Pulmonary and Renal Long COVID at Two-year Revisit (preprint)

More than 450 million individuals have recovered from COVID-19, but little is known about the host responses to long COVID. We performed proteomic and metabolomic analyses of 991 blood and urine specimens from 144 COVID-19 patients with comprehensive clinical data and up to 763 days of follow up. Our data showed that the lungs and kidneys are the most vulnerable organs in long COVID patients. Pulmonary and renal long COVID of one-year revisit can be predicted by a machine learning model based on clinical and multi-omics data collected during the first month from the disease onset with an ACC of 87.5%. Serum protein SFTPB and ATR were associated with pulmonary long COVID and might be potential therapeutic targets. Notably, our data show that all the patients with persistent pulmonary ground glass opacity or patchy opacity lesions developed into pulmonary fibrosis at two-year revisit. Together, this study depicts the longitudinal clinical and molecular landscape of COVID-19 with up to two-year follow-up and presents a method to predict pulmonary and renal long COVID.

Distribution of ABO Blood Groups and Their Association With Low Risk of Severe COVID-19 Infection in Patients (preprint)

Background: To date, only few studies have focused on the correlation between ABO blood groups and COVID-19 infection risk, especially gender differences in infection risk. Our study aimed to describe the ABO blood group distribution and its association with risk of severe COVID-19 infection for effective identification of the susceptible population. Method：From January 21 to February 20, 2020, we compared the ABO blood group distribution and gender distribution and performed a correlation analysis in severe, non-severe, and non-COVID-19 patients. Results The results showed that the laboratory indices were significantly different between blood type O and non-blood-type-O COVID-19 patients. This indicated that patients of the type O blood group had a relatively lower risk of severe COVID-19 infection than patients of other blood types; in particular, females with blood type O had a lower risk of severe COVID-19 infection than males. Conclusion: Herein, we report a potentially simple prediction decision system to minimize the risk of severe COVID-19 infection based on blood type. Special attention should be paid to patients with blood types other than type O to minimize their risk of severe COVID-19 infection.

Eleven Routine Clinical Features Predict COVID-19 Severity Uncovered by Machine Learning of Longitudinal Measurements (preprint)

Background: Severity prediction of COVID-19 remains one of the major clinical challenges for the ongoing pandemic. In this study, we aim to establish a model for COVID-19 severity prediction and depict dynamic changes of key clinical features over 7 weeks.Methods: In our retrospective study, a total of 841 patients have been screened with the SARS-CoV-2 nucleic acid test, of which 144 patients were virus RNA (COVID-19) positive, resulting in a data matrix containing of 3,065 readings for 124 types of measurements from 17 categories. We built a support vector machine model assisted with genetic algorithm for feature selection based on the longitudinal measurement. 25 patients as a test cohort were included from an independent hospital.Findings: A panel of 11 routine clinical factors constructed a classifier for COVID-19 severity prediction, achieving an accuracy of over 94%. Validation of the model in an independent cohort containing 25 patients achieved an accuracy of 80%. The overall sensitivity, specificity, PPV and NPV were 0.70, 0.99, 0.93 and 0.93, respectively. This study presents a practical model for timely severity prediction for COVID-19, which is freely available at a webserver https://guomics.shinyapps.io/covidAI/.Interpretation: The model provided a classifier composed of 11 routine clinical features which are widely available during COVID-19 management which could predict the severity and may guide the medical care of COVID-19 patients.Funding: This work is supported by grants from Tencent Foundation (2020), National Natural Science Foundation of China (81972492, 21904107, 81672086), Zhejiang Provincial Natural Science Foundation for Distinguished Young Scholars (LR19C050001), Hangzhou Agriculture and Society Advancement Program (20190101A04).Declaration of Interests: NAEthics Approval Statement: This study was approved by the Medical Ethics Committee of Taizhou Hospital, Shaoxing People’s Hospital and Westlake University, Zhejiang province of China, and informed consent was obtained from each enrolled subject.

Eleven Routine Clinical Features Predict COVID-19 Severity (preprint)

Severity prediction of COVID-19 remains one of the major clinical challenges for the ongoing pandemic. Here, we have recruited a 144 COVID-19 patient cohort consisting of training, validation, and internal test sets, longitudinally recorded 124 routine clinical and laboratory parameters, and built a machine learning model to predict the disease progression based on measurements from the first 12 days since the disease onset when no patient became severe. A panel of 11 routine clinical factors, including oxygenation index, basophil counts, aspartate aminotransferase, gender, magnesium, gamma glutamyl transpeptidase, platelet counts, activated partial thromboplastin time, oxygen saturation, body temperature and days after symptom onset, constructed a classifier for COVID-19 severity prediction, achieving accuracy of over 94%. Validation of the model in an independent cohort containing 25 patients achieved accuracy of 80%. The overall sensitivity, specificity, PPV and NPV were 0.70, 0.99, 0.93 and 0.93, respectively. Our model captured predictive dynamics of LDH and CK while their levels were in the normal range. This study presents a practical model for timely severity prediction and surveillance for COVID-19, which is freely available at webserver https://guomics.shinyapps.io/covidAI/.

Distribution of ABO blood groups and association to low risk of COVID-19 infection in patients (preprint)

Background Since December 2019, the novel coronavirus pandemic (COVID-19) has become a global health emergency. To date, studies on the correlation between ABO blood groups and COVID-19 infected risk had rarely reported. This study aimed to describe the ABO blood groups distribution and association to low risk of COVID-19 infection for effectively concerning about the susceptible population.Methods We included 138 COVID-19 diagnosed patients and 82 non- COVID-19 patients between January 21 and February 20, 2020.We compared ABO blood group distribution, gender distribution and correlation analysis in Severe, Non-severe and Non-COVID19 patients, and analyzed the laboratory indexes of type O and non-type O groups in COVID19 patients.Results The laboratory results were significantly difference between type O and non-type O COVID19 patients (P < 0.05). Patients with blood type O had lower risk of severe COVID-19 infection (χ2 = 4.066, p = 0.044, OR = 0.380), and especially, female with the type O blood had lower risk in deteriorating severe COVID19 infection (p = 0.049).Conclusion Patients with the blood group of type O had relatively lower risk of COVID19 infection, especially, female with the type O blood had lower risk in deteriorating severe COVID19 infection. We should concern more to the patients with non-type O blood to minimize the risk of COVID19 infection.