Marker subset selection and decision support range identification for acute myeloid leukemia classification model development with multiparameter flow cytometry
In this study, we developed acute myeloid leukemia (AML) classification model through Wilks lambda-based important marker-identification method and stepwise-forward selection approach, and spotted important decision-support range of flow-cytometry parameter using insights provided by machine-learning algorithm. AML flow-cytometry data released from FlowCAP-II challenge in 2011 was used. In FlowCAP-II challenge, several sample classification algorithms were able to effectively classify AML and non-AML. Most algorithms extracted features from high-dimensional flow-cytometry readout comprised of multiple fluorescent parameters for a large number of antibodies. Multiple parameters with forward scatter and side scatter increase computational complexity in the feature-extraction procedure as well as in the model development. Parameter-subset selection can decrease model complexity, improve model performance, and contribute to a panel design specific for target disease. With this motivation, we estimated importance of each parameter via Wilks lambda and then identified the best subset of parameters using stepwise-forward selection. In the importance-estimation process, histogram matrix of each parameter was used. As a result, parameters, which are associated with blasts gating and identification of immature myeloid cells, were identified as important descriptors in AML classification, and combination of these markers is more effective than an individual marker. A random-forest, supervised-classification machine-learning algorithm was used for the model development. We highlighted decision-support range of the fluorescent signal for the identified important parameters, which significantly contribute to AML classification, through a mean decrease in Gini supported in random forest. These specific ranges could help with establishing diagnosis criteria and elaborate the AML classification model. Because methodology proposed in this study can not only estimate the importance of each parameter but also identify the best subset and the specific ranges, we expect that it would contribute to in silico modeling using flow- and mass-cytometry readout as well as panel design for sample classification.\n\nAuthor summaryFlow cytometry is a widely used technique to analyze multiple physical characteristics of an individual cell and diagnose and monitor human disease as well as response to therapy. Recent developments in hardware (multiple lasers and fluorescence detectors), fluorochromes, and antibodies have facilitated the comprehensive and in-depth analysis of high numbers of cells on a single cell level and led to the creation of various computational analysis methods for cell type identification, rare cell identification, and sample classification. Flow cytometry typically uses panels with a large number of antibodies, leading to high-dimensional multiparameter flow cytometry readout. It increases computational complexity and makes interpretation difficult. In this study, we identified the best subset of the parameters for AML classification model development. The subset would contribute to panel design specific for the target disease and lead to easy interpretation of the results. In addition, we spotted important decision-support range of flow-cytometry parameter via insights provided by machine-learning algorithm. We expect that profiling information of fluorescence expression over the identified decision-support range would complement existing diagnosis criteria.