{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T01:13:29Z","timestamp":1792113209416,"version":"4.4.0"},"reference-count":45,"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. Oncol."],"abstract":"<jats:sec><jats:title>Background<\/jats:title><jats:p>Neuregulin 4 (NRG4) is a novel metabolic regulator closely associated with insulin resistance and thyroid dysfunction. However, its role in the pathogenesis of comorbid type 2 diabetes mellitus and hyperthyroidism (T2DM-FT) remains to be systematically elucidated. Given the complex clinical characteristics of T2DM-FT patients, traditional statistical methods are often insufficient to effectively analyze nonlinear relationships among multiple variables. Machine learning techniques have garnered widespread attention due to their advantages in modeling high-dimensional, heterogeneous data.<\/jats:p><\/jats:sec><jats:sec><jats:title>Objective<\/jats:title><jats:p>This study was to evaluate the predictive capability of a support vector machine (SVM) model based on serum NRG4 combined with a convolutional neural network (CNN) and long short-term memory network (LSTM)-based ultrasound feature classification (SVM-CNN+LSTM) model for predicting the occurrence of FT in patients with T2DM.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>Studied 500 T2DM patients (60 with FT, 440 without), and 200 healthy controls. Collected data on demographics, disease characteristics, NRG4, and thyroid indices. Pearson correlation was used to identify features correlated with NRG4. A parameter-optimized SVM model (C=1, linear kernel) was constructed for structured data modeling. Additionally, a CNN+LSTM network was employed to extract spatial (thyroid morphology) and temporal (hemodynamics) features from ultrasound sequences. These features were then fused with biochemical indicators, such as NRG4, to develop the final SVM-CNN+LSTM multimodal predictive model.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Serum NRG4 levels in T2DM+FT patients were significantly higher than those in the healthy Ctrl group (4.44 \u00b1 1.25 <jats:italic>vs.<\/jats:italic> 2.17 \u00b1 0.48 \u03bcg\/L, <jats:italic>P<\/jats:italic>&amp;lt; 0.05). NRG4 levels were positively correlated with HOMA-IR (<jats:italic>r<\/jats:italic> = 0.593), FT3 (<jats:italic>r<\/jats:italic> = 0.773), FT4 (<jats:italic>r<\/jats:italic> = 0.683), thyroid volume (<jats:italic>r<\/jats:italic> = 0.652), and the resistance index (RI) (<jats:italic>r<\/jats:italic> = 0.473) (<jats:italic>P<\/jats:italic>&amp;lt; 0.05). The optimized SVM model demonstrated a sensitivity of 86.23%, specificity of 90.33%, and an area under the curve (AUC) of 0.887. In contrast, the fusion model SVM-CNN+LSTM outperformed the SVM model across all metrics, achieving a sensitivity of 91.32%, specificity of 94.18%, and an AUC of 0.943 (<jats:italic>P<\/jats:italic>&amp;lt; 0.05).<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>The SVM-CNN+LSTM multimodal model, which integrates serum NRG4 levels with ultrasound features, significantly enhances the predictive accuracy of hyperthyroidism in T2DM patients. This approach effectively reveals the multifactorial mechanisms underlying T2DM-FT comorbidity, providing a powerful tool for early clinical intervention.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fonc.2025.1595553","type":"journal-article","created":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T05:35:33Z","timestamp":1752644133000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Predictive study of machine learning combined with serum Neuregulin 4 levels for hyperthyroidism in type II diabetes mellitus"],"prefix":"10.3389","volume":"15","author":[{"given":"Huilan","family":"Gu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ye","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,7,16]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1038\/s41574-022-00776-2","article-title":"Cardiorenal diseases in type 2 diabetes mellitus: clinical trials and real-world practice","volume":"19","author":"Lim","year":"2023","journal-title":"Nat Rev Endocrinol"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1016\/j.sjbs.2021.09.008","article-title":"Analysis of OCT1, OCT2 and OCT3 gene polymorphisms among Type 2 diabetes mellitus subjects in Indian ethnicity, Malaysia","volume":"29","author":"Ghasan Abood Al-Ashoor","year":"2022","journal-title":"Saudi J Biol Sci"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.7861\/clinmed.2023-0195","article-title":"Assessment and management of chronic kidney disease in people living with obesity","volume":"23","author":"Jacob","year":"2023","journal-title":"Clin Med (London England)"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.2147\/DMSO.S271328","article-title":"Prevalence of thyroid dysfunction in a chinese population with different glucose intolerance status: A community-based cross-sectional study","volume":"13","author":"Huang","year":"2020","journal-title":"Diabetes Metab syndrome obesity: Targets Ther"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.4103\/jfmpc.jfmpc_2106_21","article-title":"Prevalence and predictors of thyroid dysfunction amongst patients with Type 2 diabetes mellitus in Pakistan","volume":"11","author":"Bukhari","year":"2022","journal-title":"J Family Med primary Care"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.2147\/IJGM.S273900","article-title":"Prevalence and predictors of thyroid dysfunction among type 2 diabetic patients: A case-control study","volume":"13","author":"Khassawneh","year":"2020","journal-title":"Int J Gen Med"},{"key":"B7","doi-asserted-by":"publisher","first-page":"195","DOI":"10.5222\/MMJ.2020.29964","article-title":"Is there any relationship between thyroid function abnormalities, thyroid antibodies and development of gestational diabetes mellitus (GDM) in pregnant women","volume":"35","author":"Sert","year":"2020","journal-title":"Medeniyet Med J"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.33314\/jnhrc.v20i4.4541","article-title":"Dyslipidemia and thyroid dysfunction associated with psoriasis","volume":"20","author":"Rizal","year":"2023","journal-title":"J Nepal Health Res Council"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.11604\/pamj.2023.44.86.35649","article-title":"Characterization of Hashimoto\u00b4s thyroiditis in Sudanese children: a cross-sectional study at Gaafar Ibnauf Hospital, Khartoum","volume":"44","author":"Fadlalbari","year":"2023","journal-title":"Pan Afr Med J"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyt.2023.1156481","article-title":"Thyroid dysfunction in young, first-episode and drug-na\u00efve patients with major depressive disorder: prevalence and associated clinical factors","volume":"14","author":"Wu","year":"2023","journal-title":"Front Psychiatry"},{"key":"B11","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1080\/07435800.2020.1721528","article-title":"Differences in neuregulin 4 expression in children: effects of fat depots and obese status","volume":"45","author":"Wang","year":"2020","journal-title":"Endocrine Res"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1080\/21623945.2024.2390833","article-title":"Low circulating levels of neuregulin 4 as a potential biomarker associated with the severity and prognosis of obesity-related metabolic diseases: a systematic review","volume":"13","author":"Ziqubu","year":"2024","journal-title":"Adipocyte"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.2147\/JIR.S492115","article-title":"The potential of neuregulin 4 as a novel biomarker and therapeutic agent for vascular complications in type 2 diabetes mellitus","volume":"17","author":"Dan","year":"2024","journal-title":"J Inflammation Res"},{"key":"B14","doi-asserted-by":"publisher","first-page":"11981","DOI":"10.1038\/s41598-020-68771-z","article-title":"Early detection of type 2 diabetes mellitus using machine learning-based prediction models","volume":"10","author":"Kopitar","year":"2020","journal-title":"Sci Rep"},{"key":"B15","doi-asserted-by":"publisher","first-page":"e16850","DOI":"10.2196\/16850","article-title":"Predicting the development of type 2 diabetes in a large Australian cohort using machine-learning techniques: longitudinal survey study","volume":"8","author":"Zhang","year":"2020","journal-title":"JMIR Med Inf"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10185-6","article-title":"Developments in the detection of diabetic retinopathy: a state-of-the-art review of computer-aided diagnosis and machine learning methods","volume":"56","author":"Selvachandran","year":"2023","journal-title":"Artif Intell Rev"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1016\/j.jjcc.2021.06.002","article-title":"Predicting 30-day mortality after ST elevation myocardial infarction: Machine learning- based random forest and its external validation using two independent nationwide datasets","volume":"78","author":"Hadanny","year":"2021","journal-title":"J Cardiol"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocaa306","article-title":"Importance-aware personalized learning for early risk prediction using static and dynamic health data","volume":"28","author":"Tan","year":"2021","journal-title":"J Am Med Inf Association: JAMIA"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.3760\/cma.j.issn.0253-9624.2019.08.004","article-title":"Prospective cohort study on association between peri-conceptional air pollution exposure and gestational diabetes mellitus","volume":"53","author":"Yao","year":"2019","journal-title":"Chin J Prev Med"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.3881\/j.issn.1000-503X.15754","article-title":"Diagnostic value of american thyroid association guidelines,American college of radiology thyroid imaging reporting and data system,and chinese thyroid imaging reporting and data system alone and combined with BRAFV600E mutation in atypia of undetermined significance\/follicular lesion of undetermined significance","volume":"45","author":"Lin","year":"2023","journal-title":"Acta Academiae Medicinae Sinicae"},{"key":"B21","doi-asserted-by":"publisher","first-page":"e14487","DOI":"10.1111\/dme.14487","article-title":"Trends in prevalence and incidence of type 2 diabetes among adults in Beijing, China, from 2008 to 2017","volume":"38","author":"Wang","year":"2021","journal-title":"Diabetic medicine: J Br Diabetic Assoc"},{"key":"B22","doi-asserted-by":"publisher","first-page":"e20697","DOI":"10.7759\/cureus.20697","article-title":"The relationship between type 2 diabetes mellitus and related thyroid diseases","volume":"13","author":"Mohammed Hussein","year":"2021","journal-title":"Cureus"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.2147\/DMSO.S404172","article-title":"Relationship between serum 25-hydroxyvitamin D deficiency and thyroid disease in postmenopausal women with type 2 diabetes mellitus","volume":"16","author":"Li","year":"2023","journal-title":"Diabetes Metab syndrome obesity: Targets Ther"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.3390\/biomedicines11020346","article-title":"Type 2 diabetes mellitus coincident with clinical and subclinical thyroid dysfunctions results in dysregulation of circulating chemerin, resistin and visfatin","volume":"11","author":"Tabandeh","year":"2023","journal-title":"Biomedicines"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.13702\/j.1000-0607.20230187","article-title":"Electroacupuncture intervention improves lipid metabolism and promotes browning of white adipose tissue by activating AMPK\/Sirt1 pathway and up-regulating Nrg4 content in middle-aged and aged obese rats","volume":"48","author":"He","year":"2023","journal-title":"Zhen ci yan jiu = Acupuncture Res"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1016\/j.clnesp.2023.10.013","article-title":"Effects of oleoylethanolamide supplementation on the expression of lipid metabolism-related genes and serum NRG4 levels in patients with non-alcoholic fatty liver disease: A randomized controlled trial","volume":"58","author":"Tutunchi","year":"2023","journal-title":"Clin Nutr ESPEN"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.3389\/fphys.2021.667330","article-title":"Adiposity measurements and metabolic syndrome are linked through circulating neuregulin 4 and adipsin levels in obese adults","volume":"12","author":"Guo","year":"2021","journal-title":"Front Physiol"},{"key":"B28","doi-asserted-by":"publisher","first-page":"687","DOI":"10.1016\/j.gendis.2023.03.021","article-title":"The journey towards physiology and pathology: Tracing the path of neuregulin 4","volume":"11","author":"Chen","year":"2023","journal-title":"Genes Dis"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1530\/EC-19-0175","article-title":"Elevated serum neuregulin 4 levels in patients with hyperthyroidism","volume":"8","author":"Li","year":"2019","journal-title":"Endocrine connections"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2018.00793","article-title":"Elevated serum growth differentiation factor 15 levels in hyperthyroid patients","volume":"9","author":"Zhao","year":"2019","journal-title":"Front Endocrinol"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1111\/jcpt.13233","article-title":"The impact of combination therapy with metformin and exogenous vitamin D on hypothalamic-pituitary-thyroid axis activity in women with autoimmune thyroiditis and high-normal thyrotropin levels","volume":"45","author":"Krysiak","year":"2020","journal-title":"J Clin Pharm Ther"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoenv.2020.111706","article-title":"Relationship between excess iodine, thyroid function, blood pressure, and blood glucose level in adults, pregnant women, and lactating women: A cross-sectional study","volume":"208","author":"Wang","year":"2021","journal-title":"Ecotoxicology Environ Saf"},{"key":"B33","doi-asserted-by":"publisher","first-page":"687","DOI":"10.1016\/j.gendis.2023.03.021","article-title":"The journey towards physiology and pathology: Tracing the path of neuregulin 4","volume":"11","author":"Chen","year":"2023","journal-title":"Genes Dis"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1530\/EC-19-0175","article-title":"Elevated serum neuregulin 4 levels in patients with hyperthyroidism","volume":"8","author":"Li","year":"2019","journal-title":"Endocrine connections"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.4239\/wjd.v15.i3.348","article-title":"Association of autoimmune thyroid disease with type 1 diabetes mellitus and its ultrasonic diagnosis and management","volume":"15","author":"Wang","year":"2024","journal-title":"World J Diabetes"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.2147\/IJGM.S418520","article-title":"Correlation between glycemic variability and diabetic complications: A narrative review","volume":"16","author":"Huang","year":"2023","journal-title":"Int J Gen Med"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.32604\/cmc.2023.041191","article-title":"SNSVM: squeezeNet-guided SVM for breast cancer diagnosis","volume":"76","author":"Wang","year":"2023","journal-title":"Computers materials continua"},{"key":"B38","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1016\/j.ymeth.2024.02.003","article-title":"CT radiomics analysis discriminates pulmonary lesions in patients with pulmonary MALT lymphoma and non-pulmonary MALT lymphoma","volume":"224","author":"Le","year":"2024","journal-title":"Methods (San Diego Calif.)"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.1016\/j.cellsig.2024.111134","article-title":"Deciphering alternative splicing events and their therapeutic implications in colorectal Cancer","volume":"118","author":"Ding","year":"2024","journal-title":"Cell signalling"},{"key":"B40","doi-asserted-by":"publisher","first-page":"e37363","DOI":"10.1097\/MD.0000000000037363","article-title":"A machine learning-based diagnostic model for myocardial infarction patients: Analysis of neutrophil extracellular traps-related genes and eQTL Mendelian randomization","volume":"103","author":"Sheng","year":"2024","journal-title":"Medicine"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2024.1320335","article-title":"Predictive model and risk analysis for peripheral vascular disease in type 2 diabetes mellitus patients using machine learning and shapley additive explanation","volume":"15","author":"Liu","year":"2024","journal-title":"Front Endocrinol"},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.3390\/s24051500","article-title":"A movement classification of polymyalgia rheumatica patients using myoelectric sensors","volume":"24","author":"Bawa","year":"2024","journal-title":"Sensors (Basel Switzerland)"},{"key":"B43","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2021.661358","article-title":"Detection of SARS-coV-2 infection in human nasopharyngeal samples by combining MALDI-TOF MS and artificial intelligence","volume":"8","author":"Deulofeu","year":"2021","journal-title":"Front Med"},{"key":"B44","doi-asserted-by":"publisher","first-page":"e37112","DOI":"10.1097\/MD.0000000000037112","article-title":"Specific patterns and potential risk factors to predict 3-year risk of death among non-cancer patients with advanced chronic kidney disease by machine learning","volume":"103","author":"Chang","year":"2024","journal-title":"Medicine"},{"key":"B45","doi-asserted-by":"publisher","DOI":"10.1186\/s12902-023-01368-5","article-title":"Comparison of the cox regression to machine learning in predicting the survival of anaplastic thyroid carcinoma","volume":"23","author":"Xu","year":"2023","journal-title":"BMC endocrine Disord"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2025.1595553\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T05:35:37Z","timestamp":1752644137000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2025.1595553\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,16]]},"references-count":45,"alternative-id":["10.3389\/fonc.2025.1595553"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2025.1595553","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,16]]},"article-number":"1595553"}}