article-title":"Genetic risk factors for type 1 diabetes","volume":"387","author":"Pociot","year":"2016","journal-title":"Lancet"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Bonifacio, E., Beyerlein, A., Hippich, M., Winkler, C., Vehik, K., Weedon, M.N., Laimighofer, M., Hattersley, A.T., Krumsiek, J., and Frohnert, B.I. (2018). Genetic scores to stratify risk of developing multiple islet autoantibodies and type 1 diabetes: A prospective study in children. PLoS Med., 15.","DOI":"10.1371\/journal.pmed.1002548"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1016\/j.molmet.2016.02.003","article-title":"Primary prevention of beta-cell autoimmunity and type 1 diabetes\u2014The Global Platform for the Prevention of Autoimmune Diabetes (GPPAD) perspectives","volume":"5","author":"Ziegler","year":"2016","journal-title":"Mol. Metab."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"2151","DOI":"10.1056\/NEJMoa2308743","article-title":"Teplizumab and \u03b2-Cell Function in Newly Diagnosed Type 1 Diabetes","volume":"389","author":"Ramos","year":"2023","journal-title":"N. Engl. J. Med."},{"key":"ref_7","first-page":"1","article-title":"\u00bfEstamos en una nueva era en el tratamiento de la diabetes de tipo 1?","volume":"14","year":"2024","journal-title":"Rev. Espa\u00f1ola Endocrinol. Pedi\u00e1trica"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"733","DOI":"10.1111\/j.1399-5448.2011.00774.x","article-title":"The Environmental Determinants of Diabetes in the Young (TEDDY): Genetic criteria and international diabetes risk screening of 421,000 infants","volume":"12","author":"Hagopian","year":"2011","journal-title":"Pediatr. Diabetes"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1111\/j.1464-5491.2011.03419.x","article-title":"Miscoding, misclassification and misdiagnosis of diabetes in primary care","volume":"29","author":"Sadek","year":"2012","journal-title":"Diabet. Med."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"S112","DOI":"10.2337\/dc09-S203","article-title":"Diabetes in African American Youth","volume":"32","author":"Beyer","year":"2009","journal-title":"Diabetes Care"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"406","DOI":"10.2337\/dc18-1727","article-title":"Type 1 Diabetes Risk in African-Ancestry Participants and Utility of an Ancestry-Specific Genetic Risk Score","volume":"42","author":"Chen","year":"2019","journal-title":"Diabetes Care"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"200","DOI":"10.2337\/dc18-1785","article-title":"Development and Standardization of an Improved Type 1 Diabetes Genetic Risk Score for Use in Newborn Screening and Incident Diagnosis","volume":"42","author":"Sharp","year":"2019","journal-title":"Diabetes Care"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"320","DOI":"10.1111\/pedi.13310","article-title":"Improved genetic risk scoring algorithm for type 1 diabetes prediction","volume":"23","author":"Qu","year":"2022","journal-title":"Pediatr. Diabetes"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1124","DOI":"10.2337\/dc20-2872","article-title":"Utility of Diabetes Type\u2013Specific Genetic Risk Scores for the Classification of Diabetes Type Among Multiethnic Youth","volume":"45","author":"Oram","year":"2022","journal-title":"Diabetes Care"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"e81","DOI":"10.2337\/dc25-0142","article-title":"Standardized Measurement of Type 1 Diabetes Polygenic Risk Across Multiancestry Population Cohorts","volume":"48","author":"Luckett","year":"2025","journal-title":"Diabetes Care"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Sudlow, C., Gallacher, J., Allen, N., Beral, V., Burton, P., Danesh, J., Downey, P., Elliott, P., Green, J., and Landray, M. (2015). UK Biobank: An Open Access Resource for Identifying the Causes of a Wide Range of Complex Diseases of Middle and Old Age. PLoS Med., 12.","DOI":"10.1371\/journal.pmed.1001779"},{"key":"ref_17","first-page":"1929","article-title":"Dropout: A Simple Way to Prevent Neural Networks from Overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"The GDS Group, Szendroedi, J., Saxena, A., Weber, K.S., Strassburger, K., Herder, C., Burkart, V., Nowotny, B., Icks, A., and Kuss, O. (2016). Cohort profile: The German Diabetes Study (GDS). Cardiovasc. Diabetol., 15, 59.","DOI":"10.1186\/s12933-016-0374-9"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"American Diabetes Association (2012). Diagnosis and Classification of Diabetes Mellitus. Diabetes Care, 35, S64\u2013S71.","DOI":"10.2337\/dc12-s064"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Di Santo, R., Niccolini, B., Rosa, E., De Spirito, M., Pizzolante, F., Pitocco, D., Tartaglione, L., Rizzi, A., Basile, U., and Petito, V. (2025). Artificial Intelligence for Liquid Biopsy: FTIR Spectroscopy and Autoencoder-Based Detection of Cancer Biomarkers in Extracellular Vesicles. Cells, 14.","DOI":"10.3390\/cells14231909"}],"container-title":["International Journal of Molecular Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1422-0067\/27\/7\/2966\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T15:48:29Z","timestamp":1775058509000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1422-0067\/27\/7\/2966"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,25]]},"references-count":20,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["ijms27072966"],"URL":"https:\/\/doi.org\/10.3390\/ijms27072966","relation":{},"ISSN":["1422-0067"],"issn-type":[{"value":"1422-0067","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,25]]}}}