Automated COVID-19 screening framework via Deep Convolutional Neural Network with Chest X-ray Medical Images

COVID-19 screening using chest X-rays plays a significant role in the early diagnosis of COVID-19 illness during the ongoing pandemic. Manually identifying this infection from chest X-ray films is a challenging and time-consuming technique due to time restrictions and the competence of radiologists. Also, the manual Covid-19 identification technique is made much more difficult and opaquer by the feature similarity between positive and negative chest X-ray images. Therefore, we propose an automated COVID-19 screening framework that utilizes artificial intelligence techniques with a transfer learning approach for COVID-19 diagnosis using chest X-ray images. Specifically, we employ the transfer learning concept for feature extraction before further processing with modified deep neural networks. Also, Grad-CAM visualization is used for our case study to support the predicted diagnosis. The results of the experiments on the publicly accessible dataset show that the convolutional neural network model, which is simple yet effective, performs significantly better than other deep learning techniques across all metrics, including accuracy, precision, recall, and F-measure. © 2022 IEEE.

Author Correction: Advancing COVID-19 diagnosis with privacy-preserving collaboration in artificial intelligence (Nature Machine Intelligence, (2021), 3, 12, (1081-1089), 10.1038/s42256-021-00421-z)

In the version of this article initially published, the first name of Chuansheng Zheng was misspelled as Chuangsheng. The error has been corrected in the HTML and PDF versions of the article. © The Author(s) 2022.

Beyond fear go viral: A machine learning study on infodemic detection during covid-19 pandemic

With the restrictions in our daily life activities under the current situation of the covid-19 pandemic worldwide, billions of people rely on social media platforms to share and obtaining covid-19 related news information. This made social media platforms easily be used as a source of myths and disinformation, which can cause severe public risks. It is thus of vital importance to constraint the spread of misinformation to the public. Although many works have shown promising results on the misinformation detection problem, only a few studies focus on the infodemic detection during the covid-19 pandemic, especially in the low resource language like Thai. Therefore, in this paper, we conduct extensive experiments on the real-world social network datasets to detect misinformation about covid-19 targeting both English and Thai languages. In particular, we perform an exploratory data analysis to get the statistic and characteristics of real and fake content. Also, we evaluate a series of three feature extraction, seven traditional machine learning, and eleven deep learning methods in detecting the fabricated content on social media platforms. The experimental results demonstrate that the transformer-based model significantly outperforms other deep learning and traditional machine learning methods in all metrics, including accuracy and F-measure. © 2022 IEEE.

Advancing COVID-19 diagnosis with privacy-preserving collaboration in artificial intelligence

Artificial intelligence provides a promising solution for streamlining COVID-19 diagnoses;however, concerns surrounding security and trustworthiness impede the collection of large-scale representative medical data, posing a considerable challenge for training a well-generalized model in clinical practices. To address this, we launch the Unified CT-COVID AI Diagnostic Initiative (UCADI), where the artificial intelligence (AI) model can be distributedly trained and independently executed at each host institution under a federated learning framework without data sharing. Here we show that our federated learning framework model considerably outperformed all of the local models (with a test sensitivity/specificity of 0.973/0.951 in China and 0.730/0.942 in the United Kingdom), achieving comparable performance with a panel of professional radiologists. We further evaluated the model on the hold-out (collected from another two hospitals without the federated learning framework) and heterogeneous (acquired with contrast materials) data, provided visual explanations for decisions made by the model, and analysed the trade-offs between the model performance and the communication costs in the federated training process. Our study is based on 9,573 chest computed tomography scans from 3,336 patients collected from 23 hospitals located in China and the United Kingdom. Collectively, our work advanced the prospects of utilizing federated learning for privacy-preserving AI in digital health. The COVID-19 pandemic sparked the need for international collaboration in using clinical data for rapid development of diagnosis and treatment methods. But the sensitive nature of medical data requires special care and ideally potentially sensitive data would not leave the organization which collected it. Xiang Bai and colleagues present a privacy-preserving AI framework for CT-based COVID-19 diagnosis and demonstrate it on data from 23 hospitals in China and the United Kingdom.