Advancing COVID-19 Diagnosis with Privacy-Preserving Collaboration in Artificial Intelligence (preprint)

Artificial intelligence (AI) provides a promising substitution 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-generalised model in clinical practices. To address this, we launch the Unified CT-COVID AI Diagnostic Initiative (UCADI), where the AI model can be distributedly trained and independently executed at each host institution under a federated learning framework (FL) without data sharing. Here we show that our FL model outperformed all the local models by a large yield (test sensitivity /specificity in China: 0.973/0.951, in the UK: 0.730/0.942), achieving comparable performance with a panel of professional radiologists. We further evaluated the model on the hold-out (collected from another two hospitals leaving out the FL) 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 (CTs) from 3,336 patients collected from 23 hospitals located in China and the UK. Collectively, our work advanced the prospects of utilising federated learning for privacy-preserving AI in digital health.

Effectiveness of inactive COVID-19 vaccines against severe illness in B.1.617.2 (Delta) variant-infected patients in Jiangsu, China (preprint)

The SARS-CoV-2 B.1.617.2 (Delta) variant has caused a new surge in the number of COVID-19 cases. The effectiveness of vaccines against this variant is not fully understood. Using data from a recent large-scale outbreak of COVID-19 in China, we conducted a real-world study to explore the effect of inactivated vaccine immunization on the course of disease in patients infected with Delta variants. We recruited 476 confirmed cases over the age of 18, of which 42 were severe. After adjusting for age, gender, and comorbidities, patients who received two doses of inactivated vaccine (fully vaccinated) had an 88% reduced risk in progressing to the severe stage (adjusted OR: 0.12, 95% CI: 0.02- 0.45). However, this protective effect was not observed in patients who only received only one dose of the vaccine(adjusted OR: 1.11, 95% CI: 0.51- 2.36). The full immunization offered 100% protection from a severe illness among women. The effect of the vaccine was potentially affected by underlying medical conditions (OR: 0.26, 95% CI: 0.03-1.23). This is the largest real-world study confirming the effectiveness of inactive COVID-19 vaccines against severe illness in Delta variant-infected patients in Jiangsu, China.

Report on Three Round COVID-19 Risk Blind Tests by Screening Eye-region Manifestations (preprint)

The Coronavirus disease 2019 (COVID-19) has affected several million people since 2019. Despite various vaccines of COVID-19 protect million people in many countries, the worldwide situations of more the asymptomatic and mutated strain discovered are urging the more sensitive COVID-19 testing in this turnaround time. Unfortunately, it is still nontrivial to develop a new fast COVID-19 screening method with the easier access and lower cost, due to the technical and cost limitations of the current testing methods in the medical resource-poor districts. On the other hand, there are more and more ocular manifestations that have been reported in the COVID-19 patients as growing clinical evidence[1]. This inspired this project. We have conducted the joint clinical research since January 2021 at the ShiJiaZhuang City, Heibei province, China, which approved by the ethics committee of The fifth hospital of ShiJiaZhuang of Hebei Medical University. We undertake several blind tests of COVID-19 patients by Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China. Meantime as an important part of the ongoing globally COVID-19 eye test program by AIMOMICS since February 2020, we propose a new fast screening method of analyzing the eye-region images, captured by common CCD and CMOS cameras. This could reliably make a rapid risk screening of COVID-19 with the sustainable stable high performance in different countries and races. For this clinical trial in ShiJiaZhuang, we compare and analyze 1194 eye-region images of 115 patients, including 66 COVID-19 positive patients, 44 rehabilitation patients (nucleic acid changed from positive to negative), 5 liver patients, as well as 117 healthy people. Remarkably, we consistently achieved very high testing results (> 0.94) in terms of both sensitivity and specificity in our blind test of COVID-19 patients. This confirms the viability of the COVID-19 fast screening by the eye-region manifestations. Particularly and impressively, the results have the similar conclusion as the other clinical trials of the globally COVID-19 eye test program[1]. Hopefully, this series of ongoing globally COVID-19 eye test study, and potential rapid solution of fully self-performed COVID risk screening method, can be inspiring and helpful to more researchers in the world soon. Our model for COVID-19 rapid prescreening have the merits of the lower cost, fully self-performed, non-invasive, importantly real-time, and thus enables the continuous health surveillance. We further implement it as the open accessible APIs, and provide public service to the world. Our pilot experiments show that our model is ready to be usable to all kinds of surveillance scenarios, such as infrared temperature measurement device at airports and stations, or directly pushing to the target people groups smartphones as a packaged application.

AI-assisted CT imaging analysis for COVID-19 screening: Building and deploying a medical AI system in four weeks (preprint)

The sudden outbreak of novel coronavirus 2019 (COVID-19) increased the diagnostic burden of radiologists. In the time of an epidemic crisis, we hoped artificial intelligence (AI) to help reduce physician workload in regions with the outbreak, and improve the diagnosis accuracy for physicians before they could acquire enough experience with the new disease. Here, we present our experience in building and deploying an AI system that automatically analyzes CT images to detect COVID-19 pneumonia features. Different from conventional medical AI, we were dealing with an epidemic crisis. Working in an interdisciplinary team of over 30 people with medical and / or AI background, geographically distributed in Beijing and Wuhan, we were able to overcome a series of challenges in this particular situation and deploy the system in four weeks. Using 1,136 training cases (723 positives for COVID-19) from five hospitals, we were able to achieve a sensitivity of 0.974 and specificity of 0.922 on the test dataset, which included a variety of pulmonary diseases. Besides, the system automatically highlighted all lesion regions for faster examination. As of today, we have deployed the system in 16 hospitals, and it is performing over 1,300 screenings per day.

Clinical Characteristics of 24 Asymptomatic Infections with COVID-19 Screened among Close Contacts in Nanjing, China (preprint)

Background: Previous studies have showed clinical characteristics of patients with the 2019 novel coronavirus disease (COVID-19) and the evidence of person-to-person transmission. Limited data are available for asymptomatic infections. This study aims to present the clinical characteristics of 24 cases with asymptomatic infection screened from close contacts and to show the transmission potential of asymptomatic COVID-19 virus carriers. Methods: Epidemiological investigations were conducted among all close contacts of COVID-19 patients (or suspected patients) in Nanjing, Jiangsu Province, China, from Jan 28 to Feb 9, 2020, both in clinic and in community. Asymptomatic carriers were laboratory-confirmed positive for the COVID-19 virus by testing the nucleic acid of the pharyngeal swab samples. Their clinical records, laboratory assessments, and chest CT scans were reviewed. Findings: None of the 24 asymptomatic cases presented any obvious symptoms before nucleic acid screening. Five cases (20.8%) developed symptoms (fever, cough, fatigue and etc.) during hospitalization. Twelve (50.0%) cases showed typical CT images of ground-glass chest and five (20.8%) presented stripe shadowing in the lungs. The remaining seven (29.2%) cases showed normal CT image and had no symptoms during hospitalization. These seven cases were younger (median age: 14.0 years; P = 0.012) than the rest. None of the 24 cases developed severe COVID-19 pneumonia or died. The median communicable period, defined as the interval from the first day of positive nucleic acid tests to the first day of continuous negative tests, was 9.5 days (up to 21 days among the 24 asymptomatic cases). Through epidemiological investigation, we observed a typical asymptomatic transmission to the cohabiting family members, which even caused severe COVID-19 pneumonia. Interpretation: The asymptomatic carriers identified from close contacts were prone to be mildly ill during hospitalization. However, the communicable period could be up to three weeks and the communicated patients could develop severe illness. These results highlighted the importance of close contact tracing and longitudinally surveillance via virus nucleic acid tests. Further isolation recommendation and continuous nucleic acid tests may also be recommended to the patients discharged.