Current best evidence for clinical care (more info)
OBJECTIVES: To study whether a trained convolutional neural network (CNN) can be of assistance to radiologists in differentiating Coronavirus disease (COVID)-positive from COVID-negative patients using chest X-ray (CXR) through an ambispective clinical study. To identify subgroups of patients where artificial intelligence (AI) can be of particular value and analyse what imaging features may have contributed to the performance of AI by means of visualisation techniques.
METHODS: CXR of 487 patients were classified into  categories-normal, classical COVID, indeterminate, and non-COVID by consensus opinion of 2 radiologists. CXR which were classified as "normal" and "indeterminate" were then subjected to analysis by AI, and final categorisation provided as guided by prediction of the network. Precision and recall of the radiologist alone and radiologist assisted by AI were calculated in comparison to reverse transcriptase-polymerase chain reaction (RT-PCR) as the gold standard. Attention maps of the CNN were analysed to understand regions in the CXR important to the AI algorithm in making a prediction.
RESULTS: The precision of radiologists improved from 65.9 to 81.9% and recall improved from 17.5 to 71.75 when assistance with AI was provided. AI showed 92% accuracy in classifying "normal" CXR into COVID or non-COVID. Analysis of attention maps revealed attention on the cardiac shadow in these "normal" radiographs.
CONCLUSION: This study shows how deployment of an AI algorithm can complement a human expert in the determination of COVID status. Analysis of the detected features suggests possible subtle cardiac changes, laying ground for further investigative studies into possible cardiac changes.
KEY POINTS: • Through an ambispective clinical study, we show how assistance with an AI algorithm can improve recall (sensitivity) and precision (positive predictive value) of radiologists in assessing CXR for possible COVID in comparison to RT-PCR. • We show that AI achieves the best results in images classified as "normal" by radiologists. We conjecture that possible subtle cardiac in the CXR, imperceptible to the human eye, may have contributed to this prediction. • The reported results may pave the way for a human computer collaboration whereby the expert with some help from the AI algorithm achieves higher accuracy in predicting COVID status on CXR than previously thought possible when considering either alone.
|Discipline / Specialty Area||Score|
This paper employs a deep learning ("artificial intelligence") strategy to augment radiologists' interpretation of chest x-rays in the setting of COVID-19 disease. The use of deep learning improved radiologists' interpretation of films when compared with diagnosis by PCR. This is an important study in that it was a "real world" experiment that relied on AP views only and did not exclude poor quality films. The approach of using deep learning to improve diagnostic accuracy in chest x-rays is valuable. There are flaws in the paper, none fatal, including the timing of the x-ray relative to the disease natural history and these flaws are acknowledged by the authors.