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 Show more
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. Show less
Founder populations are ideally suited for studies on the clinical effects of alleles that are rare in general populations but occur at higher frequencies in these isolated populations. Whole genome s Show more
Founder populations are ideally suited for studies on the clinical effects of alleles that are rare in general populations but occur at higher frequencies in these isolated populations. Whole genome sequencing in 98 Hutterites, a founder population of European descent, and subsequent imputation revealed 660,238 single nucleotide polymorphisms that are rare (<1%) or absent in European populations, but occur at frequencies >1% in the Hutterites. We examined the effects of these rare in European variants on plasma lipid levels in 828 Hutterites and applied a Bayesian hierarchical framework to prioritize potentially causal variants based on functional annotations. We identified two novel non-coding rare variants associated with LDL cholesterol (rs17242388 in LDLR) and HDL cholesterol (rs189679427 between GOT2 and APOOP5), and replicated previous associations of a splice variant in APOC3 (rs138326449) with triglycerides and HDL-C. All three variants are at well-replicated loci in GWAS but are independent from and have larger effect sizes than the known common variation in these regions. Candidate eQTL analyses in in LCLs in the Hutterites suggest that these rare non-coding variants are likely to mediate their effects on lipid traits by regulating gene expression. Show less