Enhanced SARS-CoV-2 case prediction using public health data and machine learning models.

Objectives: The goal of this study is to propose and test a scalable framework for machine learning (ML) algorithms to predict near-term severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) cases by incorporating and evaluating the impact of real-time dynamic public health data. Materials and Methods: Data used in this study include patient-level results, procurement, and location information of all SARS-CoV-2 tests reported in West Virginia as part of their mandatory reporting system from January 2021 to March 2022. We propose a method for incorporating and comparing widely available public health metrics inside of a ML framework, specifically a long-short-term memory network, to forecast SARS-CoV-2 cases across various feature sets. Results: Our approach provides better prediction of localized case counts and indicates the impact of the dynamic elements of the pandemic on predictions, such as the influence of the mixture of viral variants in the population and variable testing and vaccination rates during various eras of the pandemic. Discussion: Utilizing real-time public health metrics, including estimated Rt from multiple SARS-CoV-2 variants, vaccination rates, and testing information, provided a significant increase in the accuracy of the model during the Omicron and Delta period, thus providing more precise forecasting of daily case counts at the county level. This work provides insights on the influence of various features on predictive performance in rural and non-rural areas. Conclusion: Our proposed framework incorporates available public health metrics with operational data on the impact of testing, vaccination, and current viral variant mixtures in the population to provide a foundation for combining dynamic public health metrics and ML models to deliver forecasting and insights in healthcare domains. It also shows the importance of developing and deploying ML frameworks in rural settings.

Ultrasound Blood-Brain Barrier Opening and Aducanumab in Alzheimer's Disease.

Antiamyloid antibodies have been used to reduce cerebral amyloid-beta (Aß) load in patients with Alzheimer's disease. We applied focused ultrasound with each of six monthly aducanumab infusions to temporarily open the blood-brain barrier with the goal of enhancing amyloid removal in selected brain regions in three participants over a period of 6 months. The reduction in the level of Aß was numerically greater in regions treated with focused ultrasound than in the homologous regions in the contralateral hemisphere that were not treated with focused ultrasound, as measured by fluorine-18 florbetaben positron-emission tomography. Cognitive tests and safety evaluations were conducted over a period of 30 to 180 days after treatment. (Funded by the Harry T. Mangurian, Jr. Foundation and the West Virginia University Rockefeller Neuroscience Institute.).

Safety and feasibility clinical trial of nucleus accumbens deep brain stimulation for treatment-refractory opioid use disorder.

OBJECTIVE: There were more than 107,000 drug overdose deaths in the US in 2021, the most ever recorded. Despite advances in behavioral and pharmacological treatments, over 50% of those receiving treatment for opioid use disorder (OUD) experience drug use recurrence (relapse). Given the prevalence of OUD and other substance use disorders (SUDs), the high rate of drug use recurrence, and the number of drug overdose deaths, novel treatment strategies are desperately needed. The objective of this study was to evaluate the safety and feasibility of deep brain stimulation (DBS) targeting the nucleus accumbens (NAc)/ventral capsule (VC) and potential impact on outcomes in individuals with treatment-refractory OUD. METHODS: A prospective, open-label, single-arm study was conducted among participants with longstanding treatment-refractory OUD (along with other co-occurring SUDs) who underwent DBS in the NAc/VC. The primary study endpoint was safety; secondary/exploratory outcomes included opioid and other substance use, substance craving, and emotional symptoms throughout follow-up and 18FDG-PET neuroimaging. RESULTS: Four male participants were enrolled and all tolerated DBS surgery well with no serious adverse events (AEs) and no device- or stimulation-related AEs. Two participants sustained complete substance abstinence for > 1150 and > 520 days, respectively, with significant post-DBS reductions in substance craving, anxiety, and depression. One participant experienced post-DBS drug use recurrences with reduced frequency and severity. The DBS system was explanted in one participant due to noncompliance with treatment requirements and the study protocol. 18FDG-PET neuroimaging revealed increased glucose metabolism in the frontal regions for the participants with sustained abstinence only. CONCLUSIONS: DBS of the NAc/VC was safe, feasible, and can potentially reduce substance use, craving, and emotional symptoms in those with treatment-refractory OUD. A randomized, sham-controlled trial in a larger cohort of patients is being initiated.

Low-intensity focused ultrasound targeting the nucleus accumbens as a potential treatment for substance use disorder: safety and feasibility clinical trial.

Introduction: While current treatments for substance use disorder (SUD) are beneficial, success rates remain low and treatment outcomes are complicated by co-occurring SUDs, many of which are without available medication treatments. Research involving neuromodulation for SUD has recently gained momentum. This study evaluated two doses (60 and 90 W) of Low Intensity Focused Ultrasound (LIFU), targeting the bilateral nucleus accumbens (NAc), in individuals with SUD. Methods: Four participants (three male), who were receiving comprehensive outpatient treatment for opioid use disorder at the time of enrollment and who also had a history of excessive non-opioid substance use, completed this pilot study. After confirming eligibility, these participants received 10 min sham LIFU followed by 20 min active LIFU (10 min to left then right NAc). Outcomes were the safety, tolerability, and feasibility during the LIFU procedure and throughout the 90-day follow-up. Outcomes also included the impact of LIFU on cue-induced substance craving, assessed via Visual Analog Scale (VAS), both acutely (pre-, during and post-procedure) and during the 90-day follow-up. Daily craving ratings (without cues) were also obtained for one-week prior to and one-week following LIFU. Results: Both LIFU doses were safe and well-tolerated based on reported adverse events and MRI scans revealed no structural changes (0 min, 24 h, and 1-week post-procedure). For the two participants receiving "enhanced" (90 W) LIFU, VAS craving ratings revealed active LIFU attenuated craving for participants' primary substances of choice relative to sham sonication. For these participants, reductions were also noted in daily VAS craving ratings (0 = no craving; 10 = most craving ever) across the week following LIFU relative to pre-LIFU; Participant #3 pre- vs. post-LIFU: opioids (3.6 ± 0.6 vs. 1.9 ± 0.4), heroin (4.2 ± 0.8 vs. 1.9 ± 0.4), methamphetamine (3.2 ± 0.4 vs. 0.0 ± 0.0), cocaine (2.4 ± 0.6 vs. 0.0 ± 0.0), benzodiazepines (2.8 ± 0.5 vs. 0.0 ± 0.0), alcohol (6.0 ± 0.7 vs. 2.7 ± 0.8), and nicotine (5.6 ± 1.5 vs. 3.1 ± 0.7); Participant #4: alcohol (3.5 ± 1.3 vs. 0.0 ± 0.0) and nicotine (5.0 ± 1.8 vs. 1.2 ± 0.8) (all p's < 0.05). Furthermore, relative to screening, longitudinal reductions in cue-induced craving for several substances persisted during the 90-day post-LIFU follow-up evaluation for all participants. Discussion: In conclusion, LIFU targeting the NAc was safe and acutely reduced substance craving during the LIFU procedure, and potentially had longer-term impact on craving reductions. While early observations are promising, NAc LIFU requires further investigation in a controlled trial to assess the impact on substance craving and ultimately substance use and relapse.

Identifying biomarkers of drug use recurrence using wearable device technologies and phone applications.

BACKGROUND: Identifying predictors of drug use recurrence (DUR) is critical to combat the addiction epidemic. Wearable devices and phone-based applications for obtaining self-reported assessments in the patient's natural environment (e.g., ecological momentary assessment; EMA) have been used in various healthcare settings. However, the utility of combining these technologies to predict DUR in substance use disorder (SUD) has not yet been explored. This study investigates the combined use of wearable technologies and EMA as a potential mechanism for identifying physiological/behavioral biomarkers of DUR. METHODS: Participants, recruited from an SUD treatment program, were provided with a commercially available wearable device that continuously monitors biometric signals (e.g., heart rate/variability [HR/HRV], sleep characteristics). They were also prompted daily to complete an EMA via phone-based application (EMA-APP) that included questionnaires regarding mood, pain, and craving. RESULTS: Seventy-seven participants are included in this pilot study (34 participants experienced a DUR during enrollment). Wearable technologies revealed that physiological markers were significantly elevated in the week prior to DUR relative to periods of sustained abstinence (p<0.001). Results from the EMA-APP revealed that those who experienced a DUR reported greater difficulty concentrating, exposure to triggers associated with substance use, and increased isolation the day prior to DUR (p<0.001). Compliance with study procedures during the DUR week was lower than any other period of measurement (p<0.001). CONCLUSIONS: These results suggest that data acquired via wearable technologies and the EMA-APP may serve as a method of predicting near-term DUR, thereby potentially prompting intervention before drug use occurs.

Assessing the effects of therapeutic combinations on SARS-CoV-2 infected patient outcomes: A big data approach.

BACKGROUND: The COVID-19 pandemic has demonstrated the need for efficient and comprehensive, simultaneous assessment of multiple combined novel therapies for viral infection across the range of illness severity. Randomized Controlled Trials (RCT) are the gold standard by which efficacy of therapeutic agents is demonstrated. However, they rarely are designed to assess treatment combinations across all relevant subgroups. A big data approach to analyzing real-world impacts of therapies may confirm or supplement RCT evidence to further assess effectiveness of therapeutic options for rapidly evolving diseases such as COVID-19. METHODS: Gradient Boosted Decision Tree, Deep and Convolutional Neural Network classifiers were implemented and trained on the National COVID Cohort Collaborative (N3C) data repository to predict the patients' outcome of death or discharge. Models leveraged the patients' characteristics, the severity of COVID-19 at diagnosis, and the calculated proportion of days on different treatment combinations after diagnosis as features to predict the outcome. Then, the most accurate model is utilized by eXplainable Artificial Intelligence (XAI) algorithms to provide insights about the learned treatment combination impacts on the model's final outcome prediction. RESULTS: Gradient Boosted Decision Tree classifiers present the highest prediction accuracy in identifying patient outcomes with area under the receiver operator characteristic curve of 0.90 and accuracy of 0.81 for the outcomes of death or sufficient improvement to be discharged. The resulting model predicts the treatment combinations of anticoagulants and steroids are associated with the highest probability of improvement, followed by combined anticoagulants and targeted antivirals. In contrast, monotherapies of single drugs, including use of anticoagulants without steroid or antivirals are associated with poorer outcomes. CONCLUSIONS: This machine learning model by accurately predicting the mortality provides insights about the treatment combinations associated with clinical improvement in COVID-19 patients. Analysis of the model's components suggests benefit to treatment with combination of steroids, antivirals, and anticoagulant medication. The approach also provides a framework for simultaneously evaluating multiple real-world therapeutic combinations in future research studies.

Community risks for SARS-CoV-2 infection among fully vaccinated US adults by rurality: A retrospective cohort study from the National COVID Cohort Collaborative.

BACKGROUND: While COVID-19 vaccines reduce adverse outcomes, post-vaccination SARS-CoV-2 infection remains problematic. We sought to identify community factors impacting risk for breakthrough infections (BTI) among fully vaccinated persons by rurality. METHODS: We conducted a retrospective cohort study of US adults sampled between January 1 and December 20, 2021, from the National COVID Cohort Collaborative (N3C). Using Kaplan-Meier and Cox-Proportional Hazards models adjusted for demographic differences and comorbid conditions, we assessed impact of rurality, county vaccine hesitancy, and county vaccination rates on risk of BTI over 180 days following two mRNA COVID-19 vaccinations between January 1 and September 21, 2021. Additionally, Cox Proportional Hazards models assessed the risk of infection among adults without documented vaccinations. We secondarily assessed the odds of hospitalization and adverse COVID-19 events based on vaccination status using multivariable logistic regression during the study period. RESULTS: Our study population included 566,128 vaccinated and 1,724,546 adults without documented vaccination. Among vaccinated persons, rurality was associated with an increased risk of BTI (adjusted hazard ratio [aHR] 1.53, 95% confidence interval [CI] 1.42-1.64, for urban-adjacent rural and 1.65, 1.42-1.91, for nonurban-adjacent rural) compared to urban dwellers. Compared to low vaccine-hesitant counties, higher risks of BTI were associated with medium (1.07, 1.02-1.12) and high (1.33, 1.23-1.43) vaccine-hesitant counties. Compared to counties with high vaccination rates, a higher risk of BTI was associated with dwelling in counties with low vaccination rates (1.34, 1.27-1.43) but not medium vaccination rates (1.00, 0.95-1.07). Community factors were also associated with higher odds of SARS-CoV-2 infection among persons without a documented vaccination. Vaccinated persons with SARS-CoV-2 infection during the study period had significantly lower odds of hospitalization and adverse events across all geographic areas and community exposures. CONCLUSIONS: Our findings suggest that community factors are associated with an increased risk of BTI, particularly in rural areas and counties with high vaccine hesitancy. Communities, such as those in rural and disproportionately vaccine hesitant areas, and certain groups at high risk for adverse breakthrough events, including immunosuppressed/compromised persons, should continue to receive public health focus, targeted interventions, and consistent guidance to help manage community spread as vaccination protection wanes.

Focused ultrasound-mediated blood-brain barrier opening in Alzheimer's disease: long-term safety, imaging, and cognitive outcomes.

OBJECTIVE: MRI-guided low-intensity focused ultrasound (FUS) has been shown to reversibly open the blood-brain barrier (BBB), with the potential to deliver therapeutic agents noninvasively to target brain regions in patients with Alzheimer's disease (AD) and other neurodegenerative conditions. Previously, the authors reported the short-term safety and feasibility of FUS BBB opening of the hippocampus and entorhinal cortex (EC) in patients with AD. Given the need to treat larger brain regions beyond the hippocampus and EC, brain volumes and locations treated with FUS have now expanded. To evaluate any potential adverse consequences of BBB opening on disease progression, the authors report safety, imaging, and clinical outcomes among participants with mild AD at 6-12 months after FUS treatment targeted to the hippocampus, frontal lobe, and parietal lobe. METHODS: In this open-label trial, participants with mild AD underwent MRI-guided FUS sonication to open the BBB in ß-amyloid positive regions of the hippocampus, EC, frontal lobe, and parietal lobe. Participants underwent 3 separate FUS treatment sessions performed 2 weeks apart. Outcome assessments included safety, imaging, neurological, cognitive, and florbetaben ß-amyloid PET. RESULTS: Ten participants (range 55-76 years old) completed 30 separate FUS treatments at 2 participating institutions, with 6-12 months of follow-up. All participants had immediate BBB opening after FUS and BBB closure within 24-48 hours. All FUS treatments were well tolerated, with no serious adverse events related to the procedure. All 10 participants had a minimum of 6 months of follow-up, and 7 participants had a follow-up out to 1 year. Changes in the Alzheimer's Disease Assessment Scale-cognitive and Mini-Mental State Examination scores were comparable to those in controls from the Alzheimer's Disease Neuroimaging Initiative. PET scans demonstrated an average ß-amyloid plaque of 14% in the Centiloid scale in the FUS-treated regions. CONCLUSIONS: This study is the largest cohort of participants with mild AD who received FUS treatment, and has the longest follow-up to date. Safety was demonstrated in conjunction with reversible and repeated BBB opening in multiple cortical and deep brain locations, with a concomitant reduction of ß-amyloid. There was no apparent cognitive worsening beyond expectations up to 1 year after FUS treatment, suggesting that the BBB opening treatment in multiple brain regions did not adversely influence AD progression. Further studies are needed to determine the clinical significance of these findings. FUS offers a unique opportunity to decrease amyloid plaque burden as well as the potential to deliver targeted therapeutics to multiple brain regions in patients with neurodegenerative disorders.

Higher hospitalization and mortality rates among SARS-CoV-2-infected persons in rural America.

PURPOSE: Rural communities are among the most underserved and resource-scarce populations in the United States. However, there are limited data on COVID-19 outcomes in rural America. This study aims to compare hospitalization rates and inpatient mortality among SARS-CoV-2-infected persons stratified by residential rurality. METHODS: This retrospective cohort study from the National COVID Cohort Collaborative (N3C) assesses 1,033,229 patients from 44 US hospital systems diagnosed with SARS-CoV-2 infection between January 2020 and June 2021. Primary outcomes were hospitalization and all-cause inpatient mortality. Secondary outcomes were utilization of supplemental oxygen, invasive mechanical ventilation, vasopressor support, extracorporeal membrane oxygenation, and incidence of major adverse cardiovascular events or hospital readmission. The analytic approach estimates 90-day survival in hospitalized patients and associations between rurality, hospitalization, and inpatient adverse events while controlling for major risk factors using Kaplan-Meier survival estimates and mixed-effects logistic regression. FINDINGS: Of 1,033,229 diagnosed COVID-19 patients included, 186,882 required hospitalization. After adjusting for demographic differences and comorbidities, urban-adjacent and nonurban-adjacent rural dwellers with COVID-19 were more likely to be hospitalized (adjusted odds ratio [aOR] 1.18, 95% confidence interval [CI], 1.16-1.21 and aOR 1.29, CI 1.24-1.1.34) and to die or be transferred to hospice (aOR 1.36, CI 1.29-1.43 and 1.37, CI 1.26-1.50), respectively. All secondary outcomes were more likely among rural patients. CONCLUSIONS: Hospitalization, inpatient mortality, and other adverse outcomes are higher among rural persons with COVID-19, even after adjusting for demographic differences and comorbidities. Further research is needed to understand the factors that drive health disparities in rural populations.

Novel Strategies to Increase COVID-19 Testing Among Underserved and Vulnerable Populations in West Virginia.

This project addressed severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) testing barriers in rural West Virginia by providing testing enhancements that included (1) a flexible testing staff, (2) mobile testing, (3) essential supplies, and (4) specialized testing in communities of color. A total of 142 775 polymerase chain reaction tests were performed from December 2021 through February 2022; positivity rates were 21% and 17% in clinics and mobile testing venues, respectively. The project results showed that, within a statewide network of health care clinics, administrators quickly identified and distributed enhancements and thus reduced testing barriers. (Am J Public Health. 2022;112(S9):S892-S895. https://doi.org/10.2105/AJPH.2022.307004).

Persistence and Protective Potential of SARS-CoV-2 Antibody Levels After COVID-19 Vaccination in a West Virginia Nursing Home Cohort.

Importance: West Virginia prioritized SARS-CoV-2 vaccine delivery to nursing home facilities because of increased risk of severe illness in elderly populations. However, the persistence and protective role of antibody levels remain unclear. Objective: To examine the persistence of humoral immunity after COVID-19 vaccination and the association of SARS-CoV-2 antibody levels and subsequent infection among nursing home residents and staff. Design, Setting, and Participants: In this cross-sectional study, blood samples were procured between September 13 and November 30, 2021, from vaccinated residents and staff at participating nursing home facilities in the state of West Virginia for measurement of SARS-CoV-2 antibody (anti-receptor binding domain [RBD] IgG). SARS-CoV-2 infection and vaccination history were documented during specimen collection and through query of the state SARS-CoV-2 surveillance system through January 16, 2022. Exposure: SARS-CoV-2 vaccination (with BNT162b2, messenger RNA-1273, or Ad26.COV2.S). Main Outcomes and Measures: Anti-RBD IgG levels were assessed using multivariate analysis to examine associations between time since vaccination or infection, age, sex, booster doses, and vaccine type. Antibody levels from participants who became infected after specimen collection were compared with those without infection to correlate antibody levels with subsequent infection. Results: Among 2139 SARS-CoV-2 vaccinated residents and staff from participating West Virginia nursing facilities (median [range] age, 67 [18-103] years; 1660 [78%] female; 2045 [96%] White), anti-RBD IgG antibody levels decreased with time after vaccination or infection (mean [SE] estimated coefficient, -0.025 [0.0015]; P < .001). Multivariate regression modeling of participants with (n = 608) and without (n = 1223) a known history of SARS-CoV-2 infection demonstrated significantly higher mean (SE) antibody indexes with a third (booster) vaccination (with infection: 11.250 [1.2260]; P < .001; without infection: 8.056 [0.5333]; P < .001). Antibody levels (calculated by dividing the sample signal by the mean calibrator signal) were significantly lower among participants who later experienced breakthrough infection during the Delta surge (median, 2.3; 95% CI, 1.8-2.9) compared with those without breakthrough infection (median, 5.8; 95% CI, 5.5-6.1) (P = .002); however, no difference in absorbance indexes was observed in participants with breakthrough infections occurring after specimen collection (median, 5.9; 95% CI, 3.7-11.1) compared with those without breakthrough infection during the Omicron surge (median, 5.8; 95% CI, 5.6-6.2) (P = .70). Conclusions and Relevance: In this cross-sectional study, anti-RBD IgG levels decreased after vaccination or infection. Higher antibody responses were found in individuals who received a third (booster) vaccination. Although lower antibody levels were associated with breakthrough infection during the Delta surge, no significant association was found between antibody level and infection observed during the Omicron surge. The findings of this cross-sectional study suggest that among nursing home residents, COVID-19 vaccine boosters are important and updated vaccines effective against emerging SARS-CoV-2 variants are needed.

An ordinal severity scale for COVID-19 retrospective studies using Electronic Health Record data.

Objectives: Although the World Health Organization (WHO) Clinical Progression Scale for COVID-19 is useful in prospective clinical trials, it cannot be effectively used with retrospective Electronic Health Record (EHR) datasets. Modifying the existing WHO Clinical Progression Scale, we developed an ordinal severity scale (OS) and assessed its usefulness in the analyses of COVID-19 patient outcomes using retrospective EHR data. Materials and Methods: An OS was developed to assign COVID-19 disease severity using the Observational Medical Outcomes Partnership common data model within the National COVID Cohort Collaborative (N3C) data enclave. We then evaluated usefulness of the developed OS using heterogenous EHR data from January 2020 to October 2021 submitted to N3C by 63 healthcare organizations across the United States. Principal component analysis (PCA) was employed to characterize changes in disease severity among patients during the 28-day period following COVID-19 diagnosis. Results: The data set used in this analysis consists of 2 880 456 patients. PCA of the day-to-day variation in OS levels over the totality of the 28-day period revealed contrasting patterns of variation in disease severity within the first and second 14 days and illustrated the importance of evaluation over the full 28-day period. Discussion: An OS with well-defined, robust features, based on discrete EHR data elements, is useful for assessments of COVID-19 patient outcomes, providing insights on the progression of COVID-19 disease severity over time. Conclusions: The OS provides a framework that can facilitate better understanding of the course of acute COVID-19, informing clinical decision-making and resource allocation.

Association of Vitamin D Prescribing and Clinical Outcomes in Adults Hospitalized with COVID-19.

It is unclear whether vitamin D benefits inpatients with COVID-19. Objective: To examine the relationship between vitamin D and COVID-19 outcomes. Design: Cohort study. Setting: National COVID Cohort Collaborative (N3C) database. Patients: 158,835 patients with confirmed COVID-19 and a sub-cohort with severe disease (n = 81,381) hospitalized between 1 January 2020 and 31 July 2021. Methods: We identified vitamin D prescribing using codes for vitamin D and its derivatives. We created a sub-cohort defined as having severe disease as those who required mechanical ventilation or extracorporeal membrane oxygenation (ECMO), had hospitalization >5 days, or hospitalization ending in death or hospice. Using logistic regression, we adjusted for age, sex, race, BMI, Charlson Comorbidity Index, and urban/rural residence, time period, and study site. Outcomes of interest were death or transfer to hospice, longer length of stay, and mechanical ventilation/ECMO. Results: Patients treated with vitamin D were older, had more comorbidities, and higher BMI compared with patients who did not receive vitamin D. Vitamin D treatment was associated with an increased odds of death or referral for hospice (adjusted odds ratio (AOR) 1.10: 95% CI 1.05−1.14), hospital stay >5 days (AOR 1.78: 95% CI 1.74−1.83), and increased odds of mechanical ventilation/ECMO (AOR 1.49: 95% CI 1.44−1.55). In the sub-cohort of severe COVID-19, vitamin D decreased the odds of death or hospice (AOR 0.90, 95% CI 0.86−0.94), but increased the odds of hospital stay longer >5 days (AOR 2.03, 95% CI 1.87−2.21) and mechanical ventilation/ECMO (AOR 1.16, 95% CI 1.12−1.21). Limitations: Our findings could reflect more aggressive treatment due to higher severity. Conclusion: Vitamin D treatment was associated with greater odds of extended hospitalization, mechanical ventilation/ECMO, and death or hospice referral.

Predicting increases in COVID-19 incidence to identify locations for targeted testing in West Virginia: A machine learning enhanced approach.

During the COVID-19 pandemic, West Virginia developed an aggressive SARS-CoV-2 testing strategy which included utilizing pop-up mobile testing in locations anticipated to have near-term increases in SARS-CoV-2 infections. This study describes and compares two methods for predicting near-term SARS-CoV-2 incidence in West Virginia counties. The first method, Rt Only, is solely based on producing forecasts for each county using the daily instantaneous reproductive numbers, Rt. The second method, ML+Rt, is a machine learning approach that uses a Long Short-Term Memory network to predict the near-term number of cases for each county using epidemiological statistics such as Rt, county population information, and time series trends including information on major holidays, as well as leveraging statewide COVID-19 trends across counties and county population size. Both approaches used daily county-level SARS-CoV-2 incidence data provided by the West Virginia Department Health and Human Resources beginning April 2020. The methods are compared on the accuracy of near-term SARS-CoV-2 increases predictions by county over 17 weeks from January 1, 2021- April 30, 2021. Both methods performed well (correlation between forecasted number of cases and the actual number of cases week over week is 0.872 for the ML+Rt method and 0.867 for the Rt Only method) but differ in performance at various time points. Over the 17-week assessment period, the ML+Rt method outperforms the Rt Only method in identifying larger spikes. Results show that both methods perform adequately in both rural and non-rural predictions. Finally, a detailed discussion on practical issues regarding implementing forecasting models for public health action based on Rt is provided, and the potential for further development of machine learning methods that are enhanced by Rt.

Predicting increases in COVID-19 incidence to identify locations for targeted testing in West Virginia: A machine learning enhanced approach.

During the COVID-19 pandemic, West Virginia developed an aggressive SARS-CoV-2 testing strategy which included utilizing pop-up mobile testing in locations anticipated to have near-term increases in SARS-CXoV-2 infections. In this study, we describe and compare two methods for predicting near-term SARS-CoV-2 incidence in West Virginia counties. The first method, R t Only, is solely based on producing forecasts for each county using the daily instantaneous reproductive numbers, R t. The second method, ML+ R t , is a machine learning approach that uses a Long Short-Term Memory network to predict the near-term number of cases for each county using epidemiological statistics such as Rt, county population information, and time series trends including information on major holidays, as well as leveraging statewide COVID-19 trends across counties and county population size. Both approaches used daily county-level SARS-CoV-2 incidence data provided by the West Virginia Department Health and Human Resources beginning April 2020. The methods are compared on the accuracy of near-term SARS-CoV-2 increases predictions by county over 17 weeks from January 1, 2021-April 30, 2021. Both methods performed well (correlation between forecasted number of cases and the actual number of cases week over week is 0.872 for the ML+R t method and 0.867 for the R t Only method) but differ in performance at various time points. Over the 17-week assessment period, the ML+R t method outperforms the R t Only method in identifying larger spikes. We also find that both methods perform adequately in both rural and non-rural predictions. Finally, we provide a detailed discussion on practical issues regarding implementing forecasting models for public health action based on R t , and the potential for further development of machine learning methods that are enhanced by R t.

Prediction of viral symptoms using wearable technology and artificial intelligence: A pilot study in healthcare workers.

Conventional testing and diagnostic methods for infections like SARS-CoV-2 have limitations for population health management and public policy. We hypothesize that daily changes in autonomic activity, measured through off-the-shelf technologies together with app-based cognitive assessments, may be used to forecast the onset of symptoms consistent with a viral illness. We describe our strategy using an AI model that can predict, with 82% accuracy (negative predictive value 97%, specificity 83%, sensitivity 79%, precision 34%), the likelihood of developing symptoms consistent with a viral infection three days before symptom onset. The model correctly predicts, almost all of the time (97%), individuals who will not develop viral-like illness symptoms in the next three days. Conversely, the model correctly predicts as positive 34% of the time, individuals who will develop viral-like illness symptoms in the next three days. This model uses a conservative framework, warning potentially pre-symptomatic individuals to socially isolate while minimizing warnings to individuals with a low likelihood of developing viral-like symptoms in the next three days. To our knowledge, this is the first study using wearables and apps with machine learning to predict the occurrence of viral illness-like symptoms. The demonstrated approach to forecasting the onset of viral illness-like symptoms offers a novel, digital decision-making tool for public health safety by potentially limiting viral transmission.

Serological survey of SARS-CoV-2 incidence conducted at a rural West Virginia hospital.

The SARS-CoV-2 pandemic has affected all types of global communities. Differences in urban and rural environments have led to varying levels of transmission within these subsets of the population. To fully understand the prevalence and impact of SARS-CoV-2 it is critical to survey both types of community. This study establishes the prevalence of SARS-CoV-2 in a rural community: Montgomery, West Virginia. Approximately 10% of participants exhibited serological or PCR-based results indicating exposure to SARS-CoV-2 within 6 months of the sampling date. Quantitative analysis of IgG levels against SARS-CoV-2 receptor binding domain (RBD) was used to stratify individuals based on antibody response to SARS-CoV-2. A significant negative correlation between date of exposure and degree of anti-SARS-CoV-2 RBD IgG (R 2 = 0.9006) was discovered in addition to a correlation between neutralizing anti-SARS-CoV-2 antibodies (R 2 = 0.8880) and days post exposure. Participants were confirmed to have normal immunogenic profiles by determining serum reactivity B. pertussis antigens commonly used in standardized vaccines. No significant associations were determined between anti-SARS-CoV-2 RBD IgG and age or biological sex. Reporting of viral-like illness symptoms was similar in SARS-CoV-2 exposed participants greater than 30 years old (100% reporting symptoms 30-60 years old, 75% reporting symptoms >60 years old) in contrast to participants under 30 years old (25% reporting symptoms). Overall, this axnalysis of a rural population provides important information about the SARS-CoV-2 pandemic in small rural communities. The study also underscores the fact that prior infection with SARS-CoV-2 results in antibody responses that wane over time which highlights the need for vaccine mediated protection in the absence of lasting protection.