{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T04:50:36Z","timestamp":1782449436797,"version":"3.54.5"},"reference-count":24,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T00:00:00Z","timestamp":1781827200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JCM"],"abstract":"<jats:p>Background\/Objectives: Iron deficiency remains a prevalent condition, needing specific laboratory tests for diagnosis. This study aimed to evaluate whether routine complete blood cell count (CBC) parameters can be used within a machine learning framework to predict low ferritin and low transferrin saturation, used as biochemical markers of altered iron status, potentially supporting more targeted laboratory test utilization. Methods: In this single-center retrospective outpatient study, we analyzed 32,437 records from subjects undergoing both complete blood cell count and iron metabolism testing between 2023 and 2026. Low ferritin and low transferrin saturation were defined using sex-specific thresholds. Low ferritin was present in 14,344 subjects (44.2%), whereas low transferrin saturation was present in 7791 subjects (24.0%). After cleaning data and excluding incomplete records, demographic variables and CBC indices were tested as potential predictors. The dataset was split into training and test sets with stratified sampling. Multiple supervised machine learning models, including logistic regression, decision tree, random forest, XGBoost, support vector machine, k-nearest neighbors, and Naive Bayes, were trained. Hyperparameter tuning and model selection were performed using repeated stratified 10-fold cross-validation, optimizing the area under the curve (AUC). Model performance was assessed by AUC, sensitivity, and specificity, and validated on an independent test set. Results: All models showed predictive capability for low ferritin and low transferrin saturation using CBC parameters alone. Ensemble methods, especially random forest and XGBoost, reached the best performance (AUC values of 0.80\u20130.87 for ferritin and 0.85\u20130.96 for transferrin saturation). Sensitivity and specificity were balanced, supporting clinical screening applicability. Results were maintained across validation and confirmed in the test set. Prediction of transferrin saturation showed slightly higher accuracy than ferritin. Feature importance analysis identified mean corpuscular volume (MCV), mean corpuscular hemoglobin (MCH), and red blood cell distribution width (RDW) as key predictors. Conclusions: CBC-based machine learning models may help identify subjects with low ferritin or low transferrin saturation, supporting subsequent targeted assessment of iron status.<\/jats:p>","DOI":"10.3390\/jcm15124783","type":"journal-article","created":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T13:04:04Z","timestamp":1781874244000},"page":"4783","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Predicting Iron Deficiencies Using Routine Complete Blood Cell Count Parameters: A Machine Learning Approach and Evaluation"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8275-453X","authenticated-orcid":false,"given":"Davide","family":"Negrini","sequence":"first","affiliation":[{"name":"Section of Clinical Biochemistry, University of Verona, 37134 Verona, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Laura","family":"Pighi","sequence":"additional","affiliation":[{"name":"Section of Clinical Biochemistry, University of Verona, 37134 Verona, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Simone","family":"Mignolli","sequence":"additional","affiliation":[{"name":"Section of Clinical Biochemistry, University of Verona, 37134 Verona, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gian Luca","family":"Salvagno","sequence":"additional","affiliation":[{"name":"Section of Clinical Biochemistry, University of Verona, 37134 Verona, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9523-9054","authenticated-orcid":false,"given":"Giuseppe","family":"Lippi","sequence":"additional","affiliation":[{"name":"Section of Clinical Biochemistry, University of Verona, 37134 Verona, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,6,19]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"537","DOI":"10.1079\/PHN2001139","article-title":"Iron deficiency in Europe","volume":"4","author":"Hercberg","year":"2001","journal-title":"Public Health Nutr."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"e40","DOI":"10.1097\/HS9.0000000000000040","article-title":"Anemia in the Elderly","volume":"2","author":"Girelli","year":"2018","journal-title":"Hemasphere"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1132","DOI":"10.1002\/ajh.27686","article-title":"Cost-Effectiveness of Ferritin Screening Thresholds for Iron Deficiency in Reproductive-Age Women","volume":"100","author":"Wang","year":"2025","journal-title":"Am. J. Hematol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"E680","DOI":"10.1503\/cmaj.240570","article-title":"Diagnosis and management of iron deficiency in females","volume":"197","author":"Sholzberg","year":"2025","journal-title":"Can. Med. Assoc. J."},{"key":"ref_5","first-page":"1","article-title":"Lights and shadows of artificial intelligence in laboratory medicine","volume":"6","author":"Lippi","year":"2025","journal-title":"Adv. Lab. Med."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.clinbiochem.2022.02.011","article-title":"Applications of machine learning in routine laboratory medicine: Current state and future directions","volume":"103","author":"Rabbani","year":"2022","journal-title":"Clin. Biochem."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"27857","DOI":"10.1038\/s41598-025-09439-4","article-title":"Machine learning models based on routine blood and biochemical test data for diagnosis of neurological diseases","volume":"15","author":"Ning","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Negrini, D., Zecchin, P., Ruzzenente, A., Bagante, F., De Nitto, S., Gelati, M., Salvagno, G.L., Danese, E., and Lippi, G. (2020). Machine Learning Model Comparison in the Screening of Cholangiocarcinoma Using Plasma Bile Acids Profiles. Diagnostics, 10.","DOI":"10.3390\/diagnostics10080551"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1031","DOI":"10.1093\/clinchem\/hvad100","article-title":"A Machine Learning Model for the Routine Detection of \u201cWrong Blood in Complete Blood Count Tube\u201d Errors","volume":"69","author":"Farrell","year":"2023","journal-title":"Clin. Chem."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"444","DOI":"10.1093\/clinchem\/hvad207","article-title":"Automating the Detection of IV Fluid Contamination Using Unsupervised Machine Learning","volume":"70","author":"Spies","year":"2024","journal-title":"Clin. Chem."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1002\/ajh.24201","article-title":"How we diagnose and treat iron deficiency anemia","volume":"91","author":"Auerbach","year":"2016","journal-title":"Am. J. Hematol."},{"key":"ref_12","first-page":"6","article-title":"Clinical evaluation of iron deficiency","volume":"19","author":"Cook","year":"1982","journal-title":"Semin. Hematol."},{"key":"ref_13","first-page":"98","article-title":"Iron Deficiency Anemia: Evaluation and Management","volume":"87","author":"Short","year":"2013","journal-title":"Am. Fam. Physician"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1085","DOI":"10.1053\/j.gastro.2020.06.046","article-title":"AGA Clinical Practice Guidelines on the Gastrointestinal Evaluation of Iron Deficiency Anemia","volume":"159","author":"Ko","year":"2020","journal-title":"Gastroenterology"},{"key":"ref_15","unstructured":"Scientific Advisory Committee on Nutrition (2010). Iron and Health."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1585","DOI":"10.3945\/ajcn.114.103366","article-title":"Guidelines on the Diagnosis and Treatment of Iron Deficiency across Indications: A Systematic Review","volume":"102","author":"Williet","year":"2015","journal-title":"Am. J. Clin. Nutr."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v028.i05","article-title":"Building Predictive Models in R Using the caret Package","volume":"28","author":"Kuhn","year":"2008","journal-title":"J. Stat. Softw."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Robin, X., Turck, N., Hainard, A., Tiberti, N., Lisacek, F., Sanchez, J.C., and M\u00fcller, M. (2011). pROC: An open-source package for R and S+ to analyze and compare ROC curves. BMC Bioinform., 12.","DOI":"10.1186\/1471-2105-12-77"},{"key":"ref_19","doi-asserted-by":"crossref","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":"ref_20","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1111\/ijlh.13537","article-title":"Machine learning in health care and laboratory medicine: General overview of supervised learning and Auto-ML","volume":"43","author":"Rashidi","year":"2021","journal-title":"Int. J. Lab. Hematol."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"16917","DOI":"10.1038\/s41598-025-01458-5","article-title":"Machine learning approach for differentiating iron deficiency anemia and thalassemia using random forest and gradient boosting algorithms","volume":"15","author":"Tepakhan","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"e1063","DOI":"10.1002\/jha2.1063","article-title":"Factors related to mean corpuscular volume in HFE p.C282Y homozygotes","volume":"6","author":"Barton","year":"2024","journal-title":"EJHaem"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1093\/ajcp\/aqae031","article-title":"Early identification of patients at risk for iron-deficiency anemia using deep learning techniques","volume":"162","author":"Ng","year":"2024","journal-title":"Am. J. Clin. Pathol."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"e097016","DOI":"10.1136\/bmjopen-2024-097016","article-title":"Predictive machine-learning model for screening iron deficiency without anaemia: A retrospective cohort study","volume":"15","author":"Efros","year":"2025","journal-title":"BMJ Open"}],"container-title":["Journal of Clinical Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2077-0383\/15\/12\/4783\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T04:30:36Z","timestamp":1782448236000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2077-0383\/15\/12\/4783"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,19]]},"references-count":24,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["jcm15124783"],"URL":"https:\/\/doi.org\/10.3390\/jcm15124783","relation":{},"ISSN":["2077-0383"],"issn-type":[{"value":"2077-0383","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,19]]}}}