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

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Mina Jahangiri ◽  
Fakher Rahim ◽  
Najmaldin Saki ◽  
Amal Saki Malehi

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.

Anemia ◽  
2014 ◽  
Vol 2014 ◽  
pp. 1-7 ◽  
Author(s):  
Aysel Vehapoglu ◽  
Gamze Ozgurhan ◽  
Ayşegul Dogan Demir ◽  
Selcuk Uzuner ◽  
Mustafa Atilla Nursoy ◽  
...  

Background. The two most frequent types of microcytic anemia are beta thalassemia trait (β-TT) and iron deficiency anemia (IDA). We retrospectively evaluated the reliability of various indices for differential diagnosis of microcytosis andβ-TT in the same patient groups.Methods. A total of 290 carefully selected children aged 1.1–16 years were evaluated. We calculated 12 discrimination indices in all patients with hemoglobin (Hb) values of 8.7–11.4 g/dL. None of the subjects had a combined case of IDA andβ-TT. All children with IDA received oral iron for 16 weeks, and HbA2 screening was performed after iron therapy. The patient groups were evaluated according to red blood cell (RBC) count; red blood distribution width index; the Mentzer, Shine and Lal, England and Fraser, Srivastava and Bevington, Green and King, Ricerca, Sirdah, and Ehsani indices; mean density of hemoglobin/liter of blood; and mean cell density of hemoglobin.Results. The Mentzer index was the most reliable index, as it had the highest sensitivity (98.7%), specificity (82.3%), and Youden’s index (81%) for detectingβ-TT; this was followed by the Ehsani index (94.8%, 73.5%, and 68.3%, resp.) and RBC count (94.8%, 70.5%, and 65.3%).Conclusion. The Mentzer index provided the highest reliabilities for differentiatingβ-TT from IDA.


2017 ◽  
Vol 33 (3) ◽  
Author(s):  
Tahir Ahmed Jameel ◽  
Mukhtar Baig ◽  
Ijaz Ahmed ◽  
Muhammad Barakat Hussain ◽  
Motlag bin Doghaim Alkhamaly

Author(s):  
Pravin M. Meshram ◽  
Hemant R. Kokandakar ◽  
Rajan S. Bindu

Background: Iron deficiency anemia (IDA) and beta thalassaemia trait (BTT) are two of the most common causes of microcytic anemia.It is essential to differentiate between the two, so as to avoid unnecessary iron therapy which is contraindicated in beta thalassaemia .We retrospectively evaluated the reliability of various indices for differential diagnosis of microcytosis and 𝛽-TT in the same patient groups .Methods: A total of 200 patients were evaluated. We calculated 6 discrimination indices in all patients with anemia or suspected beta thalassemia. None of the subjects had  combined  IDA and 𝛽-TT. The patient groups were evaluated according to  the Mentzer, Shine and Lal, England and Fraser,Srivastava, Green and King, Ricerca.Results: According to percentage correctly diagnosed criteria, Ricerca  and Mentzer  index are considered as the two best discrimination indices in differentiation between β thalassemia trait  and iron deficiency anaemia .Youden’s index showed the following ranking with respect to the indices’ ability to distinguish between 𝛽-TT and IDA, Ricerca index >  Mentzer index > Green and King index >  Srivastava index >  Shine and Lal index > England and Fraser index.Conclusions: Ricerca  and Mentzer  index are considered as the two best discrimination indices in differentiation between β thalassemia trait  and iron deficiency anaemia.Keywords: Iron deficiency anemia (IDA) and beta thalassaemia trait (𝛽-TT) 


2021 ◽  
Vol 12 ◽  
Author(s):  
Lourdes Méndez-Mora ◽  
Maria Cabello-Fusarés ◽  
Josep Ferré-Torres ◽  
Carla Riera-Llobet ◽  
Elena Krishnevskaya ◽  
...  

The purpose of this work is to develop a hematocrit-independent method for the detection of beta-thalassemia trait (β-TT) and iron deficiency anemia (IDA), through the rheological characterization of whole blood samples from different donors. The results obtained herein are the basis for the development of a front microrheometry point-of-care device for the diagnosis and clinical follow-up of β-TT patients suffering hematological diseases and alterations in the morphology of the red blood cell (RBC). The viscosity is calculated as a function of the mean front velocity by detecting the sample fluid-air interface advancing through a microfluidic channel. Different viscosity curves are obtained for healthy donors, β-TT and IDA samples. A mathematical model is introduced to compare samples of distinct hematocrit, classifying the viscosity curve patterns with respect to the health condition of blood. The viscosity of the fluid at certain shear rate values varies depending on several RBC factors such as shape and size, hemoglobin (Hb) content, membrane rigidity and hematocrit concentration. Blood and plasma from healthy donors are used as reference. To validate their potential clinical value as a diagnostic tool, the viscosity results are compared to those obtained by the gold-standard method for RBC deformability evaluation, the Laser-Optical Rotational Red Cell Analyzer (LoRRCA).


Sign in / Sign up

Export Citation Format

Share Document