Summary of Revisiting the Disequilibrium Issues in Tackling Heart Disease Classification Tasks, by Thao Hoang et al.
Revisiting the Disequilibrium Issues in Tackling Heart Disease Classification Tasks
by Thao Hoang, Linh Nguyen, Khoi Do, Duong Nguyen, Viet Dung Nguyen
First submitted to arxiv on: 19 Jul 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Signal Processing (eess.SP)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed approach addresses two primary obstacles in heart disease classification: imbalanced and biased ECG datasets, as well as the issue of overfitting caused by diverse lead signals. The authors design a Channel-wise Magnitude Equalizer (CME) to reduce redundancy in feature data and highlight changes in the dataset, thereby reducing high dimensionality. Additionally, they propose Inverted Weight Logarithmic Loss (IWL) to alleviate imbalances among the data, which improves state-of-the-art models’ accuracy by up to 5% on the CPSC2018 dataset when combined with CME. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Heart disease classification is an important task that requires accurate and reliable algorithms. However, existing ECG datasets often have biases and imbalances, making it difficult for deep learning models to perform well. The authors of this paper propose two new methods to address these issues: a Channel-wise Magnitude Equalizer (CME) to reduce dimensionality and an Inverted Weight Logarithmic Loss (IWL) to counteract data imbalance. These methods can improve the accuracy of state-of-the-art models by up to 10%. |
Keywords
» Artificial intelligence » Classification » Deep learning » Overfitting
