{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T12:15:59Z","timestamp":1791375359824,"version":"4.3.1"},"reference-count":36,"publisher":"Wiley","issue":"2","license":[{"start":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T00:00:00Z","timestamp":1764633600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T00:00:00Z","timestamp":1764633600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Int J Lab Hematology"],"published-print":{"date-parts":[[2026,4]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Thalassemia is a major global health concern, as declared by the World Health Organization (WHO). Accurate screening of heterozygotes is of paramount importance for diagnostic guidance and disease mitigation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Multiclass machine\u2010learning (ML) models were developed to classify alpha, beta, and delta\/beta\u2010thalassemia heterozygotes, individuals with iron deficiency microcytic anemia and healthy individuals. Complete blood count (CBC) data were derived from 1518 individuals, simultaneously measured in four different hematological analyzers [Sysmex K\u20101000 (Sysmex), Cell\u2010Dyn Sapphire (Abbott), ADVIA 2120 (Siemens), BC\u20106800 (Mindray)]. The Recursive Feature Elimination (RFE) method was applied to investigate the optimal number and combination of hematological parameters required for adequate model training, and their importance was determined using the SHAP method. Random Forest classifier and Active Learning (AL) method were used to evaluate diagnostic accuracy and enhance the model's performance, respectively. Dimensionality reduction techniques were applied for visualization purposes. Additionally, the existence of subclusters within each class was investigated using unsupervised techniques.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Four hematological parameters (MCH, MCV, HGB, and RDW) are sufficient to classify basic types of microcytosis, achieving an accuracy of over 80%. Adding further parameters to the training process can improve the stability and reliability of the model when applied to unseen data, but does not increase test accuracy beyond 90%. Each microcytosis cluster is discriminated by assigning different weights to selected hematological parameters, forming five distinct clusters in the 2D plane (heterozygous alpha\u2010, beta\u2010, and delta\/beta\u2010thalassemia, iron deficiency anemia, and normal individuals). The greatest overlap between clusters occurs between alpha\u2010 and beta\u2010thalassemia. The alpha\u2010thalassemia cluster appears to have a more diffuse scatter on the 2D plane, but two distinct subclusters are identified within this class, characterized by the differential expression of specific parameters (PCT, MPV, P\u2010LCR, PDW, MCV, MCH, and RBC). The developed model can estimate the probabilities of classifying a new case into the core established clusters and, in the case of alpha\u2010thalassemia, the possible subcluster.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The application of ML models for the automated differential diagnosis of microcytosis, using CBC data, revealed that the diagnostic accuracy is not proportionally dependent on the use of an increasing number of hematological parameters. A developed model is proposed which can correctly classify a new case in the core clusters or subclusters of patients with microcytosis.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1111\/ijlh.70033","type":"journal-article","created":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T08:37:10Z","timestamp":1764664630000},"page":"447-457","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["The Application of Machine\u2010Learning Algorithms for Multiclass Classification of Microcytic Anemia Revealed That a Minimum Required Number of Hematological Parameters Is Enough to Achieve High Diagnostic Accuracy"],"prefix":"10.1111","volume":"48","author":[{"given":"Veroniki","family":"Komninaka","sequence":"first","affiliation":[{"name":"Hematology Laboratory, GNA G. Gennimatas  Athens Greece"},{"name":"Centre of Excellence in Rare Haematological (Haemoglobinopathies) &amp; Rare Metabolic (Gaucher Disease) Diseases, Laiko General Hospital  Athens Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sofia","family":"Liossi","sequence":"additional","affiliation":[{"name":"Laboratory of Reliability and Quality Control in Laboratory Hematology, Department of Biomedical Sciences, School of Health and Welfare Sciences, University of West Attica  Athens Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9759-0048","authenticated-orcid":false,"given":"Nikolaos J.","family":"Tsagarakis","sequence":"additional","affiliation":[{"name":"Hematology Laboratory, GNA G. Gennimatas  Athens Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ioanna","family":"Fotopoulou","sequence":"additional","affiliation":[{"name":"Department of Immunology GNA G. Gennimatas  Athens Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8539-5202","authenticated-orcid":false,"given":"Georgios","family":"Oudatzis","sequence":"additional","affiliation":[{"name":"Department of Immunology GNA G. Gennimatas  Athens Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ioulia","family":"Chaliori","sequence":"additional","affiliation":[{"name":"Hematology Laboratory, GNA G. Gennimatas  Athens Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christina","family":"Karela","sequence":"additional","affiliation":[{"name":"Department of Immunology GNA G. Gennimatas  Athens Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dimitrios","family":"Liakopoulos","sequence":"additional","affiliation":[{"name":"Hematology Laboratory, GNA G. Gennimatas  Athens Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paraskevi","family":"Vasileiou","sequence":"additional","affiliation":[{"name":"Flowdiagnosis Diagnostic Center  Athens Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Effie G.","family":"Papageorgiou","sequence":"additional","affiliation":[{"name":"Laboratory of Reliability and Quality Control in Laboratory Hematology, Department of Biomedical Sciences, School of Health and Welfare Sciences, University of West Attica  Athens Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Georgios","family":"Paterakis","sequence":"additional","affiliation":[{"name":"Department of Immunology GNA G. Gennimatas  Athens Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2025,12,2]]},"reference":[{"key":"e_1_2_12_2_1","doi-asserted-by":"publisher","DOI":"10.1053\/j.seminhematol.2015.05.002"},{"key":"e_1_2_12_3_1","doi-asserted-by":"publisher","DOI":"10.1515\/cclm-2015-0179"},{"key":"e_1_2_12_4_1","doi-asserted-by":"publisher","DOI":"10.5824\/1309-1581.2014.3.001.x"},{"issue":"1","key":"e_1_2_12_5_1","first-page":"85","article-title":"Iron\u2010Deficiency Anemia Detection From Hematology Parameters by Using Decision Trees","volume":"3","author":"Dogan S.","year":"2008","journal-title":"International Journal of Science & Technology"},{"key":"e_1_2_12_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-011-9772-4"},{"key":"e_1_2_12_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-011-9668-3"},{"issue":"4","key":"e_1_2_12_8_1","first-page":"55","article-title":"Discrimination Between Iron Deficiency Anaemia (IDA) and \u03b2\u2010Thalassemia Trait (\u03b2\u2010Tt) Based on Pattern\u2010Based Input Selection Artificial Neural Network (PBIS\u2010ANN)","volume":"7","author":"Khaki Jamei M.","year":"2016","journal-title":"Journal of Advances in Computer Research"},{"key":"e_1_2_12_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CSNT.2015.112"},{"key":"e_1_2_12_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jestch.2020.12.003"},{"key":"e_1_2_12_11_1","doi-asserted-by":"publisher","DOI":"10.58491\/2735-4202.3144"},{"key":"e_1_2_12_12_1","doi-asserted-by":"publisher","DOI":"10.1093\/clinchem\/hvae081"},{"key":"e_1_2_12_13_1","unstructured":"G.Maheshwari D.Ivanov andK. E.Haddad \u201cEfficacy of Synthetic Data as a Benchmark \u201d2024 arXiv preprint arXiv:240911968."},{"key":"e_1_2_12_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/69.553159"},{"key":"e_1_2_12_15_1","doi-asserted-by":"publisher","DOI":"10.3390\/app14198860"},{"issue":"2","key":"e_1_2_12_16_1","first-page":"111","article-title":"Data Preprocessing for Supervised Leaning","volume":"1","author":"Kotsiantis S. B.","year":"2006","journal-title":"International Journal of Computer Science"},{"key":"e_1_2_12_17_1","first-page":"429","volume-title":"Sixth International Conference on Machine Learning and Applications (ICMLA 2007)","author":"Xw C.","year":"2007"},{"key":"e_1_2_12_18_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953"},{"key":"e_1_2_12_19_1","volume-title":"Hands\u2010On Automated Machine Learning: A Beginner's Guide to Building Automated Machine Learning Systems Using AutoML and Python","author":"Das S.","year":"2018"},{"key":"e_1_2_12_20_1","doi-asserted-by":"publisher","DOI":"10.1177\/1536867X20909688"},{"key":"e_1_2_12_21_1","doi-asserted-by":"publisher","DOI":"10.4236\/jdaip.2020.84020"},{"key":"e_1_2_12_22_1","doi-asserted-by":"publisher","DOI":"10.3991\/ijoe.v19i06.38157"},{"key":"e_1_2_12_23_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-56706-x"},{"key":"e_1_2_12_24_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010920819831"},{"key":"e_1_2_12_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2007.05.001"},{"key":"e_1_2_12_26_1","doi-asserted-by":"publisher","DOI":"10.3390\/app13052942"},{"key":"e_1_2_12_27_1","doi-asserted-by":"publisher","DOI":"10.1088\/1757-899X\/569\/5\/052024"},{"key":"e_1_2_12_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/DSAA49011.2020.00096"},{"key":"e_1_2_12_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.crmeth.2022.100390"},{"key":"e_1_2_12_30_1","unstructured":"scikit\u2010learn. Gaussian mixture models2024. 2007\u20132024."},{"key":"e_1_2_12_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/SIBGRAPI51738.2020.00053"},{"key":"e_1_2_12_32_1","doi-asserted-by":"publisher","DOI":"10.1038\/s43586-022-00184-w"},{"key":"e_1_2_12_33_1","volume-title":"Mathematical Modelling of Haematopoiesis and Blood Diseases","author":"Demin I.","year":"2009"},{"key":"e_1_2_12_34_1","doi-asserted-by":"publisher","DOI":"10.1055\/s-0039-1677913"},{"key":"e_1_2_12_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2024.108581"},{"key":"e_1_2_12_36_1","doi-asserted-by":"publisher","DOI":"10.1111\/ejh.14160"},{"issue":"3","key":"e_1_2_12_37_1","first-page":"541","article-title":"The Performance Characteristics of an Expert System for the \u2018On\u2010Line\u2019 Assessment of Thalassemia Trait and Iron Deficiency\u2010Micro Hema Screen","volume":"15","author":"Paterakis G. S.","year":"1989","journal-title":"Blood Cells"}],"container-title":["International Journal of Laboratory Hematology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/ijlh.70033","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/ijlh.70033","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/ijlh.70033","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T16:33:47Z","timestamp":1772987627000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/ijlh.70033"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,2]]},"references-count":36,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["10.1111\/ijlh.70033"],"URL":"https:\/\/doi.org\/10.1111\/ijlh.70033","archive":["Portico"],"relation":{},"ISSN":["1751-5521","1751-553X"],"issn-type":[{"value":"1751-5521","type":"print"},{"value":"1751-553X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,2]]},"assertion":[{"value":"2025-05-27","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-26","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-02","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}