Applying AI to Pediatric Chest Imaging: Will Leveraging Adult-Based AI Models Prove Reliable?

Researchers

Journal

Modalities

Models

Abstract

The scarcity of AI applications designed for use in pediatric patients can cause a significant health disparity in this vulnerable population. We investigated the performance of an adult trained algorithm in detecting pneumonia in a pediatric population to explore the viability of leveraging adult-trained algorithms to accelerate pediatric AI research.We analyzed a publicly available pediatric chest x-ray dataset using an AI algorithm from TorchXRayVision. A 60% threshold was used to make binary predictions for pneumonia presence. Predictions were compared to dataset labels. Performance measures including true positive (TP) rate, false positive (FP) rate, true negative (TN) rate, false negative (FN) rate, sensitivity, specificity, positive and negative predictive values (PPV & NPV), accuracy, and F1-score were calculated for the complete dataset and bacterial/viral pneumonia subsets.Overall (n = 5,856), the algorithm identified 3,923 cases with pneumonia (67.00%) and 1,933 (33.00%) normal cases. In comparison to the actual image labels, there were 3,411 (58.25%) TP cases, 512 (8.74%) FP cases, 1,071 (18.29%) TN cases, and 862 (14.72%) FN cases resulting in 79.83% sensitivity, 67.66% specificity, 86.95% PPV, 55.41% NPV, 76.54% accuracy, and an F1-score of 0.83. While the performance remained consistent in the bacterial pneumonia group, there was a significant decrease in PPV (69.9%) and F1 score (0.74) in the viral pneumonia group.An adult-trained model adequately detected pneumonia in pediatric patients aged 1 to 5 years. Though models trained exclusively on pediatric images performed better, leveraging adult-based algorithms and datasets can expedite pediatric AI research.Copyright © 2023. Published by Elsevier Inc.