Recently deep learning has attained a breakthrough in model accuracy for the classification of images due mainly to convolutional neural networks. In the present study, we attempted to investigate the presence of subclinical voice feature alteration in COVID-19 patients after the recent resolution of disease using deep learning. The study was a prospective study of 76 post COVID-19 patients and 40 healthy individuals. The diagnoses of post COVID-19 patients were based on more than the eighth week after onset of symptoms. Voice samples of an ‘ah’ sound, coughing sound and a polysyllabic sentence were collected and preprocessed to log-mel spectrogram. Transfer learning using the VGG19 pre-trained convolutional neural network was performed with all voice samples. The performance of the model using the polysyllabic sentence yielded the highest classification performance of all models. The coughing sound produced the lowest classification performance while the ability of the monosyllabic ‘ah’ sound to predict the recent COVID-19 fell between the other two vocalizations. The model using the polysyllabic sentence achieved 85% accuracy, 89% sensitivity, and 77% specificity. In conclusion, deep learning is able to detect the subtle change in voice features of COVID-19 patients after recent resolution of the disease.

最近，深度学习在图像分类的模型精度方面取得了突破，这主要归功于卷积神经网络。在本研究中，我们尝试使用深度学习研究最近疾病解决后 COVID-19 患者是否存在亚临床语音特征改变。该研究是对 76 名 COVID-19 后患者和 40 名健康人的前瞻性研究。COVID-19 后患者的诊断基于症状出现后超过八周。收集“啊”声、咳嗽声和多音节句子的语音样本，并将其预处理为对数梅尔频谱图。使用 VGG19 预训练卷积神经网络对所有语音样本进行迁移学习。使用多音节句子的模型的性能产生了所有模型中最高的分类性能。咳嗽声产生的分类性能最低，而单音节“啊”声预测最近 COVID-19 的能力介于其他两种发声之间。使用多音节句子的模型实现了 85% 的准确度、89% 的灵敏度和 77% 的特异性。总而言之，深度学习能够检测到 COVID-19 患者在近期疾病解决后语音特征的细微变化。89% 的敏感性和 77% 的特异性。总而言之，深度学习能够检测到 COVID-19 患者在近期疾病解决后语音特征的细微变化。89% 的敏感性和 77% 的特异性。总而言之，深度学习能够检测到 COVID-19 患者在近期疾病解决后语音特征的细微变化。