Post by Institute for Developing Science and Health Initiatives (ideSHi)

New Publication Alert! We are pleased to share our latest research article: "Diagnostic performance of discriminant formulas and machine learning models for detecting β-thalassemia trait in Bangladesh", published in PLOS One. In this study, we evaluated 47 discriminant indices and 12 machine learning (ML) models, alongside complete blood count (CBC) metrics, to identify optimal predictors for differentiating between anemic and β-thalassemia trait (βTT) cases. Population-specific optimal cut-off values were determined for the discriminant formulas. The newly proposed formulas, DF-6 and DF-27, ranked among the top ten performers. DF-6 achieved the best overall performance across the diagnostic metrics. ML models revealed that XGBoost (XGB) and Support Vector Machine (SVM) provided the highest diagnostic accuracy. We believe our findings can contribute significantly to improving the early detection and management of β-thalassemia in Bangladesh, particularly in resource-limited settings. We are grateful to all co-authors, collaborators, and participants who made this work possible. Read the full article here: https://lnkd.in/gqHyCibe #research #publicationalert #ThalassemiaAwareness #MachineLearning #hematology #Bangladesh #medicalresearch #PublicHealth #datascience