A novel discriminant algorithm for differential diagnosis of mild to moderate thalassemia and iron deficiency anemia

Abstract

Background: Mild to moderate thalassemia trait (TT) and iron deficiency anemia (IDA) are the most common conditions of microcytic hypochromic anemia (MHA) and they exhibit highly similar clinical and laboratory features. It is sometimes difficult to make a differential diagnosis between TT and IDA in clinical practice. Therefore, a simple, effective, and reliable index is needed to discriminate between TT and IDA.

Methods: Data of 598 patients (320 for TT and 278 for IDA) were enrolled and randomly assigned to training set (278 of 598, 70%) and validation set (320 of 598, 30%). Stepwise discriminant analysis was used to define the best diagnostic formula for the discrimination between TT and IDA in training set. The accuracy and diagnostic performance of formula was tested and verified by receiver operating characteristic (ROC) analysis in validation set and its diagnostic performance was compared with other published indices.

Results: A novel formula, Thalassemia and IDA Discrimination Index (TIDI) = -13.932 + 0.434 × RBC + 0.033 × Hb + 0.025 ×MCHC + 53.593 × RET%, was developed to discriminate TT from IDA. TIDI showed a high discrimination performance in ROC analysis, with the Area Under the Curve (AUC) = 0.936, Youden' s index = 78.7%, sensitivity = 89.5%, specificity = 89.2%, respectively. Furthermore, the formula index also obtained a good classification performance in distinguishing 5 common genotypes of TT from IDA (AUC from 0.854-0.987).

Conclusion: The new, simple algorithm can be used as an effective and robust tool for the differential diagnosis of mild to moderate TT and IDA in Guangxi region, China.

Figure 1.

The diagram of sample selection and grouping process.

Figure 2.

The new formula TIDI developed by Fisher discriminant analysis. (A) The confusion matrix obtained by discriminating between mild to moderate TT and IDA using TIDI. (B) Mild to moderate TT and IDA groups clustered distinctly from each other by using TIDI. (C) ROC curve of the TIDI. IDA = iron deficiency anemia, ROC = receiver operating characteristic, TIDI = thalassemia and iron deficiency anemia discrimination index, TT = thalassemia trait.

Figure 3.

Verification results of new discriminant formula TIDI. (A) The ROC curves of different diagnostic indices. (B) Summary of the accuracy, sensitivity, specificity, Youden index, AUC obtained for each index. (C, D) Performance data and ROC curves of our new formula TIDI for differentiating IDA from different genotypes of mild to moderate TT. AUC = area under the curve, IDA = iron deficiency anemia, ROC = receiver operating characteristic, TIDI = thalassemia and iron deficiency anemia discrimination index, TT = thalassemia trait.