Related Experiment Video
Updated: Aug 3, 2025
Flow Cytometric Analysis for Identification of the Innate and Adaptive Immune Cells of Murine Lung
Published on: November 16, 2021
A random forest model using flow cytometry data identifies pulmonary infection after thoracic injury
Rondi B Gelbard1, Hannah Hensman, Seth Schobel
1From the Department of Surgery (R.B.G., C.J.D., T.G.B.), Emory University, Atlanta, Georgia; Uniformed Services University of the Health Sciences (S.S., E.G., E.E.), Walter Reed National Military Medical Center (E.E.), Surgical Critical Care Initiative (R.B.G., H.H., S.S., L.S., E.G., C.J.D., T.G.B., A.D.K., E.E.), Bethesda, Maryland; DecisionQ (H.H.), Arlington, Virginia; Department of Surgery (L.S., D.M., A.D.K.), Duke University, Durham, North Carolina; Department of Surgery, Trauma, Burns, and Surgical Critical Care (R.B.G.), University of Alabama at Birmingham, Birmingham, Alabama; and Henry M Jackson Foundation for the Advancement of Military Medicine (S.S., E.G.), Bethesda, Maryland.
Flow cytometry assessment of cell phenotypes can identify pneumonia risk in thoracic trauma patients. Lower CD4+ central memory cell frequency and physiological stress indicate higher pneumonia rates.
Area of Science:
- Immunology
- Critical Care Medicine
- Pulmonary Medicine
Background:
- Thoracic injuries can impair lung function and lead to pneumonia (PNA).
- Central memory T cells are crucial for pulmonary immunity.
- Assessing cell phenotypes via flow cytometry (FCM) may help identify PNA post-thoracic trauma.
Purpose of the Study:
- To explore the utility of flow cytometry (FCM) in identifying pulmonary infection (PNA) after thoracic trauma.
- To determine if cell phenotypes can predict PNA risk in trauma patients.
Main Methods:
- Prospective study of trauma patients with thoracic injuries (2014-2020).
- Clinical and FCM data from serum samples collected within 24 hours of admission were analyzed.
- Random forest and logistic regression models were used to estimate PNA risk, with backwards elimination for variable selection and leave-one-out internal validation.
Main Results:
- Seventy patients were included; 20% developed PNA.
- A random forest model using Acute Physiology and Chronic Health Evaluation score, highest pulse rate, and CD4+ central memory cell frequency identified PNA with AUC 0.93, sensitivity 0.91, and specificity 0.88.
- Logistic regression with the same variables achieved AUC 0.86, sensitivity 0.76, and specificity 0.85.
Conclusions:
- Clinical and FCM data are valuable for early PNA risk identification in thoracic trauma patients.
- Physiological stress indicators and a lower frequency of central memory T cells are associated with increased PNA risk.
