{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T17:59:31Z","timestamp":1790704771334,"version":"4.1.0"},"reference-count":51,"publisher":"Public Library of Science (PLoS)","issue":"9","license":[{"start":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T00:00:00Z","timestamp":1790640000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Choosing an appropriate imputation strategy for clinical datasets requires understanding which missing data mechanism is operative, yet most imputation benchmarks conflate performance across mechanisms. The present work addresses this gap by conducting the first mechanism-stratified comparison of three imputation approaches\u2014CHIT, Multiple Imputation by Chained Equations via BayesianRidge (MICE), and Random-Forest-based Iterative Imputation\u2014across Missing Completely at Random (MCAR), Missing at Random (MAR), and Missing Not at Random (MNAR) conditions. Three health datasets serve as experimental platforms: the Chronic Kidney Disease (CKD) dataset, the Heart Disease Dataset (HDD), and the Mice Protein Expression Dataset (MPED). Domain-knowledge-driven missingness patterns are constructed for each mechanism (Fig 2) at approximately 20\u201325% overall rates. Eight classifiers\u2014KNN, Logistic Regression, SVC, Decision Tree, Random Forest, Gaussian Na\u00efve Bayes, MLP, and a deep neural network\u2014are trained on imputed data following GridSearchCV optimisation. Across all conditions, CHIT achieves near-perfect or perfect downstream classification, with SVC reaching up to 100% accuracy on the CKD dataset under MNAR, and 98.75% under MCAR and MAR. Competing methods degrade by up to 19.38 percentage points under MNAR, while CHIT\u2019s accuracy remains stable. Two structural properties account for this resilience: an iterative enrichment of the regression training set as records are completed, and a within-record prioritisation of the most data-scarce features for model-based filling. Taken together, these results provide mechanism-specific guidance for imputation selection in health informatics pipelines. Statistical significance of classifier accuracy differences between CHIT and MICE was assessed using McNemar\u2019s test (two-tailed, continuity-corrected chi-square) applied to the exact binary prediction vectors from each experiment [n_test\u2009=\u200980]. Ninety-five percent confidence intervals for all reported accuracy values were computed using the Wilson score method [z\u2009=\u20091.96]. The 42-configuration mean accuracy and standard deviation for CHIT are reported in Supplementary Table S1. Full McNemar results with confidence intervals are in Supplementary Table S2.<\/jats:p>","DOI":"10.1371\/journal.pone.0359577","type":"journal-article","created":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T17:25:25Z","timestamp":1790702725000},"page":"e0359577","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Evaluating the Cyclical Hybrid Imputation Technique (CHIT) under MCAR, MAR, and MNAR missing data mechanisms: Evidence from health datasets"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6660-0565","authenticated-orcid":true,"given":"Kurban","family":"Kotan","sequence":"first","affiliation":[{"name":"Manisa Celal Bayar University","place":["Manisa, Turkey"],"department":["Department of Artificial Intelligence and Machine Learning, Faculty of Computer and Information Sciences"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4416-6657","authenticated-orcid":true,"given":"Serdar","family":"K\u0131r\u0131\u015fo\u011flu","sequence":"additional","affiliation":[{"name":"Engineering Faculty, Duzce University","place":["D\u00fczce, Turkey"],"department":["Department of Computer Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,9,29]]},"reference":[{"issue":"10","key":"pone.0359577.ref001","doi-asserted-by":"crossref","first-page":"1087","DOI":"10.1016\/j.jclinepi.2006.01.014","article-title":"Review: a gentle introduction to imputation of missing values","volume":"59","author":"ART Donders","year":"2006","journal-title":"J Clin Epidemiol"},{"issue":"6","key":"pone.0359577.ref002","doi-asserted-by":"crossref","first-page":"618","DOI":"10.1002\/pds.1934","article-title":"Issues in multiple imputation of missing data for large general practice clinical databases","volume":"19","author":"L Marston","year":"2010","journal-title":"Pharmacoepidemiol Drug Saf"},{"issue":"28","key":"pone.0359577.ref003","doi-asserted-by":"crossref","first-page":"2920","DOI":"10.1002\/sim.3944","article-title":"Bias and efficiency of multiple imputation compared with complete-case analysis for missing covariate values","volume":"29","author":"IR White","year":"2010","journal-title":"Stat Med"},{"key":"pone.0359577.ref004","article-title":"Multiple imputation for missing data in epidemiological and clinical research: potential and pitfalls","volume":"338","author":"JAC Sterne","year":"2009","journal-title":"BMJ"},{"key":"pone.0359577.ref005","doi-asserted-by":"crossref","DOI":"10.1002\/9780470510445","volume-title":"Missing data in clinical studies","author":"G Molenberghs","year":"2007"},{"key":"pone.0359577.ref006","volume-title":"Statistical analysis with missing data","author":"RJA Little","year":"2019","edition":"3"},{"issue":"3","key":"pone.0359577.ref007","doi-asserted-by":"crossref","first-page":"581","DOI":"10.1093\/biomet\/63.3.581","article-title":"Inference and missing data","volume":"63","author":"DB Rubin","year":"1976","journal-title":"Biometrika"},{"issue":"1","key":"pone.0359577.ref008","doi-asserted-by":"crossref","first-page":"6543","DOI":"10.1038\/s41598-025-90964-7","article-title":"Cyclical hybrid imputation technique for missing values in data sets","volume":"15","author":"K Kotan","year":"2025","journal-title":"Sci Rep"},{"issue":"10","key":"pone.0359577.ref009","doi-asserted-by":"crossref","first-page":"1631","DOI":"10.1681\/ASN.2011111078","article-title":"Mechanisms of anemia in CKD","volume":"23","author":"JL Babitt","year":"2012","journal-title":"J Am Soc Nephrol"},{"issue":"15","key":"pone.0359577.ref010","doi-asserted-by":"crossref","first-page":"1553","DOI":"10.1001\/jama.2011.451","article-title":"A predictive model for progression of chronic kidney disease to kidney failure","volume":"305","author":"N Tangri","year":"2011","journal-title":"JAMA"},{"issue":"3","key":"pone.0359577.ref011","doi-asserted-by":"crossref","first-page":"278","DOI":"10.1177\/0962280210395740","article-title":"Review of inverse probability weighting for dealing with missing data","volume":"22","author":"SR Seaman","year":"2013","journal-title":"Stat Methods Med Res"},{"key":"pone.0359577.ref012","doi-asserted-by":"crossref","DOI":"10.1201\/9780429492259","volume-title":"Flexible imputation of missing data","author":"S Van Buuren","year":"2018","edition":"2"},{"issue":"3","key":"pone.0359577.ref013","article-title":"mice: Multivariate Imputation by Chained Equations inR","volume":"45","author":"S van Buuren","year":"2011","journal-title":"J Stat Soft"},{"key":"pone.0359577.ref014","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","volume":"12","author":"F Pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"pone.0359577.ref015","volume-title":"Multiple imputation and its application","author":"JR Carpenter","year":"2023","edition":"2"},{"issue":"6","key":"pone.0359577.ref016","doi-asserted-by":"crossref","first-page":"520","DOI":"10.1093\/bioinformatics\/17.6.520","article-title":"Missing value estimation methods for DNA microarrays","volume":"17","author":"O Troyanskaya","year":"2001","journal-title":"Bioinformatics"},{"key":"pone.0359577.ref017","doi-asserted-by":"crossref","first-page":"639","DOI":"10.1007\/978-3-642-17103-1_60","article-title":"The treatment of missing values and its effect on classifier accuracy.","volume-title":"Classification, clustering and data mining applications","author":"E Acuna","year":"2004"},{"issue":"8","key":"pone.0359577.ref018","doi-asserted-by":"crossref","DOI":"10.1136\/bmjopen-2013-002847","article-title":"Comparison of imputation methods for missing laboratory data in medicine","volume":"3","author":"AK Waljee","year":"2013","journal-title":"BMJ Open"},{"issue":"1","key":"pone.0359577.ref019","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1093\/bioinformatics\/btr597","article-title":"MissForest--non-parametric missing value imputation for mixed-type data","volume":"28","author":"DJ Stekhoven","year":"2012","journal-title":"Bioinformatics"},{"key":"pone.0359577.ref020","doi-asserted-by":"crossref","first-page":"693674","DOI":"10.3389\/fdata.2021.693674","article-title":"A Benchmark for Data Imputation Methods","volume":"4","author":"S J\u00e4ger","year":"2021","journal-title":"Front Big Data"},{"key":"pone.0359577.ref021","doi-asserted-by":"crossref","first-page":"260","DOI":"10.1007\/978-3-319-93040-4_21","article-title":"MIDA: Multiple Imputation Using Denoising Autoencoders.","volume-title":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","author":"L Gondara","year":"2018"},{"key":"pone.0359577.ref022","doi-asserted-by":"crossref","first-page":"107501","DOI":"10.1016\/j.patcog.2020.107501","article-title":"Handling incomplete heterogeneous data using VAEs","volume":"107","author":"A Naz\u00e1bal","year":"2020","journal-title":"Pattern Recognit"},{"key":"pone.0359577.ref023","unstructured":"Jarrett D., Cebere B.C., Liu T., Curth A., van der Schaar M. HyperImpute: Generalised iterative imputation with automatic model selection. In: Proc. ICML. PMLR; 2022;162:9916\u201337."},{"issue":"24","key":"pone.0359577.ref024","doi-asserted-by":"crossref","first-page":"3167","DOI":"10.3390\/electronics10243167","article-title":"A Hybrid Imputation Method for Multi-Pattern Missing Data: A Case Study on Type II Diabetes Diagnosis","volume":"10","author":"MH Nadimi-Shahraki","year":"2021","journal-title":"Electronics"},{"issue":"2","key":"pone.0359577.ref025","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1037\/1082-989X.7.2.147","article-title":"Missing data: our view of the state of the art","volume":"7","author":"JL Schafer","year":"2002","journal-title":"Psychol Methods"},{"issue":"1","key":"pone.0359577.ref026","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1186\/s40537-021-00516-9","article-title":"A survey on missing data in machine learning","volume":"8","author":"T Emmanuel","year":"2021","journal-title":"J Big Data"},{"key":"pone.0359577.ref027","doi-asserted-by":"crossref","DOI":"10.4135\/9781452272054","volume-title":"The SAGE sourcebook of advanced data analysis methods for communication research","author":"AF Hayes","year":"2008"},{"issue":"1","key":"pone.0359577.ref028","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1038\/s43856-023-00356-z","article-title":"The impact of imputation quality on machine learning classifiers for datasets with missing values","volume":"3","author":"T Shadbahr","year":"2023","journal-title":"Commun Med (Lond)"},{"issue":"7","key":"pone.0359577.ref029","doi-asserted-by":"crossref","first-page":"950","DOI":"10.1016\/j.patrec.2008.01.010","article-title":"Good methods for coping with missing data in decision trees","volume":"29","author":"BETH Twala","year":"2008","journal-title":"Pattern Recognit Lett"},{"key":"pone.0359577.ref030","unstructured":"Dua D., Graff C. UCI Machine Learning Repository. University of California, School of Information and Computer Science. 2019. http:\/\/archive.ics.uci.edu\/ml"},{"key":"pone.0359577.ref031","doi-asserted-by":"crossref","first-page":"20991","DOI":"10.1109\/ACCESS.2019.2963053","article-title":"A Machine Learning Methodology for Diagnosing Chronic Kidney Disease","volume":"8","author":"J Qin","year":"2020","journal-title":"IEEE Access"},{"key":"pone.0359577.ref032","doi-asserted-by":"crossref","first-page":"9266889","DOI":"10.1155\/2023\/9266889","article-title":"Machine Learning Hybrid Model for the Prediction of Chronic Kidney Disease","volume":"2023","author":"H Khalid","year":"2023","journal-title":"Comput Intell Neurosci"},{"issue":"3","key":"pone.0359577.ref033","doi-asserted-by":"crossref","first-page":"98","DOI":"10.3390\/bdcc6030098","article-title":"Machine Learning Techniques for Chronic Kidney Disease Risk Prediction","volume":"6","author":"E Dritsas","year":"2022","journal-title":"BDCC"},{"issue":"4","key":"pone.0359577.ref034","doi-asserted-by":"crossref","first-page":"1210","DOI":"10.3390\/pr11041210","article-title":"Enhancing Heart Disease Prediction Accuracy through Machine Learning Techniques and Optimization","volume":"11","author":"N Chandrasekhar","year":"2023","journal-title":"Processes"},{"issue":"24","key":"pone.0359577.ref035","first-page":"12672","article-title":"Analyzing the effect of data preprocessing techniques using machine learning algorithms on the diagnosis of COVID-19","volume":"12","author":"G Erol","year":"2022","journal-title":"Appl Sci"},{"issue":"2","key":"pone.0359577.ref036","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1007\/s00521-009-0295-6","article-title":"Pattern classification with missing data: a review","volume":"19","author":"PJ Garc\u00eda-Laencina","year":"2009","journal-title":"Neural Comput Appl"},{"issue":"2","key":"pone.0359577.ref037","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1016\/j.artmed.2010.05.002","article-title":"Missing data imputation using statistical and machine learning methods in a real breast cancer problem","volume":"50","author":"JM Jerez","year":"2010","journal-title":"Artif Intell Med"},{"key":"pone.0359577.ref038","doi-asserted-by":"crossref","first-page":"549","DOI":"10.1146\/annurev.psych.58.110405.085530","article-title":"Missing data analysis: making it work in the real world","volume":"60","author":"JW Graham","year":"2009","journal-title":"Annu Rev Psychol"},{"key":"pone.0359577.ref039","author":"A Janosi","year":"1988"},{"key":"pone.0359577.ref040","author":"C. Higuera","year":"2015","journal-title":"Mice Protein Expression (UCI Machine Learning Repository)"},{"issue":"4","key":"pone.0359577.ref041","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2382577.2382579","article-title":"Leakage in data mining: formulation, detection, and avoidance","volume":"6","author":"S Kaufman","year":"2012","journal-title":"ACM Trans Knowl Discov Data"},{"issue":"1","key":"pone.0359577.ref042","first-page":"1","article-title":"KDIGO 2017 clinical practice guideline update for the diagnosis, evaluation, prevention, and treatment of chronic kidney disease\u2013mineral and bone disorder (CKD-MBD)","volume":"7","author":"KDIGO","year":"2017","journal-title":"Kidney Int Suppl"},{"key":"pone.0359577.ref043","volume-title":"Haemoglobin concentrations for the diagnosis of anaemia and assessment of severity","author":"WHO","year":"2011"},{"issue":"7553","key":"pone.0359577.ref044","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"Y LeCun","year":"2015","journal-title":"Nature"},{"key":"pone.0359577.ref045","volume-title":"Deep learning","author":"I Goodfellow","year":"2016"},{"issue":"404","key":"pone.0359577.ref046","doi-asserted-by":"crossref","first-page":"1198","DOI":"10.1080\/01621459.1988.10478722","article-title":"A Test of Missing Completely at Random for Multivariate Data with Missing Values","volume":"83","author":"RJA Little","year":"1988","journal-title":"J Am Stat Assoc"},{"issue":"2","key":"pone.0359577.ref047","doi-asserted-by":"crossref","first-page":"837","DOI":"10.29130\/dubited.980594","article-title":"\u00c7ok Katmanl\u0131 Alg\u0131lay\u0131c\u0131 ile A\u011f Trafi\u011fi S\u0131n\u0131fland\u0131rma Analizi","volume":"10","author":"S K\u0131r\u0131\u015fo\u011flu","year":"2022","journal-title":"D\u00fczce \u00dcniversitesi Bilim ve Teknoloji Dergisi"},{"key":"pone.0359577.ref048","unstructured":"Zhang H. The optimality of Na\u00efve Bayes. In: Proc. 17th International FLAIRS Conference. AAAI Press; 2004. p. 562\u20137."},{"issue":"2","key":"pone.0359577.ref049","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1097\/EDE.0b013e318209dec7","article-title":"Sensitivity analysis when data are missing not-at-random","volume":"22","author":"N Resseguier","year":"2011","journal-title":"Epidemiology"},{"key":"pone.0359577.ref050","doi-asserted-by":"crossref","first-page":"44917","DOI":"10.1109\/ACCESS.2025.3567743","article-title":"Detection of Economic Crises With Language Models and Comparative Analysis of Simple Time Series Analysis Models and Machine Learning Algorithms on the Stock Market","volume":"13","author":"K Kotan","year":"2025","journal-title":"IEEE Access"},{"issue":"4","key":"pone.0359577.ref051","doi-asserted-by":"crossref","first-page":"292","DOI":"10.3390\/su17041536","article-title":"Sustainable Economic Development Through Crisis Detection Using AI Techniques","volume":"17","author":"K Kotan","year":"2025","journal-title":"Sustainability"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0359577","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T17:25:35Z","timestamp":1790702735000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0359577"}},"subtitle":[],"editor":[{"given":"Hiroyuki","family":"Maruyama","sequence":"first","affiliation":[{"name":"Takushoku University","place":["JAPAN"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,9,29]]},"references-count":51,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9,29]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0359577","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,29]]}}}