Improving Fairness of Automated Chest X-ray Diagnosis by Contrastive Learning (preprint)

Purpose: Limited studies exploring concrete methods or approaches to tackle and enhance model fairness in the radiology domain. Our proposed AI model utilizes supervised contrastive learning to minimize bias in CXR diagnosis. Materials and Methods: In this retrospective study, we evaluated our proposed method on two datasets: the Medical Imaging and Data Resource Center (MIDRC) dataset with 77,887 CXR images from 27,796 patients collected as of April 20, 2023 for COVID-19 diagnosis, and the NIH Chest X-ray (NIH-CXR) dataset with 112,120 CXR images from 30,805 patients collected between 1992 and 2015. In the NIH-CXR dataset, thoracic abnormalities include atelectasis, cardiomegaly, effusion, infiltration, mass, nodule, pneumonia, pneumothorax, consolidation, edema, emphysema, fibrosis, pleural thickening, or hernia. Our proposed method utilizes supervised contrastive learning with carefully selected positive and negative samples to generate fair image embeddings, which are fine-tuned for subsequent tasks to reduce bias in chest X-ray (CXR) diagnosis. We evaluated the methods using the marginal AUC difference ($\delta$ mAUC). Results: The proposed model showed a significant decrease in bias across all subgroups when compared to the baseline models, as evidenced by a paired T-test (p<0.0001). The $\delta$ mAUC obtained by our method were 0.0116 (95\% CI, 0.0110-0.0123), 0.2102 (95% CI, 0.2087-0.2118), and 0.1000 (95\% CI, 0.0988-0.1011) for sex, race, and age on MIDRC, and 0.0090 (95\% CI, 0.0082-0.0097) for sex and 0.0512 (95% CI, 0.0512-0.0532) for age on NIH-CXR, respectively. Conclusion: Employing supervised contrastive learning can mitigate bias in CXR diagnosis, addressing concerns of fairness and reliability in deep learning-based diagnostic methods.

Effect of Paxlovid Treatment on Long COVID Onset: An EHR-Based Target Trial Emulation from N3C (preprint)

Preventing and treating post-acute sequelae of SARS-CoV-2 infection (PASC), commonly known as Long COVID, has become a public health priority. In this study, we examined whether treatment with Paxlovid in the acute phase of COVID-19 helps prevent the onset of PASC. We used electronic health records from the National Covid Cohort Collaborative (N3C) to define a cohort of 426,461 patients who had COVID-19 since April 1, 2022, and were eligible for Paxlovid treatment due to risk for progression to severe COVID-19. We used the target trial emulation (TTE) framework to estimate the effect of Paxlovid treatment on PASC incidence. Our primary outcome measure was a PASC computable phenotype. Secondary outcomes were the onset of novel cognitive, fatigue, and respiratory symptoms in the post-acute period. Paxlovid treatment did not have a significant effect on overall PASC incidence (relative risk [RR] = 0.99, 95% confidence interval [CI] 0.96-1.01). However, its effect varied across the cognitive (RR = 0.85, 95% CI 0.79-0.90), fatigue (RR = 0.93, 95% CI 0.89-0.96), and respiratory (RR = 0.99, 95% CI 0.95-1.02) symptom clusters, suggesting that Paxlovid treatment may help prevent post-acute cognitive and fatigue symptoms more than others.

Real-world Effectiveness of BNT162b2 in Children and Adolescents in Preventing Infection and Severe Diseases with SARS-CoV-2 During the Delta and Omicron Periods: Findings from Trial Emulation Using an EHR-based Cohort (preprint)

BACKGROUND The current understanding of the long-term effectiveness of the BNT162b2 vaccine for a range of outcomes across diverse U.S. pediatric populations is limited. In this study, we assessed the effectiveness of BNT162b2 against various strains of the SARS-CoV-2 virus using data from a national collaboration of pediatric health systems (PEDSnet). METHODS We emulated three target trials to assess the real-world effectiveness of BNT162b2: adolescents aged 12 to 20 years during the Delta variant period (Target trial 1), children aged 5 to 11 years (Target trial 2) and adolescents aged 12 to 20 years during the Omicron variant period (Target trial 3). The outcomes included documented infection, COVID-19 illness severity, admission to an intensive care unit (ICU), and two cardiac-related outcomes, myocarditis and pericarditis. In the U.S., immunization records are often captured and stored across multiple disconnected sources, resulting in incomplete vaccination records in patients' electronic health records (EHR). We implemented a novel trial emulation pipeline accounting for possible misclassification bias in vaccine documentation in EHRs. The effectiveness of the BNT162b2 vaccine was estimated from the Poisson regression model with confounders balanced via propensity score stratification. RESULTS During the Delta period, the BNT162b2 vaccine demonstrated an overall effectiveness 98.4% (95% CI, 98.1 to 98.7) against documented infection among adolescents, with no significant waning after receipt of the first dose. During the Omicron period, the overall effectiveness was estimated to be 74.3% (95% CI, 72.2 to 76.2) in preventing documented infection among children, which was higher against moderate or severe COVID-19 (75.5%; 95% CI, 69.0 to 81.0) and ICU admission with COVID-19 (84.9%; 95% CI, 64.8 to 93.5). In the adolescent population, the overall effectiveness against documented Omicron infection was 85.5% (95% CI, 83.8 to 87.1), with effectiveness of 84.8% (95% CI, 77.3 to 89.9) against moderate or severe COVID-19, and 91.5% (95% CI, 69.5 to 97.6) against ICU admission with COVID-19. The effectiveness of the BNT162b2 vaccine against the Omicron variant declined after 4 months following the first dose and then stabilized with higher levels of uncertainty. Across all three cohorts, the risk of cardiac outcomes was approximately 65% to 85% lower in the vaccinated group than that of the unvaccinated group accounting for possible misclassification bias. CONCLUSIONS This study suggests BNT162b2 was effective among children and adolescents in Delta and Omicron periods for a range of COVID-19-related outcomes and is associated with a lower risk for cardiac complications. Waning effectiveness over time suggests that revaccination may be needed in the future.

Excess burden of respiratory and abdominal conditions following COVID-19 infections during the ancestral and Delta variant periods in the United States: An EHR-based cohort study from the RECOVER Program (preprint)

Importance The frequency and characteristics of post-acute sequelae of SARS-CoV-2 infection (PASC) may vary by SARS-CoV-2 variant. Objective To characterize PASC-related conditions among individuals likely infected by the ancestral strain in 2020 and individuals likely infected by the Delta variant in 2021. Design Retrospective cohort study of electronic medical record data for approximately 27 million patients from March 1, 2020-November 30, 2021. Setting Healthcare facilities in New York and Florida. Participants Patients who were at least 20 years old and had diagnosis codes that included at least one SARS-CoV-2 viral test during the study period. Exposure Laboratory-confirmed COVID-19 infection, classified by the most common variant prevalent in those regions at the time. Main Outcome(s) and Measure(s) Relative risk (estimated by adjusted hazard ratio [aHR]) and absolute risk difference (estimated by adjusted excess burden) of new conditions, defined as new documentation of symptoms or diagnoses, in persons between 31-180 days after a positive COVID-19 test compared to persons with only negative tests during the 31-180 days after the last negative test. Results We analyzed data from 560,752 patients. The median age was 57 years; 60.3% were female, 20.0% non-Hispanic Black, and 19.6% Hispanic. During the study period, 57,616 patients had a positive SARS-CoV-2 test; 503,136 did not. For infections during the ancestral strain period, pulmonary fibrosis, edema (excess fluid), and inflammation had the largest aHR, comparing those with a positive test to those with a negative test, (aHR 2.32 [95% CI 2.09 2.57]), and dyspnea (shortness of breath) carried the largest excess burden (47.6 more cases per 1,000 persons). For infections during the Delta period, pulmonary embolism had the largest aHR comparing those with a positive test to a negative test (aHR 2.18 [95% CI 1.57, 3.01]), and abdominal pain carried the largest excess burden (85.3 more cases per 1,000 persons). Conclusions and Relevance We documented a substantial relative risk of pulmonary embolism and large absolute risk difference of abdomen-related symptoms after SARS-CoV-2 infection during the Delta variant period. As new SARS-CoV-2 variants emerge, researchers and clinicians should monitor patients for changing symptoms and conditions that develop after infection.

Risk Factors and Predictive Modeling for Post-Acute Sequelae of SARS-CoV-2 Infection: Findings from EHR Cohorts of the RECOVER Initiative (preprint)

Background Patients who were SARS-CoV-2 infected could suffer from newly incidental conditions in their post-acute infection period. These conditions, denoted as the post-acute sequelae of SARS-CoV-2 infection (PASC), are highly heterogeneous and involve a diverse set of organ systems. Limited studies have investigated the predictability of these conditions and their associated risk factors. Method In this retrospective cohort study, we investigated two large-scale PCORnet clinical research networks, INSIGHT and OneFlorida+, including 11 million patients in the New York City area and 16.8 million patients from Florida, to develop machine learning prediction models for those who are at risk for newly incident PASC and to identify factors associated with newly incident PASC conditions. Adult patients aged  20 with SARS-CoV-2 infection and without recorded infection between March 1st, 2020, and November 30th, 2021, were used for identifying associated factors with incident PASC after removing background associations. The predictive models were developed on infected adults. Results We find several incident PASC, e.g., malnutrition, COPD, dementia, and acute kidney failure, were associated with severe acute SARS-CoV-2 infection, defined by hospitalization and ICU stay. Older age and extremes of weight were also associated with these incident conditions. These conditions were better predicted (C-index >0.8). Moderately predictable conditions included diabetes and thromboembolic disease (C-index 0.7-0.8). These were associated with a wider variety of baseline conditions. Less predictable conditions included fatigue, anxiety, sleep disorders, and depression (C-index around 0.6). Conclusions This observational study suggests that a set of likely risk factors for different PASC conditions were identifiable from EHRs, predictability of different PASC conditions was heterogeneous, and using machine learning-based predictive models might help in identifying patients who were at risk of developing incident PASC. 

Single-cell multi-omic topic embedding reveals cell-type-specific and COVID-19 severity-related immune signatures (preprint)

The advent of single-cell multi-omics sequencing technology makes it possible for researchers to leverage multiple modalities for individual cells and explore cell heterogeneity. However, the high dimensional, discrete, and sparse nature of the data make the downstream analysis particularly challenging. Most of the existing computational methods for single-cell data analysis are either limited to single modality or lack flexibility and interpretability. In this study, we propose an interpretable deep learning method called multi-omic embedded topic model (moETM) to effectively perform integrative analysis of high-dimensional single-cell multimodal data. moETM integrates multiple omics data via a product-of-experts in the encoder for efficient variational inference and then employs multiple linear decoders to learn the multi-omic signatures of the gene regulatory programs. Through comprehensive experiments on public single-cell transcriptome and chromatin accessibility data (i.e., scRNA+scATAC), as well as scRNA and proteomic data (i.e., CITE-seq), moETM demonstrates superior performance compared with six state-of-the-art single-cell data analysis methods on seven publicly available datasets. By applying moETM to the scRNA+scATAC data in human peripheral blood mononuclear cells (PBMCs), we identified sequence motifs corresponding to the transcription factors that regulate immune gene signatures. Applying moETM analysis to CITE-seq data from the COVID-19 patients revealed not only known immune cell-type-specific signatures but also composite multi-omic biomarkers of critical conditions due to COVID-19, thus providing insights from both biological and clinical perspectives.

Immune response of primary and booster immunity of SARS-CoV-2 vaccination among patients with chronic liver disease: a real-world study (preprint)

Aim: The present study discussed the humoral immune response and antibody dynamics after primary and booster immunity of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) vaccines among patients with chronic liver disease (CLD) in the real world. Thus, it provided data to develop SARS-CoV-2 vaccination strategy. Methods: Patients with confirmed CLD and completed primary or booster immunity of SARS-CoV-2 vaccines were enrolled. Serological specimens were collected after primary or booster immunity of SARS-CoV-2 vaccines to detect novel coronavirus neutralizing antibody (nCoV NTAb) and novel coronavirus spike receptor-binding domain antibody (nCoV S-RBD). Thus, we could evaluate the humoral immune response and antibody dynamics after primary and booster immunity of SARS-CoV-2 vaccines among patients with CLD. Simultaneously, baseline demographics, liver disease-related situations, comorbidity-related situations, SARS-CoV-2 vaccination information, and laboratory examination-related indicators of patients were collected. Results: A total of 315 patients received SARS-CoV-2 vaccines, including 223 patients who completed the primary immunity of SARS-CoV-2 vaccines, 114 patients who completed booster immunity of SARS-CoV-2 vaccines, and 22 patients who underwent the antibody detection of SARS-CoV-2 vaccines after both primary and booster immunities. The positive rate of nCoV NTAb was 59.64% in Primary and 87.72% in Booster (P<0.001). The median level of nCoV NTAb was 11.53 AU/mL in Primary and 31.98 AU/mL in Booster (P<0.001). The positive rate of nCoV S-RBD was 69.06% in Primary and 91.23% in Booster (P<0.001). The median level of nCoV S-RBD was 21.60AU/mL in Primary and 112.65 AU/mL in Booster (P<0.001). After booster immunity of SARS-CoV-2 vaccines in 22 patients, the positive rate of nCoV NTAb increased from 59.09% to 86.36%, and that of nCoV S-RBD increased from 68.18% to 90.91%. The median level of nCoV NTAb increased from 11.24 AU /mL to 59.14 AU /mL after booster immunity. The median level of nCoV S-RBD increased from 27.28 AU/mL to 219.10 AU/mL. Compared to the antibody level of primary immunity, the median level of nCoV NTAb and nCoV S-RBD in 22 patients was increased by 5.26 and 8.03 times, respectively. Among 22 patients, 9 were negative for nCoV NTAb after primary immunity, while 6 were transformed positive after booster immunity, and the positive conversion rate of nCoV NTAb was 66.7%. On the other hand, 7 patients were negative for nCoV S-RBD after primary immunity, while 5 were transformed positive after booster immunity, and the positive conversion rate of nCoV S-RBD was 71.4%. Conclusion: Patients with CLD show improved humoral immune response after completing primary and booster immunity of SARS-CoV-2 vaccines, while booster immunity further improves the positive rate and antibody level of patients with CLD. Finally, the positive conversion rate among patients with primary immunity failure also can be improved after booster immunity. Keywords: immune response; primary and booster immunity; SARS-CoV-2 vaccination; chronic liver disease

Combating Health Misinformation in Social Media: Characterization, Detection, Intervention, and Open Issues (preprint)

Social media has been one of the main information consumption sources for the public, allowing people to seek and spread information more quickly and easily. However, the rise of various social media platforms also enables the proliferation of online misinformation. In particular, misinformation in the health domain has significant impacts on our society such as the COVID-19 infodemic. Therefore, health misinformation in social media has become an emerging research direction that attracts increasing attention from researchers of different disciplines. Compared to misinformation in other domains, the key differences of health misinformation include the potential of causing actual harm to humans' bodies and even lives, the hardness to identify for normal people, and the deep connection with medical science. In addition, health misinformation on social media has distinct characteristics from conventional channels such as television on multiple dimensions including the generation, dissemination, and consumption paradigms. Because of the uniqueness and importance of combating health misinformation in social media, we conduct this survey to further facilitate interdisciplinary research on this problem. In this survey, we present a comprehensive review of existing research about online health misinformation in different disciplines. Furthermore, we also systematically organize the related literature from three perspectives: characterization, detection, and intervention. Lastly, we conduct a deep discussion on the pressing open issues of combating health misinformation in social media and provide future directions for multidisciplinary researchers.

Identifying Contextual and Spatial Risk Factors for Post-Acute Sequelae of SARS-CoV-2 Infection: An EHR-based Cohort Study from the RECOVER Program (preprint)

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 contextual and spatial risk factors for PASC. Using electronic health data of patients with COVID-19 from two large clinical research networks in New York City and Florida, we identified contextual and spatial risk factors from nearly 200 environmental characteristics for 23 PASC symptoms and conditions of eight organ systems. 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 contextual and spatial 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) contextual and spatial characteristics identified from Phase I and adjusting for confounders. We identified air toxicants (e.g., methyl methacrylate), criteria air pollutants (e.g., sulfur dioxide), 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, respiratory, blood, circulatory, endocrine, and other organ systems. Specific contextual and spatial risk factors for each PASC condition and symptom were different across New York City area and Florida. Future research is warranted to extend the analyses to other regions and examine more granular contextual and spatial characteristics to inform public health efforts to help patients recover from SARS-CoV-2 infection.

Stunting among kindergarten children in China in the context of COVID-19: A cross-sectional study

Background The impact of COVID-19 has most likely increased the prevalence of stunting. The study aimed to determine the prevalence of stunting among kindergarten children in the context of coronavirus disease 2019 (COVID-19) in Longgang District, Shenzhen, China, and its risk factors. Methods A cross-sectional study was conducted to identify children from 11 sub districts of 481 kindergartens in the Longgang District of Shenzhen City from May to July 2021. In the context of COVID-19, an online survey was conducted to gather demographic information, height, birth information, and lifestyle. The prevalence of stunting was calculated, and the risk factors were analyzed using binary logistic regression with three stepwise models. Results A total of 118,404 subjects were included from May to July 2021, with a response and questionnaire effective rates of 85.75% and 95.03%, respectively. The prevalence of stunting and severe stunting were 3.3% and 0.8%, respectively. Model 3 showed that risk factors for stunting were male sex [odds ratio (OR) = 1.07], low birth weight (OR = 2.02), insufficient sleep time (OR = 1.08), less food intake than their peers (OR = 1.66), slower eating than their peers (OR = 1.16), accompanied by grandparents alone or non-lineal relatives (reference: parents accompanying) (OR = 1.23, 1.51), and children induced to eat (OR = 1.17). Protective factors included only-child status (OR = 0.66), reported high activity (OR = 0.37, 0.26, 0.23), parents with high education levels (father: OR = 0.87, 0.69;mother: OR = 0.69, 0.58), high monthly income per capita of the family (OR = 0.88, 0.74, 0.68), and allowing children to make food choices (OR = 0.82). Conclusion The stunting rate of children in kindergartens in Longgang District is 3.3%, close to the level of developed countries but higher than the average level of developed cities in China. The relatively high stunting rate in children under 3 years old in 2021 may be associated with the influence of COVID-19. Appropriate policies should be formulated for individuals and families with children to help children establish good living habits and reduce stunting.

Experiences, life changes, and support systems of recovered COVID-19 patients from practitioners’ perspectives: A qualitative study

The spread of COVID-19 brought a worldwide pandemic that interrupted daily life and activities. By the end of 2020, there were more than 83 million diagnosed cases and 1.8 million deaths worldwide (World Health Organization, 2020). In Wuhan, China, more than 7 million individuals were quarantined at the beginning of the pandemic. Despite the widespread impact of the pandemic, limited studies have focused on recovered COVID-19 patients? experiences. Therefore, this qualitative study was conducted to better understand the shared experiences of recovered COVID-19 patients in Wuhan, through the lens of social work practitioners working with them. A thematic analysis of 14 individual interviews resulted in three main themes: trauma, long-term perspective change, and support systems. Recovered patients commonly reported rejection, discrimination, stigma, and self-blame as a result of having had COVID-19. Although some reported receiving social support from family members, neighbors, or employers, others reported severe rejection and maltreatment. Experiences also influenced whether patients had a more positive or negative outlook toward the future. Findings call for health care practitioners and service providers to better support COVID-19 patients using a culturally sensitive, trauma-informed approach. Neighborhood-level factors and interventions are also discussed.

Exploring the Antecedents to the Reputation of Chinese Public Sector Organizations During COVID-19: An Extension of Situational Crisis Communication Theory

The study is intended to examine the impact of crisis responsibility on the reputation of the Chinese public sector organization during the COVID-19 crisis. In addition to that, the study has also examined the mediating role of crisis response strategy in the relationship between crisis responsibility and the reputation of the Chinese public sector organization during the COVID-19 crisis. Lastly, the study has also examined the moderating role of internal crisis communication in the relationship between the crisis responsibility and crisis response strategy of the Chinese public sector organization during COVID-19. This study bases on a quantitative research approach along with a cross-sectional research design. The population of the study is the Chinese public sector organization companies. Data is collected from the employees working in Chinese public sector organizations. The current study used 500 sample sizes;205 valid responses are received which were used in data analysis. The SEM-PLS is used for the data analysis. The result of the study indicates that all the direct hypotheses are accepted significantly, which indicates that the crisis responsibility and crisis response strategy are significant determinants of organizational reputation during the COVID-19. In a similar vein, the crisis responsibility has placed a significant impact on the crisis response strategy of Chinese organizations during COVID-19. The study is among the pioneer studies on crisis responsibility in the Chinese public sector organization during COVID-19. The study has employed an extended framework encircling the literature on crisis responsibility, crisis response strategy, internal crisis communication, and organizational reputation. Theoretically, the study has extended the situational crisis communication theory framework by incorporating internal crisis communication in the framework.

Clinical advancement of patients infected with SARS-CoV-2 Omicron variant in Shanghai, China (preprint)

Background Studies on the Omicron variant infection have generally been restricted to descriptions of its initial clinical and epidemiological characteristics, we investigated the timeline-related advancement in individuals with Omicron variant. Methods We conducted a retrospective, single centered study including 226 laboratory confirmed cases with Omicron variant between April 6th and May 11th, 2022 in Shanghai, China. Final date of follow-up was May 30, 2022. Results Among 226 enrolled patients, the median age was 52 years old, and 118 (52.2%) were female. The duration from onset of symptoms to hospitalization was 3 (IQR, 2-4) days for symptomatic patients. Cough occurred in 168 patients (74.3% ). The median interval to negative reverse-transcriptase PCR tests of nasopharynx swab was 10 days (interquartile range [IQR]: 8-13 days). No radiographic progressions were found in 196 patients on the 7th day after onset of symptoms. The median duration of fever in all participants was 5 days (IQR: 4-6 days). The median PCR conversion time of Paxlovid-treated patients was 8 days (IQR: 7-10 days) compared with that of Lianhuaqingwen (10 days, IQR: 8-13 days) (p=0.00056). Booster vaccination can significantly decrease the severity of Omicron infection when compared with unvaccinated, partially or fully vaccinated patients (p=0.009). The median time of PCR conversion in individuals aged under 14 recovered significantly faster than older patients (median 8 days versus 11 days, P < 0.0001). In multivariate logistic analysis, erythrocyte sedimentation rate (ESR) (OR=1.05) was independently related to the severity of the infection. Conclusions The majority clinical symptoms of Omicron infection were not severe. Early and aggressive administration of Paxlovid can significantly reduce the PCR conversion time. Booster vaccination should also be highly recommended in population over 14 years old.

Machine Learning for Identifying Data-Driven Subphenotypes of Incident Post-Acute SARS-CoV-2 Infection Conditions with Large Scale Electronic Health Records: Findings from the RECOVER Initiative (preprint)

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 post-acute SARS-CoV-2 infection period of COVID-19 patients. Most studies have examined these conditions individually without providing concluding evidence on co-occurring conditions. To answer this question, this study leveraged electronic health records (EHRs) from two large clinical research networks from the national Patient-Centered Clinical Research Network (PCORnet) and investigated patients’ newly incident diagnoses that appeared within 30 to 180 days after a documented SARS-CoV-2 infection. Through machine learning, we identified four reproducible subphenotypes of PASC dominated by blood and circulatory system, respiratory, musculoskeletal and nervous system, and digestive system problems, respectively. We also demonstrated that these subphenotypes were associated with distinct patterns of patient demographics, underlying conditions present prior to SARS-CoV-2 infection, acute infection phase severity, and use of new medications in the post-acute period. Our study provides novel insights into the heterogeneity of PASC and can inform stratified decision-making in the treatment of COVID-19 patients with PASC conditions.

Understanding Post-Acute Sequelae of SARS-CoV-2 Infection through Data-Driven Analysis with Longitudinal Electronic Health Records: Findings from the RECOVER Initiative (preprint)

Recent studies have investigated post-acute sequelae of SARS-CoV-2 infection (PASC) using real-world patient data such as electronic health records (EHR). Prior studies have typically been conducted on patient cohorts with small sample sizes 1 or specific patient populations 2,3 limiting generalizability. This study aims to characterize PASC using the EHR data warehouses from two large national patient-centered clinical research networks (PCORnet), INSIGHT and OneFlorida+, which include 11 million patients in New York City (NYC) and 16.8 million patients in Florida respectively. With a high-throughput causal inference pipeline using high-dimensional inverse propensity score adjustment, we identified a broad list of diagnoses and medications with significantly higher incidence 30-180 days after the laboratory-confirmed SARS-CoV-2 infection compared to non-infected patients. We found more PASC diagnoses and a higher risk of PASC in NYC than in Florida, which highlights the heterogeneity of PASC in different populations.

Investigation of Anti-Epithelial-Mesenchymal Transition and Anti-Inflammation effects of Qing Fei Hua Xian Decotion on Pulmonary Fibrosis via Network Pharmacology and Experimental Verification (preprint)

Background Pulmonary fibrosis (PF) is a common interstitial pneumonia disease, also occurred in post-COVID-19 survivors. The mechanism underlying the anti-PF effect of Qing Fei Hua Xian Decotion (QFHXD), a traditional Chinese medicine formula applied for treating PF in COVID-19 survivors, is unclear. This study aimed to uncover the mechanisms related to the anti-PF effect of QFHXD through analysis of network pharmacology and experimental verification.Methods The candidate chemical compounds of QFHXD and its putative targets for treating PF were achieved from public databases, thereby we established the corresponding “herb- compound -target” network of QFHXD. Moreover, The protein–protein interaction (PPI) network of potential targets was also constructed to screen the core targets. Furthermore, Gene ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analysis were used to predict targets, and pathways, then validated by in vivo experiments.Results A total of 188 active compounds in QFHXD and 50 target genes were identified from databases. The key therapeutic targets of QFHXD, such as PI3K/Akt, IL-6, TNF, IL-1β, STAT3, MMP-9, and TGF-β1 were identified by KEGG and GO analysis. Anti-PF effects of QFHXD (in a dose-dependent manner) and prednisone were confirmed by HE, Masson staining, and Sirius red staining as well as in vivo Micro-CT and immunohistochemical analysis in a rat model of bleomycin-induced PF. Besides, QFXHD remarkably inhibits the activity of PI3K/Akt/NF-κB and TGF‑β1/Smad2/3.Conclusion QFXHD significantly attenuated bleomycin-induced PF via inhibiting inflammation and EMT. PI3K/Akt/NF-κB and TGF‑β1/Smad2/3 pathways might be the potential therapeutic effects of QFHXD for treating PF.

Mask Wearing Status Estimation with Smartwatches (preprint)

We present MaskReminder, an automatic mask-wearing status estimation system based on smartwatches, to remind users who may be exposed to the COVID-19 virus transmission scenarios, to wear a mask. MaskReminder with the powerful MLP-Mixer deep learning model can effectively learn long-short range information from the inertial measurement unit readings, and can recognize the mask-related hand movements such as wearing a mask, lowering the metal strap of the mask, removing the strap from behind one side of the ears, etc. Extensive experiments on 20 volunteers and 8000+ data samples show that the average recognition accuracy is 89%. Moreover, MaskReminder is capable to remind a user to wear with a success rate of 90% even in the user-independent setting.