Related Experiment Video
Updated: Jul 18, 2025
Database-guided Flow-cytometry for Evaluation of Bone Marrow Myeloid Cell Maturation
Published on: November 3, 2018
Classifying flow cytometry data using Bayesian analysis helps to distinguish ALS patients from healthy controls
Saskia Räuber1, Christopher Nelke1, Christina B Schroeter1
1Department of Neurology, Medical Faculty, Heinrich Heine University of Düsseldorf, Düsseldorf, Germany.
Insights
Bayesian network analysis accurately identifies amyotrophic lateral sclerosis (ALS) patients using multidimensional flow cytometry (mFC) data. This novel computational approach outperforms existing methods, offering a promising tool for disease classification.
Area of Science:
- Immunology
- Computational Biology
- Biostatistics
Background:
- Multidimensional flow cytometry (mFC) is crucial in immunology for analyzing cell populations.
- Traditional mFC data analysis relies on manual gating, which can be subjective and time-consuming.
- Computational methods are emerging to enhance mFC data analysis.
Purpose of the Study:
- To develop and validate a Bayesian network analysis model for classifying amyotrophic lateral sclerosis (ALS) using raw, ungated mFC data.
- To compare the performance of Bayesian network analysis against a commercial algorithm (Citrus).
Main Methods:
- A Bayesian network model was constructed using raw mFC data from healthy controls (HC) to create a reference 'HC tree'.
- This model was used to predict disease status (ALS or HC) based on marker distribution.
- The algorithm calculated the probability of zero marker distribution to assess similarity between samples and the HC tree.
Main Results:
- The Bayesian network model correctly identified 64/68 ALS cases in the primary cohort and 100% in a validation cohort.
- Optimal performance was achieved using 7 markers, 200 bins, and 20 patients (p < 0.0001).
- Bayesian network analysis demonstrated superior performance compared to the commercial algorithm 'Citrus'.
Conclusions:
- Bayesian network analysis offers a novel, data-preserving method for classifying mFC data without reduction techniques.
- This approach shows potential as a complementary diagnostic tool in clinical settings for diseases like ALS.
Introduction:
Given its wide availability and cost-effectiveness, multidimensional flow cytometry (mFC) became a core method in the field of immunology allowing for the analysis of a broad range of individual cells providing insights into cell subset composition, cellular behavior, and cell-to-cell interactions. Formerly, the analysis of mFC data solely relied on manual gating strategies. With the advent of novel computational approaches, (semi-)automated gating strategies and analysis tools complemented manual approaches.
Methods:
Using Bayesian network analysis, we developed a mathematical model for the dependencies of different obtained mFC markers. The algorithm creates a Bayesian network that is a HC tree when including raw, ungated mFC data of a randomly selected healthy control cohort (HC). The HC tree is used to classify whether the observed marker distribution (either patients with amyotrophic lateral sclerosis (ALS) or HC) is predicted. The relative number of cells where the probability q is equal to zero is calculated reflecting the similarity in the marker distribution between a randomly chosen mFC file (ALS or HC) and the HC tree.
Results:
Including peripheral blood mFC data from 68 ALS and 35 HC, the algorithm could correctly identify 64/68 ALS cases. Tuning of parameters revealed that the combination of 7 markers, 200 bins, and 20 patients achieved the highest AUC on a significance level of p < 0.0001. The markers CD4 and CD38 showed the highest zero probability. We successfully validated our approach by including a second, independent ALS and HC cohort (55 ALS and 30 HC). In this case, all ALS were correctly identified and side scatter and CD20 yielded the highest zero probability. Finally, both datasets were analyzed by the commercially available algorithm 'Citrus', which indicated superior ability of Bayesian network analysis when including raw, ungated mFC data.
Discussion:
Bayesian network analysis might present a novel approach for classifying mFC data, which does not rely on reduction techniques, thus, allowing to retain information on the entire dataset. Future studies will have to assess the performance when discriminating clinically relevant differential diagnoses to evaluate the complementary diagnostic benefit of Bayesian network analysis to the clinical routine workup.
