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. 

Flexible, anti-damage, and non-contact sensing electronic skin implanted with MWCNT to block public pathogens contact infection.

If a person comes into contact with pathogens on public facilities, there is a threat of contact (skin/wound) infections. More urgently, there are also reports about COVID-19 coronavirus contact infection, which once again reminds that contact infection is a very easily overlooked disease exposure route. Herein, we propose an innovative implantation strategy to fabricate a multi-walled carbon nanotube/polyvinyl alcohol (MWCNT/PVA, MCP) interpenetrating interface to achieve flexibility, anti-damage, and non-contact sensing electronic skin (E-skin). Interestingly, the MCP E-skin had a fascinating non-contact sensing function, which can respond to the finger approaching 0-20 mm through the spatial weak field. This non-contact sensing can be applied urgently to human-machine interactions in public facilities to block pathogen. The scratches of the fruit knife did not damage the MCP E-skin, and can resist chemical corrosion after hydrophobic treatment. In addition, the MCP E-skin was developed to real-time monitor the respiratory and cough for exercise detection and disease diagnosis. Notably, the MCP E-skin has great potential for emergency applications in times of infectious disease pandemics. Electronic Supplementary Material: Supplementary material (fabrication of MCP E-skin, laser confocal tomography, parameter optimization, mechanical property characterization, finite element simulation, sensing mechanism, signal processing) is available in the online version of this article at 10.1007/s12274-021-3831-z.

The Role of Radiotherapy Fractionation And Volume In Patients With Early Breast Cancer After Conserving Surgery: A Systematic Review And Network Meta-Analysis (preprint)

Background：Hypofractionated whole breast irradiation (HF-WBI) can achieve the same treatment effect as conventional fractionated whole breast irradiation (CF-WBI) within limits , without increasing adverse reactions. Because of its characteristics of reducing the number of radiation therapy (RT) during the COVID-19 Pandemic, it is recommended as the first choice of treatment for patients with early breast cancer after breast conserving surgery. However, the choice of RT is still under exploration. Here, we conducted a network meta-analysis to evaluate the problem comprehensively using data from new randomized trials. Methods: We analyzed data from eligible studies for published events for ipsilateral breast tumor recurrence (IBTR), distant metastasis, total deaths, and non-breast cancer-related deaths. Statistical analysis was performed using a fixed-effects or random-effects model in cases of low and high heterogeneity, respectively. Network meta-analysis was conducted using a node-splitting model for two-category data among three RTs based on a Bayesian approach.Results: 16 studies with 23,418 patients were included. For IBTR, pairwise comparison showed that CF-WBI was significantly better than PBI, and HF-WBI was similar to CF-WBI. HF-WBI was superior to PBI, but the difference was not significant. However, indirect comparison of three RTs by network meta-analysis showed that HF-WBI was significantly better than PBI (OR=0.67, CI95%: 0.46–0.95). Paired and network meta-analyses found no significant differences in other endpoints among three radiotherapies. Conclusion: This meta-analysis demonstrated PBI was associated with increased IBTR compared with HF-WBI or CF-WBI in early-stage breast cancer patients.

Machine learning analysis highlights the down-trending of the proportion of COVID-19 patients with a distinct laboratory result profile (preprint)

BackgroundNew 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. MethodsWe 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. ResultsA 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 COVID19-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. ConclusionsOur study visualized the down-trending of the proportion of SARS-CoV-2 patients with the distinct COVID19-HRP. 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.

Routine laboratory blood tests predict SARS-CoV-2 infection using machine learning (preprint)

BackgroundAccurate diagnostic strategies to rapidly identify SARS-CoV-2 positive individuals for management of patient care and protection of health care personnel are urgently needed. The predominant diagnostic test is viral RNA detection by RT-PCR from nasopharyngeal swabs specimens, however the results are not promptly obtainable in all patient care locations. Routine laboratory testing, in contrast, is readily available with a turn-around time (TAT) usually within 1-2 hours. MethodWe developed a machine learning model incorporating patient demographic features (age, sex, race) with 27 routine laboratory tests to predict an individuals SARS-CoV-2 infection status. Laboratory test results obtained within two days before the release of SARS-CoV-2-RT-PCR result were used to train a gradient boosted decision tree (GBDT) model from 3,356 SARS-CoV-2 RT-PCR tested patients (1,402 positive and 1,954 negative) evaluated at a metropolitan hospital. ResultsThe model achieved an area under the receiver operating characteristic curve (AUC) of 0.854 (95% CI: 0.829-0.878). Application of this model to an independent patient dataset from a separate hospital resulted in a comparable AUC (0.838), validating the generalization of its use. Moreover, our model predicted initial SARS-CoV-2 RT-PCR positivity in 66% individuals whose RT-PCR result changed from negative to positive within two days. ConclusionThis model employing routine laboratory test results offers opportunities for early and rapid identification of high-risk SARS-CoV-2 infected patients before their RT-PCR results are available. It may play an important role in assisting the identification of SARS-COV-2 infected patients in areas where RT-PCR testing is not accessible due to financial or supply constraints.