A deep learning model using ECG waveforms identified the accessory pathway location with 78% accuracy compared to 61% for the conventional algorithm (p<0.001), and adding chest X-ray images further improved accuracy to 80%.
Observational (n=294)
Yes
Does a multimodal deep learning model using combined ECG and chest X-ray data improve the accuracy of identifying accessory pathway locations in patients with WPW syndrome compared to conventional decision tree algorithms?
A multimodal deep learning model combining ECG and chest X-ray data significantly improves the accuracy of localizing accessory pathways in WPW syndrome compared to conventional algorithms.
Absolute Event Rate: 0.78% vs 0.61%
p-value: p=<0.001
Cardiac accessory pathways (APs) in Wolff-Parkinson-White (WPW) syndrome are conventionally diagnosed with decision tree algorithms; however, there are problems with clinical usage. We assessed the efficacy of the artificial intelligence model using electrocardiography (ECG) and chest X-rays to identify the location of APs. We retrospectively used ECG and chest X-rays to analyse 206 patients with WPW syndrome. Each AP location was defined by an electrophysiological study and divided into four classifications. We developed a deep learning model to classify AP locations and compared the accuracy with that of conventional algorithms. Moreover, 1519 chest X-ray samples from other datasets were used for prior learning, and the combined chest X-ray image and ECG data were put into the previous model to evaluate whether the accuracy improved. The convolutional neural network (CNN) model using ECG data was significantly more accurate than the conventional tree algorithm. In the multimodal model, which implemented input from the combined ECG and chest X-ray data, the accuracy was significantly improved. Deep learning with a combination of ECG and chest X-ray data could effectively identify the AP location, which may be a novel deep learning model for a multimodal model.
Nishimori et al. (Tue,) conducted a observational in Wolff-Parkinson-White syndrome (n=294). Deep learning model (ECG alone or multimodal with chest X-ray) vs. Conventional decision tree algorithm was evaluated on Accuracy of accessory pathway location classification (p=<0.001). A deep learning model using ECG waveforms identified the accessory pathway location with 78% accuracy compared to 61% for the conventional algorithm (p<0.001), and adding chest X-ray images further improved accuracy to 80%.