Demystifying COVID-19 Mortality Causes with Interpretable Data Mining (preprint)

While SARS-CoV-2 infection rates are declining, older adults remain vulnerable to severe disease with high mortality. Although there have been some studies on revealing different risk factors affecting the death of COVID-19 patients, such as bilirubin, organ failure, patient age, and underlying disease, they fail to provide a comprehensive analysis to reveal their relationships and interactive effects on the risk of death. Based on the demographic information, inspection indicators, and underlying diseases of 1917 patients (102 were dead) admitted to Xiangya Hospital over a 4-month period, we used the association rule mining method to identify the risk factors leading causes of death among elderly Omicron patients. Firstly, we used the Affinity Propagation clustering to extract key features such as blood parameters, liver function indicators, renal function indicators, coagulation function indicators, and underlying diseases affecting death from the dataset. Then, we applied the Apriori to obtain 7 groups of abnormal feature combinations with significant increments in mortality rate. The results showed a relationship between the number of abnormal feature combinations and mortality rates within different groups. For instance, patients with “C-reactive protein > 8 mg/L”, “neutrophils percentage > 75.0 %”, “lymphocytes percentage < 20 %”, and “albumin < 40 g/L” have a 2x mortality rate than the basic one. If the characteristics of “D-dimer > 0.5 mg/L” and “WBC > 9.5 * 10 9 /L” are continuously included in this foundation, the mortality rate can be increased to 3x or 4x. In addition, we also found that liver and kidney diseases significantly affect patient mortality. Given patients with liver and renal diseases associated with other abnormal features, their mortality rate can be as high as 100 %. These findings can support auxiliary diagnosis and treatment to, facilitate early intervention in patients, thereby reducing patient mortality.

A model based on CT radiomic features for predicting RT-PCR becoming negative in coronavirus disease 2019 (COVID-19) patients (preprint)

Background: Coronavirus disease 2019 (COVID-19) has emerged as a global pandemic. According to the diagnosis and treatment guidelines of China, negative reverse transcription-polymerase chain reaction (RT-PCR) is the key criterion for discharging COVID-19 patients. However, repeated RT-PCR tests lead to medical waste and prolonged hospital stays for COVID-19 patients during the recovery period. Our purpose is to assess a model based on chest computed tomography (CT) radiomic features and clinical characteristics to predict RT-PCR negativity during clinical treatment. Methods: : From February 10 to March 10, 2020, 203 mild COVID-19 patients in Fangcang Shelter Hospital were retrospectively included (training: n=141; testing: n=62), and clinical characteristics were collected. Lung abnormalities on chest CT images were segmented with a deep learning algorithm. CT quantitative features and radiomic features were automatically extracted. Clinical characteristics and CT quantitative features were compared between RT-PCR-negative and RT-PCR-positive groups. Univariate logistic regression and Spearman correlation analyses identified the strongest features associated with RT-PCR negativity, and a multivariate logistic regression model was established. The diagnostic performance was evaluated for both cohorts. Results: : The RT-PCR-negative group had a longer time interval from symptom onset to CT exams than the RT-PCR-positive group (median 23 vs. 16 days, p<0.001). There was no significant difference in the other clinical characteristics or CT quantitative features. In addition to the time interval from symptom onset to CT exams, nine CT radiomic features were selected for the model. ROC curve analysis revealed AUCs of 0.811 and 0.812 for differentiating the RT-PCR-negative group, with sensitivity/specificity of 0.765/0.625 and 0.784/0.600 in the training and testing datasets, respectively. Conclusion: The model combining CT radiomic features and clinical data helped predict RT-PCR negativity during clinical treatment, indicating the proper time for RT-PCR retesting.

Influencing factors of virus duration and virus clearance in COVID-19 patients in Shenzhen: A retrospective study. (preprint)

Abstract Background. We aimed to analyze the influencing factors of virus duration and virus clearance in coronavirus disease 2019 (COVID-19) in Shenzhen, China, and to provide our experience in the treatment and management of COVID-19. Methods. The clinical data and laboratory test results of COVID-19 inpatients admitted to the Third People's Hospital of Shenzhen, Guangdong Province from January 2020 to March 2020 were retrospectively collected. In COVID-19 rehabilitation patients, two consecutive negative RT-PCR results on nasopharyngeal swabs were defined as virus clearance. The time from onset of the disease to virus clearance was defined as the virus duration. We analyzed the virus clearance rate at different time points and the impact of clinical features and treatments on virus clearance. Results. A total of 201 patients with COVID-19, including 89 women (44.3%) and 112 men (55.7%), were included in our study. According to the severity of the disease, the patients were divided into no severe patients and severe patients. The overall median virus duration for all patients was 17 days. The overall virus clearance rates within 1, 2, 3, 4, 5, and 6 weeks after onset were 1.5%, 36.6%, 73.4%, 90.2%, 97.3%, and 100%, respectively. A multiple linear regression model was performed to analyze the factors influencing virus clearanc.The factors influencing virus clearance within 2 weeks were treatment timing and glucocorticoid usage. The influencing factors for virus clearance within 4 weeks were treatment timing, glucocorticoid usage and age. Conclusion. Treatment timing was related to virus clearance. The earlier the treatment was initiated, the faster the virus clearance. For COVID-19 patients, early detection and early treatment strategies should be adopted. Glucocorticoid usage may be detrimental to virus clearance and should be more restricted. Age > 60 years may also be a detrimental factor for virus clearance.

Raising Concern About Cross-Infection Between Humans and Companion Animals by Evolutionary Analysis of Receptors for SARS-CoV-2 (preprint)

Since the COVID-19 caused by SARS-CoV-2 break out in Wuhan China from Dec. 2019, it has spread to hundreds of countries up to now. Scientists from all over the world have paid tremendous efforts to research and try to control the disease. Previous studies suggested that some of the wild animals could be intermediate hosts between humans and origination of SARS-CoV-2, and some companion animals of humans can be infected by SARS-CoV-2, which raised our curiosity about cross-infection of SARS-CoV-2 between animals and humans. Thus, we select some kinds of animals that might have contact with humans to estimate the susceptibility to SARS-CoV-2 in different animals by evolutionary analysis of their receptors for SARS-CoV-2. The results show that some companion animals of the Felidae family like the cat has a higher infection possibility while the species of the Rodent family like the rat and mouse having close contact with humans show an opposite result, which consist with recent animal experiments and researches. These should raise concerns about cross-infection between human and companion animals or animals having close contact with humans which might turn animals into depositaries of the coronavirus even after control of SARS-CoV-2 spreading and cause second or more waves of infections after social reopening. Another side of our results stands by the opinion that bioinformatic analysis can be consistent with experiments in some respects so that we can prevent unnecessary sacrifice of laboratory animals in future experiments.

Epidemiological investigation and intergenerational clinical characteristics of 24 COVID-19 patients associated with supermarket cluster (preprint)

Objective: To analyze the epidemiological and intergenerational clinical characteristics of COVID-19 patients associated with cluster, so as to understand the rules of the patients associated with cluster of this outbreak and provide help for the prevention and control of COVID-19. Methods: All close contacts of the patient were screened since the first supermarket employee with COVID-19 was identified. A retrospective analysis was made on the epidemiological and clinical characteristics of the confirmed cases admitted to the designated hospitals for centralized treatment. The patients were divided into two groups according to the first generation (supermarket employees, group A) and the second or third generation (family members or friends of supermarket employees, group B), and the similarities and differences between the two groups were compared. Results: A total of 24 COVID-19 patients were diagnosed, with an average age of 48{+/-}1.73 years. The mean duration from onset to release form quarantine was 21.04{+/-}6.77 days, and the onset time was concentrated in 5-11 days after the first patient was diagnosed. Among all the patients, 23 patients were moderate, among which 7 patients (29.17%) were asymptomatic. Symptoms of symptomatic patients were cough (75.00%), low fever (62.50%), shortness of breath (41.67%), sore throat (25.00%), gastrointestinal symptoms (25.00%), fatigue (20.83%), etc. Biochemical examination on admission showed that the white blood cell count < 4.010x9/L (29.17%) and the lymphocyte count <1.1x109/L (58.33%). The lymphocyte count of 50.00% of the patients was [≤]0.6x109/L. On admission, chest CT showed pneumonia (100%) with bilateral infiltration (75.00%). Treatment: antiviral drug (100%), Chinese medicine (100%), common oxygen therapy (45.83%). There were 11 cases in group A (first generation, 11 cases) and 13 cases in group B (second generation, 11 cases; third generation, 2 cases). In group B, there were more males, from onset to admission later, more patients had underlying diseases, and more patients were treated with albumin (P<0.05). However, there was no statistical difference between the two groups in other clinical indicators, including the duration from onset to release form quarantine(P>0.05). There was no improvement in granulocyte count in all patients, as well as in groups A and B, between admission and release from quarantine(P>0.05). Conclusion: The clinical characteristics of COVID-19 patients associated with cluster were similar to those of other COVID-19 patients, but there were some special features. The severity of the disease was similar and there was intergenerational spread. There was no difference in clinical characteristics between generations. Asymptomatic infections occurred in a proportion of patients and could cause spread.

CT features and artificial intelligence quantitative analysis of recovered COVID-19 patients with negative RT-PCR and clinical symptoms (preprint)

Objectives: To evaluate imaging features and performed quantitative analysis for mild novel coronavirus pneumonia (COVID-19) cases ready for discharge.Methods: CT images of 125 patients (16-67 years, 63 males) recovering from COVID-19 were examined. We defined the double-negative period (DNp) as the period between the sampling days of two consecutive negative RT-PCR and three days thereafter. Lesion demonstrations and distributions on CT in DNp (CTDN) were evaluated by radiologists and artificial intelligence (AI) software. Major lesion transformations and the involvement range for patients with follow-up CT were analyzed.Results: Twenty (16.0%) patients exhibited normal CTDN; abnormal CTDN for 105 indicated ground-glass opacity (GGO) (99/125, 79.2%) and fibrosis (56/125, 44.8%) as the most frequent CT findings. Bilateral-lung involvement with mixed or random distribution was most common for GGO on CTDN. Fibrous lesions often affected both lungs, tending to distribute on the subpleura. Follow-up CT showed lesion improvement manifesting as GGO thinning (40/40, 100%), fibrosis reduction (17/26, 65.4%), and consolidation fading (9/11, 81.8%), with or without range reduction. AI analysis showed the highest proportions for right lower lobe involvement (volume, 12.01±35.87cm3; percentage; 1.45±4.58%) and CT-value ranging –570 to –470 HU (volume, 2.93±7.04cm3; percentage, 5.28±6.47%). Among cases with follow-up CT, most of lung lobes and CT-value ranges displayed a significant reduction after DNp.Conclusions: The main CT imaging manifestations were GGO and fibrosis in DNp, which weakened with or without volume reduction. AI analysis results were consistent with imaging features and changes, possibly serving as an objective indicator for disease monitoring and discharge.