[论文解读] Virufy: Global Applicability of Crowdsourced and Clinical Datasets for AI Detection of COVID-19 from Cough

Gunvant Chaudhari, Xinyi Jiang+5 more|arXiv (Cornell University)|Nov 26, 2020

COVID-19 diagnosis using AI被引用 54

一句话总结

本论文显示来自全球的众包咳嗽音频可以训练一个 AI 以 77.1% 的 ROC-AUC 检测 COVID-19，并且该模型对拉丁美洲众包数据和南亚临床数据具有跨区域泛化能力，而无需地区特定的训练。

ABSTRACT

Rapid and affordable methods of testing for COVID-19 infections are essential to reduce infection rates and prevent medical facilities from becoming overwhelmed. Current approaches of detecting COVID-19 require in-person testing with expensive kits that are not always easily accessible. This study demonstrates that crowdsourced cough audio samples recorded and acquired on smartphones from around the world can be used to develop an AI-based method that accurately predicts COVID-19 infection with an ROC-AUC of 77.1% (75.2%-78.3%). Furthermore, we show that our method is able to generalize to crowdsourced audio samples from Latin America and clinical samples from South Asia, without further training using the specific samples from those regions. As more crowdsourced data is collected, further development can be implemented using various respiratory audio samples to create a cough analysis-based machine learning (ML) solution for COVID-19 detection that can likely generalize globally to all demographic groups in both clinical and non-clinical settings.

研究动机与目标

• 推动使用智能手机记录的咳嗽声快速、经济地进行 COVID-19 测试，减少对线下试剂包的依赖。
• 证明全球众包咳嗽数据集可训练 AI 以稳健的 ROC-AUC 性能预测 COVID-19 感染。
• 展示模型在不同区域的泛化能力（拉丁美洲众包数据和南亚临床数据），无需区域特定再训练。

提出的方法

• 通过智能手机收集来自全球的众包咳嗽音频样本。
• 开发基于 AI 的模型，以咳嗽音频来判断 COVID-19 感染。
• 使用 ROC-AUC 评估模型性能，并评估跨区域泛化。
• 将众包数据的性能与来自不同区域的临床样本进行比较。

实验结果

研究问题

• RQ1 来自全球多样人群的众包咳嗽音频是否能使AI实现对 COVID-19 的准确检测？
• RQ2 在全球众包数据训练的模型是否能够在不进行额外区域特定训练的情况下对区域数据泛化？
• RQ3 报告的 ROC-AUC 性能是多少，以及跨区域泛化如何在结果中体现？

主要发现

• 基于 AI 的方法达到 ROC-AUC 77.1%（75.2%-78.3%）。
• 模型对拉丁美洲的众包音频具有泛化，不需要区域特定训练。
• 模型对来自南亚的临床样本具有泛化，无需对这些样本进行额外训练。
• 众包数据可以随着时间累积，扩展用于全球 COVID-19 检测的咳嗽分析机器学习解决方案。