Objectives: To develop a machine learning (ML)-based framework using red blood cell (RBC) parameters for the prediction of the α⁺-thalassemia trait (α⁺-thal trait) and to compare the diagnostic performance with a conventional method using a single RBC parameter or a combination of RBC parameters. Methods: A retrospective study was conducted on possible couples at risk for fetus with hemoglobin H (Hb H disease). Subjects with molecularly confirmed normal status (not thalassemia), α⁺-thal trait, and two-allele α-thalassemia mutation were included. Clinical parameters (age and gender) and RBC parameters (Hb, Hct, MCV, MCH, MCHC, RDW, and RBC count) obtained from their antenatal thalassemia screen were retrieved and analyzed using a machine learning (ML)-based framework and a conventional method. The performance of α⁺-thal trait prediction was evaluated. Results: In total, 594 cases (female/male: 330/264, mean age: 29.7 ± 6.6 years) were included in the analysis. There were 229 normal controls, 160 cases with the α⁺-thalassemia trait, and 205 cases in the two-allele α-thalassemia mutation category, respectively. The ML-derived model improved the diagnostic performance, giving a sensitivity of 80% and specificity of 81%. The experimental results indicated that DeepThal achieved a better performance compared with other ML-based methods in terms of the independent test dataset, with an accuracy of 80.77%, sensitivity of 70.59%, and the Matthews correlation coefficient (MCC) of 0.608. Of all the red blood cell parameters, MCH < 28.95 pg as a single parameter had the highest performance in predicting the α⁺-thal trait with the AUC of 0.857 and 95% CI of 0.816–0.899. The combination model derived from the binary logistic regression analysis exhibited improved performance with the AUC of 0.868 and 95% CI of 0.830–0.906, giving a sensitivity of 80.1% and specificity of 75.1%. Conclusions: The performance of DeepThal in terms of the independent test dataset is sufficient to demonstrate that DeepThal is capable of accurately predicting the α⁺-thal trait. It is anticipated that DeepThal will be a useful tool for the scientific community in the large-scale prediction of the α⁺-thal trait.

Objective: To determine the diagnostic performance of maternal abdominal visceral adipose tissue thickness, measured by ultrasound, in predicting gestational diabetes mellitus (GDM). Patients and methods: A prospective diagnostic study was conducted on low-risk pregnant women attending our antenatal care clinic. All underwent abdominal visceral adipose tissue (VAT) measurement by two-dimension transabdominal ultrasound twice, at late first trimester (gestational age: GA 11–14 weeks) and second trimester (GA 18–22 weeks). All patients underwent a two-step approach for screening and diagnosis of GDM between GA 24 and 28 weeks. Results: A total of 141 women were recruited into the study; including 32 (22.7%) women with GDM, and 109 (77.3%) women of non-GDM, between GA 24 and 28 weeks. The means VAT at the 1st, 2nd trimester and the difference of VAT of GDM group were 4.0 ± 0.27 cm, 5.7 ± 1.12 cm, and 1.6 ± 0.91 cm respectively. The means VAT at 1st, 2nd trimester and the difference of VAT of non-GDM group were 3.8 ± 1.01 cm, 5.4 ± 1.07 cm, and 1.6 ± 1.12 cm respectively. There were no significant differences of VAT measurements (1st, 2nd and the difference) between both groups. The VAT thickness was slightly greater in the GDM group but the mean differences between 1st and 2nd trimester were comparable between the two groups. The diagnostic performance of VAT, maternal age and body mass index (BMI) in predicting GDM was comparable. Conclusion: Measurement of maternal visceral adipose thickness in early pregnancy is not effective in predicting GDM among Thai women, which is different from most studies conducted on western women. However, a trend of higher VAT in the GDM group was noted.