RT Journal Article
A1 Mauvieux, Laurent
A1 Herbrecht, Raoul
A1 Eischen, Alice
A1 Galoisy, Anne-Cécile
A1 Rolland, Delphine
A1 Gervais, Carine
A1 Mayeur-Rousse, Caroline
A1 Hueber-Bonnot, Sarah
A1 Nicolae, Alina
A1 Fornecker, Luc-Matthieu
A1 Goetsch, Thibaut
A1 Severac, François
A1 Bizoï, Razvan
A1 Fabacher, Thibaut
A1 Miguet, Laurent
T1 Artificial intelligence–based flow cytometry for the diagnosis of B-cell chronic lymphoproliferative disorders
JF Blood Advances
JO Blood Adv
YR 2025
DO 10.1182/bloodadvances.2025016424
VO 9
IS 22
SP 5880
OP 5887
SN 2473-9529
AB Accurate diagnosis of B-cell chronic lymphoproliferative disorders (B-CLPDs) remains challenging due to overlapping phenotypes across subtypes. Machine learning (ML) offers promising tools to improve marker evaluation and refine flow cytometry analysis. We investigated the use of ML algorithms to evaluate the diagnostic value of incorporating CD148, CD180, and CD200 into standard B-CLPD phenotyping panel and to develop a diagnosis decision tree. We trained models with flow cytometry data from 480 patients with B-CLPDs using XGBoost and DecisionTree algorithms. The final models integrated 2 categorical markers (CD5 and CD10) and quantiles of fluorescence intensity of 4 quantitative markers (CD20, CD180, and CD200) to classify 6 B-CLPD subtypes. These trained models were applied to an independent cohort of 433 patients with B-CLPD analyzed on a different flow cytometer platform. DecisionTree models achieved the highest classification accuracy (mean accuracy, 0.88) in the validation cohort. The overall specificity ranged from 0.95 lymphoplasmacytic lymphoma (LPL) to 1 hairy cell leukemia (HCL), whereas sensitivity varied from 0.75 (LPL) to 1 (HCL). The DecisionTree model demonstrated superior identification of chronic lymphocytic leukemia compared to a Matutes score of 4 or 5 (P = .029). In more than half of the cases, a diagnosis was determined with near certainty using only the cytometry data. For the remaining cases, a hierarchical approach incorporating additional tests was proposed. For practical implementation, an interactive interface provides diagnostic predictions, positive predictive values, and Gini index scores. This study establishes a ML-optimized strategy for B-CLPD classification, combining phenotypic, cytogenetic, and molecular data to enhance diagnostic accuracy of leukemic B-CLPD cells. This trial was registered at www.ClinicalTrials.gov as #NCT04952974.
RD 11/14/2025
UL https://doi.org/10.1182/bloodadvances.2025016424