Federated Active Learning for Multicenter Collaborative Disease Diagnosis.

Current computer-aided diagnosis system with deep learning method plays an important role in the field of medical imaging. The collaborative diagnosis of diseases by multiple medical institutions has become a popular trend. However, large scale annotations put heavy burdens on medical experts. Furthermore, the centralized learning system has defects in privacy protection and model generalization. To meet these challenges, we propose two federated active learning methods for multicenter collaborative diagnosis of diseases: the Labeling Efficient Federated Active Learning (LEFAL) and the Training Efficient Federated Active Learning (TEFAL). The proposed LEFAL applies a task-agnostic hybrid sampling strategy considering data uncertainty and diversity simultaneously to improve data efficiency. The proposed TEFAL evaluates the client informativeness with a discriminator to improve client efficiency. On the Hyper-Kvasir dataset for gastrointestinal disease diagnosis, with only 65% of labeled data, the LEFAL achieves 95% performance on the segmentation task with whole labeled data. Moreover, on the CC-CCII dataset for COVID-19 diagnosis, with only 50 iterations, the accuracy and F1-score of TEFAL are 0.90 and 0.95, respectively on the classification task. Extensive experimental results demonstrate that the proposed federated active learning methods outperform state-of-the-art methods on segmentation and classification tasks for multicenter collaborative disease diagnosis.

Traditional Chinese medicine treatment for COVID-19: An overview of systematic reviews and meta-analyses.

BACKGROUND: Coronavirus disease 2019 (COVID-19) is a rapidly spreading disease that has caused an extensive burden to the world. Consequently, a large number of clinical trials have examined the efficacy of traditional Chinese medicine (TCM) for treating and preventing COVID-19, with coinciding proliferation of reviews summarizing these studies. OBJECTIVE: This study aimed to evaluate the methodological quality and evidence quality of systematic reviews and meta-analyses on the efficacy of TCM. SEARCH STRATEGY: Seven electronic databases, including PubMed, Cochrane Library, Web of Science, China National Knowledge Infrastructure, Chongqing VIP, Wanfang Data and SinoMed, were searched for systematic reviews and meta-analyses in October 2021. Search terms such as "Chinese medicine," "Lianhua Qingwen" and "COVID-19" were used. INCLUSION CRITERIA: Systematic reviews and meta-analyses of randomized controlled trials that evaluated the efficacy of TCM treatment of COVID-19 were included. DATA EXTRACTION AND ANALYSIS: A Measurement Tool to Assess Systematic Reviews Version 2.0 (AMSTAR 2) was used to evaluate the methodological quality. The quality of evidence was graded using the Grading of Recommendations Assessment, Development, and Evaluation (GRADE) system. Data extraction and analysis were performed by two reviewers independently. RESULTS: There were 17 meta-analyses included in our overview. The intervention group was defined as TCM combined with Western medicine, while the control group was Western medicine alone. The methodological quality of all the included studies was moderate to poor. A total of 89 outcome indicators were evaluated, of which, 8 were rated as moderate quality, 39 as low quality, and 41 as very low quality. Only one outcome measure was graded as being of high quality. The moderate quality of evidence indicated that, for the treatment of COVID-19, the clinical efficacy of TCM in combination with Western medicine was better, in terms of lung recovery, rate of conversion to severe/critical cases, symptom scores, duration of symptoms, mortality, and length of hospital stay. CONCLUSION: Evidence from the included studies shows that, compared with conventional Western medical therapy alone, the addition of TCM to COVID-19 treatment may improve clinical outcomes. Overall, the quality of evidence of TCM for COVID-19 was moderate to poor. Meta-analyses of the use of TCM in the treatment of COVID-19 can be used for clinical decision making by accounting for the experiences of clinical experts, medical policies, and other factors.

Association between ageing population, median age, life expectancy and mortality in coronavirus disease (COVID-19).

As of May 5, 2020, the number of confirmed coronavirus disease (COVID-19) cases has been more than 3.5 million with 243,540 deaths. We aimed to determine the associations between ageing population, median age, life expectancy at birth and COVID-19 mortality. The numbers of COVID-19 cases and deaths in the European region were obtained from the World Health Organization database. The data on percentage of the population aged 65 and over, median age and life expectancy at birth were extracted from the World Factbook of Central Intelligence Agency. A total of 56 countries/areas in the Europe reported COVID-19 cases and deaths (1,121,853 cases and 100,938 deaths) on April 20, 2020. The results showed significant positive associations between COVID-19 mortality and ageing population (r =0.274; P =0.021), median age (r =0.255; P=0.029), male median age (r =0.284; P =0.017), female median age (r =0.224; P=0.049), life expectancy at birth (r =0.336; P=0.006), male life expectancy at birth (r =0.342; P=0.005), female life expectancy at birth (r =0.312; P=0.01) in the 56 European countries/areas. This study illustrated that COVID-19 mortality was positively associated with ageing population, median age, and life expectancy at birth.