Predicting the Double Heterozygotes of HbE and α-Thalassemia-1 (Southeast Asian Type) Using RapidMiner-Generated Hematologic Algorithm.

Abstract

Double heterozygotes of HbE and α-Thalassemia-1 (Southeast Asian type) ((β^A/β^E, - -SEA/αα) can result in severe thalassemia conditions, such as HbE/β-thalassemia (β^E/β^T)) and Hb Bart's hydrops fetalis syndrome (- -^SEA/- -^SEA). Identification of these double heterozygotes is crucial for preventing births affected by Hb Bart's hydrops fetalis syndrome. The most accurate method for detecting HbE/SEA-α-Thalassemia-1 double heterozygotes is PCR-based analysis, which is complex and costly. This study aimed to develop a hematologic algorithm for predicting double heterozygotes of HbE/SEA-α-Thalassemia-1. A retrospective analysis was conducted on 471 datasets of red blood cell indices and HbE levels collected from hospitals in Northern Thailand. Data analysis and algorithm development were performed using statistical tools and RapidMiner software. The prevalence of HbE/SEA-α-Thalassemia-1 double heterozygotes was 12.1%. Significant differences were found in HbE levels, MCV, MCH, and RBC count between single HbE heterozygotes and HbE/SEA-α-Thalassemia-1 double heterozygotes. The predictive algorithm, named the 'Nation SEAE Algorithm,' was established as follows: HbE ≤ 20.5%; RBC > 4.55 × 10⁶/µL; and MCV ≤ 70.5 fL. This algorithm demonstrated 40% sensitivity (95% CI: 30.3-50.3), 100% specificity (95% CI: 96.4-100), 100% positive predictive value (95% CI: 96.4-100), 95.6% negative predictive value (95% CI: 90.0-98.9), a negative likelihood ratio of 0.6 (95% CI: 0.3-1.2), an infinite positive likelihood ratio, 95.7% accuracy (95% CI: 90.1-98.9), and an area under the ROC curve of 0.99 (95% CI: 0.97-1.00) for identifying HbE/SEA-α-Thalassemia-1 double heterozygotes. Therefore, the 'Nation SEAE Algorithm' is a valuable clinical tool to support accurate identification of the double heterozygotes of HbE and SEA-α thalassemia 1.