Deep Learning Models to Predict Fatal Pneumonia Using Chest X-Ray Images

Figure 6

Comparison and nature of prediction performance of fatal and nonfatal pneumonia in the external validation test dataset by deep learning models and physicians. (a) Performance of the deep learning models, two board-certified respiratory physicians, and two residents based on assessments of the external validation test dataset of 100 CXR images. (b) In 100 CXR images of the test dataset for external validation, respiratory physicians 1 and 2 evaluated the cavities, the number of involved lung lobes, the location of infiltrates, and pleural effusions, respectively. The percentages of these findings were compared between the groups that the deep learning model by Google Cloud AutoML Vision predicted as nonfatal or fatal pneumonia. We also compared the rates of cardiomegaly and CHF in the group that the deep learning model by Google Cloud AutoML Vision predicted as nonfatal or fatal pneumonia. Error bars represent 95% confidence intervals. values were determined by Fisher’s exact test. CXR, chest X-ray; CHF, congestive heart failure.

(a)

(b)