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

Abstract

Objective. Several discriminating techniques have been proposed to discriminate between β-thalassemia trait (βTT) 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 βTT 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 βTT 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 βTT 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 βTT 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 βTT 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 βTT from IDA to avoid much more expensive, time-consuming laboratory tests, especially in countries with limited recourses or poor health services.

Analysis of Application Status of Bayesian Decision

“…The primary challenge in gross detecting errors is to increase the proportion of accurate detections while decreasing the proportion of false positives. This improvement may be achieved in two ways: first, by including as much relevant data as possible in the identification and detection process, and second, by making the best possible use of the data collected [14]. Conservation constraints, a covariance matrix of error margins, variable boundaries, and measured process of the data have traditionally formed the backbone of most statistical approaches to gross error detection [14].…”

“…This improvement may be achieved in two ways: first, by including as much relevant data as possible in the identification and detection process, and second, by making the best possible use of the data collected [14]. Conservation constraints, a covariance matrix of error margins, variable boundaries, and measured process of the data have traditionally formed the backbone of most statistical approaches to gross error detection [14]. With the proliferation of online-accessible computerized data accrual and management systems, it is possible to utilize data about previous failures of measuring devices to guide current efforts to improve the test procedure's output.…”

“…The efficiency and resolution performance of the method were highly excellent. The suggested technique can significantly reduce the average time required to complete an experiment compared to module syntheses (MLS), and modified MLS (MMLS) approaches [14].…”

Predicting Thalassemia Using Feature Selection Techniques: A Comparative Analysis

“…The least accurate TSVM, with an average recall of 99.79%, is polynomial. CART and BLTREED [55] are applied to the hematological parameters to separate βT and IDA individuals. The test dataset shows that for discriminating βT from IDA, CART outperforms BLTREED in terms of negative predictive value and sensitivity.…”

Logistic‐Nomogram model based on red blood cell parameters to differentiate thalassemia trait and iron deficiency anemia in southern region of Fujian Province, China

“…TT is a hereditary disease that is characterized by the aberrant synthesis of hemoglobin beta chain due to genetic abnormality, whereas IDA is characterized by the insufficiency of healthy red blood cells (RBCs) because of the lack of iron 2,3 . However, TT and IDA share some common clinical presentations, and it is challenging to differentiate between TT and IDA using regular laboratory examinations and the clinical symptoms of the patients 4–7 . Clinically, if IDA is misdiagnosed as TT, clinicians may neglect supplementation with iron and further investigate the real etiology.…”