Back

ACQuA: Anomaly Classification with Quasi-Attractors

Rudman, W.; Merullo, J.; Mercurio, L.; Eickhoff, C.

2022-09-02 cardiovascular medicine
10.1101/2022.08.31.22279436 medRxiv
Show abstract

In recent years, deep learning has redefined algorithms for detecting cardiac abnormalities. However, many state of the art algorithms still rely on calculating handcrafted features from a given heart signal that are then fed into shallow 1D convolutional networks or transformer architectures. We propose ACQuA (Anomaly Classification with Quasi Attractors), a task agnostic algorithm that can be used in a wide variety of cardiac settings, from classifying cardiac arrhythmias from ECG signals to detecting heart murmurs from PCG signals. Using theorems from dynamical analysis and topological data analysis, we create informative attractor images that 1) are human distinguishable and 2) can be used to train small, off the shelf deep neural networks for anomaly classification. In the George B. Moody 2022 Challenge, we receive an official score of 0.433 (263/305) for murmur classification and a score of 12616 (208/305) for outcome classification. Additionally, we evaluate our model on the CinC 2017 Challenge data that tasks practitioners to classify cardiac arrhythmias from ECG signals. On the CinC 2017 Challenge data, we improve upon the winning F1 scores by approximately 14% on the hidden validation data.

Matching journals

The top 6 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.