Application of Bayesian Decision Tree in Hematology Research: Differential Diagnosis of β-Thalassemia Trait from Iron Deficiency Anemia

Objective. Several discriminating techniques have been proposed to discriminate between beta -thalassemia trait (beta TT) and iron deficiency anemia (IDA). These discrimination techniques are essential clinically, but they are challenging and typically difficult. This study is the first application of the Bayesian tree-based method for differential diagnosis of beta TT from IDA. Method. This cross-sectional study included 907 patients with ages over 18 years old and a mean (+/- SD) age of 25 +/- 16.1 with either beta TT or IDA. Hematological parameters were measured using a Sysmex KX-21 automated hematology analyzer. Bayesian Logit Treed (BLTREED) and Classification and Regression Trees (CART) were implemented to discriminate beta TT from IDA based on the hematological parameters. Results. This study proposes an automatic detection model of beta-thalassemia carriers based on a Bayesian tree-based method. The BLTREED model and CART showed that mean corpuscular volume (MCV) was the main predictor in diagnostic discrimination. According to the test dataset, CART indicated higher sensitivity and negative predictive value than BLTREED for differential diagnosis of beta TT from IDA. However, the CART algorithm had a high false-positive rate. Overall, the BLTREED model showed better performance concerning the area under the curve (AUC). Conclusions. The BLTREED model showed excellent diagnostic accuracy for differentiating beta TT from IDA. In addition, understanding tree-based methods are easy and do not need statistical experience. Thus, it can help physicians in making the right clinical decision. So, the proposed model could support medical decisions in the differential diagnosis of beta TT from IDA to avoid much more expensive, time-consuming laboratory tests, especially in countries with limited recourses or poor health services.

Automated summary

This study introduces a Bayesian tree-based method for differentiating between beta-thalassemia trait and iron deficiency anemia. The models propose automatic detection of beta-thalassemia carriers, with mean corpuscular volume being the main predictor in diagnostic discrimination. CART showed higher sensitivity and negative predictive value compared to BLTREED, but with a higher false-positive rate. The BLTREED model demonstrated better performance in terms of area under the curve.