Artificial intelligence model on chest imaging to diagnose COVID-19 and other pneumonias: A systematic review and meta-analysis.

Objectives: When diagnosing Coronavirus disease 2019(COVID-19), radiologists cannot make an accurate judgments because the image characteristics of COVID-19 and other pneumonia are similar. As machine learning advances, artificial intelligence(AI) models show promise in diagnosing COVID-19 and other pneumonias. We performed a systematic review and meta-analysis to assess the diagnostic accuracy and methodological quality of the models. Methods: We searched PubMed, Cochrane Library, Web of Science, and Embase, preprints from medRxiv and bioRxiv to locate studies published before December 2021, with no language restrictions. And a quality assessment (QUADAS-2), Radiomics Quality Score (RQS) tools and CLAIM checklist were used to assess the quality of each study. We used random-effects models to calculate pooled sensitivity and specificity, I2 values to assess heterogeneity, and Deeks' test to assess publication bias. Results: We screened 32 studies from the 2001 retrieved articles for inclusion in the meta-analysis. We included 6737 participants in the test or validation group. The meta-analysis revealed that AI models based on chest imaging distinguishes COVID-19 from other pneumonias: pooled area under the curve (AUC) 0.96 (95 % CI, 0.94-0.98), sensitivity 0.92 (95 % CI, 0.88-0.94), pooled specificity 0.91 (95 % CI, 0.87-0.93). The average RQS score of 13 studies using radiomics was 7.8, accounting for 22 % of the total score. The 19 studies using deep learning methods had an average CLAIM score of 20, slightly less than half (48.24 %) the ideal score of 42.00. Conclusions: The AI model for chest imaging could well diagnose COVID-19 and other pneumonias. However, it has not been implemented as a clinical decision-making tool. Future researchers should pay more attention to the quality of research methodology and further improve the generalizability of the developed predictive models.

Pediococcus acidilactici CCFM6432 mitigates chronic stress-induced anxiety and gut microbial abnormalities.

The discovery of psychobiotics has improved the therapeutic choices available for clinical mental disorders and shows promise for regulating mental health in people by combining the properties of food and medicine. A Pediococcus acidilactici strain CCFM6432 was previously isolated and its mood-regulating effect was investigated in this study. Viable bacteria were given to chronically stressed mice for five weeks, and then the behavioral, neurobiological, and gut microbial changes were determined. CCFM6432 significantly reduced stress-induced anxiety-like behaviors, mitigated hypothalamic-pituitary-adrenal (HPA) axis hyperactivity, and reversed the abnormal expression of hippocampal phosphorylated CREB and the c-Fos protein. In particular, CCFM6432 improved the gut microbial composition by inhibiting the over-proliferated pathogenic bacteria (e.g., Escherichia-shigella) and promoting beneficial bacteria growth (e.g., Bifidobacterium). Lactic acid, rather than bacteriocin, was further confirmed as the key compound that determined the antimicrobial activity of CCFM6432. Collectively, these results first proved the psychobiotic potential of the Pediococcus acidilactici strain. Ingestion of CCFM6432, or fermented food containing it, may facilitate mental health management in daily life, especially during the COVID-19 pandemic.

The Potential Role of Probiotics in Protection against Influenza a Virus Infection in Mice.

Influenza A virus induces severe respiratory tract infection and results in a serious global health problem. Influenza infection disturbs the cross-talk connection between lung and gut. Probiotic treatment can inhibit influenza virus infection; however, the mechanism remains to be explored. The mice received Lactobacillus mucosae 1025, Bifidobacterium breve CCFM1026, and their mixture MIX for 19 days. Effects of probiotics on clinical symptoms, immune responses, and gut microbial alteration were evaluated. L. mucosae 1025 and MIX significantly reduced the loss of body weight, pathological symptoms, and viral loading. B. breve CCFM1026 significantly reduced the proportion of neutrophils and increased lymphocytes, the expressions of TLR7, MyD88, TRAF6, and TNF-α to restore the immune disorders. MIX increased the antiviral protein MxA expression, the relative abundances of Lactobacillus, Mucispirillum, Adlercreutzia, Bifidobacterium, and further regulated SCFA metabolism resulting in an enhancement of butyrate. The correlation analysis revealed that the butyrate was positively related to MxA expression (p < 0.001) but was negatively related to viral loading (p < 0.05). The results implied the possible antiviral mechanisms that MIX decreased viral loading and increased the antiviral protein MxA expression, which was closely associated with the increased butyrate production resulting from gut microbial alteration.

Cancer associates with risk and severe events of COVID-19: A systematic review and meta-analysis.

Evidence is mounting to indicate that cancer patients may have more likelihood of having coronavirus disease 2019 (COVID-19) but lack consistency. A robust estimate is urgently needed to convey appropriate information to the society and the public, in the time of ongoing COVID-19 pandemic. We performed a systematic review and meta-analysis through a comprehensive literature search in major databases in English and Chinese, and two investigators conducted publication selection and data extraction independently. A meta-analysis was used to obtain estimates of pooled prevalence of cancer in patients with COVID-19 and determine the association of cancer with severe events, after assessment of potential heterogeneity, publication bias, and correction for the estimates when necessary. Total 38 studies comprising 7094 patients with COVID-9 were included; the pooled prevalence of cancer was estimated at 2.3% (95% confidence limit [CL] [0.018, 0.029]; P < .001) overall and 3.2% (95% CL [0.023, 0.041]; P < .001) in Hubei province; the corresponding estimates were 1.4% and 1.9% after correction for publication bias; cancer was significantly associated with the events of severe cases (odds ratio [OR] = 2.20, 95% CL [1.53, 3.17]; P < .001) and death (OR = 2.97, 95% CL [1.48, 5.96]; P = .002) in patients with COVID-19, there was no significant heterogeneity and a minimal publication bias. We conclude that cancer comorbidity is associated with the risk and severe events of COVID-19; special measures should be taken for individuals with cancer.