{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T19:06:42Z","timestamp":1782846402890,"version":"3.54.5"},"reference-count":47,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Diabetes"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n The global prevalence of type 2 diabetes mellitus (T2DM) poses significant challenges due to its association with increased cardiovascular risk and complications like cardiovascular autonomic neuropathy. Measures derived from heart rate variability (HRV) and cardiorespiratory interactions quantified through frequency response function (FRF) and impulse response (IR) metrics reflect different aspects of autonomic regulation and may provide complementary physiological information relevant to diabetes-related autonomic alterations.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n The study aimed to investigate whether these metrics, individually or in combination, provide useful physiological features for distinguishing individuals with and without T2DM using machine learning classifiers.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n Electrocardiogram and respiratory signals from 2 PhysioNet datasets were used to derive 3 domains of autonomic and cardiorespiratory features: (1) spectral HRV indices reflecting overall variability; (2) FRF metrics characterizing frequency-specific respiratory-cardiac transfer properties; and (3) causal IR metrics capturing time-domain responsiveness to respiratory inputs. ML classifiers\u2014logistic regression, support vector machine (SVM) with linear kernel, and SVM with radial basis function (SVM RBF) kernel\u2014assessed the predictive value of individual and combined feature sets under NearMiss-1 (NM) undersampling and Synthetic Minority Oversampling Technique oversampling. This systems-based framework may capture subtle differences in respiratory-cardiac regulation associated with T2DM more effectively than HRV alone by reflecting integrated cardiorespiratory coupling.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n Across classifiers and balancing strategies, IR features frequently produced comparatively strong standalone performance, suggesting that causal, time-domain cardiorespiratory dynamics capture informative physiological differences between groups. With logistic regression and NM, IR features achieved mean accuracy of 0.770 (SD 0.179), precision of 0.783 (SD 0.217), recall of 0.900 (SD 0.224), and\n F<\/jats:italic>\n 1<\/jats:sub>\n -score of 0.798 (SD 0.140). While HRV metrics were the least informative standalone feature set, the combined HRV+FRF feature set under NM yielded the highest observed performance, with accuracy of 0.830 (SD 0.172), precision of 0.800 (SD 0.183), recall of 0.933 (SD 0.149), and\n F<\/jats:italic>\n 1<\/jats:sub>\n -score of 0.853 (SD 0.145; SVM RBF). Under Synthetic Minority Oversampling Technique, HRV+IR showed the strongest observed combined performance, yielding accuracy of 0.700 (SD 0.128), precision of 0.783 (SD 0.217), recall of 0.683 (SD 0.207), and\n F<\/jats:italic>\n 1<\/jats:sub>\n -score of 0.691 (SD 0.097) with SVM RBF, surpassing standalone IR in most metrics, though IR alone retained superior recall (0.950, SD 0.112) and\n F<\/jats:italic>\n 1<\/jats:sub>\n -score (0.708, SD 0.038). These results reflect that performance depends on both feature domain and sampling strategy and that combining features capturing complementary physiological aspects of autonomic regulation may enhance discriminative ability.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n HRV, FRF, and IR metrics each reflect distinct dimensions of autonomic and cardiorespiratory regulation. Systems-based approaches incorporating frequency-domain and causal dynamic features may offer richer characterization of diabetes-related regulatory differences than HRV alone. Although preliminary and limited by sample size, these findings highlight promising physiological feature domains and sampling strategies for future investigation. Larger datasets with well-defined autonomic phenotyping are needed to evaluate generalizability and determine clinical relevance.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/82084","type":"journal-article","created":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T23:55:07Z","timestamp":1767052507000},"page":"e82084-e82084","source":"Crossref","is-referenced-by-count":0,"title":["Cardiorespiratory Markers of Type 2 Diabetes: Machine Learning\u2013Based Analysis"],"prefix":"10.2196","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4894-9007","authenticated-orcid":false,"given":"Flavia Maria G S A","family":"Oliveira","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7714-481X","authenticated-orcid":false,"given":"Sandro Muniz","family":"Cavalcanti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7680-5989","authenticated-orcid":false,"given":"Michael C K","family":"Khoo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,2,23]]},"reference":[{"key":"R1","unstructured":"IDF Diabetes Atlas. 11th ed. International Diabetes Federation; 2025. URL: https:\/\/diabetesatlas.org\/media\/uploads\/sites\/3\/2025\/04\/IDF_Atlas_11th_Edition_2025-1.pdf [Accessed 03-02-2026] ISBN: 978-2-930229-96-6"},{"issue":"9733","key":"R2","doi-asserted-by":"publisher","first-page":"2215","DOI":"10.1016\/S0140-6736(10)60484-9","article-title":"Diabetes mellitus, fasting blood glucose concentration, and risk of vascular disease: a collaborative meta-analysis of 102 prospective studies","volume":"375","author":"Emerging Risk Factors Collaboration","journal-title":"Lancet"},{"issue":"6","key":"R3","doi-asserted-by":"publisher","first-page":"1895","DOI":"10.2337\/diacare.26.6.1895","article-title":"The association between cardiovascular autonomic neuropathy and mortality in individuals with diabetes: a meta-analysis","volume":"26","author":"Maser","journal-title":"Diabetes Care"},{"issue":"12","key":"R4","doi-asserted-by":"publisher","first-page":"2611","DOI":"10.1007\/s00125-024-06242-0","article-title":"Cardiovascular autonomic neuropathy in diabetes: an update with a focus on management","volume":"67","author":"Eleftheriadou","journal-title":"Diabetologia"},{"issue":"18","key":"R5","doi-asserted-by":"publisher","first-page":"1339","DOI":"10.1161\/CIRCULATIONAHA.116.023446","article-title":"Prediabetes and type 2 diabetes are associated with generalized microvascular dysfunction: the Maastricht Study","volume":"134","author":"S\u00f6rensen","journal-title":"Circulation"},{"issue":"1","key":"R6","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-15824-0","article-title":"Reduced heart rate variability is related to the number of metabolic syndrome components and manifest diabetes in the sixth Troms\u00f8 study 2007-2008","volume":"12","author":"Azulay","journal-title":"Sci Rep"},{"issue":"4","key":"R7","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0195166","article-title":"Heart rate variability in type 2 diabetes mellitus: a systematic review and meta-analysis","volume":"13","author":"Benichou","journal-title":"PLoS One"},{"issue":"10","key":"R8","doi-asserted-by":"publisher","first-page":"2510","DOI":"10.1210\/clinem\/dgad200","article-title":"Heart rate variability and incident type 2 diabetes in general population","volume":"108","author":"Wang","journal-title":"J Clin Endocrinol Metab"},{"issue":"5","key":"R9","doi-asserted-by":"publisher","first-page":"1126","DOI":"10.2337\/dc19-2367","article-title":"Both prediabetes and type 2 diabetes are associated with lower heart rate variability: the Maastricht Study","volume":"43","author":"Coopmans","journal-title":"Diabetes Care"},{"issue":"4","key":"R10","doi-asserted-by":"publisher","DOI":"10.2174\/1573399817666210827130339","article-title":"Cardiovascular autonomic reflex tests and 7 heart rate variability indices for early diagnosis of cardiovascular autonomic neuropathy in type 2 diabetes individuals","volume":"18","author":"Atala","journal-title":"Curr Diabetes Rev"},{"issue":"5","key":"R11","doi-asserted-by":"publisher","first-page":"807","DOI":"10.1164\/ajrccm.164.5.2010124","article-title":"Cardiac autonomic control in obstructive sleep apnea: effects of long-term CPAP therapy","volume":"164","author":"Khoo","journal-title":"Am J Respir Crit Care Med"},{"key":"R12","doi-asserted-by":"crossref","unstructured":"Vaschillo EG Vaschillo B . Transfer function of the heart rate control system with respiratory input: the classical engineering approach. Presented at: Proceedings of the International Conference on Bio-inspired Systems and Signal Processing; Jan 14-17, 2009:233-238; Porto, Portugal. [doi: 10.5220\/0001434002330238]","DOI":"10.5220\/0001434002330238"},{"issue":"4 Pt 2","key":"R13","doi-asserted-by":"publisher","first-page":"H1231","DOI":"10.1152\/ajpheart.1991.261.4.H1231","article-title":"Transfer function analysis of the circulation: unique insights into cardiovascular regulation","volume":"261","author":"Saul","journal-title":"Am J Physiol"},{"issue":"5","key":"R14","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1109\/51.620500","article-title":"Linear and nonlinear system identification of autonomic heart-rate modulation","volume":"16","author":"Chon","journal-title":"IEEE Eng Med Biol Mag"},{"key":"R15","unstructured":"Khoo MCK . Physiological Control Systems: Analysis, Simulation, and Estimation. 2nd ed. John Wiley & Sons; 2018. URL: https:\/\/www.wiley-vch.de\/en\/areas-interest\/engineering\/physiological-control-systems-978-1-119-05533-4 [Accessed 03-02-2026] ISBN: 9781119055334"},{"key":"R16","unstructured":"Novak V Mendez L . Cerebral vasoregulation in diabetes. PhysioNet. 2020. URL: https:\/\/physionet.org\/content\/cerebral-vasoreg-diabetes\/1.0.0\/ [Accessed 03-02-2026]"},{"key":"R17","unstructured":"Novak V Quispe R Saunders C . Cerebral perfusion and cognitive decline in type 2 diabetes. PhysioNet. 2022. URL: https:\/\/physionet.org\/content\/cerebral-perfusion-diabetes\/1.0.1\/ [Accessed 03-02-2026]"},{"issue":"5","key":"R18","doi-asserted-by":"publisher","first-page":"1043","DOI":"10.1161\/01.CIR.93.5.1043","article-title":"Heart rate variability: standards of measurement, physiological interpretation, and clinical use","volume":"93","author":"Task Force of the European Society of Cardiology and the North American Society of Pacing and Electrophysiology","journal-title":"Circulation"},{"issue":"3","key":"R19","doi-asserted-by":"publisher","first-page":"728","DOI":"10.1109\/JBHI.2019.2914211","article-title":"CRSIDLab: a toolbox for multivariate autonomic nervous system analysis using cardiorespiratory identification","volume":"24","author":"da Silva","journal-title":"IEEE J Biomed Health Inform"},{"issue":"3","key":"R20","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1109\/TBME.1985.325532","article-title":"A real-time QRS detection algorithm","volume":"32","author":"Pan","journal-title":"IEEE Trans Biomed Eng"},{"issue":"1","key":"R21","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1093\/sleep\/26.1.65","article-title":"Model-based assessment of autonomic control in obstructive sleep apnea syndrome","volume":"26","author":"Belozeroff","journal-title":"Sleep"},{"issue":"1","key":"R22","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1152\/physiologyonline.1990.5.1.32","article-title":"Beat-to-beat variations of heart rate reflect modulation of cardiac autonomic outflow","volume":"5","author":"Saul","journal-title":"Physiology"},{"issue":"12","key":"R23","doi-asserted-by":"publisher","first-page":"1530","DOI":"10.1016\/j.hrthm.2007.08.005","article-title":"The never-ending story: unraveling the mysteries of the low-frequency component of heart rate variability","volume":"4","author":"Bonnemeier","journal-title":"Heart Rhythm"},{"issue":"4 Pt 2","key":"R24","doi-asserted-by":"publisher","first-page":"H867","DOI":"10.1152\/ajpheart.1985.249.4.H867","article-title":"Hemodynamic regulation: investigation by spectral analysis","volume":"249","author":"Akselrod","journal-title":"Am J Physiol"},{"issue":"2","key":"R25","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1161\/01.res.59.2.178","article-title":"Power spectral analysis of heart rate and arterial pressure variabilities as a marker of sympatho-vagal interaction in man and conscious dog","volume":"59","author":"Pagani","journal-title":"Circ Res"},{"key":"R26","doi-asserted-by":"publisher","DOI":"10.3389\/fphys.2013.00026","article-title":"The LF\/HF ratio does not accurately measure cardiac sympatho-vagal balance","volume":"4","author":"Billman","journal-title":"Front Physiol"},{"issue":"9","key":"R27","doi-asserted-by":"publisher","first-page":"3224","DOI":"10.1161\/01.cir.96.9.3224","article-title":"Sympathovagal balance: a critical appraisal","volume":"96","author":"Eckberg","journal-title":"Circulation"},{"issue":"1 Pt 2","key":"R28","doi-asserted-by":"publisher","first-page":"H142","DOI":"10.1152\/ajpheart.1989.256.1.H142","article-title":"Transfer function analysis of autonomic regulation. I. Canine atrial rate response","volume":"256","author":"Berger","journal-title":"Am J Physiol"},{"issue":"1887","key":"R29","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1098\/rsta.2008.0229","article-title":"Multimodal signal processing for the analysis of cardiovascular variability","volume":"367","author":"Porta","journal-title":"Philos Trans A Math Phys Eng Sci"},{"issue":"2","key":"R30","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1164\/rccm.200202-096OC","article-title":"Model-based assessment of autonomic control in obstructive sleep apnea syndrome during sleep","volume":"167","author":"Jo","journal-title":"Am J Respir Crit Care Med"},{"key":"R31","unstructured":"Zhang J Mani I . KNN approach to unbalanced data distributions: a case study involving information extraction. Presented at: Proceedings of the ICML\u20192003 - Workshop on Learning from Imbalanced Datasets; Aug 21, 2003; Washington, DC, USA. URL: https:\/\/www.bibsonomy.org\/bibtex\/2cf4d2ac8bdac874b3d4841b4645a5a90\/diana [Accessed 03-02-2026]"},{"key":"R32","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953","article-title":"SMOTE: synthetic minority over-sampling technique","volume":"16","author":"Chawla","journal-title":"J Artif Intell Res"},{"key":"R33","doi-asserted-by":"crossref","unstructured":"Graf ABA Borer S . Normalization in support vector machines. Presented at: Pattern Recognition: 23rd DAGM Symposium; Sep 10-12, 2001; Munich, Germany. [doi: 10.1007\/3-540-45404-7_37]","DOI":"10.1007\/3-540-45404-7_37"},{"key":"R34","unstructured":"Jurafsky D Martin JH . Logistic regression. In: Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition with Language Models. 3rd ed. 2026. URL: https:\/\/web.stanford.edu\/~jurafsky\/slp3 [Accessed 10-02-2026]"},{"issue":"Part B","key":"R35","doi-asserted-by":"publisher","first-page":"105524","DOI":"10.1016\/j.asoc.2019.105524","article-title":"Investigating the impact of data normalization on classification performance","volume":"97","author":"Singh","journal-title":"Appl Soft Comput"},{"issue":"1","key":"R36","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1111\/j.1600-0587.2012.07348.x","article-title":"Collinearity: a review of methods to deal with it and a simulation study evaluating their performance","volume":"36","author":"Dormann","journal-title":"Ecography"},{"key":"R37","volume":"3","author":"Guyon","journal-title":"J Mach Learn Res"},{"key":"R38","unstructured":"Kohavi R . A study of cross-validation and bootstrap for accuracy estimation and model selection. Presented at: Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence (IJCAI \u201995); Aug 20-25, 1995:1137-1143; Montr\u00e9al, QC. URL: https:\/\/ai.stanford.edu\/~ronnyk\/accEst.pdf [Accessed 03-02-2026]"},{"issue":"11","key":"R39","doi-asserted-by":"publisher","first-page":"1288","DOI":"10.1177\/0271678X241254716","article-title":"Data-based modeling of cerebral hemodynamics quantifies impairment of cerebral blood flow regulation in type-2 diabetes","volume":"44","author":"Marmarelis","journal-title":"J Cereb Blood Flow Metab"},{"key":"R40","doi-asserted-by":"publisher","DOI":"10.1016\/j.resp.2023.104042","article-title":"Cardiorespiratory coupling as an early marker of cardiac autonomic dysfunction in type 2 diabetes mellitus patients","volume":"311","author":"Da Silva","journal-title":"Respir Physiol Neurobiol"},{"key":"R41","doi-asserted-by":"publisher","DOI":"10.3389\/fphys.2019.01319","article-title":"Comparison of causal and non\u2011causal strategies for the assessment of baroreflex sensitivity in predicting acute kidney dysfunction after coronary artery bypass grafting","volume":"10","author":"Bari","journal-title":"Front Physiol"},{"key":"R42","doi-asserted-by":"crossref","unstructured":"Nayan NM Islam A Islam MU Ahmed E Hossain MM Alam MZ . SMOTE oversampling and Near Miss undersampling based diabetes diagnosis from imbalanced dataset with XAI visualization. Presented at: 2023 IEEE Symposium on Computers and Communications (ISCC); Jul 9-12, 2023; Gammarth, Tunisia. [doi: 10.1109\/ISCC58397.2023.10218281]","DOI":"10.1109\/ISCC58397.2023.10218281"},{"issue":"1","key":"R43","doi-asserted-by":"publisher","first-page":"136","DOI":"10.2337\/dc16-2042","article-title":"Diabetic neuropathy: a position statement by the American Diabetes Association","volume":"40","author":"Pop-Busui","journal-title":"Diabetes Care"},{"issue":"2","key":"R44","doi-asserted-by":"publisher","first-page":"361","DOI":"10.3233\/THC-213048","article-title":"Heart rate variability measured during rest and after orthostatic challenge to detect autonomic dysfunction in type 2 diabetes mellitus using the classification and regression tree model","volume":"30","author":"Rathod","journal-title":"Technol Health Care"},{"key":"R45","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2018.05.041","article-title":"Automated detection of diabetes using CNN and CNN\u2013LSTM network and heart rate signals","volume":"132","author":"G","journal-title":"Procedia Comput Sci"},{"issue":"4","key":"R46","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1016\/j.icte.2018.10.005","article-title":"Diabetes detection using deep learning algorithms","volume":"4","author":"Swapna","journal-title":"ICT Express"},{"key":"R47","unstructured":"Research. Flavia M G S Oliveira. URL: https:\/\/flavia.ene.unb.br\/research [Accessed 17-02-2026]"}],"container-title":["JMIR Diabetes"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/diabetes.jmir.org\/2026\/1\/e82084","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:16:02Z","timestamp":1782843362000},"score":1,"resource":{"primary":{"URL":"https:\/\/diabetes.jmir.org\/2026\/1\/e82084"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,23]]},"references-count":47,"URL":"https:\/\/doi.org\/10.2196\/82084","relation":{},"ISSN":["2371-4379"],"issn-type":[{"value":"2371-4379","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,23]]},"article-number":"v11i9733e82084"}}