Support Vector Machine-Based Formula for Detecting Suspected α Thalassemia Carriers: A Path toward Universal Screening.

ABSTRACT

The blood counts of α thalassemia carriers (α-thal) are similar to those of ß thalassemia carriers, except for Hemoglobin A2 (Hb A2), which is not elevated. The objective of this study was to determine whether mathematical formulas are effective for detecting suspected α-thal. The data were obtained from the database of the prevention program for detecting couples at risk for having a child with hemoglobinopathy. Red Blood Cells (RBC) indices were analyzed using mathematical formulas, and the sensitivity and negative predictive value (NPV) were calculated. Among 1334 blood counts suspected of α-thal analyzed, only the Shine and Lal and the Support Vector Machine formulas revealed high sensitivity and NPV. Sensitivity was 85.54 and 99.33%, and NPV was 98.93 and 99.93%, respectively. Molecular defects were found in 291, and 81 had normal α genes. Molecular analysis was not performed in 962 of the samples. Based on these results, mathematical formulas incorporating one of these reliable formulas for detecting suspected α or ß thalassemia carriers in the program of the automatic analyzers can flag these results, increase the awareness of the primary physicians about the carrier risk, and send an alert with a recommendation for further testing.