{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T15:22:16Z","timestamp":1788362536637,"version":"build-2803163510"},"reference-count":41,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T00:00:00Z","timestamp":1788307200000},"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. Artif. Intell."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Dyslexia affects around 10% of the global population, yet early screening depends heavily on resource-intensive clinical assessments that are difficult to scale. Gamified cognitive platforms offer a practical alternative, but most existing machine learning approaches rely on raw task metrics without exploiting the hierarchical cognitive structure of multi-task assessment batteries.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      NEUROCOG-DysNet is a multi-scale cognitive feature engineering and stacking ensemble framework for dyslexia screening using gamified assessment data from the Dytective platform (\n                      <jats:italic>N<\/jats:italic>\n                      = 3,644; 392 dyslexic, 3,252 non-dyslexic). The framework extracts 258 hierarchical features across five cognitive levels-task, phase, temporal, global, and cross-domain-from raw game interactions, supplemented by four demographic variables. LightGBM-based feature selection retains the 50 most discriminative features. Seven base classifiers, configured to emphasize high sensitivity, balanced performance, or high AUC, are combined using five ensemble strategies and evaluated under a leakage-safe nested cross-validation protocol.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The stacking meta-learner achieves the highest composite score and attains an AUC-ROC of 0.8924 (95% CI: 0.8543\u20130.9253), sensitivity of 0.8077, specificity of 0.8187, and balanced accuracy of 0.8132. DeLong's test (\n                      <jats:italic>p<\/jats:italic>\n                      = 0.6946) and McNemar's test (\n                      <jats:italic>p<\/jats:italic>\n                      = 0.1443) indicate that AUC gains over the strongest individual baseline (XGB_HighAUC) are not statistically significant. Nested cross-validation confirms a small optimism gap (+0.011 AUC). Clinical utility analysis yields a 5.25 \u00d7 lift in the highest-risk decile and a negative predictive value of 0.9726. Ablation shows that demographic variables contribute more to discrimination than any engineered cognitive level; a demographics-free variant attains AUC 0.7948.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>NEUROCOG-DysNet provides a tunable sensitivity-specificity balance and well-calibrated risk scores suitable for a first-stage screening aid. The ensemble's advantage over fixed-weight alternatives is marginal on this dataset, and the cross-domain feature level is effectively inert. External validation across independent language cohorts and prospective multi-center evaluation are required before clinical deployment.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frai.2026.1909141","type":"journal-article","created":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T14:53:16Z","timestamp":1788360796000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["NEUROCOG-DysNet: a multi-scale cognitive feature engineering framework with stacking ensemble for improved dyslexia screening"],"prefix":"10.3389","volume":"9","author":[{"given":"Sudha","family":"M","sequence":"first","affiliation":[{"name":"School of Advanced Sciences (SAS), Vellore Institute of Technology","place":["Vellore, Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Murali","family":"S","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering (SCOPE), Vellore Institute of Technology","place":["Vellore, Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,2]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"13557","DOI":"10.1007\/s11042-022-13939-0","article-title":"A comprehensive review of machine learning approaches for dyslexia diagnosis","volume":"82","author":"Ahire","year":"2023","journal-title":"Multimed. Tools Appl"},{"key":"B2","doi-asserted-by":"publisher","first-page":"e2077","DOI":"10.7717\/peerj-cs.2077","article-title":"Deep learning-driven dyslexia detection model using multi-modality data","volume":"10","author":"Alkhurayyif","year":"2024","journal-title":"PeerJ Comput. Sci"},{"key":"B3","doi-asserted-by":"publisher","first-page":"2804","DOI":"10.3390\/app13052804","article-title":"Deep learning applications for dyslexia prediction","volume":"13","author":"Alqahtani","year":"2023","journal-title":"Appl. Sci"},{"key":"B4","doi-asserted-by":"publisher","first-page":"e70077","DOI":"10.1002\/cpp.70077","article-title":"Exploring and identifying key factors in predicting dyslexia in children: advanced machine learning algorithms from screening to diagnosis","volume":"32","author":"Alrubaian","year":"2025","journal-title":"Clin. Psychol. Psychother"},{"key":"B5","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn"},{"key":"B6","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1613\/jair.953","article-title":"Smote: synthetic minority over-sampling technique","volume":"16","author":"Chawla","year":"2002","journal-title":"J. Artif. Intell. Res"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785","article-title":"\u201cXgboost: a scalable tree boosting system,\u201d","author":"Chen","year":"2016","journal-title":"Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining"},{"key":"B8","doi-asserted-by":"publisher","first-page":"837","DOI":"10.2307\/2531595","article-title":"Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach","volume":"44","author":"DeLong","year":"1988","journal-title":"Biometrics"},{"key":"B9","doi-asserted-by":"publisher","first-page":"863","DOI":"10.1613\/jair.1.11192","article-title":"Smote for learning from imbalanced data: progress and challenges, marking the 15-year anniversary","volume":"61","author":"Fern\u00e1ndez","year":"2018","journal-title":"J. Artif. Intell. Res"},{"key":"B10","doi-asserted-by":"publisher","first-page":"1189","DOI":"10.1214\/aos\/1013203451","article-title":"Greedy function approximation: a gradient boosting machine","volume":"29","author":"Friedman","year":"2001","journal-title":"Ann. Statist"},{"key":"B11","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s10994-006-6226-1","article-title":"Extremely randomized trees","volume":"63","author":"Geurts","year":"2006","journal-title":"Mach. Learn"},{"key":"B12","doi-asserted-by":"publisher","first-page":"8004","DOI":"10.3390\/app14178004","article-title":"Diagnosing dyslexia in early school-aged children using the lstm network and eye tracking technology","volume":"14","author":"Gomolka","year":"2024","journal-title":"Appl. Sci"},{"key":"B13","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-84858-7","volume-title":"The Elements of Statistical Learning","author":"Hastie","year":"2009"},{"key":"B14","doi-asserted-by":"publisher","first-page":"1263","DOI":"10.1109\/TKDE.2008.239","article-title":"Learning from imbalanced data","volume":"21","author":"He","year":"2009","journal-title":"IEEE Trans. Knowl. Data Eng"},{"key":"B15","doi-asserted-by":"crossref","DOI":"10.1002\/9781118548387","volume-title":"Applied Logistic Regression","author":"Hosmer","year":"2013"},{"key":"B16","doi-asserted-by":"publisher","first-page":"511","DOI":"10.1007\/s40031-023-00853-8","article-title":"A systematic review of research dimensions towards dyslexia screening using machine learning","volume":"104","author":"Jan","year":"2023","journal-title":"J. Instit. Eng"},{"key":"B17","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1016\/j.icte.2022.02.011","article-title":"Integrating oversampling and ensemble-based machine learning techniques for an imbalanced dataset in dyslexia screening tests","volume":"8","author":"Kaisar","year":"2022","journal-title":"ICT Express"},{"key":"B18","first-page":"3149","article-title":"\u201cLightGBM: a highly efficient gradient boosting decision tree,\u201d","author":"Ke","year":"2017","journal-title":"NIPS'17: proceedings of the 31st international conference on neural information processing systems"},{"key":"B19","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1080\/19404158.2018.1479975","article-title":"Developmental dyslexia: emotional impact and consequences","volume":"23","author":"Livingston","year":"2018","journal-title":"Austr. J. Learn. Diffic"},{"key":"B20","first-page":"4765","article-title":"\u201cA unified approach to interpreting model predictions,\u201d","author":"Lundberg","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"B21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11881-003-0001-9","article-title":"A definition of dyslexia","volume":"53","author":"Lyon","year":"2003","journal-title":"Ann. Dyslexia"},{"key":"B22","doi-asserted-by":"publisher","first-page":"79","DOI":"10.3390\/jintelligence11050079","article-title":"The use of cognitive tests in the assessment of dyslexia","volume":"11","author":"Mather","year":"2023","journal-title":"J. Intell"},{"key":"B23","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1007\/BF02295996","article-title":"Note on the sampling error of the difference between correlated proportions or percentages","volume":"12","author":"McNemar","year":"1947","journal-title":"Psychometrika"},{"key":"B24","unstructured":"Scikit-learn: machine learning in python\n          \n          2825\n          2830\n          \n            \n              Pedregosa\n              F.\n            \n            \n              Varoquaux\n              G.\n            \n            \n              Gramfort\n              A.\n            \n            \n              Michel\n              V.\n            \n            \n              Thirion\n              B.\n            \n            \n              Grisel\n              O.\n            \n          \n          J. Mach. Learn. Res\n          12\n          2011"},{"key":"B25","doi-asserted-by":"publisher","first-page":"1997","DOI":"10.1016\/S0140-6736(12)60198-6","article-title":"Developmental dyslexia","volume":"379","author":"Peterson","year":"2012","journal-title":"Lancet"},{"key":"B26","doi-asserted-by":"publisher","first-page":"1840","DOI":"10.1037\/dev0000976","article-title":"Developmental profiles of reading fluency and reading comprehension from grades 1 to 9 and their early identification","volume":"57","author":"Psyridou","year":"2021","journal-title":"Dev. Psychol"},{"key":"B27","doi-asserted-by":"publisher","first-page":"2379","DOI":"10.1037\/dev0001622","article-title":"Developmental profiles of arithmetic fluency skills from grades 1 to 9 and their early identification","volume":"59","author":"Psyridou","year":"2023","journal-title":"Dev. Psychol"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1145\/3371300.3383342","article-title":"\u201cScreening risk of dyslexia through a web-game using language-independent content and machine learning,\u201d","author":"Rauschenberger","year":"2020","journal-title":"Proceedings of the 17th international web for all conference"},{"key":"B29","author":"Rello","year":"2020","journal-title":"Dytective test data"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1145\/2899475.2899491","article-title":"\u201cDytective: towards detecting dyslexia across languages using an online game,\u201d","author":"Rello","year":"2016","journal-title":"Proceedings of the 13th international web for all conference"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939778","author":"Ribeiro","year":"2016","journal-title":"Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining"},{"key":"B32","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1056\/NEJM199801293380507","article-title":"Dyslexia","volume":"338","author":"Shaywitz","year":"1998","journal-title":"New Engl. J. Med"},{"key":"B33","doi-asserted-by":"publisher","first-page":"593","DOI":"10.1111\/j.1469-7610.2011.02495.x","article-title":"Annual research review: the nature and classification of reading disorders-a commentary on proposals for DSM-5","volume":"53","author":"Snowling","year":"2012","journal-title":"J. Child Psychol. Psychiat"},{"key":"B34","doi-asserted-by":"publisher","first-page":"36879","DOI":"10.1109\/ACCESS.2021.3062709","article-title":"Advance machine learning methods for dyslexia biomarker detection: a review of implementation details and challenges","volume":"9","author":"Usman","year":"2021","journal-title":"IEEE Access"},{"key":"B35","doi-asserted-by":"publisher","first-page":"3024","DOI":"10.1109\/ACCESS.2023.3234438","article-title":"Eye-tracking image encoding: autoencoders for the crossing of language boundaries in developmental dyslexia detection","volume":"11","author":"Vajs","year":"2023","journal-title":"IEEE Access"},{"key":"B36","doi-asserted-by":"publisher","first-page":"565","DOI":"10.1177\/0272989X06295361","article-title":"Decision curve analysis: a novel method for evaluating prediction models","volume":"26","author":"Vickers","year":"2006","journal-title":"Med. Dec. Making"},{"key":"B37","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1016\/S0893-6080(05)80023-1","article-title":"Stacked generalization","volume":"5","author":"Wolpert","year":"1992","journal-title":"Neural Netw"},{"key":"B38","doi-asserted-by":"publisher","first-page":"7123","DOI":"10.1109\/ACCESS.2025.3526189","article-title":"Artificial intelligence in dyslexia research and education: a scoping review","volume":"13","author":"Yap","year":"2025","journal-title":"IEEE Access"},{"key":"B39","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1002\/1097-0142(1950)3:1<32::AID-CNCR2820030106>3.0.CO;2-3","article-title":"Index for rating diagnostic tests","volume":"3","author":"Youden","year":"1950","journal-title":"Cancer"},{"key":"B40","doi-asserted-by":"publisher","first-page":"28575","DOI":"10.1038\/s41598-024-80210-x","article-title":"Using machine learning to develop a stacking ensemble learning model for the ct radiomics classification of brain metastases","volume":"14","author":"Zhang","year":"2024","journal-title":"Sci. Rep"},{"key":"B41","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1038\/s41598-023-50879-7","article-title":"A machine learning-based classification model to support university students with dyslexia with personalized tools and strategies","volume":"14","author":"Zingoni","year":"2024","journal-title":"Sci. Rep"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1909141\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T14:53:17Z","timestamp":1788360797000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1909141\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,2]]},"references-count":41,"alternative-id":["10.3389\/frai.2026.1909141"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1909141","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,2]]},"article-number":"1909141"}}