Morphology-based classification of sickle cell disease and β-thalassemia using a low-cost automated microscope and machine learning

Sickle cell disease (SCD) and {beta}-thalassemia are the most common monogenic diseases, disproportionately affecting low- and middle-income countries, where low-cost and accurate diagnostic tools are needed to reduce the global disease burden. Although the sickling test is commonly used to screen for the sickle mutation, it cannot distinguish between the asymptomatic sickle cell trait (SCT) and SCD, or identify {beta}-thalassemia. Here, we enhanced the inexpensive sickling test using automated microscopy and morphology-based machine learning classification to detect SCD, trait conditions (SCT and {beta}-thalassemia trait) and normal individuals with an overall area under receiver operating curve, sensitivity and specificity of 0.940 (95% confidence intervals: 0.938-0.942), 84.6% (84.2%-84.9%), and 92.3% (92.1%-92.4%), respectively. Notably, the sensitivity and specificity to detect severe disease (SCD) was over 97% and 98%, respectively, thus establishing a low-cost automated screening option for disease detection in low-resource settings. Furthermore, leveraging high-throughput microscopy, we generated an open-access dataset comprising over 300,000 images with 1.5 trillion segmented cells from 138 individuals in Canada and Nepal including individuals with sickle and/or {beta}-thalassemia mutations, to accelerate further research.