Darrin M. auteur aut IRD Samudre A. auteur aut IRD Sahun M. auteur aut IRD Atwell S. auteur aut IRD Badens C. auteur aut IRD Charrier A. auteur aut IRD Helfer E. auteur aut IRD Viallat A. auteur aut IRD Cohen-Addad V. auteur aut IRD Giffard-Roisin Sophie auteur aut IRD text journalArticle eng text/pdf reformatted digital access The fraction of red blood cells adopting a specific motion under low shear flow is a promising inexpensive marker for monitoring the clinical status of patients with sickle cell disease. Its high-throughput measurement relies on the video analysis of thousands of cell motions for each blood sample to eliminate a large majority of unreliable samples (out of focus or overlapping cells) and discriminate between tank-treading and flipping motion, characterizing highly and poorly deformable cells respectively. Moreover, these videos are of different durations (from 6 to more than 100 frames). We present a two-stage end-to-end machine learning pipeline able to automatically classify cell motions in videos with a high class imbalance. By extending, comparing, and combining two state-of-the-art methods, a convolutional neural network (CNN) model and a recurrent CNN, we are able to automatically discard 97% of the unreliable cell sequences (first stage) and classify highly and poorly deformable red cell sequences with 97% accuracy and an F1-score of 0.94 (second stage). Dataset and codes are publicly released for the community. specialized 050 020 13 1 [12 ] 2023 2045-2322 https://www.documentation.ird.fr/hor/fdi:010087700 10.1038/s41598-023-27718-w 2045-2322 [F B010087700] https://www.documentation.ird.fr/hor/fdi:010087700 https://horizon.documentation.ird.fr/exl-doc/pleins_textes/2023-06/010087700.pdf IRD - Base Horizon / Pleins textes 2023-06-30 2025-02-24 fdi:010087700 fre