Leveraging Kappa-Lambda Signatures in a Multistage Machine Learning Pipeline for B-Cell Lymphoma Detection by Flow...

Area of Science:

• Hematology
• Computational Biology
• Immunology

Background:

• Manual interpretation of flow cytometry data for B-cell lymphoma diagnosis is subjective and time-consuming.
• Existing computational methods often fail to incorporate crucial biological principles like immunoglobulin light chain restriction.

Purpose of the Study:

• To develop a biologically informed machine learning pipeline for accurate and reproducible B-cell lymphoma detection.
• To integrate immunoglobulin kappa (IGK) and lambda (IGL) signatures into an automated analysis.

Main Methods:

• A three-stage XGBoost machine learning pipeline was developed using 21 immunophenotypic markers on over 15 million single-cell events.
• The pipeline sequentially classified light chain expression, cell phenotypes, and sample-level predictions, incorporating IGK/IGL signatures.

Main Results:

• The IGK/IGL classifier achieved 88.0% test accuracy (AUC 0.957), and cell-level classification reached 92.9% accuracy (AUC 0.983).
• Sample-level classification achieved 94.7% accuracy (AUC 0.976), with IGK/IGL enrichment being the most informative feature.

Conclusions:

• Incorporating biologically grounded features like IGK/IGL signatures enhances automated flow cytometry analysis accuracy and interpretability.
• This approach provides a scalable, reproducible, and clinically relevant alternative to manual review for B-cell lymphoma diagnosis.