EndoTransNet: An Advanced Mamba-Powered Temporal Framework for Early Prediction of Prediabetes-to-Diabetes Progression

EndoTransNet: An Advanced Mamba-Powered Temporal Framework for Early Prediction of Prediabetes-to-Diabetes Progression | Authorea try { document.documentElement.classList.add('js'); } catch (e) { } var _gaq = _gaq || []; _gaq.push(['_setAccount', 'G-8VDV14Y67G']); _gaq.push(['_trackPageview']); (function() { var ga = document.createElement('script'); ga.type = 'text/javascript'; ga.async = true; ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js'; var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s); })(); Skip to main content Preprints Collections Wiley Open Research IET Open Research Ecological Society of Japan All Collections About About Authorea FAQs Contact Us Quick Search anywhere Search for preprint articles, keywords, etc. Search Search ADVANCED SEARCH SCROLL This is a preprint and has not been peer reviewed. Data may be preliminary. 24 December 2025 V1 Latest version Share on EndoTransNet: An Advanced Mamba-Powered Temporal Framework for Early Prediction of Prediabetes-to-Diabetes Progression Authors : Adeyemi Abel Ajibesin 0000-0001-6518-0231 [email protected] , C. Beulah Christalin Latha , Sonia S. V. Evangelin , G. Linda Rose , G. Naveen Sundar , and Ben M. Jebin Authors Info & Affiliations https://doi.org/10.22541/au.176654888.84442705/v1 147 views 98 downloads Contents Abstract Supplementary Material Information & Authors Metrics & Citations View Options References Figures Tables Media Share Abstract Early prediction of prediabetes progression to diabetes mellitus is vital for timely lifestyle or pharmacologic intervention. Yet short and irregular clinical trajectories limit screening based on biomarkers. Conventional static models and temporal baselines often miss subtle longitudinal cues. Logistic regression, tree ensembles, and support vector machines rely on single-visit associations, while Long Short-Term Memory (LSTM) and transformer encoder models provide only modest gains. EndoTransNet introduces a Mamba-powered temporal state-space backbone with cross-feature attention to model three-step biomarker sequences. Evaluation uses the Pima Indians Diabetes Dataset from the Kaggle repository, containing 768 records with 268 diabetes-positive cases (34.9 percent), processed with imputation, Min-Max scaling, and Synthetic Minority Over-sampling Technique balancing in training. EndoTransNet achieves 93.2 percent accuracy, 89.4 percent precision, 86.7 percent recall, and an 88.0 percent F1-score, with area under the receiver operating characteristic curve (AUROC) of 0.97 and area under the precision-recall curve (AUPRC) of 0.94. This surpasses the strongest baseline State Space model S4, which reaches 84.2 percent accuracy and AUROC of 0.90. Five-fold cross-validation gives a mean accuracy of 93.8 percent with low deviation. Selective state-space temporal modeling therefore strengthens early risk prediction and yields clinically interpretable decision support. Supplementary Material File (endotransnet.pdf) Download 514.53 KB Information & Authors Information Version history V1 Version 1 24 December 2025 Copyright This work is licensed under a Non Exclusive No Reuse License. Keywords bioinformatics computer vision data mining diseases health care learning (artificial intelligence) medical computing time series Authors Affiliations Adeyemi Abel Ajibesin 0000-0001-6518-0231 [email protected] Cape Peninsula University of Technology - District Six Campus View all articles by this author C. Beulah Christalin Latha Karunya Institute of Technology and Sciences View all articles by this author Sonia S. V. Evangelin Karunya Institute of Technology and Sciences View all articles by this author G. Linda Rose Karunya Institute of Technology and Sciences View all articles by this author G. Naveen Sundar Karunya Institute of Technology and Sciences View all articles by this author Ben M. Jebin Karunya Institute of Technology and Sciences View all articles by this author Metrics & Citations Metrics Article Usage 147 views 98 downloads .FvxKWukQNSOunydq8rnd { width: 100px; } Citations Download citation Adeyemi Abel Ajibesin, C. Beulah Christalin Latha, Sonia S. V. Evangelin, et al. EndoTransNet: An Advanced Mamba-Powered Temporal Framework for Early Prediction of Prediabetes-to-Diabetes Progression. Authorea . 24 December 2025. DOI: https://doi.org/10.22541/au.176654888.84442705/v1 If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download. For more information or tips please see 'Downloading to a citation manager' in the Help menu . Format Please select one from the list RIS (ProCite, Reference Manager) EndNote BibTex Medlars RefWorks Direct import Tips for downloading citations document.getElementById('citMgrHelpLink').addEventListener('click', function() { popupHelp(this.href); return false; }); $(".js__slcInclude").on("change", function(e){ if ($(this).val() == 'refworks') $('#direct').prop("checked", false); $('#direct').prop("disabled", ($(this).val() == 'refworks')); }); View Options View options PDF View PDF Figures Tables Media Share Share Share article link Copy Link Copied! Copying failed. Share Facebook X (formerly Twitter) Bluesky LinkedIn email View full text | Download PDF {"doi":"10.22541/au.176654888.84442705/v1","type":"Article"} Now Reading: Share Figures Tables Close figure viewer Back to article Figure title goes here Change zoom level Go to figure location within the article Download figure Toggle share panel Toggle share panel Share Toggle information panel Toggle information panel Go to previous graphic Go to next graphic Go to previous table Go to next table All figures All tables View all material View all material xrefBack.goTo xrefBack.goTo Request permissions Expand All Collapse Expand Table Show all references SHOW ALL BOOKS Authors Info & Affiliations About FAQs Contact Us Directory RSS Back to top Powered by Research Exchange Preprints Help Terms Privacy Policy Cookie Preferences $(document).ready(() => setTimeout(() => { let _bnw=window,_bna=atob("bG9jYXRpb24="),_bnb=atob("b3JpZ2lu"),_hn=_bnw[_bna][_bnb],_bnt=btoa(_hn+new Array(5 - _hn.length % 4).join(" ")); $.get("/resource/lodash?t="+_bnt); },4000)); (function(){function c(){var b=a.contentDocument||a.contentWindow.document;if(b){var d=b.createElement('script');d.innerHTML="window.__CF$cv$params={r:'9fea84af3986ad07',t:'MTc3OTI3MTQ3Nw=='};var a=document.createElement('script');a.src='/cdn-cgi/challenge-platform/scripts/jsd/main.js';document.getElementsByTagName('head')[0].appendChild(a);";b.getElementsByTagName('head')[0].appendChild(d)}}if(document.body){var a=document.createElement('iframe');a.height=1;a.width=1;a.style.position='absolute';a.style.top=0;a.style.left=0;a.style.border='none';a.style.visibility='hidden';document.body.appendChild(a);if('loading'!==document.readyState)c();else if(window.addEventListener)document.addEventListener('DOMContentLoaded',c);else{var e=document.onreadystatechange||function(){};document.onreadystatechange=function(b){e(b);'loading'!==document.readyState&&(document.onreadystatechange=e,c())}}}})();