Related Experiment Video
Updated: Jun 4, 2025
A Microfluidic Model of Biomimetically Breathing Pulmonary Acinar Airways
Published on: May 9, 2016
Use of Machine Learning Models to Predict Microaspiration Measured by Tracheal Pepsin A
Annette Bourgault1, Ilana Logvinov2, Chang Liu3
1Annette Bourgault is an associate professor in Nursing, University of Central Florida College of Nursing, Orlando.
Background:
Enteral feeding intolerance, a common type of gastrointestinal dysfunction leading to underfeeding, is associated with increased mortality. Tracheal pepsin A, an indicator of microaspiration, was found in 39% of patients within 24 hours of enteral feeding. Tracheal pepsin A is a potential biomarker of enteral feeding intolerance.
Objective:
To identify predictors of microaspiration (tracheal or oral pepsin A). It was hypothesized that variables predicting the presence of tracheal pepsin A might be similar to predictors of enteral feeding intolerance.
Methods:
In this secondary analysis, machine learning models were fit for 283 adults receiving mechanical ventilation who had tracheal and oral aspirates obtained every 12 hours for up to 14 days. Pepsin A levels were measured using the proteolytic enzyme assay method, and values of 6.25 ng/mL or higher were classified as indicating microaspiration. Demographics, comorbidities, and variables associated with enteral feeding were analyzed with 3 machine learning models-random forest, XGBoost, and support vector machines with recursive feature elimination-using 5-fold cross-validation tuning.
Results:
Random forest for tracheal pepsin A was the best-performing model (area under the curve, 0.844 [95% CI, 0.792-0.897]; accuracy, 87.55%). The top 20 predictors of tracheal pepsin A were identified.
Conclusion:
Four predictor variables for tracheal pepsin A (microaspiration) are also reported predictors of enteral feeding intolerance, supporting the exploration of tracheal pepsin A as a potential biomarker of enteral feeding intolerance. Identification of predictor variables using machine learning models may facilitate treatment of patients at risk for enteral feeding intolerance.
Insights
Tracheal pepsin A indicates microaspiration and may predict enteral feeding intolerance. Machine learning identified key predictors, aiding early intervention for at-risk patients.
Area of Science:
- Critical care medicine
- Gastroenterology
- Biomarker discovery
Background:
- Enteral feeding intolerance is common and linked to higher mortality.
- Microaspiration, indicated by tracheal pepsin A, occurs frequently in patients on mechanical ventilation.
- Tracheal pepsin A is a potential biomarker for enteral feeding intolerance.
Purpose of the Study:
- To identify predictors of microaspiration using tracheal or oral pepsin A.
- To determine if predictors of tracheal pepsin A overlap with those of enteral feeding intolerance.
Main Methods:
- Machine learning models (random forest, XGBoost, SVM) were applied to data from 283 ventilated adults.
- Tracheal and oral aspirates were analyzed for pepsin A levels over 14 days.
- Predictors were identified using 5-fold cross-validation.
Main Results:
- The random forest model demonstrated high performance for predicting tracheal pepsin A (AUC 0.844).
- The top 20 predictors of tracheal pepsin A were successfully identified.
- Four predictors of tracheal pepsin A were also linked to enteral feeding intolerance.
Conclusions:
- Tracheal pepsin A shows promise as a biomarker for enteral feeding intolerance.
- Machine learning effectively identified predictors of microaspiration.
- Identifying at-risk patients can facilitate timely treatment for enteral feeding intolerance.
