Summary of Mitigating Sex Bias in Audio Data-driven Copd and Covid-19 Breathing Pattern Detection Models, by Rachel Pfeifer et al.
Mitigating Sex Bias in Audio Data-driven COPD and COVID-19 Breathing Pattern Detection Models
by Rachel Pfeifer, Sudip Vhaduri, James Eric Dietz
First submitted to arxiv on: 16 Sep 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Sound (cs.SD); Audio and Speech Processing (eess.AS)
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 This research paper investigates machine learning models used in diagnosing respiratory illnesses like chronic obstructive pulmonary disease (COPD) and COVID-19 based on patients’ breathing patterns. The study highlights the issue of sex bias in these models, which can lead to unfair diagnoses when trained with datasets that are predominantly male or female. To mitigate this bias, the authors employ decision tree models, threshold optimizers, and constraints like demographic parity and equalized odds to reduce the disparity. By comparing the performance of biased and debiased models on two open-source datasets, the researchers observe significant improvements in accuracy, with a 81.43% reduction in demographic parity difference and a 71.81% decrease in equalized odds difference. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research paper is about making sure that machine learning models used to diagnose respiratory illnesses like COPD and COVID-19 are fair and don’t favor one gender over the other. The current models often have biases because they’re trained on datasets that are mostly made up of men or women, which can lead to incorrect diagnoses. To fix this problem, the researchers used special techniques to train their models and tested them on real audio recordings of breathing patterns from patients with COPD and COVID-19. They found that their method worked well, reducing biases by 81% for demographic parity and 72% for equalized odds. |
Keywords
» Artificial intelligence » Decision tree » Machine learning
