{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,31]],"date-time":"2026-10-31T20:17:50Z","timestamp":1793477870456,"version":"4.5.0"},"reference-count":51,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T00:00:00Z","timestamp":1759968000000},"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. Neurol."],"abstract":"<jats:sec><jats:title>Background<\/jats:title><jats:p>Patients with type 2 diabetes mellitus (T2DM) exhibit a heightened susceptibility to developing dementia, especially those who already present with mild cognitive impairment (MCI). Nevertheless, the fundamental etiology remains elusive, underscoring the pressing need for an objective and precise diagnostic approach in clinical settings. This study investigates the utilization of machine learning algorithms in conjunction with high-resolution sagittal T1-weighted structural imaging to facilitate automated diagnosis of T2DM patients with MCI, differentiating them from both T2DM patients without MCI and healthy controls (HCs).<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>Thirty patients with T2DM and MCI, thirty T2DM patients without MCI, and thirty matched healthy controls (HCs) were enrolled to identify independent biomarkers and develop a diagnostic model for early cognitive impairment in T2DM. Whole-brain structural features-including cortical surface area, volume, thickness, curvature index, folding index, Gaussian curvature, mean curvature, thickness standard deviation, nuclear volume, hippocampal volume, and white matter volume-were extracted from the images of brains using automated segmentation methods. The minimum redundancy maximum relevance (MRMR) method was employed to filter out irrelevant and redundant features, reducing the dimensionality of the dataset. Subsequently, the least absolute shrinkage and selection operator (LASSO) algorithm was applied for further feature selection, ensuring the retention of only the most diagnostic features. The Random Forest (RF) classifier, a powerful machine learning model within the realm of artificial intelligence, was meticulously trained utilizing a curated feature set that had undergone rigorous refinement. To ensure the robust diagnostic performance and generalizability of the established random forest model, a 5-fold cross-validation was employed, providing a dependable estimation of the model\u2019s effectiveness.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The FreeSurfer software automatically segmented the cerebral imaging data into up to 70 regions. For model establishment, a comprehensive set of 705 structural features, a series of neuropsychological tests, and standard laboratory tests were utilized. Ultimately, 8 features were selected through two feature selection strategies aimed at refining the optimal features. These included bilateral brainstem volume, left hippocampus volume, left transverse temporal gyrus volume, bilateral posterior corpus callosum volume, left medial orbitofrontal cortex Gaussian curvature, glycosylated hemoglobin, blood sugar levels, and the Digit Span Test (DST) backward score. The Random Forest (RF) model, based on the combined features, exhibited the excellent performance, with mean AUCs of 0.959 (95% CI, 0.940\u20130.997, mean specificity\u202f=\u202f94.2%, mean sensitivity\u202f=\u202f88.3%, mean accuracy\u202f=\u202f88.3% and mean precision\u202f=\u202f88.3%) for the training dataset and mean AUCs of 0.887 (95% CI, 0.746\u20130.992, mean specificity\u202f=\u202f85.0%, mean sensitivity\u202f=\u202f70.0%, mean accuracy\u202f=\u202f70.0% and mean precision\u202f=\u202f69.6%) for the testing dataset, based on 5-fold cross-validation.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>The RF model, leveraging a combination of features, demonstrates high accuracy in diagnosing T2DM with MCI. The exclusion of T2DM patients with complications may limit generalizability to the broader T2DM population, potentially inflating performance estimates. Among these features, 8 optimal indicators comprising 5 structural features, 1 neuropsychological test feature, and 2 standard laboratory test features emerge as the potential independent biomarkers for detecting early-stage cognitive impairment in T2DM patients. These features hold significant importance in understanding the pathophysiological mechanisms of T2DM-related cognitive impairment. Our fully automated model is capable of swiftly processing MRI data, enabling precise and objective differentiation of T2DM with MCI. This model significantly enhances diagnostic efficiency and holds considerable value in clinical practice, facilitating early diagnosis of T2DM with MCI.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fneur.2025.1599793","type":"journal-article","created":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T04:22:57Z","timestamp":1759983777000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Automatic diagnosis of type 2 diabetes mellitus with mild cognitive impairment using artificial intelligence based on routine T1-weighted MRI"],"prefix":"10.3389","volume":"16","author":[{"given":"Chang","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Xue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuwei","family":"Xia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingyan","family":"Le","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junbang","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuanming","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,10,9]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1016\/S1474-4422(05)70284-2","article-title":"Risk of dementia in diabetes mellitus: a systematic review","volume":"5","author":"Biessels","year":"2006","journal-title":"Lancet Neurol"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/s0014-2999(02)01486-3","article-title":"Ageing and diabetes: implications for brain function","volume":"441","author":"Biessels","year":"2002","journal-title":"Eur J Pharmacol"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"944","DOI":"10.1007\/s12529-024-10274-6","article-title":"The effects of type 2 diabetes on cognitive performance: a review of reviews","volume":"31","author":"Sola","year":"2024","journal-title":"Int J Behav Med"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"1004557","DOI":"10.3389\/fnagi.2022.1004557","article-title":"Astragaloside IV supplementation attenuates cognitive impairment by inhibiting neuroinflammation and oxidative stress in type 2 diabetic mice","volume":"14","author":"Zhang","year":"2022","journal-title":"Front Aging Neurosci"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"3172692","DOI":"10.1155\/2017\/3172692","article-title":"NRF2 plays a critical role in both self and EGCG protection against diabetic testicular damage","volume":"2017","author":"Pan","year":"2017","journal-title":"Oxidative Med Cell Longev"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"856","DOI":"10.3389\/fnins.2020.00856","article-title":"Type 2 diabetes mellitus may exacerbate gray matter atrophy in patients with early-onset mild cognitive impairment","volume":"14","author":"Li","year":"2020","journal-title":"Front Neurosci"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"615048","DOI":"10.3389\/fnagi.2020.615048","article-title":"Alterations of brain structural network connectivity in type 2 diabetes mellitus patients with mild cognitive impairment","volume":"12","author":"Li","year":"2020","journal-title":"Front Aging Neurosci"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"525","DOI":"10.1038\/s41574-022-00690-7","article-title":"The burden and risks of emerging complications of diabetes mellitus","volume":"18","author":"Tomic","year":"2022","journal-title":"Nat Rev Endocrinol"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"e823","DOI":"10.1212\/WNL.0000000000006955","article-title":"Type 2 diabetes mellitus, brain atrophy, and cognitive decline","volume":"92","author":"Moran","year":"2019","journal-title":"Neurology"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"1769","DOI":"10.1002\/alz.12482","article-title":"The impact of diabetes on cognitive impairment and its progression to dementia","volume":"17","author":"Dove","year":"2021","journal-title":"Alzheimers Dement"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"1056","DOI":"10.2337\/dc15-2331","article-title":"Long-term variability in glycemic control is associated with white matter hyperintensities in APOE4 genotype carriers with type 2 diabetes","volume":"39","author":"Livny","year":"2016","journal-title":"Diabetes Care"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"4425","DOI":"10.2147\/DMSO.S489819","article-title":"Risk prediction models for mild cognitive impairment in patients with type 2 diabetes mellitus: a systematic review and meta-analysis","volume":"17","author":"Xia","year":"2024","journal-title":"Diabetes Metab Syndr Obes"},{"key":"ref13","first-page":"213","article-title":"Type 2 diabetes mellitus and cognitive impairment","volume":"53","author":"Damanik","year":"2021","journal-title":"Acta Med Indones"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"602501","DOI":"10.3389\/fnins.2020.602501","article-title":"White matter atrophy in type 2 diabetes mellitus patients with mild cognitive impairment","volume":"14","author":"Li","year":"2020","journal-title":"Front Neurosci"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"622","DOI":"10.1093\/nutrit\/nuad085","article-title":"Association of vitamin D and cognition in people with type 2 diabetes: a systematic review","volume":"82","author":"da Silva","year":"2024","journal-title":"Nutr Rev"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"111036","DOI":"10.1016\/j.diabres.2023.111036","article-title":"Potential risk factors for mild cognitive impairment among patients with type 2 diabetes experiencing hypoglycemia","volume":"207","author":"Gao","year":"2024","journal-title":"Diabetes Res Clin Pract"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"e0297785","DOI":"10.1371\/journal.pone.0297785","article-title":"Serum brain-derived neurotrophic factor levels in type 2 diabetes mellitus patients and its association with cognitive impairment: a meta-analysis","volume":"19","author":"He","year":"2024","journal-title":"PLoS One"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1186\/s12902-023-01476-2","article-title":"Risk factors for cognitive dysfunction and glycemic management in older adults with type 2 diabetes mellitus: a retrospective study","volume":"23","author":"Ma","year":"2023","journal-title":"BMC Endocr Disord"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"1171","DOI":"10.2147\/DMSO.S448321","article-title":"Development and validation of a risk score for mild cognitive impairment in individuals with type 2 diabetes in China: a practical cognitive prescreening tool","volume":"17","author":"Ding","year":"2024","journal-title":"Diabetes Metab Syndr Obes"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"e12371","DOI":"10.1002\/trc2.12371","article-title":"Functional connectivity and mild behavioral impairment in dementia-free elderly","volume":"9","author":"Ghahremani","year":"2023","journal-title":"Alzheimer's Dementia"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"1115634","DOI":"10.3389\/fneur.2023.1115634","article-title":"Micro- and macro-changes in early-stage type 2 diabetes mellitus without cognitive impairment: a diffusion tensor imaging (DTI) and surface-based morphometry (SBM) study","volume":"14","author":"Tang","year":"2023","journal-title":"Front Neurol"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"104551","DOI":"10.1016\/j.neubiorev.2022.104551","article-title":"The role of glucose in cognition, risk of dementia, and related biomarkers in individuals without type 2 diabetes mellitus or the metabolic syndrome: a systematic review of observational studies","volume":"135","author":"Kirvalidze","year":"2022","journal-title":"Neurosci Biobehav Rev"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"1967","DOI":"10.1016\/j.euroneuro.2014.01.023","article-title":"Brain imaging in type 2 diabetes","volume":"24","author":"Brundel","year":"2014","journal-title":"Eur Neuropsychopharmacol"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"1491","DOI":"10.21037\/qims-24-1591","article-title":"Association of diffusion tensor imaging along the perivascular space index with cognitive impairment in type 2 diabetes mellitus","volume":"15","author":"Hu","year":"2025","journal-title":"Quant Imaging Med Surg"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.1136\/bmjdrc-2023-003744","article-title":"Association between brain imaging biomarkers and continuous glucose monitoring-derived glycemic control indices in Japanese patients with type 2 diabetes mellitus","volume":"12","author":"Inoue","year":"2024","journal-title":"BMJ Open Diabetes Res Care"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"1519397","DOI":"10.3389\/fneur.2024.1519397","article-title":"Association of individual-based morphological brain network alterations with cognitive impairment in type 2 diabetes mellitus","volume":"15","author":"Shen","year":"2024","journal-title":"Front Neurol"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1002\/ana.24992","article-title":"Brain microvascular injury and white matter disease provoked by diabetes-associated hyperamylinemia","volume":"82","author":"Ly","year":"2017","journal-title":"Ann Neurol"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"1153784","DOI":"10.3389\/fradi.2023.1153784","article-title":"uRP: an integrated research platform for one-stop analysis of medical images","volume":"3","author":"Wu","year":"2023","journal-title":"Front Radiol"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3390\/ijms26020542","article-title":"Associations between diabetes mellitus and neurodegenerative diseases","volume":"26","author":"Szablewski","year":"2025","journal-title":"Int J Mol Sci"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1038\/s41392-025-02175-1","article-title":"Diabetic neuropathy: cutting-edge research and future directions","volume":"10","author":"Yang","year":"2025","journal-title":"Signal Transduct Target Ther"},{"key":"ref31","article-title":"Optimized integration of metabolomics and lipidomics reveals brain region-specific changes of oxidative stress and neuroinflammation in type 1 diabetic mice with cognitive decline","author":"Xiong","year":"2022","journal-title":"J Adv Res"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1196\/annals.1440.011","article-title":"The brain's default network: anatomy, function, and relevance to disease","volume":"1124","author":"Buckner","year":"2008","journal-title":"Ann N Y Acad Sci"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"660","DOI":"10.1038\/nrn4019","article-title":"Hippocampal insulin resistance and cognitive dysfunction","volume":"16","author":"Biessels","year":"2015","journal-title":"Nat Rev Neurosci"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"711","DOI":"10.1007\/s00125-007-0602-7","article-title":"Hippocampal damage and memory impairments as possible early brain complications of type 2 diabetes","volume":"50","author":"Gold","year":"2007","journal-title":"Diabetologia"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"e14706","DOI":"10.1111\/cns.14706","article-title":"Spontaneous brain activity in the hippocampal regions could characterize cognitive impairment in patients with Parkinson's disease","volume":"30","author":"Chen","year":"2024","journal-title":"CNS Neurosci Ther"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"100915","DOI":"10.1016\/j.yfrne.2021.100915","article-title":"A multimodal meta-analysis of regional structural and functional brain alterations in type 2 diabetes","volume":"62","author":"Yao","year":"2021","journal-title":"Front Neuroendocrinol"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1016\/j.bbr.2011.04.018","article-title":"How does the corpus callosum mediate interhemispheric transfer? A review","volume":"223","author":"van der Knaap","year":"2011","journal-title":"Behav Brain Res"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1016\/j.neulet.2016.05.035","article-title":"Aberrant structural and functional connectivity in the salience network and central executive network circuit in schizophrenia","volume":"627","author":"Chen","year":"2016","journal-title":"Neurosci Lett"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1016\/j.neuron.2015.09.035","article-title":"Input- and output-specific regulation of serial order performance by corticostriatal circuits","volume":"88","author":"Rothwell","year":"2015","journal-title":"Neuron"},{"key":"ref40","doi-asserted-by":"publisher","first-page":"2349","DOI":"10.1523\/JNEUROSCI.5587-06.2007","article-title":"Dissociable intrinsic connectivity networks for salience processing and executive control","volume":"27","author":"Seeley","year":"2007","journal-title":"J Neurosci"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1016\/j.jchemneu.2003.10.002","article-title":"The human raphe nuclei and the serotonergic system","volume":"26","author":"Hornung","year":"2003","journal-title":"J Chem Neuroanat"},{"key":"ref42","doi-asserted-by":"publisher","first-page":"658198","DOI":"10.3389\/fendo.2021.658198","article-title":"Altered white matter microstructures in type 2 diabetes mellitus: a coordinate-based meta-analysis of diffusion tensor imaging studies","volume":"12","author":"Zhou","year":"2021","journal-title":"Front Endocrinol"},{"key":"ref43","doi-asserted-by":"publisher","first-page":"1351","DOI":"10.1212\/WNL.0b013e3182315a56","article-title":"Advanced glycation end product level, diabetes, and accelerated cognitive aging","volume":"77","author":"Yaffe","year":"2011","journal-title":"Neurology"},{"key":"ref44","doi-asserted-by":"publisher","first-page":"2463","DOI":"10.1172\/JCI79742","article-title":"Hyperglycemia modulates extracellular amyloid-\u03b2 concentrations and neuronal activity in vivo","volume":"125","author":"Macauley","year":"2015","journal-title":"J Clin Invest"},{"key":"ref45","doi-asserted-by":"publisher","first-page":"685","DOI":"10.1038\/382685a0","article-title":"RAGE and amyloid-beta peptide neurotoxicity in Alzheimer's disease","volume":"382","author":"Yan","year":"1996","journal-title":"Nature"},{"key":"ref46","doi-asserted-by":"publisher","first-page":"9925","DOI":"10.1038\/s41598-020-67022-5","article-title":"Regional brain gray matter changes in patients with type 2 diabetes mellitus","volume":"10","author":"Roy","year":"2020","journal-title":"Sci Rep"},{"key":"ref47","doi-asserted-by":"publisher","first-page":"1698","DOI":"10.1016\/j.jdiacomp.2017.09.001","article-title":"Brain gray matter changes in type 2 diabetes mellitus: a meta-analysis of whole-brain voxel-based morphometry study","volume":"31","author":"Wu","year":"2017","journal-title":"J Diabetes Complicat"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3390\/ijms24119352","article-title":"Hyperglycemia and oxidative stress: an integral, updated and critical overview of their metabolic interconnections","volume":"24","author":"Gonz\u00e1lez","year":"2023","journal-title":"Int J Mol Sci"},{"key":"ref49","doi-asserted-by":"publisher","first-page":"142","DOI":"10.3892\/ijmm.2021.4975","article-title":"Damage to the blood-brain barrier and activation of neuroinflammation by focal cerebral ischemia under hyperglycemic condition","volume":"48","author":"Guo","year":"2021","journal-title":"Int J Mol Med"},{"key":"ref50","doi-asserted-by":"publisher","first-page":"1579","DOI":"10.1080\/13813455.2020.1784952","article-title":"Research progress of mechanisms for tight junction damage on blood-brain barrier inflammation","volume":"128","author":"Zhao","year":"2022","journal-title":"Arch Physiol Biochem"},{"key":"ref51","year":""}],"container-title":["Frontiers in Neurology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2025.1599793\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T04:23:00Z","timestamp":1759983780000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2025.1599793\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,9]]},"references-count":51,"alternative-id":["10.3389\/fneur.2025.1599793"],"URL":"https:\/\/doi.org\/10.3389\/fneur.2025.1599793","relation":{},"ISSN":["1664-2295"],"issn-type":[{"value":"1664-2295","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,9]]},"article-number":"1599793"}}