Machine learning assisted real-time deformability cytometry of CD34+cells allows to identify patients with myelodysplastic syndromes

Diagnosis of myelodysplastic syndrome (MDS) mainly relies on a manual assessment of the peripheral blood and bone marrow cell morphology. The WHO guidelines suggest a visual screening of 200 to 500 cells which inevitably turns the assessor blind to rare cell populations and leads to low reproducibility. Moreover, the human eye is not suited to detect shifts of cellular properties of entire populations. Hence, quantitative image analysis could improve the accuracy and reproducibility of MDS diagnosis. We used real-time deformability cytometry (RT-DC) to measure bone marrow biopsy samples of MDS patients and age-matched healthy individuals. RT-DC is a high-throughput (1000 cells/s) imaging flow cytometer capable of recording morphological and mechanical properties of single cells. Properties of single cells were quantified using automated image analysis, and machine learning was employed to discover morpho-mechanical patterns in thousands of individual cells that allow to distinguish healthy vs. MDS samples. We found that distribution properties of cell sizes differ between healthy and MDS, with MDS showing a narrower distribution of cell sizes. Furthermore, we found a strong correlation between the mechanical properties of cells and the number of disease-determining mutations, inaccessible with current diagnostic approaches. Hence, machine-learning assisted RT-DC could be a promising tool to automate sample analysis to assist experts during diagnosis or provide a scalable solution for MDS diagnosis to regions lacking sufficient medical experts.

Automated summary

The diagnosis of myelodysplastic syndrome (MDS) currently relies on manual assessment of blood and marrow cell morphologies, which has limitations in terms of accuracy and reproducibility. This study proposes the use of real-time deformability cytometry (RT-DC) combined with machine learning to improve MDS diagnosis. RT-DC is capable of measuring morphological and mechanical properties of single cells, and the use of automated image analysis and machine learning allows for the identification of patterns that differentiate healthy and MDS samples. The study found differences in cell size distribution and a correlation between mechanical properties and disease-determining mutations in MDS samples. This approach may provide an automated and scalable solution for MDS diagnosis.