Summary of How to Count Coughs: An Event-based Framework For Evaluating Automatic Cough Detection Algorithm Performance, by Lara Orlandic et al.
How to Count Coughs: An Event-Based Framework for Evaluating Automatic Cough Detection Algorithm Performance
by Lara Orlandic, Jonathan Dan, Jerome Thevenot, Tomas Teijeiro, Alain Sauty, David Atienza
First submitted to arxiv on: 3 Jun 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Sound (cs.SD)
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 Machine learning algorithms running on wearable devices are being explored for quantifying daily coughs, providing clinicians with objective metrics to track symptoms and evaluate treatments. The current state-of-the-art metrics focus on distinguishing cough from non-cough samples, which doesn’t directly provide clinically relevant outcomes like the number of cough events or their temporal patterns. Instead, researchers propose using event-based evaluation metrics aligned with clinical guidelines on significant cough counting endpoints. This approach aims to improve the accuracy and relevance of cough counting algorithms for clinicians. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Wearable devices are being used to track daily coughs, which is helping doctors get a better understanding of symptoms and treatments. Right now, most researchers focus on telling the difference between cough sounds and other sounds, but this isn’t directly giving them the information they need about how often people are coughing or when those coughs happen. Instead, some experts think we should be looking at events instead of samples, and using metrics that align with what doctors want to know. |
Keywords
» Artificial intelligence » Machine learning
