A Deep Learning Approach to Forecast Short-Term COVID-19 Cases and Deaths in the US (preprint)

Since the US reported its first COVID-19 case on January 21, 2020, the science community has been applying various techniques to forecast incident cases and deaths. To date, providing an accurate and robust forecast at a high spatial resolution has proved challenging, even in the short term. Here we present a novel multi-stage deep learning model to forecast the number of COVID-19 cases and deaths for each US state at a weekly level for a forecast horizon of 1 to 4 weeks. The model is heavily data driven, and relies on epidemiological, mobility, survey, climate, and demographic. We further present results from a case study that incorporates SARS-CoV-2 genomic data (i.e. variant cases) to demonstrate the value of incorporating variant cases data into model forecast tools. We implement a rigorous and robust evaluation of our model – specifically we report on weekly performance over a one-year period based on multiple error metrics, and explicitly assess how our model performance varies over space, chronological time, and different outbreak phases. The proposed model is shown to consistently outperform the CDC ensemble model for all evaluation metrics in multiple spatiotemporal settings, especially for the longer-term (3 and 4 weeks ahead) forecast horizon. Our case study also highlights the potential value of virus genomic data for use in short-term forecasting to identify forthcoming surges driven by new variants. Based on our findings, the proposed forecasting framework improves upon the available forecasting tools currently used to support public health decision making with respect to COVID-19 risk. Research in context Evidence before this study A systematic review of the COVID-19 forecasting and the EPIFORGE 2020 guidelines reveal the lack of consistency, reproducibility, comparability, and quality in the current COVID-19 forecasting literature. To provide an updated survey of the literature, we carried out our literature search on Google Scholar, PubMed, and medRxi , using the terms “Covid-19,” “SARS-CoV-2,” “coronavirus,” “short-term,” “forecasting,” and “genomic surveillance.” Although the literature includes a significant number of papers, it remains lacking with respect to rigorous model evaluation, interpretability and translation. Furthermore, while SARS-CoV-2 genomic surveillance is emerging as a vital necessity to fight COVID-19 (i.e. wastewater sampling and airport screening), to our knowledge, no published forecasting model has illustrated the value of virus genomic data for informing future outbreaks. Added value of this study We propose a multi-stage deep learning model to forecast COVID-19 cases and deaths with a horizon window of four weeks. The data driven model relies on a comprehensive set of input features, including epidemiological, mobility, behavioral survey, climate, and demographic. We present a robust evaluation framework to systematically assess the model performance over a one-year time span, and using multiple error metrics. This rigorous evaluation framework reveals how the predictive accuracy varies over chronological time, space, and outbreak phase. Further, a comparative analysis against the CDC ensemble, the best performing model in the COVID-19 ForecastHub, shows the model to consistently outperform the CDC ensemble for all evaluation metrics in multiple spatiotemporal settings, especially for the longer forecasting windows. We also conduct a feature analysis, and show that the role of explanatory features changes over time. Specifically, we note a changing role of climate variables on model performance in the latter half of the study period. Lastly, we present a case study that reveals how incorporating SARS-CoV-2 genomic surveillance data may improve forecasting accuracy compared to a model without variant cases data. Implications of all the available evidence Results: from the robust evaluation analysis highlight extreme model performance variability over time and space, and suggest that forecasting models should be accompanied with specifications on the conditions under which they perform best (and worst), in order to maximize their value and utility in aiding public health decision making. The feature analysis reveals the complex and changing role of factors contributing to COVID-19 transmission over time, and suggests a possible seasonality effect of climate on COVID-19 spread, but only after August 2021. Finally, the case study highlights the added value of using genomic surveillance data in short-term epidemiological forecasting models, especially during the early stage of new variant introductions.

Method versatility in RNA extraction-free PCR detection of SARS-CoV-2 in saliva samples (preprint)

Early in the pandemic, a simple, open-source, RNA extraction-free RT-qPCR protocol for SARS-CoV-2 detection in saliva was developed and made widely available. This simplified approach (SalivaDirect) requires only sample treatment with proteinase K prior to PCR testing. However, feedback from clinical laboratories highlighted a need for a flexible workflow that can be seamlessly integrated into their current health and safety requirements for the receiving and handling of potentially infectious samples. To address these varying needs, we explored additional pre-PCR workflows. We built upon the original SalivaDirect workflow to include an initial incubation step (95{degrees}C for 30 minutes, 95{degrees}C for 5 minutes or 65{degrees}C for 15 minutes) with or without addition of proteinase K. The limit of detection for the workflows tested did not significantly differ from that of the original SalivaDirect workflow. When tested on de-identified saliva samples from confirmed COVID-19 individuals, these workflows also produced comparable virus detection and assay sensitivities, as determined by RT-qPCR analysis. Exclusion of proteinase K did not negatively affect the sensitivity of the assay. The addition of multiple heat pretreatment options to the SalivaDirect protocol increases the accessibility of this cost-effective SARS-CoV-2 test as it gives diagnostic laboratories the flexibility to implement the workflow which best suits their safety protocols.

Evaluation of Saliva Self-Collection Devices for SARS-CoV-2 Diagnostics (preprint)

There is an urgent need to expand testing for SARS-CoV-2 and other respiratory pathogens as the global community struggles to control the COVID-19 pandemic. Current diagnostic methods can be affected by supply chain bottlenecks and require the assistance of medical professionals, impeding the implementation of large-scale testing. Self-collection of saliva may solve these problems, as it can be completed without specialized training and uses generic materials. In this study, we observed thirty individuals who self-collected saliva using four different collection devices and analyzed their feedback. Two of these devices, a funnel and bulb pipette, were used to evaluate at-home saliva collection by 60 individuals. All devices enabled the safe, unsupervised self-collection of saliva. The quantity and quality of the samples received were acceptable for SARS-CoV-2 diagnostic testing, as determined by RNase P detection. Here, we demonstrate inexpensive, generic, buffer free collection devices suitable for unsupervised and home saliva self-collection.Funding Information: This work was funded by Tempus Labs, Inc (N.D.G and A.L.W), Yale Center for Clinical Investigation TL1 TR001864 (M.E.P.) and Fast Grant from Emergent Ventures at the Mercatus Center at George Mason University (N.D.G and A.L.W).Declaration of Interests: N.D.G. is a paid consultant for Tempus. The remaining authors declare no competing interests.Ethics Approval Statement: This study was conducted in accordance with an Institutional Review Board protocol reviewed and approved by the Yale University Human Research Protection Program (IRB Protocol ID: 2000028394).

Sequencing SARS-CoV-2 Genomes from Saliva (preprint)

Genomic sequencing is crucial to understanding the epidemiology and evolution of SARS-CoV-2. Often, genomic studies rely on remnant diagnostic material, typically nasopharyngeal swabs, as input into whole genome SARS-CoV-2 next-generation sequencing pipelines. Saliva has proven to be a safe and stable specimen for the detection of SARS-CoV-2 RNA via traditional diagnostic assays, however saliva is not commonly used for SARS-CoV-2 sequencing. Using the ARTIC Network amplicon-generation approach with sequencing on the Oxford Nanopore MinION, we demonstrate that sequencing SARS-CoV-2 from saliva produces genomes comparable to those from nasopharyngeal swabs, and that RNA extraction is necessary to generate complete genomes from saliva. In this study, we show that saliva is a useful specimen type for genomic studies of SARS-CoV-2.

COVID-19 Outcomes and Sequencing of SARS-CoV-2 isolated from Veterans in New England (preprint)

Background: Clinical outcomes of Veterans with COVID-19 in New England and respective genomic variants of SARS-CoV-2 have not been described. Factors impacting outcomes will inform triage and management algorithms. We proposed to conduct these clinical and genomic evaluations. Methods: We recorded demographics, comorbidities, and outcomes for 274 patients with COVID-19 in 6 states (CT, MA, ME, NH, RI, VT) from 4/8/20-9/16/20, and used STATA v16 for logistic regressions. Peak disease severity was defined from grade 1-5 as no O2 requirement, 1-3 liters (L) by nasal cannula (NC), 4-6 L NC, >6 L O2 or non-invasive positive pressure ventilation, and mechanical ventilation. We generated 64 whole genomes from 3/31/20-5/11/20 using Illumina (238) and Nanopore (61) platforms and built a phylogenetic tree (Nextstrain). Results: Of 274 Veterans, 92.7% were male, 83.2% white, and mean age was 63 years (IQR: 51 to 74 years). Over a third resided in a long-term care facility, and most common comorbidities were coronary artery disease (27%), diabetes (25%), and tobacco use (23%). 11.7% of patients required O2 within 24 hours of admission, with 20.8% of all patients requiring O2 support above their baseline during the hospitalization. Overall, 28.8% were hospitalized, with the highest rates in people with COPD (50%), CAD (45.9%), and those over age 80 years (44.4%). The overall mortality rate was 10.6%, with the highest rates in people with dementia (33.3%), age >80 (28.9%), and those from LTC (23.9%). On multivariate regression, significant predictors of hospitalization were age (OR: 1.05) and Non-white race (OR: 2.39). Peak severity also varied by age (OR: 1.07) and O2 requirement on admission (OR: 45.7). Mortality was predicted by age (OR: 1.06), dementia (OR: 3.44), and O2 requirement on admission (OR: 6.74). Most of our samples were in the A (2.36%) and B (97.3%) lineages. One genome was part of the N.1 lineage. Notably, the majority of genomes (97%) are part of the B1 lineage, which is defined by a D614G substitution. Conclusions: Our study found that in an older cohort of Veterans from the six New England states with a high comorbidity burden, age was the single strongest predictor of hospitalization, peak severity, and mortality. Non-white Veterans were more likely to be hospitalized, and patients who required oxygen on admission were more likely to have severe disease and higher rates of mortality. Furthermore, patients with dementia were more likely to die. Multiple genomic variants of SARS-CoV-2 were distributed in patients in New England early in the COVID-19 era, mostly in the New York clade with a D614G mutation.

Longitudinal immune profiling of a SARS-CoV-2 reinfection in a solid organ transplant recipient (preprint)

The underlying immunologic deficiencies enabling SARS-CoV-2 reinfections are currently unknown. Here we describe a renal-transplant recipient who developed recurrent, symptomatic SARS-CoV-2 infection 7 months after primary infection. To elucidate the immunological mechanisms responsible for reinfection, we performed longitudinal profiling of cellular and humoral responses during both primary and recurrent SARS-CoV-2 infection. We found that the patient responded to the primary infection with transient, poor-quality adaptive immune responses that was further compromised by intervening treatment for acute rejection of the renal allograft prior to reinfection. Importantly, we identified the development of neutralizing antibodies and humoral memory responses prior to SARS-CoV-2 reinfection. However, these neutralizing antibodies failed to confer protection against reinfection, suggesting that additional factors are required for efficient prevention of SARS-CoV-2 reinfection. Further, we found no evidence supporting viral evasion of primary adaptive immune responses, suggesting that susceptibility to reinfection may be determined by host factors rather than pathogen adaptation.

Saliva viral load is a dynamic unifying correlate of COVID-19 severity and mortality (preprint)

While several clinical and immunological parameters correlate with disease severity and mortality in SARS-CoV-2 infection, work remains in identifying unifying correlates of coronavirus disease 2019 (COVID-19) that can be used to guide clinical practice. Here, we examine saliva and nasopharyngeal (NP) viral load over time and correlate them with patient demographics, and cellular and immune profiling. We found that saliva viral load was significantly higher in those with COVID-19 risk factors; that it correlated with increasing levels of disease severity and showed a superior ability over nasopharyngeal viral load as a predictor of mortality over time (AUC=0.90). A comprehensive analysis of immune factors and cell subsets revealed strong predictors of high and low saliva viral load, which were associated with increased disease severity or better overall outcomes, respectively. Saliva viral load was positively associated with many known COVID-19 inflammatory markers such as IL-6, IL-18, IL-10, and CXCL10, as well as type 1 immune response cytokines. Higher saliva viral loads strongly correlated with the progressive depletion of platelets, lymphocytes, and effector T cell subsets including circulating follicular CD4 T cells (cTfh). Anti-spike (S) and anti-receptor binding domain (RBD) IgG levels were negatively correlated with saliva viral load showing a strong temporal association that could help distinguish severity and mortality in COVID-19. Finally, patients with fatal COVID-19 exhibited higher viral loads, which correlated with the depletion of cTfh cells, and lower production of anti-RBD and anti-S IgG levels. Together these results demonstrated that viral load, as measured by saliva but not nasopharyngeal, is a dynamic unifying correlate of disease presentation, severity, and mortality over time.

Detection of SARS-CoV-2 RNA by multiplex RT-qPCR (preprint)

The current RT-qPCR assay recommended for SARS-CoV-2 testing in the United States requires analysis of three genomic targets per sample: two viral and one host. To simplify testing and reduce the volume of required reagents, we developed a multiplex RT-qPCR assay to detect SARS-CoV-2 in a single reaction. We used existing N1, N2, and RP primer and probe sets by the CDC, but substituted fluorophores to allow multiplexing of the assay. The cycle threshold (Ct) values of our multiplex RT-qPCR were comparable to those obtained by the singleplex assay adapted for research purposes. Low copies (>500 copies / reaction) of SARS-CoV-2 RNA were consistently detected by the multiplex RT-qPCR. Our novel multiplex RT-qPCR improves upon current singleplex diagnostics by saving reagents, costs, time and labor.