{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T08:03:49Z","timestamp":1784534629133,"version":"3.55.0"},"reference-count":48,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,6,9]],"date-time":"2027-06-09T00:00:00Z","timestamp":1812499200000},"content-version":"am","delay-in-days":251,"URL":"http:\/\/www.elsevier.com\/open-access\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100002429","name":"Amgen Inc","doi-asserted-by":"publisher","award":["20187183"],"award-info":[{"award-number":["20187183"]}],"id":[{"id":"10.13039\/100002429","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["K23NS070891"],"award-info":[{"award-number":["K23NS070891"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000005","name":"US Department of Defense","doi-asserted-by":"publisher","award":["W81XWH1910534"],"award-info":[{"award-number":["W81XWH1910534"]}],"id":[{"id":"10.13039\/100000005","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000005","name":"US Department of Defense","doi-asserted-by":"publisher","award":["W81XWH-15-1-0286"],"award-info":[{"award-number":["W81XWH-15-1-0286"]}],"id":[{"id":"10.13039\/100000005","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000065","name":"National Institute of Neurological Disorders and Stroke","doi-asserted-by":"publisher","award":["1R61NS113315-01"],"award-info":[{"award-number":["1R61NS113315-01"]}],"id":[{"id":"10.13039\/100000065","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["clinicalkey.com","clinicalkey.com.au","clinicalkey.es","clinicalkey.fr","clinicalkey.jp","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Artificial Intelligence in Medicine"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.artmed.2026.103464","type":"journal-article","created":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T16:18:10Z","timestamp":1780676290000},"page":"103464","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Self-tuned healthy homogeneous core: Addressing heterogeneities in biomedical datasets"],"prefix":"10.1016","volume":"180","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-7559-8493","authenticated-orcid":false,"given":"Abhidnya","family":"Patharkar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9067-3679","authenticated-orcid":false,"given":"Yutong","family":"Wen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7235-9678","authenticated-orcid":false,"given":"Jiajing","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3083-1775","authenticated-orcid":false,"given":"Firas","family":"Al-Hindawi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0529-7048","authenticated-orcid":false,"given":"Teresa","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7780-7086","authenticated-orcid":false,"given":"Todd J.","family":"Schwedt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9035-8748","authenticated-orcid":false,"given":"Catherine D.","family":"Chong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.artmed.2026.103464_b1","doi-asserted-by":"crossref","DOI":"10.1016\/j.enbuild.2024.114378","article-title":"An entropy-based causality framework for cross-level faults diagnosis and isolation in building HVAC systems","volume":"317","author":"Huang","year":"2024","journal-title":"Energy Build"},{"key":"10.1016\/j.artmed.2026.103464_b2","series-title":"2024 IEEE 20th international conference on automation science and engineering","first-page":"2067","article-title":"A feature extraction framework with entropy on graphs for cross-dataset building fault detection","author":"Huang","year":"2024"},{"key":"10.1016\/j.artmed.2026.103464_b3","unstructured":"Huang J, Patharkar A, Al-Hindawi F, Joshi AM, Wu T, Wen J, O\u2019Neill Z, Candan KS. EE-GFE: An information-entropy graph-based feature extraction approach for cross-datasets fault detection in building HVAC systems, Available At SSRN 5111469."},{"key":"10.1016\/j.artmed.2026.103464_b4","series-title":"Advanced techniques for multivariate time series analysis in biomedical applications","author":"Patharkar","year":"2025"},{"issue":"1","key":"10.1016\/j.artmed.2026.103464_b5","doi-asserted-by":"crossref","first-page":"16076","DOI":"10.1038\/s41598-024-66953-7","article-title":"Eigen-entropy based time series signatures to support multivariate time series classification","volume":"14","author":"Patharkar","year":"2024","journal-title":"Sci Rep"},{"key":"10.1016\/j.artmed.2026.103464_b6","doi-asserted-by":"crossref","DOI":"10.3389\/fphys.2024.1386760","article-title":"Predictive modeling of biomedical temporal data in healthcare applications: review and future directions","volume":"15","author":"Patharkar","year":"2024","journal-title":"Front Physiol"},{"issue":"15","key":"10.1016\/j.artmed.2026.103464_b7","doi-asserted-by":"crossref","first-page":"17826","DOI":"10.1109\/JSEN.2023.3283648","article-title":"Corrections to \u201cSTRIDE: Systematic radar intelligence analysis for ADRD risk evaluation with gait signature simulation and deep learning\u201d","volume":"23","author":"Cai","year":"2023","journal-title":"IEEE Sensors J"},{"issue":"1","key":"10.1016\/j.artmed.2026.103464_b8","doi-asserted-by":"crossref","first-page":"86","DOI":"10.3390\/bioengineering12010086","article-title":"LiveDrive AI: A pilot study of a machine learning-powered diagnostic system for real-time, non-invasive detection of mild cognitive impairment","volume":"12","author":"Al-Hindawi","year":"2025","journal-title":"Bioengineering"},{"issue":"24","key":"10.1016\/j.artmed.2026.103464_b9","doi-asserted-by":"crossref","first-page":"8062","DOI":"10.3390\/s24248062","article-title":"Smart driving technology for non-invasive detection of age-related cognitive decline","volume":"24","author":"Serhan","year":"2024","journal-title":"Sensors"},{"key":"10.1016\/j.artmed.2026.103464_b10","unstructured":"Huang J, Li T, Xu Y, Wu T, Yoon H, Charlton JR, Bennett KM. EE-SMOTE: An oversampling method in conjunction with information entropy for imbalanced learning. In: IISE annual conference. Proceedings. 2022."},{"key":"10.1016\/j.artmed.2026.103464_b11","first-page":"1","article-title":"Healthy bio-core: A framework for selection of homogeneous healthy biomedical multivariate time series employing classification performance","author":"Patharkar","year":"2025","journal-title":"IEEE J Biomed Health Informatics"},{"key":"10.1016\/j.artmed.2026.103464_b12","series-title":"Harmonizing healthy cohorts to support multicenter studies on migraine classification using brain MRI data","author":"Yoon","year":"2023"},{"issue":"1","key":"10.1016\/j.artmed.2026.103464_b13","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1186\/s12916-019-1426-2","article-title":"Key challenges for delivering clinical impact with artificial intelligence","volume":"17","author":"Kelly","year":"2019","journal-title":"BMC Med"},{"issue":"1","key":"10.1016\/j.artmed.2026.103464_b14","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41746-019-0105-1","article-title":"Deep learning predicts hip fracture using confounding patient and healthcare variables","volume":"2","author":"Badgeley","year":"2019","journal-title":"NPJ Digit Med"},{"key":"10.1016\/j.artmed.2026.103464_b15","doi-asserted-by":"crossref","DOI":"10.1016\/j.artmed.2023.102747","article-title":"Contrastive image adaptation for acquisition shift reduction in medical imaging","volume":"148","author":"Hognon","year":"2024","journal-title":"Artif Intell Med"},{"issue":"11","key":"10.1016\/j.artmed.2026.103464_b16","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pmed.1002683","article-title":"Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: A cross-sectional study","volume":"15","author":"Zech","year":"2018","journal-title":"PLOS Med"},{"key":"10.1016\/j.artmed.2026.103464_b17","series-title":"Underspecification presents challenges for credibility in modern machine learning","author":"D\u2019Amour","year":"2020"},{"key":"10.1016\/j.artmed.2026.103464_b18","series-title":"European conference on computer vision","first-page":"338","article-title":"Fast diffusion-based counterfactuals for shortcut removal and generation","author":"Weng","year":"2024"},{"key":"10.1016\/j.artmed.2026.103464_b19","series-title":"Information theory and statistics","author":"Kullback","year":"1997"},{"issue":"1","key":"10.1016\/j.artmed.2026.103464_b20","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1214\/aoms\/1177729694","article-title":"On information and sufficiency","volume":"22","author":"Kullback","year":"1951","journal-title":"Ann Math Stat"},{"issue":"1","key":"10.1016\/j.artmed.2026.103464_b21","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1007\/BF02418571","article-title":"Sur les fonctions convexes et les in\u00e9galit\u00e9s entre les valeurs moyennes","volume":"30","author":"Jensen","year":"1906","journal-title":"Acta Math"},{"key":"10.1016\/j.artmed.2026.103464_b22","series-title":"Information theory: coding theorems for discrete memoryless systems","author":"Csisz\u00e1r","year":"2011"},{"key":"10.1016\/j.artmed.2026.103464_b23","unstructured":"Toneva M, Sordoni A, des Combes RT, Trischler A, Bengio Y, Gordon GJ. An empirical study of example forgetting during deep neural network learning. In: International conference on learning representations. ICLR, 2019."},{"key":"10.1016\/j.artmed.2026.103464_b24","unstructured":"Sener O, Savarese S. Active Learning for Convolutional Neural Networks: A Core-Set Approach. In: International conference on learning representations. ICLR, 2018."},{"key":"10.1016\/j.artmed.2026.103464_b25","unstructured":"Ash JT, Zhang C, Krishnamurthy A, Langford J, Agarwal A. Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds. In: International conference on learning representations. ICLR, 2020."},{"key":"10.1016\/j.artmed.2026.103464_b26","doi-asserted-by":"crossref","unstructured":"Killamsetty K, Sivasubramanian D, Ramakrishnan G, Iyer R. Glister: Generalization based data subset selection for efficient and robust learning. In: Proceedings of the AAAI conference on artificial intelligence. vol. 35, 2021, p. 8110\u20138.","DOI":"10.1609\/aaai.v35i9.16988"},{"key":"10.1016\/j.artmed.2026.103464_b27","doi-asserted-by":"crossref","DOI":"10.1016\/j.artmed.2020.101815","article-title":"Efficient treatment of outliers and class imbalance for diabetes prediction","volume":"104","author":"Nnamoko","year":"2020","journal-title":"Artif Intell Med"},{"key":"10.1016\/j.artmed.2026.103464_b28","doi-asserted-by":"crossref","first-page":"558","DOI":"10.1016\/j.ins.2023.01.090","article-title":"A stochastic approximation approach to fixed instance selection","volume":"628","author":"Yeo","year":"2023","journal-title":"Inform Sci"},{"key":"10.1016\/j.artmed.2026.103464_b29","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1016\/j.ins.2022.04.036","article-title":"Cluster-oriented instance selection for classification problems","volume":"602","author":"Saha","year":"2022","journal-title":"Inform Sci"},{"key":"10.1016\/j.artmed.2026.103464_b30","doi-asserted-by":"crossref","first-page":"794","DOI":"10.1016\/j.ins.2022.07.025","article-title":"Curious instance selection","volume":"608","author":"Moran","year":"2022","journal-title":"Inform Sci"},{"key":"10.1016\/j.artmed.2026.103464_b31","doi-asserted-by":"crossref","first-page":"579","DOI":"10.1016\/j.ins.2021.07.015","article-title":"Efficient and decision boundary aware instance selection for support vector machines","volume":"577","author":"Aslani","year":"2021","journal-title":"Inform Sci"},{"key":"10.1016\/j.artmed.2026.103464_b32","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1016\/j.ins.2018.10.029","article-title":"Under-sampling class imbalanced datasets by combining clustering analysis and instance selection","volume":"477","author":"Tsai","year":"2019","journal-title":"Inform Sci"},{"key":"10.1016\/j.artmed.2026.103464_b33","series-title":"Information theory, inference and learning algorithms","author":"MacKay","year":"2003"},{"key":"10.1016\/j.artmed.2026.103464_b34","series-title":"2014 information theory and applications workshop","first-page":"1","article-title":"Total variation distance and the distribution of relative information","author":"Verd\u00fa","year":"2014"},{"issue":"11","key":"10.1016\/j.artmed.2026.103464_b35","doi-asserted-by":"crossref","first-page":"559","DOI":"10.1080\/14786440109462720","article-title":"LIII. On lines and planes of closest fit to systems of points in space","volume":"2","author":"Pearson","year":"1901","journal-title":"Lond Edinb Dublin Philos Mag J Sci"},{"issue":"23","key":"10.1016\/j.artmed.2026.103464_b36","doi-asserted-by":"crossref","first-page":"e215","DOI":"10.1161\/01.CIR.101.23.e215","article-title":"PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals","volume":"101","author":"Goldberger","year":"2000","journal-title":"Circulation"},{"key":"10.1016\/j.artmed.2026.103464_b37","series-title":"PTB-XL+, a comprehensive electrocardiographic feature dataset","author":"Strodthoff","year":"2023"},{"key":"10.1016\/j.artmed.2026.103464_b38","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1038\/s41597-023-02153-8","article-title":"PTB-XL+, a comprehensive electrocardiographic feature dataset","volume":"10","author":"Strodthoff","year":"2023","journal-title":"Sci Data"},{"key":"10.1016\/j.artmed.2026.103464_b39","series-title":"Arrhythmia","author":"Guvenir","year":"1997"},{"issue":"9","key":"10.1016\/j.artmed.2026.103464_b40","doi-asserted-by":"crossref","first-page":"828","DOI":"10.1177\/0333102416652091","article-title":"Migraine classification using magnetic resonance imaging resting-state functional connectivity data","volume":"37","author":"Chong","year":"2017","journal-title":"Cephalalgia"},{"key":"10.1016\/j.artmed.2026.103464_b41","series-title":"2008 eighth IEEE international conference on data mining","first-page":"413","article-title":"Isolation forest","author":"Liu","year":"2008"},{"issue":"7","key":"10.1016\/j.artmed.2026.103464_b42","doi-asserted-by":"crossref","first-page":"552","DOI":"10.1016\/j.biopsych.2015.12.023","article-title":"Understanding heterogeneity in clinical cohorts using normative models: Beyond case\u2013control studies","volume":"80","author":"Marquand","year":"2016","journal-title":"Biol Psychiatry"},{"key":"10.1016\/j.artmed.2026.103464_b43","doi-asserted-by":"crossref","DOI":"10.7554\/eLife.85082","article-title":"Evidence for embracing normative modeling","volume":"12","author":"Rutherford","year":"2023","journal-title":"ELife"},{"key":"10.1016\/j.artmed.2026.103464_b44","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1016\/j.ins.2018.12.034","article-title":"A factor graph model for unsupervised feature selection","volume":"480","author":"Wang","year":"2019","journal-title":"Inform Sci"},{"key":"10.1016\/j.artmed.2026.103464_b45","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.ins.2019.01.041","article-title":"Feature selection for imbalanced data based on neighborhood rough sets","volume":"483","author":"Chen","year":"2019","journal-title":"Inform Sci"},{"key":"10.1016\/j.artmed.2026.103464_b46","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1016\/j.ins.2022.05.076","article-title":"Domain knowledge-enhanced variable selection for biomedical data analysis","volume":"606","author":"Wu","year":"2022","journal-title":"Inform Sci"},{"key":"10.1016\/j.artmed.2026.103464_b47","doi-asserted-by":"crossref","DOI":"10.1016\/j.artmed.2022.102277","article-title":"A novel multi-objective medical feature selection compass method for binary classification","volume":"127","author":"Gutowski","year":"2022","journal-title":"Artif Intell Med"},{"key":"10.1016\/j.artmed.2026.103464_b48","doi-asserted-by":"crossref","DOI":"10.1016\/j.ins.2024.120277","article-title":"Unsupervised feature selection using orthogonal encoder-decoder factorization","volume":"663","author":"Mozafari","year":"2024","journal-title":"Inform Sci"}],"container-title":["Artificial Intelligence in Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0933365726001168?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0933365726001168?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T07:21:22Z","timestamp":1784532082000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0933365726001168"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":48,"alternative-id":["S0933365726001168"],"URL":"https:\/\/doi.org\/10.1016\/j.artmed.2026.103464","relation":{},"ISSN":["0933-3657"],"issn-type":[{"value":"0933-3657","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Self-tuned healthy homogeneous core: Addressing heterogeneities in biomedical datasets","name":"articletitle","label":"Article Title"},{"value":"Artificial Intelligence in Medicine","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.artmed.2026.103464","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"103464"}}