Non-contact screening system based for COVID-19 on XGBoost and logistic regression.

BACKGROUND: The coronavirus disease (COVID-19) effected a global health crisis in 2019, 2020, and beyond. Currently, methods such as temperature detection, clinical manifestations, and nucleic acid testing are used to comprehensively determine whether patients are infected with the severe acute respiratory syndrome coronavirus 2. However, during the peak period of COVID-19 outbreaks and in underdeveloped regions, medical staff and high-tech detection equipment were limited, resulting in the continued spread of the disease. Thus, a more portable, cost-effective, and automated auxiliary screening method is necessary. OBJECTIVE: We aim to apply a machine learning algorithm and non-contact monitoring system to automatically screen potential COVID-19 patients. METHODS: We used impulse-radio ultra-wideband radar to detect respiration, heart rate, body movement, sleep quality, and various other physiological indicators. We collected 140 radar monitoring data from 23 COVID-19 patients in Wuhan Tongji Hospital and compared them with 144 radar monitoring data from healthy controls. Then, the XGBoost and logistic regression (XGBoost + LR) algorithms were used to classify the data according to patients and healthy subjects. RESULTS: The XGBoost + LR algorithm demonstrated excellent discrimination (precision = 92.5%, recall rate = 96.8%, AUC = 98.0%), outperforming other single machine learning algorithms. Furthermore, the SHAP value indicates that the number of apneas during REM, mean heart rate, and some sleep parameters are important features for classification. CONCLUSION: The XGBoost + LR-based screening system can accurately predict COVID-19 patients and can be applied in hotels, nursing homes, wards, and other crowded locations to effectively help medical staff.

Detecting SARS-CoV-2 in the Breath of COVID-19 Patients.

In the COVID-19 outbreak year 2020, a consensus was reached on the fact that SARS-CoV-2 spreads through aerosols. However, finding an efficient method to detect viruses in aerosols to monitor the risk of similar infections and enact effective control remains a great challenge. Our study aimed to build a swirling aerosol collection (SAC) device to collect viral particles in exhaled breath and subsequently detect SARS-CoV-2 using reverse transcription polymerase chain reaction (RT-PCR). Laboratory tests of the SAC device using aerosolized SARS-CoV-2 pseudovirus indicated that the SAC device can produce a positive result in only 10 s, with a collection distance to the source of 10 cm in a biosafety chamber, when the release rate of the pseudovirus source was 1,000,000 copies/h. Subsequent clinical trials of the device showed three positives and 14 negatives out of 27 patients in agreement with pharyngeal swabs, and 10 patients obtained opposite results, while no positive results were found in a healthy control group (n = 12). Based on standard curve calibration, several thousand viruses per minute were observed in the tested exhalations. Furthermore, referring to the average tidal volume data of adults, it was estimated that an exhaled SARS-CoV-2 concentration of approximately one copy/mL is detectable for COVID-19 patients. This study validates the original concept of breath detection of SARS-CoV-2 using SAC combined with RT-PCR.

Multicenter investigation of current status of use of personal protective equipment among healthcare workers during diagnosis and treatment of COVID-19

OBJECTIVE: To investigate the use of personal protective equipment (PPE) of healthcare workers (HCWs) in the room where confirmed COVID-19 patients are admitted and understand the current status of prevention. METHODS: The healthcare workers who from medical aid teams in Hubei in 30 hospitals were randomly selected by the trained staff for hospital infection prevention, the basic characteristics of the enrolled subjects and the use of PPE were recorded, and the questionnaires were filled out through questionnaire star. RESULTS: The survey found that all the healthcare workers received theoretical training and practical training on the use of PPE before entering the isolation ward, 95.56% (2 433) of them were inspected or supervised by someone when they put on or took off PPE. 86.57% (2 204) of the healthcare workers wore two layers of masks at the same time, most of whom (1621, 63.67%) wore medical surgical mask and respirator at the same time. 57.50% (1 464) of the healthcare workers used goggles or face shield, 42.50% (1 082) of whom used goggles and face shield at the same time. 95.25% (2 425) of the healthcare workers wore coverall and disposable gown at the same time. 96.62% (2 460) of the healthcare workers wore boot covers and shoe covers at the same time. The proportion of the healthcare workers who wore two-layer hats was the highest (70.54%), and the proportion of the healthcare workers who wore two-layer gloves was also the highest (57.31%). CONCLUSION The use of PPE of the HCWs who are from the medical aid teams has effectively prevented the COVID-19 infection, achieving a 'zero infection' among the 42.6 thousand HCWs. However, there are excessive use of PPE, and the rational use of PPE needs to be further standardized and explored.

Identify the Risk Factors of COVID-19-Related Acute Kidney Injury: A Single-Center, Retrospective Cohort Study.

Background: The kidney is a target organ that could be infected by SARS-CoV-2, and acute kidney injury (AKI) was associated with a higher risk of COVID-19 patients' in-hospital death. However, no published works discussed about the risk factors of COVID-19 related AKI. Methods: We conducted a retrospective cohort study, recruiting COVID-19 inpatients from the Sino-French branch of Tongji Hospital. Demographic, clinical, treatment, and laboratory data were collected and compared. We used univariable and multivariable logistic regression methods to identify the risk factors of COVID-19-related AKI. Results: Of the 116 patients in our study, 12 (10.3%) were recognized as AKI, including 5 (4.3%) in-hospital AKI. Multivariable regression showed increasing odds of COVID-19-related AKI associated with COVID-19 clinical classification (OR = 8.155, 95% CI = 1.848-35.983, ref = non-critical, p = 0.06), procalcitonin more than 0.1 ng/mL (OR = 4.822, 95% CI = 1.095-21.228, p = 0.037), and estimated glomerular filtration rate (eGFR) <60 mL/min/1.73 m2 (OR = 13.451, 95% CI = 1.617-111.891, p = 0.016). Conclusions: COVID-19-related AKI was likely to be related to multiorgan failure rather than the kidney tropism of SARS-CoV-2. The potential risk factors of COVID-19 clinical classification, procalcitonin more than 0.1 ng/mL, and eGFR <60 mL/min/1.73 m2 could help clinicians to identify patients with kidney injury at an early stage.