{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T06:16:33Z","timestamp":1783318593631,"version":"3.54.6"},"reference-count":0,"publisher":"Advances in Artificial Intelligence and Machine Learning","issue":"03","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAIML"],"published-print":{"date-parts":[[2026,1,1]]},"abstract":"<jats:p>Thalassemia is a severe hereditary blood disorder, where early and accurate detection significantly affects the patient\u2019s treatment. Machine learning tools have the potential to make\ndiagnostic screening more efficient\u037e however, their lack of transparency, usually referred to\nas a \u201cblack box\u201d makes a large number of clinicians reluctant to use them in practice. We\ndeveloped a feasible health IT framework centered on interpretable voting ensembles for\nthalassemia screening using standard clinical and hematological markers. The dataset we\nused was from the real world and had 25 health attributes, such as hemoglobin levels, red\nblood cell indices, and ferritin. We then trained three machine learning models: XGBoost,\nRandom Forest, and Logistic Regression. The SMOTE technique was utilized to deal with\nclass imbalance in the data. We found that a soft voting ensemble of these models outperformed individual models, achieving an accuracy of 98. 37% and an F1-score of 96. 99%. To\nopen the black box and instill confidence in the models\u2019 decisions, SHAP (SHapley Additive\nexPlanations) was used to provide explanations for each prediction in terms understandable\nby clinicians. These interpretations were then evaluated and endorsed by the clinicians who\nparticipated, thus ensuring compatibility with the diagnostic reasoning in the real world.\nThe most significant predictors, MCV, MCH, and patient age were identified. Building the\nensemble took more computational time.<\/jats:p>","DOI":"10.54364\/aaiml.2026.63310","type":"journal-article","created":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T11:09:36Z","timestamp":1781176176000},"page":"5609","source":"Crossref","is-referenced-by-count":0,"title":["A Health Information Technology Framework: Interpretable Voting Ensembles for Thalassemia Screening Using Clinical and Hematological Biomarkers"],"prefix":"10.54364","volume":"06","author":[{"given":"Ayad","family":"Hameed Mousa","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Soheir","family":"Noori","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Asam","family":"Almohamed","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"32807","published-online":{"date-parts":[[2026,1,1]]},"container-title":["Advances in Artificial Intelligence and Machine Learning"],"original-title":[],"link":[{"URL":"https:\/\/www.oajaiml.com\/uploads\/archivepdf\/993663310.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T05:57:30Z","timestamp":1783317450000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.oajaiml.com\/uploads\/archivepdf\/993663310.pdf"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,1]]},"references-count":0,"journal-issue":{"issue":"03","published-online":{"date-parts":[[2026,1,1]]},"published-print":{"date-parts":[[2026,1,1]]}},"URL":"https:\/\/doi.org\/10.54364\/aaiml.2026.63310","relation":{},"ISSN":["2582-9793"],"issn-type":[{"value":"2582-9793","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,1]]}}}