{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T12:08:54Z","timestamp":1789474134103,"version":"build-2803163510"},"reference-count":36,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","award":["CSTB2023TIAD-STX0008"],"award-info":[{"award-number":["CSTB2023TIAD-STX0008"]}],"id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","award":["2024DBXM004"],"award-info":[{"award-number":["2024DBXM004"]}],"id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:sec><jats:title>Aim<\/jats:title><jats:p>In recent years, with the change of social environment, the incidence and detection rate of hematological diseases have shown an increasing trend. Early diagnosis and detection of hematological diseases are very important to improve the quality of life and prognosis of patients.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>In this study, we employed 54 clinical and conventional laboratory parameters. By optimally combining multiple feature selection methods and machine learning algorithms, we developed 7 machine learning models with varying feature set sizes. We comprehensively evaluated the performance of these models, analyzed the interpretability of the optimal and simplified models using SHapley Additive exPlanations (SHAP), and compared these two models with the diagnostic performance of hematologists. Finally, we developed a user-friendly diagnostic platform.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The results showed that the ensemble model_1 with 46 feature parameters (EnMod1-46) and the simple ensemble model_2 with 12 feature parameters (EnMod2-12) demonstrated significant performance in diagnosing 16 types of hematological diseases. On the temporally distinct test set_1, the EnMod1-46 achieved an accuracy of 0.804 and an area under the curve (AUC) of 0.964, while EnMod2-12 attained an accuracy of 0.784 and an AUC of 0.961. To further validate the model\u2019s generalization performance, EnMod1-46 achieved an accuracy of 0.738 and an AUC of 0.973 on the independent external test set_2, while EnMod2-12 yielded an accuracy of 0.705 and an AUC of 0.962. SHAP analysis showed that PLT, WBC, MCV, HGB, RBC and age were significant parameters in both models. Comparative analysis of clinical diagnosis revealed that the performance of EnMod1-46 and EnMod2-12 outperformed junior hematologists, while EnMod1-46 was comparable to senior hematologists. Concurrently, based on EnMod2-12, we developed a user-friendly diagnostic platform to facilitate risk assessment and improve access to accurate diagnosis.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>This study provides an efficient and accurate screening method for hematological diseases, especially in resource-limited countries and regions.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fmed.2025.1605868","type":"journal-article","created":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T05:51:38Z","timestamp":1759297898000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Development and application of machine learning models for hematological disease diagnosis using routine laboratory parameters: a user-friendly diagnostic platform"],"prefix":"10.3389","volume":"12","author":[{"given":"Jingya","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Gou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wuchen","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shengwang","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siheng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tinglu","family":"Tao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongjie","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siyin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ping","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yimei","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuiqing","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangui","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,10,1]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/epigenomes7040032","article-title":"Epigenetic mechanisms in hematologic aging and premalignant conditions","volume":"7","author":"Yan","year":"2023","journal-title":"Epigenomes"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"789","DOI":"10.1111\/ijlh.14330","article-title":"Hematological cytomorphology: where we are","volume":"46","author":"Zini","year":"2024","journal-title":"Int J Lab Hematol"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"229","DOI":"10.3322\/caac.21834","article-title":"Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"74","author":"Bray","year":"2024","journal-title":"CA Cancer J Clin"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"217264","DOI":"10.1016\/j.canlet.2024.217264","article-title":"Consensus on the monitoring, treatment, and prevention of leukaemia relapse after allogeneic haematopoietic stem cell transplantation in China: 2024 update","volume":"605","author":"Wang","year":"2024","journal-title":"Cancer Lett"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1038\/s41408-022-00688-4","article-title":"Novel CD19 chimeric antigen receptor T cells manufactured next-day for acute lymphoblastic leukemia","volume":"12","author":"Zhang","year":"2022","journal-title":"Blood Cancer J"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1016\/j.canlet.2018.08.030","article-title":"The consensus on the monitoring, treatment, and prevention of leukemia relapse after allogeneic hematopoietic stem cell transplantation in China","volume":"438","author":"Wang","year":"2018","journal-title":"Cancer Lett"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"13","DOI":"10.2991\/chi.k.201130.001","article-title":"Machine learning applications in the diagnosis of benign and malignant hematological diseases","volume":"3","author":"Muhsen","year":"2020","journal-title":"Clin Hematol Int"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"265","DOI":"10.3233\/SHTI230479","article-title":"An Artificial Intelligence-Based Diagnostic System for Acute Lymphoblastic Leukemia Detection","volume":"305","author":"El Alaoui","year":"2023","journal-title":"Stud Health Technol Inform"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"e323","DOI":"10.1016\/S2589-7500(24)00044-X","article-title":"Evaluation of a machine-learning model based on laboratory parameters for the prediction of acute leukaemia subtypes: a multicentre model development and validation study in France","volume":"6","author":"Alcazer","year":"2024","journal-title":"Lancet Digital health"},{"key":"ref10","first-page":"350","article-title":"Superiority of neural networks over discriminant functions for thalassemia minor screening of red blood cell microcytosis","volume":"119","author":"Erler","year":"1995","journal-title":"Arch Pathol Lab Med"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1038\/s41598-017-18564-8","article-title":"An application of machine learning to haematological diagnosis","volume":"8","author":"Guncar","year":"2018","journal-title":"Sci Rep"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"7567","DOI":"10.1038\/s41598-021-87171-5","article-title":"Development of machine learning model for diagnostic disease prediction based on laboratory tests","volume":"11","author":"Park","year":"2021","journal-title":"Sci Rep"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"138","DOI":"10.3390\/diagnostics12010138","article-title":"Beyond the in-practice CBC: the research CBC parameters-driven machine learning predictive modeling for early differentiation among Leukemias","volume":"12","author":"Haider","year":"2022","journal-title":"Diagnostics (Basel)"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"8641194","DOI":"10.1155\/2022\/8641194","article-title":"Leukemia can be effectively early predicted in routine physical examination with the assistance of machine learning models","volume":"2022","author":"Yu","year":"2022","journal-title":"J Healthc Eng"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1109\/ICMLA.2018.00014","article-title":"Recursive feature elimination by sensitivity testing","volume":"2018","author":"Escanilla","year":"2018","journal-title":"Proceed Int Conference Machine Learn Applications"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"4071","DOI":"10.1109\/EMBC.2016.7591621","article-title":"Recursive feature elimination for biomarker discovery in resting-state functional connectivity","volume":"2016","author":"Ravishankar","year":"2016","journal-title":"Annual Int Conference IEEE Eng Med Biol Society IEEE Eng Med Biol Society Annual Int Conference"},{"key":"ref17","author":"Ke","year":"2017"},{"key":"ref18","author":"Wang","year":"2017"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"1146","DOI":"10.1016\/j.ipm.2007.09.014","article-title":"Using information gain to improve multi-modal information retrieval systems","volume":"44","author":"Mart\u00edn-Valdivia","year":"2008","journal-title":"Inf Process Manag"},{"key":"ref20","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":"2022","journal-title":"J Artif Intell Res"},{"key":"ref21","author":"Akiba","year":"2019"},{"key":"ref22","author":"Lundberg","year":"2017"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"993","DOI":"10.1186\/s12885-024-12646-3","article-title":"Artificial intelligence reveals the predictions of hematological indexes in children with acute leukemia","volume":"24","author":"Cheng","year":"2024","journal-title":"BMC Cancer"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"656","DOI":"10.1038\/s41375-021-01435-7","article-title":"Machine learning identifies the independent role of dysplasia in the prediction of response to chemotherapy in AML","volume":"36","author":"Duchmann","year":"2022","journal-title":"Leukemia"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"4190","DOI":"10.1182\/blood-2024-200891","article-title":"Evaluation of methotrexate pharmacogenomic variants to predict acute neurotoxicity in children with acute lymphoblastic leukemia","volume":"144","author":"Brown","year":"2024","journal-title":"Blood"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"e0254976","DOI":"10.1371\/journal.pone.0254976","article-title":"Survival prognostic factors in patients with acute myeloid leukemia using machine learning techniques","volume":"16","author":"Karami","year":"2021","journal-title":"PLoS One"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"105407","DOI":"10.1016\/j.ijmedinf.2024.105407","article-title":"Evaluation of D-dimer and prothrombin time in alcohol related liver cirrhosis with comparison of machine learning analyses","volume":"186","author":"Lee","year":"2024","journal-title":"Int J Med Inform"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1186\/s12911-025-02892-1","article-title":"A novel method for screening malignant hematological diseases by constructing an optimal machine learning model based on blood cell parameters","volume":"25","author":"Sun","year":"2025","journal-title":"BMC Med Inform Decis Mak"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1613\/jair.614","article-title":"Popular ensemble methods: an empirical study","volume":"11","author":"Opitz","year":"1999","journal-title":"J Artif Intell Res"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"e2665","DOI":"10.1002\/smr.2665","article-title":"Software development effort estimation using boosting algorithms and automatic tuning of hyperparameters with Optuna","volume":"36","author":"Hassanali","year":"2024","journal-title":"J Softw Evol Process"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1016\/j.cca.2022.09.015","article-title":"Platelet\u2013acute leukemia interactions","volume":"536","author":"Zhang","year":"2022","journal-title":"Clin Chim Acta"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"505","DOI":"10.1038\/s41598-024-84120-w","article-title":"Differential diagnosis of iron deficiency anemia from aplastic anemia using machine learning and explainable artificial intelligence utilizing blood attributes","volume":"15","author":"Darshan","year":"2025","journal-title":"Sci Rep"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3390\/medicina60050731","article-title":"Leukemia types and subtypes analysis: epidemiological age-standardized exploration in the Mexican Bajio region","volume":"60","author":"Romero-Morelos","year":"2024","journal-title":"Medicina (Kaunas)"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"e097526","DOI":"10.1136\/bmjopen-2024-097526","article-title":"Development and validation of an interpretable machine learning model for predicting Philadelphia chromosome-positive acute lymphoblastic leukaemia using clinical and laboratory parameters: a single-Centre retrospective study","volume":"15","author":"Yang","year":"2025","journal-title":"BMJ Open"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1186\/s12911-024-02781-z","article-title":"A potential predictive model based on machine learning and CPD parameters in elderly patients with aplastic anemia and myelodysplastic neoplasms","volume":"24","author":"Qi","year":"2024","journal-title":"BMC Med Inform Decis Mak"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"2363","DOI":"10.2147\/jir.s495615","article-title":"Effect of age, sex and season on acute myeloid leukemia clinical characteristics: a retrospective study","volume":"18","author":"Wan","year":"2025","journal-title":"J Inflamm Res"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1605868\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T05:51:39Z","timestamp":1759297899000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1605868\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,1]]},"references-count":36,"alternative-id":["10.3389\/fmed.2025.1605868"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2025.1605868","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,1]]},"article-number":"1605868"}}