Qi-Dong-Huo-Xue-Yin balances the immune microenvironment to protect against LPS induced acute lung injury.

COVID-19 induces acute lung injury (ALI)/acute respiratory distress syndrome (ARDS) and leads to severe immunological changes that threatens the lives of COVID-19 victims. Studies have shown that both the regulatory T cells and macrophages were deranged in COVID-19-induced ALI. Herbal drugs have long been utilized to adjust the immune microenvironment in ALI. However, the underlying mechanisms of herbal drug mediated ALI protection are largely unknown. This study aims to understand the cellular mechanism of a traditional Chinese medicine, Qi-Dong-Huo-Xue-Yin (QD), in protecting against LPS induced acute lung injury in mouse models. Our data showed that QD intrinsically promotes Foxp3 transcription via promoting acetylation of the Foxp3 promoter in CD4+ T cells and consequently facilitates CD4+CD25+Foxp3+ Tregs development. Extrinsically, QD stabilized ß-catenin in macrophages to expedite CD4+CD25+Foxp3+ Tregs development and modulated peripheral blood cytokines. Taken together, our results illustrate that QD promotes CD4+CD25+Foxp3+ Tregs development via intrinsic and extrinsic pathways and balanced cytokines within the lungs to protect against LPS induced ALI. This study suggests a potential application of QD in ALI related diseases.

Erratum: Inhaled ACE2-engineered microfluidic microsphere for intratracheal neutralization of COVID-19 and calming of the cytokine storm.

[This corrects the article DOI: 10.1016/j.matt.2021.09.022.].

Enhancing thoracic disease detection using chest X-rays from PubMed Central Open Access.

Large chest X-rays (CXR) datasets have been collected to train deep learning models to detect thorax pathology on CXR. However, most CXR datasets are from single-center studies and the collected pathologies are often imbalanced. The aim of this study was to automatically construct a public, weakly-labeled CXR database from articles in PubMed Central Open Access (PMC-OA) and to assess model performance on CXR pathology classification by using this database as additional training data. Our framework includes text extraction, CXR pathology verification, subfigure separation, and image modality classification. We have extensively validated the utility of the automatically generated image database on thoracic disease detection tasks, including Hernia, Lung Lesion, Pneumonia, and pneumothorax. We pick these diseases due to their historically poor performance in existing datasets: the NIH-CXR dataset (112,120 CXR) and the MIMIC-CXR dataset (243,324 CXR). We find that classifiers fine-tuned with additional PMC-CXR extracted by the proposed framework consistently and significantly achieved better performance than those without (e.g., Hernia: 0.9335 vs 0.9154; Lung Lesion: 0.7394 vs. 0.7207; Pneumonia: 0.7074 vs. 0.6709; Pneumothorax 0.8185 vs. 0.7517, all in AUC with p< 0.0001) for CXR pathology detection. In contrast to previous approaches that manually submit the medical images to the repository, our framework can automatically collect figures and their accompanied figure legends. Compared to previous studies, the proposed framework improved subfigure segmentation and incorporates our advanced self-developed NLP technique for CXR pathology verification. We hope it complements existing resources and improves our ability to make biomedical image data findable, accessible, interoperable, and reusable.

Linear Regression Analysis of Sleep Quality in People with Insomnia in Wuhan City during the COVID-19 Pandemic.

Objective: COVID-19 has evolved into a major global public health event. The number of people reporting insomnia is growing exponentially during the pandemic. This study aimed to explore the relationship between aggravated insomnia and COVID-19-induced psychological impact on the public, lifestyle changes, and anxiety about the future. Methods: In this cross-sectional study, we used the questionnaires from 400 subjects who were obtained from the Department of Encephalopathy of the Wuhan Hospital of Traditional Chinese Medicine between July 2020 and July 2021. The data collected for the study included demographic characteristics of the participants and psychological scales consisting of the Spiegel Sleep Questionnaire, the Fear of COVID-19 Scale (FCV-19S), the Zung Self-Rating Anxiety Scale (SAS), and the Zung Self-Rating Depression Scale (SDS). The independent sample t-test and one-way ANOVA were used to compare the results. Correlation analysis of variables affecting insomnia was performed using Pearson correlation analysis. The degree of influence of the variables on insomnia was determined using linear regression, and a regression equation was derived. Results: A total of 400 insomnia patients participated in the survey. The median age was 45.75 ± 15.04 years. The average score of the Spiegel Sleep Questionnaire was 17.29 ± 6.36, that of SAS was 52.47 ± 10.39, that of SDS was 65.89 ± 8.72, and that of FCV-19S was 16.09 ± 6.81. The scores of FCV-19S, SAS, and SDS were closely related to insomnia, and the influencing degree was in the following order: fear, depression, and anxiety (OR = 1.30, 0.709, and 0.63, respectively). Conclusion: Fear of COVID-19 can be one of the primary contributors to worsening insomnia.

COVID-19 epidemic phases and morbidity in different areas of Chinese mainland, 2020.

Background: In the early stage of COVID-19 epidemic, the Chinese mainland once effectively controlled the epidemic, but COVID-19 eventually spread faster and faster in the world. The purpose of this study is to clarify the differences in the epidemic data of COVID-19 in different areas and phases in Chinese mainland in 2020, and to analyze the possible factors affecting the occurrence and development of the epidemic. Methods: We divided the Chinese mainland into areas I, I and III, and divided the epidemic process into phases I to IV: limited cases, accelerated increase, decelerated increase and containment phases. We also combined phases II and III as outbreak phase. The epidemic data included the duration of different phases, the numbers of confirmed cases, asymptomatic infections, and the proportion of imported cases from abroad. Results: In area I, II and III, only area I has a Phase I, and the Phase II and III of area I are longer. In Phase IV, there is a 17-day case clearing period in area I, while that in area II and III are 2 and 0 days, respectively. In phase III or the whole outbreak phase, the average daily increase of confirmed cases in area I was higher than that in areas II and III (P = 0.009 and P = 0.001 in phase III; P = 0.034 and P = 0.002 in the whole outbreak phase), and the average daily in-hospital cases were most in area I and least in area III (P = 0.000, P = 0.000, and P = 0.000 in phase III; P = 0.000, P = 0.000, and P = 0.009 in the whole outbreak phase). The average number of daily in-hospital COVID-19 cases in phase III was more than that in phase II in each area (P = 0.000, P = 0.000, and P = 0.001). In phase IV, from March 18, 2020 to January 1, 2021, the increase of confirmed cases in area III was higher than areas I and II (both P = 0.000), and the imported cases from abroad in Chinese mainland accounted for more than 55-61%. From June 16 to July 2, 2020, the number of new asymptomatic infections in area III was higher than that in area II (P = 0.000), while there was zero in area I. From July 3, 2020 to January 1, 2021, the increased COVID-19 cases in area III were 3534, while only 14 and 0, respectively, in areas I and II. Conclusions: The worst epidemic areas in Chinese mainland before March 18, 2020 and after June 15, 2020 were area I and area III, respectively, and area III had become the main battlefield for Chinese mainland to fight against imported epidemic since March 18, 2020. In Wuhan, human COVID-19 infection might occur before December 8, 2019, while the outbreak might occur before January 16 or even 10, 2020. Insufficient understanding of COVID-19 hindered the implementation of early effective isolation measures, leading to COVID-19 outbreak in Wuhan, and strict isolation measures were effective in controlling the epidemic. The import of foreign COVID-19 cases has made it difficult to control the epidemic of area III. When humans are once again faced with potentially infectious new diseases, it is appropriate to first and foremost take strict quarantine measures as soon as possible, and mutual cooperation between regions should be explored to combat the epidemic.

Data-driven analysis to understand long COVID using electronic health records from the RECOVER initiative.

Recent studies have investigated post-acute sequelae of SARS-CoV-2 infection (PASC, or long COVID) using real-world patient data such as electronic health records (EHR). Prior studies have typically been conducted on patient cohorts with specific patient populations which makes their generalizability unclear. This study aims to characterize PASC using the EHR data warehouses from two large Patient-Centered Clinical Research Networks (PCORnet), INSIGHT and OneFlorida+, which include 11 million patients in New York City (NYC) area and 16.8 million patients in Florida respectively. With a high-throughput screening pipeline based on propensity score and inverse probability of treatment weighting, we identified a broad list of diagnoses and medications which exhibited significantly higher incidence risk for patients 30-180 days after the laboratory-confirmed SARS-CoV-2 infection compared to non-infected patients. We identified more PASC diagnoses in NYC than in Florida regarding our screening criteria, and conditions including dementia, hair loss, pressure ulcers, pulmonary fibrosis, dyspnea, pulmonary embolism, chest pain, abnormal heartbeat, malaise, and fatigue, were replicated across both cohorts. Our analyses highlight potentially heterogeneous risks of PASC in different populations.

An Agenda-Setting Account for Psychological Typhoon Eye Effect on Responses to the Outbreak of COVID-19 in Wuhan

During the outbreak of COVID-19 in Wuhan in 2020, we conducted a nationwide survey of 8170 respondents from 31 provinces/municipalities in China via Sojump to examine the relationship between the distance to respondents' city of residence from Wuhan and their safety concerns and risk perception of the epidemic that occurred in Wuhan City. We found that (1) the farther (psychologically or physically) people were from Wuhan, the more concerned they were with the safety of the epidemic risk in Wuhan, which we dubbed the psychological typhoon eye (PTE) effect on responses to the outbreak of COVID-19;(2) agenda setting can provide a principled account for such effect: the risk information proportion mediated the PTE effect. The theoretical and managerial implications for the PTE effect and public opinion disposal were discussed, and agenda setting was identified to be responsible for the preventable overestimated risk perception.

Can google glass™ technology improve freezing of gait in parkinsonism? A pilot study.

PURPOSE: Freezing of gait (FOG) is a disabling phenomenon defined by the periodic absence or reduction of forward progression of the feet despite the intention to walk. We sought to understand whether Google Glass (GG), a lightweight wearable device that provides simultaneous visual-auditory cues, might improve FOG in parkinsonism. METHODS: Patients with parkinsonism and FOG utilized GG custom-made auditory-visual cue applications: "Walk With Me" and "Unfreeze Me" in a single session intervention. We recorded ambulation time with and without GG under multiple conditions including 25 feet straight walk, dual task of performing serial 7's while straight walking, 180 degree turn after walking 25 feet, and walking through a doorway. FOG and patient experience questionnaires were administered. RESULTS: Using the GG "Walk With Me" program, improvements were noted in the following: average 25 feet straight walk by 0.32 s (SD 2.12); average dual task of serial 7's and 25 feet straight walk by 1.79 s (SD 2.91); and average walk through doorway by 0.59 s (SD 0.81). Average 180 degree turn after 25 feet walk worsened by 1.89 s (SD 10.66). Using the "Unfreeze Me" program, only the average dual task of serial 7's and 25 feet straight walk improved (better by 0.82 s (SD 3.08 sec). All other tasks had worse performance in terms of speed of completion. CONCLUSION: This feasibility study provides preliminary data suggesting that some walking tasks may improve with GG, which uses various musical dance programs to provide visual and auditory cueing for patients with FOG.IMPLICATIONS FOR REHABILITATIONFreezing of gait in parkinsonian syndromes is a disabling motor block described by patients as having their feet stuck to the floor leading to difficulty in initiation of gait and increased risk for falls.Wearable assistive devices such as Google Glass™ use visual and auditory cueing that may improve gait pattern in patients with freezing of gait.Augmented reality programs using wearable assistive devices are a home-based therapy, with the potential for reinforcing physical therapy techniques; this is especially meaningful during the COVID-19 pandemic when access to both medical and rehabilitative care has been curtailed.

An Agenda-Setting Account for Psychological Typhoon Eye Effect on Responses to the Outbreak of COVID-19 in Wuhan.

During the outbreak of COVID-19 in Wuhan in 2020, we conducted a nationwide survey of 8170 respondents from 31 provinces/municipalities in China via Sojump to examine the relationship between the distance to respondents' city of residence from Wuhan and their safety concerns and risk perception of the epidemic that occurred in Wuhan City. We found that (1) the farther (psychologically or physically) people were from Wuhan, the more concerned they were with the safety of the epidemic risk in Wuhan, which we dubbed the psychological typhoon eye (PTE) effect on responses to the outbreak of COVID-19; (2) agenda setting can provide a principled account for such effect: the risk information proportion mediated the PTE effect. The theoretical and managerial implications for the PTE effect and public opinion disposal were discussed, and agenda setting was identified to be responsible for the preventable overestimated risk perception.

Racial/Ethnic Disparities in Post-acute Sequelae of SARS-CoV-2 Infection in New York: an EHR-Based Cohort Study from the RECOVER Program.

BACKGROUND: Compared to white individuals, Black and Hispanic individuals have higher rates of COVID-19 hospitalization and death. Less is known about racial/ethnic differences in post-acute sequelae of SARS-CoV-2 infection (PASC). OBJECTIVE: Examine racial/ethnic differences in potential PASC symptoms and conditions among hospitalized and non-hospitalized COVID-19 patients. DESIGN: Retrospective cohort study using data from electronic health records. PARTICIPANTS: 62,339 patients with COVID-19 and 247,881 patients without COVID-19 in New York City between March 2020 and October 2021. MAIN MEASURES: New symptoms and conditions 31-180 days after COVID-19 diagnosis. KEY RESULTS: The final study population included 29,331 white patients (47.1%), 12,638 Black patients (20.3%), and 20,370 Hispanic patients (32.7%) diagnosed with COVID-19. After adjusting for confounders, significant racial/ethnic differences in incident symptoms and conditions existed among both hospitalized and non-hospitalized patients. For example, 31-180 days after a positive SARS-CoV-2 test, hospitalized Black patients had higher odds of being diagnosed with diabetes (adjusted odds ratio [OR]: 1.96, 95% confidence interval [CI]: 1.50-2.56, q<0.001) and headaches (OR: 1.52, 95% CI: 1.11-2.08, q=0.02), compared to hospitalized white patients. Hospitalized Hispanic patients had higher odds of headaches (OR: 1.62, 95% CI: 1.21-2.17, q=0.003) and dyspnea (OR: 1.22, 95% CI: 1.05-1.42, q=0.02), compared to hospitalized white patients. Among non-hospitalized patients, Black patients had higher odds of being diagnosed with pulmonary embolism (OR: 1.68, 95% CI: 1.20-2.36, q=0.009) and diabetes (OR: 2.13, 95% CI: 1.75-2.58, q<0.001), but lower odds of encephalopathy (OR: 0.58, 95% CI: 0.45-0.75, q<0.001), compared to white patients. Hispanic patients had higher odds of being diagnosed with headaches (OR: 1.41, 95% CI: 1.24-1.60, q<0.001) and chest pain (OR: 1.50, 95% CI: 1.35-1.67, q < 0.001), but lower odds of encephalopathy (OR: 0.64, 95% CI: 0.51-0.80, q<0.001). CONCLUSIONS: Compared to white patients, patients from racial/ethnic minority groups had significantly different odds of developing potential PASC symptoms and conditions. Future research should examine the reasons for these differences.

Application of Deep Learning on Single-cell RNA Sequencing Data Analysis: A Review.

Single-cell RNA sequencing (scRNA-seq) has become a routinely used technique to quantify the gene expression profile of thousands of single cells simultaneously. Analysis of scRNA-seq data plays an important role in the study of cell states and phenotypes, and has helped elucidate biological processes, such as those occurring during the development of complex organisms, and improved our understanding of disease states, such as cancer, diabetes, and coronavirus disease 2019 (COVID-19). Deep learning, a recent advance of artificial intelligence that has been used to address many problems involving large datasets, has also emerged as a promising tool for scRNA-seq data analysis, as it has a capacity to extract informative and compact features from noisy, heterogeneous, and high-dimensional scRNA-seq data to improve downstream analysis. The present review aims at surveying recently developed deep learning techniques in scRNA-seq data analysis, identifying key steps within the scRNA-seq data analysis pipeline that have been advanced by deep learning, and explaining the benefits of deep learning over more conventional analytic tools. Finally, we summarize the challenges in current deep learning approaches faced within scRNA-seq data and discuss potential directions for improvements in deep learning algorithms for scRNA-seq data analysis.

Viral contamination on the surfaces of the personal protective equipment among health care professionals working in COVID-19 wards: A single-center prospective, observational study.

OBJECTIVE: To evaluate potential viral contamination on the surfaces of personal protective equipment (PPE) in COVID-19 wards. METHODS: Face shields, gloves, the chest area of PPE and shoe soles were sampled at different time points. The samples were tested for the presence of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) by PCR, and the cycle threshold (CT) values were recorded. RESULTS: The positive rate was 74.7% (239/320) for all PPE specimens. The CT values of the samples were ranked in the following order: face shields > chests > gloves > shoe soles (37.08±1.38, 35.48±2.02, 34.17±1.91 and 33.52±3.16, respectively; P for trend < .001). After disinfection, the CT values of shoe soles decreased compared with before disinfection (32.78±3.47 vs. 34.3±2.61, P = .037), whereas no significant effect of disinfection on the CT values of face shields, chests and gloves was observed. After disinfection, the CT values of specimens collected from shoe soles gradually increased; before disinfection, the CT values of shoe sole specimens were all less than 35. CONCLUSIONS: SARS-CoV-2 can attach to the surfaces of the PPE of healthcare professionals in COVID-19 wards, especially the shoe soles and undisinfected gloves. Shoe soles had the highest SARS-CoV-2 loads among all tested PPE items.

An antibody cocktail with broadened mutational resistance and effective protection against SARS-CoV-2.

Neutralizing antibodies have been proven to be highly effective in treating mild and moderate COVID-19 patients, but continuous emergence of SARS-CoV-2 variants poses significant challenges. Antibody cocktail treatments reduce the risk of escape mutants and resistance. In this study, a new cocktail composed of two highly potent neutralizing antibodies (HB27 and H89Y) was developed, whose binding epitope is different from those cocktails that received emergency use authorization. This cocktail showed more potent and balanced neutralizing activities (IC50 0.9-11.3 ng mL-1) against a broad spectrum of SARS-CoV-2 variants over individual HB27 or H89Y antibodies. Furthermore, the cocktail conferred more effective protection against the SARS-CoV-2 Beta variant in an aged murine model than monotherapy. It was shown to prevent SARS-CoV-2 mutational escape in vitro and effectively neutralize 61 types of pseudoviruses harbouring single amino acid mutation originated from variants and escape strains of Bamlanivimab, Casirivimab and Imdevimab with IC50 of 0.6-65 ng mL-1. Despite its breadth of variant neutralization, the HB27+H89Y combo and EUA cocktails lost their potencies against Omicron variant. Our results provide important insights that new antibody cocktails covering different epitopes are valuable tools to counter virus mutation and escape, highlighting the need to search for more conserved epitopes to combat Omicron.

A storm in a teacup -- A biomimetic lung microphysiological system in conjunction with a deep-learning algorithm to monitor lung pathological and inflammatory reactions.

Creating a biomimetic in vitro lung model to recapitulate the infection and inflammatory reactions has been an important but challenging task for biomedical researchers. The 2D based cell culture models - culturing of lung epithelium - have long existed but lack multiple key physiological conditions, such as the involvement of different types of immune cells and the creation of connected lung models to study viral or bacterial infection between different individuals. Pioneers in organ-on-a-chip research have developed lung alveoli-on-a-chip and connected two lung chips with direct tubing and flow. Although this model provides a powerful tool for lung alveolar disease modeling, it still lacks interactions among immune cells, such as macrophages and monocytes, and the mimic of air flow and aerosol transmission between lung-chips is missing. Here, we report the development of an improved human lung physiological system (Lung-MPS) with both alveolar and pulmonary bronchial chambers that permits the integration of multiple immune cells into the system. We observed amplified inflammatory signals through the dynamic interactions among macrophages, epithelium, endothelium, and circulating monocytes. Furthermore, an integrated microdroplet/aerosol transmission system was fabricated and employed to study the propagation of pseudovirus particles containing microdroplets in integrated Lung-MPSs. Finally, a deep-learning algorithm was developed to characterize the activation of cells in this Lung-MPS. This Lung-MPS could provide an improved and more biomimetic sensory system for the study of COVID-19 and other high-risk infectious lung diseases.

Identifying environmental risk factors for post-acute sequelae of SARS-CoV-2 infection: An EHR-based cohort study from the recover program.

Post-acute sequelae of SARS-CoV-2 infection (PASC) affects a wide range of organ systems among a large proportion of patients with SARS-CoV-2 infection. Although studies have identified a broad set of patient-level risk factors for PASC, little is known about the association between "exposome"-the totality of environmental exposures and the risk of PASC. Using electronic health data of patients with COVID-19 from two large clinical research networks in New York City and Florida, we identified environmental risk factors for 23 PASC symptoms and conditions from nearly 200 exposome factors. The three domains of exposome include natural environment, built environment, and social environment. We conducted a two-phase environment-wide association study. In Phase 1, we ran a mixed effects logistic regression with 5-digit ZIP Code tabulation area (ZCTA5) random intercepts for each PASC outcome and each exposome factor, adjusting for a comprehensive set of patient-level confounders. In Phase 2, we ran a mixed effects logistic regression for each PASC outcome including all significant (false positive discovery adjusted p-value < 0.05) exposome characteristics identified from Phase I and adjusting for confounders. We identified air toxicants (e.g., methyl methacrylate), particulate matter (PM2.5) compositions (e.g., ammonium), neighborhood deprivation, and built environment (e.g., food access) that were associated with increased risk of PASC conditions related to nervous, blood, circulatory, endocrine, and other organ systems. Specific environmental risk factors for each PASC condition and symptom were different across the New York City area and Florida. Future research is warranted to extend the analyses to other regions and examine more granular exposome characteristics to inform public health efforts to help patients recover from SARS-CoV-2 infection.

The Impact of Prior Infection With SARS-Cov-2 on Surgical Outcomes in Patients Undergoing Abdominal Body Contouring Procedures.

BACKGROUND: There is evidence of increased postoperative complications in patients who have recovered from SARS-CoV-2. However, previous studies have not examined this effect in abdominal contouring procedures. METHODS: A retrospective review was conducted for all patients who underwent abdominoplasty or panniculectomy at our institution from March 2020 to November 2021. Patients were separated into cohorts via preoperative history of SARS-CoV-2 infections. Variables collected include demographic data, concurrent comorbidities, postoperative complications, readmission/reoperation, and length of stay. Parametric, nonparametric, and multivariable regression modeling was used for analysis. RESULTS: Of the 181 patients included, 14 (7.7%) had a prior SARS-CoV-2 infection. Average time from infection to surgery was 250 days. The mean age and Charlson Comorbidity Index for nonexposed and exposed patients were 45.4 and 45.9 years, and 1.24 and 1.36 points. Patients with prior SARS-CoV-2 infection were more likely to have chronic kidney disease (odds ratio [OR], 6.79; P = 0.017) and undergo abdominoplasties compared with panniculectomies (OR, 4.43; P = 0.039). There were no other significant differences in patient or operative characteristics between the cohorts. Compared with those with no history of infection, patients with prior infections had increased odds of postoperative complications such as delayed wound healing (OR, 27.67; P < 0.001). No other significant associations were found between prior SARS-CoV-2 infection and perioperative outcomes. CONCLUSION: Prior SARS-CoV-2 infections may be associated with increased incidence of delayed wound healing despite a significant time lag between the time of infection and operation. Further studies are needed to elucidate the exact relationship and mechanism of action behind these findings.

Data-driven identification of post-acute SARS-CoV-2 infection subphenotypes.

The post-acute sequelae of SARS-CoV-2 infection (PASC) refers to a broad spectrum of symptoms and signs that are persistent, exacerbated or newly incident in the period after acute SARS-CoV-2 infection. Most studies have examined these conditions individually without providing evidence on co-occurring conditions. In this study, we leveraged the electronic health record data of two large cohorts, INSIGHT and OneFlorida+, from the national Patient-Centered Clinical Research Network. We created a development cohort from INSIGHT and a validation cohort from OneFlorida+ including 20,881 and 13,724 patients, respectively, who were SARS-CoV-2 infected, and we investigated their newly incident diagnoses 30-180 days after a documented SARS-CoV-2 infection. Through machine learning analysis of over 137 symptoms and conditions, we identified four reproducible PASC subphenotypes, dominated by cardiac and renal (including 33.75% and 25.43% of the patients in the development and validation cohorts); respiratory, sleep and anxiety (32.75% and 38.48%); musculoskeletal and nervous system (23.37% and 23.35%); and digestive and respiratory system (10.14% and 12.74%) sequelae. These subphenotypes were associated with distinct patient demographics, underlying conditions before SARS-CoV-2 infection and acute infection phase severity. Our study provides insights into the heterogeneity of PASC and may inform stratified decision-making in the management of PASC conditions.

Distinct Laboratory Test Result Profiles Between SARS-CoV-2 and Seasonable Influenza Infected Patients.

OBJECTIVE: Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and influenza viruses are contagious respiratory pathogens with similar symptoms but require different treatment and management strategies. This study investigated the differences in laboratory test result profiles between SARS-CoV-2 and influenza infected patients upon presentation to emergency department (ED). METHODS: Laboratory test results and demographic information from 723 influenza positive (2018/1/1 to 2020/3/15) and 1,281 SARS-CoV-2 positive (2020/3/11 to 2020/6/30) ED patients were retrospectively analyzed. The dataset was randomly divided into a training/validation set (2/3) and a test set (1/3) with the same SARS-CoV-2/influenza ratio. Four machine learning models in differentiating the laboratory profiles of RT-PCR confirmed SARS-CoV-2 and influenza positive patients were evaluated. The Shapley Additive Explanations technique was employed to visualize the impact of laboratory tests on the overall differentiation. Furthermore, the model performance was also evaluated in a new test dataset including 519 SARS-CoV-2 ED patients (2020/12/1 to 2021/2/28) and the previous influenza positive patients (2018/1/1 to 2020/3/15). RESULTS: A laboratory test result profile consisting of 15 blood tests, together with patient age, gender, and race can discriminate the two types of viral infections using a random forest (RF) model. The RF model achieved an area under the receiver operating characteristic curve (AUC) of 0.90 in the test set. Among the profile of 15 laboratory tests, the serum total calcium level exhibited the greatest contribution to the overall differentiation. Furthermore, the model achieved an AUC of 0.81 in a new test set. CONCLUSION: We developed a laboratory tests-based RF model differentiating SARS-CoV-2 from influenza, which may be useful for the preparedness of overlapping COVID-19 resurgence and future seasonal influenza.

Machine Learning Highlights Downtrending of COVID-19 Patients with a Distinct Laboratory Profile

Background New York City (NYC) experienced an initial surge and gradual decline in the number of SARS-CoV-2-confirmed cases in 2020. A change in the pattern of laboratory test results in COVID-19 patients over this time has not been reported or correlated with patient outcome. Methods We performed a retrospective study of routine laboratory and SARS-CoV-2 RT-PCR test results from 5,785 patients evaluated in a NYC hospital emergency department from March to June employing machine learning analysis. Results A COVID-19 high-risk laboratory test result profile (COVID19-HRP), consisting of 21 routine blood tests, was identified to characterize the SARS-CoV-2 patients. Approximately half of the SARS-CoV-2 positive patients had the distinct COVID19-HRP that separated them from SARS-CoV-2 negative patients. SARS-CoV-2 patients with the COVID19-HRP had higher SARS-CoV-2 viral loads, determined by cycle threshold values from the RT-PCR, and poorer clinical outcome compared to other positive patients without the COVID12-HRP. Furthermore, the percentage of SARS-CoV-2 patients with the COVID19-HRP has significantly decreased from March/April to May/June. Notably, viral load in the SARS-CoV-2 patients declined, and their laboratory profile became less distinguishable from SARS-CoV-2 negative patients in the later phase. Conclusions Our longitudinal analysis illustrates the temporal change of laboratory test result profile in SARS-CoV-2 patients and the COVID-19 evolvement in a US epicenter. This analysis could become an important tool in COVID-19 population disease severity tracking and prediction. In addition, this analysis may play an important role in prioritizing high-risk patients, assisting in patient triaging and optimizing the usage of resources.