Integrated machine learning approaches for flow cytometric quantification of myeloid-derived suppressor cells in acute sepsis
Highly heterogeneous cell populations require multiple flow cytometric markers for appropriate phenotypic characterization. This exponentially increases the complexity of 2D scatter plot analyses and exacerbates human errors due to variations in manual gating of flow data. We describe a semi-automat...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-11-01
|
| Series: | Frontiers in Immunology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fimmu.2022.1007016/full |
| _version_ | 1798017430722707456 |
|---|---|
| author | Anthony S. Bonavia Anthony S. Bonavia Abigail Samuelsen Joshua Luthy E. Scott Halstead |
| author_facet | Anthony S. Bonavia Anthony S. Bonavia Abigail Samuelsen Joshua Luthy E. Scott Halstead |
| author_sort | Anthony S. Bonavia |
| collection | DOAJ |
| description | Highly heterogeneous cell populations require multiple flow cytometric markers for appropriate phenotypic characterization. This exponentially increases the complexity of 2D scatter plot analyses and exacerbates human errors due to variations in manual gating of flow data. We describe a semi-automated workflow, based entirely on the Flowjo Graphical User Interface (GUI), that involves the stepwise integration of several, newly available machine learning tools for the analysis of myeloid-derived suppressor cells (MDSCs) in septic and non-septic critical illness. Supervised clustering of flow cytometric data showed correlation with, but significantly different numbers of, MDSCs as compared with the cell numbers obtained by manual gating. Neither quantification method predicted 30-day clinical outcomes in a cohort of 16 critically ill and septic patients and 5 critically ill and non-septic patients. Machine learning identified a significant decrease in the proportion of PMN-MDSC in critically ill and septic patients as compared with healthy controls. There was no difference between the proportion of these MDSCs in septic and non-septic critical illness. |
| first_indexed | 2024-04-11T16:07:00Z |
| format | Article |
| id | doaj.art-263bece57cb74cbeb38ef89a98bf3153 |
| institution | Directory Open Access Journal |
| issn | 1664-3224 |
| language | English |
| last_indexed | 2024-04-11T16:07:00Z |
| publishDate | 2022-11-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Immunology |
| spelling | doaj.art-263bece57cb74cbeb38ef89a98bf31532022-12-22T04:14:47ZengFrontiers Media S.A.Frontiers in Immunology1664-32242022-11-011310.3389/fimmu.2022.10070161007016Integrated machine learning approaches for flow cytometric quantification of myeloid-derived suppressor cells in acute sepsisAnthony S. Bonavia0Anthony S. Bonavia1Abigail Samuelsen2Joshua Luthy3E. Scott Halstead4Division of Critical Care Medicine, Department of Anesthesiology and Perioperative Medicine, Penn State Milton S. Hershey Medical Center, Hershey, PA, United StatesDepartment of Anesthesiology and Perioperative Medicine, Penn State Milton S. Hershey Medical Center, Hershey, PA, United StatesDivision of Critical Care Medicine, Department of Anesthesiology and Perioperative Medicine, Penn State Milton S. Hershey Medical Center, Hershey, PA, United StatesProduct Innovation Division, BD Life Sciences - FlowJo, Ashland, OR, United StatesDivision of Pediatric Critical Care Medicine, Department of Pediatrics, Penn State Milton S. Hershey Medical Center, Hershey, PA, United StatesHighly heterogeneous cell populations require multiple flow cytometric markers for appropriate phenotypic characterization. This exponentially increases the complexity of 2D scatter plot analyses and exacerbates human errors due to variations in manual gating of flow data. We describe a semi-automated workflow, based entirely on the Flowjo Graphical User Interface (GUI), that involves the stepwise integration of several, newly available machine learning tools for the analysis of myeloid-derived suppressor cells (MDSCs) in septic and non-septic critical illness. Supervised clustering of flow cytometric data showed correlation with, but significantly different numbers of, MDSCs as compared with the cell numbers obtained by manual gating. Neither quantification method predicted 30-day clinical outcomes in a cohort of 16 critically ill and septic patients and 5 critically ill and non-septic patients. Machine learning identified a significant decrease in the proportion of PMN-MDSC in critically ill and septic patients as compared with healthy controls. There was no difference between the proportion of these MDSCs in septic and non-septic critical illness.https://www.frontiersin.org/articles/10.3389/fimmu.2022.1007016/fullhigh parameter flow cytometrysepsis - diagnosticsclustering analysisclinical immunologymyeloid-derived suppressor cells (MDSC) |
| spellingShingle | Anthony S. Bonavia Anthony S. Bonavia Abigail Samuelsen Joshua Luthy E. Scott Halstead Integrated machine learning approaches for flow cytometric quantification of myeloid-derived suppressor cells in acute sepsis Frontiers in Immunology high parameter flow cytometry sepsis - diagnostics clustering analysis clinical immunology myeloid-derived suppressor cells (MDSC) |
| title | Integrated machine learning approaches for flow cytometric quantification of myeloid-derived suppressor cells in acute sepsis |
| title_full | Integrated machine learning approaches for flow cytometric quantification of myeloid-derived suppressor cells in acute sepsis |
| title_fullStr | Integrated machine learning approaches for flow cytometric quantification of myeloid-derived suppressor cells in acute sepsis |
| title_full_unstemmed | Integrated machine learning approaches for flow cytometric quantification of myeloid-derived suppressor cells in acute sepsis |
| title_short | Integrated machine learning approaches for flow cytometric quantification of myeloid-derived suppressor cells in acute sepsis |
| title_sort | integrated machine learning approaches for flow cytometric quantification of myeloid derived suppressor cells in acute sepsis |
| topic | high parameter flow cytometry sepsis - diagnostics clustering analysis clinical immunology myeloid-derived suppressor cells (MDSC) |
| url | https://www.frontiersin.org/articles/10.3389/fimmu.2022.1007016/full |
| work_keys_str_mv | AT anthonysbonavia integratedmachinelearningapproachesforflowcytometricquantificationofmyeloidderivedsuppressorcellsinacutesepsis AT anthonysbonavia integratedmachinelearningapproachesforflowcytometricquantificationofmyeloidderivedsuppressorcellsinacutesepsis AT abigailsamuelsen integratedmachinelearningapproachesforflowcytometricquantificationofmyeloidderivedsuppressorcellsinacutesepsis AT joshualuthy integratedmachinelearningapproachesforflowcytometricquantificationofmyeloidderivedsuppressorcellsinacutesepsis AT escotthalstead integratedmachinelearningapproachesforflowcytometricquantificationofmyeloidderivedsuppressorcellsinacutesepsis |