Contact Tracing and Epidemic Intervention via Deep Reinforcement Learning

The recent outbreak of COVID-19 poses a serious threat to people's lives. Epidemic control strategies have also caused damage to the economy by cutting off humans' daily commute. In this article, we develop an Individual-based Reinforcement Learning Epidemic Control Agent (IDRLECA) to search for smart epidemic control strategies that can simultaneously minimize infections and the cost of mobility intervention. IDRLECA first hires an infection probability model to calculate the current infection probability of each individual. Then, the infection probabilities together with individuals' health status and movement information are fed to a novel GNN to estimate the spread of the virus through human contacts. The estimated risks are used to further support an RL agent to select individual-level epidemic-control actions. The training of IDRLECA is guided by a specially designed reward function considering both the cost of mobility intervention and the effectiveness of epidemic control. Moreover, we design a constraint for control-action selection that eases its difficulty and further improve exploring efficiency. Extensive experimental results demonstrate that IDRLECA can suppress infections at a very low level and retain more than 95% of human mobility. © 2023 Copyright held by the owner/author(s). Publication rights licensed to ACM.

GeauxTrace: A Scalable Privacy-Protecting Contact Tracing App Design Using Blockchain

Contact tracing is the approach to identifying physical contact between human beings using a variety of data such as personal details and locations to discover the potential infection of diseases. Since the outbreak of the COVID-19 pandemic, contact tracing has been used extensively to quarantine the people at risk to stop the spread. Moreover, the data collected during contact tracing are typical spatiotemporal data, which can be used to study the disease and discover the spread pattern. However, both traditional labor-intensive and modern digital-based approaches have limitations in terms of cost and privacy concerns. In this paper, we proposed GeauxTrace, a Blockchain-based privacy-protecting contact tracing platform, which separates private data from proof of contact. Sensitive data collected by the front-end app via Bluetooth-based methods are stored locally, and only the proofs of contacts are uploaded onto the immutable private blockchain, which forms a global contact graph at the backend. Our approach not only enables multi-hop risky users to be notified but also reveals the infection patterns via the global graph, which could help study diseases and assist the policymaker. Our implementation shows the feasibility of the proposed platform in real-world scenarios and achieves the performance of 20-30 user requests per second. © 2022 IEEE.

Reviving the economy while saving lives: a deep reinforcement learning approach for smart POI reopening

With the gradual improvements in COVID-19 metrics and the accelerated immunization progress, countries around the world have began to focus on reviving the economy while continuously strengthening epidemic control. POInt-of-Interest (POI) reopening, as a necessity for restoring human mobilities, has become a crucial step to recouple economic recovery and public health management. In contrast to the lock-down policy, POI reopening demands a dynamic trade-off between epidemic interventions and economic costs. In the urban scenario, there exist three key challenges in developing effective POI reopening strategies as follows. (1) During the POI reopening process, there are multiple urban factors affecting the epidemic transmission, which are difficult to simultaneously incorporate and balance in a single reopening strategy;(2) the effects of POI reopening on both economic recovery and epidemic control are long-term, which are hard to capture by static models;and (3) the dual objectives of minimizing infections and maintaining POIs' visits are conflicting, making it difficult to achieve a flexible and scalable trade-off. To tackle the above challenges, we propose Reopener, a deep reinforcement learning (RL) framework for smart POI reopening. First, we utilize a bipartite graph neural network to automatically encode all urban factors that would affect the epidemic prevention and POI visit restriction. Second, we employ a RL-based deep policy network to enable flexible updates in restrictions on POIs along with the trend of epidemic. Third, we design a novel reward function to guide the RL agent to learn smartly, thus comprehensively trading off infections and visit sustainability of POIs. Extensive experimental results demonstrate that Reopener outperforms all baseline methods with remarkable improvements, by reducing the overall economic cost by at least 6.42%. Reopener can effectively suppress infections and support a phase-based POI reopening process, which provides valuable insights for strategy design in post-COVID-19 economic recovery. © 2022 Owner/Author.

Precise Mobility Intervention for Epidemic Control Using Unobservable Information via Deep Reinforcement Learning

To control the outbreak of COVID-19, efficient individual mobility intervention for EPidemic Control (EPC) strategies are of great importance, which cut off the contact among people at epidemic risks and reduce infections by intervening the mobility of individuals. Reinforcement Learning (RL) is powerful for decision making, however, there are two major challenges in developing an RL-based EPC strategy: (1) the unobservable information about asymptomatic infections in the incubation period makes it difficult for RL's decision-making, and (2) the delayed rewards for RL causes the deficiency of RL learning. Since the results of EPC are reflected in both daily infections (including unobservable asymptomatic infections) and long-term cumulative cases of COVID-19, it is quite daunting to design an RL model for precise mobility intervention. In this paper, we propose a Variational hiErarcHICal reinforcement Learning method for Epidemic control via individual-level mobility intervention, namely Vehicle. To tackle the above challenges, Vehicle first exploits an information rebuilding module that consists of a contact-risk bipartite graph neural network and a variational LSTM to restore the unobservable information. The contact-risk bipartite graph neural network estimates the possibility of an individual being an asymptomatic infection and the risk of this individual spreading the epidemic, as the current state of RL. Then, the Variational LSTM further encodes the state sequence to model the latency of epidemic spreading caused by unobservable asymptomatic infections. Finally, a Hierarchical Reinforcement Learning framework is employed to train Vehicle, which contains dual-level agents to solve the delayed reward problem. Extensive experimental results demonstrate that Vehicle can effectively control the spread of the epidemic. Vehicle outperforms the state-of-the-art baseline methods with remarkably high-precision mobility interventions on both symptomatic and asymptomatic infections. © 2022 Owner/Author.

A Neural Predictive Model of Negative Emotions for COVID-19

The long-lasting global pandemic of Coronavirus disease 2019 (COVID-19) has changed our daily life in many ways and put heavy burden on our mental health. Having a predictive model of negative emotions during COVID-19 is of great importance for identifying potential risky population. To establish a neural predictive model achieving both good interpretability and predictivity, we have utilized a large-scale (n =542) longitudinal dataset, alongside two independent samples for external validation. We built a predictive model based on psychologically meaningful resting state neural activities. The whole-brain resting-state neural activity and social-psychological profile of the subjects were obtained from Sept. to Dec. 2019 (Time 1). Their negative emotions were tracked and re-assessed twice, on Feb 22 (Time 2) and Apr 24 (Time 3), 2020, respectively. We first applied canonical correlation analysis on both the neural profiles and psychological profiles collected on Time 1, this step selects only the psychological meaningful neural patterns for later model construction. We then trained the neural predictive model using those identified features on data obtained on Time 2. It achieved a good prediction performance (r =0.44, p =8.13 ×10-27). The two most important neural predictors are associated with self-control and social interaction. This study established an effective neural prediction model of negative emotions, achieving good interpretability and predictivity. It will be useful for identifying potential risky population of emotional disorders related to COVID-19. IEEE

Procalcitonin levels in COVID-19 patients are strongly associated with mortality and ICU acceptance in an underserved, inner city population

Rationale: The novel severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), which causes COVID-19, has led to a global health crisis unlike any our contemporaries have witnessed before. SUNY Downstate Health Sciences University was designated as one of three COVID-19-only hospitals on March 28, 2020. This retrospective, single-center observational study grants a unique perspective surrounding the experience of the critical care service at a public institution serving a predominantly Afro-Caribbean, inner city population. Methods: Between March 11 and April 30, 2020, the critical care service was consulted for a total of 271 COVID-19 patients. We queried the electronic medical record for patient visits with critical care consult notes and collected data on demographics, comorbidities, ICU acceptance, treatment strategies, and clinical outcomes. Non-COVIDrelated consults were excluded. Chi-squared tests compared categorical variables, and independent samples ttest assessed differences in continuous variables based on mortality and ICU admission status. Logistic regression models determined if various factors independently predicted the odds of mortality. We conducted retrospective analyses to identify factors associated with survival and ICU acceptance. Results: Of the 271 patients with critical care consults, 33% (n=89) survived and 67% (n=182) expired. At the bivariate level, age, BUN, and neutrophil percentage were significantly associated with mortality, with age showing the strongest correlation (age: survivors, 61.62±1.50 vs. non-survivors, 68.98±0.85, p<0.001). There was a significant association between neutrophil percentage and mortality in the univariate logistic regression model (Q4 vs. Q1, OR 2.73, 95% CI (1.28-5.82), p trend = 0.044). In the multivariate analyses, procalcitonin exhibited a positive correlation with the odds of mortality, adjusting for age, sex, and race/ethnicity (procalcitonin: Q4 vs. Q1, OR 5.65, 95% CI (2.14-14.9), p trend <0.001). Adjusting for the same covariates, platelets exhibited a negative correlation with the odds of mortality (Q4 vs. Q1, OR 0.47, 95% CI (0.22-0.998), p trend = 0.010). Interestingly, of these factors, only elevated procalcitonin levels were associated with an increased likelihood of ICU acceptance. Conclusions: This retrospective, observational study during the first peak of the COVID-19 pandemic identified key factors linked to disease severity and outcomes. Of note, procalcitonin was the factor most strongly associated with both mortality and likelihood of ICU acceptance at the bivariate level. Respiratory failure is the primary cause of death in COVID-19, and our data suggests that procalcitonin is a useful marker that accurately reflects the severity of lung involvement during SARS-CoV-2 infection.

5G Healthcare Applications in COVID-19 Prevention and Control

This paper mainly focuses on the application of 5G mobile communication systems in COVID-19 prevention and control. Firstly, for the different stages of epidemic prevention and control, we give a detailed introduction for the application cases. Secondly, the application of the epidemic is summarized, and the results obtained by each application are analyzed. Then, the problems and challenge faced by 5G healthcare applications during the epidemic are analyzed. In response to these problems and challenges, we put forward suggestions for the next step. The summary, analysis and work suggestions made in this article, provide an experience for the world to fight against the COVID-19 epidemic. In addition, the research in this paper helps to promote the construction of 5G medical and health standards systems, and provides a reference for the integrated development of 5G networks and medical health. © 2020 ITU.

Clinical characteristics of several patients with coronavirus disease 2019 in Lanzhou City

Objective: To investigate and summarize the clinical and imaging features of a few patients with coronavirus disease 2019 (COVID-19) in Lanzhou City. Methods: We carried out a retrospective analysis of the epidemiological data, laboratory results and clinical imaging features of eight hospitalized patients with confirmed COVID-19 in The First Hospital of Lanzhou University from January 23 to February 23, 2020. Results: The sex ratio (men to women) of the 8 patients was 5: 3 while their age ranged from 24 to 57 years old. The incubation period was 1-10 days. Of the 8 patients, 7(87.5%) had COVID-19 brought in from other places in China and 1(12.5%) was a secondary infection case. The main clinical manifestations included cough in 6 cases (75%), fever in 4 cases (50%), expectoration in 3 cases (37.5%), and fatigue in 2 cases (25%). All the 8 cases indicated abnormal manifestations in blood routine examinations, 4 cases (50%) decreased in WBC, 7 cases (87.5%) decreased in Lym count, 5 cases (62.5%) increased in LDH, 1 case (12.5%) increased in CK, 1 case(12.5%) increased in CK-MB, 4 cases (50%) increased in CRP, 2 cases (25%) increased in PCT, and 1 case (12.5%) increased in D-dimer. Of the 2 patients examined by chest digital radiography (DR), one DR finding was not typical and the other one suggested increased bilateral lung markings. Six patients were examined by HRCT, of whom four (50%) showed multiple ground glass opacities on both lobes and two (25%) showed multiple ground glass opacities only on the right lobe;none of the 6 imaging findings suggested pleural effusion. Six patients were discharged from hospital after being cured and 1 patient still underwent treatment. Conclusion: Most of these 8 patients had COVID-19 imported from outside the city, and the patients were relatively young with few underlying diseases. Their major symptoms were fever, cough, and expectoration. All of them exhibited abnormal findings in blood routine examinations;half of them suggested increased CRP while a few ones showed abnormal CK and Ddimer values. The imaging manifestations of most patients were multiple ground glass opacities near the peripheral pleura.

[Evaluation of the emergency response strategies and measures on the epidemic of COVID-19 in Shenzhen, China].

Objectives: This study aimed to evaluate the effect of the strategies on COVID-19 outbreak control in Shenzhen, and to clarify the feasibility of these strategies in metropolitans that have high population density and strong mobility. Methods: The epidemic feature of COVID-19 was described by different phases and was used to observe the effectiveness of intervention. Hierarchical spot map was drawn to clarify the distribution and transmission risk of infection sources at different time points. The Susceptible-Exposed-Infectious-Asymptomatic-Recovered model was established to estimate case numbers without intervention and compare with the actual number of cases to determine the effect of intervention. The positive rate of the nucleic acid test was used to reflect the risk of human exposure. A survey on COVID-19 related knowledge, attitude and behaviors were used to estimate the abilities of personal protection and emergency response. Results: The epidemic of COVID-19 in Shenzhen experienced the rising, plateau and decline stage. The case number increased rapidly at the beginning, with short duration of peak period. Although the epidemic curve showed human-to-human transmission, the "trailing" was not obvious. From the spot map, during the intervention period, the source of infection was widely distributed. More cases and higher transmission risk were observed in areas with higher population density. After the effective intervention measures, both infection sources and the risk of transmission decreased. After compared with the estimated case numbers without intervention, actual number proved the COVID-19 control strategies were effective. The positive rate of nucleic acid test for high risk populations decreased and no new cases reported since February 16. Shenzhen citizens had high knowledge, attitude and behavior level, and high protection ability and emergency response. Conclusions: Although the response initiated by the health administration department played a key role at the early stage of the epidemic, it was not enough to contain the outbreak of COVID-19. The first-level emergency response initiated by provincial and municipal government was effective and ensured the start of work resumption after the Spring Festival. Metropolitans like Shenzhen can also achieve the goals of strategies and measures for containment and mitigation of COVID-19.

Current situation and suggestions for ophthalmic medical work at a non-COVID-19 treatment hospital in later stages of epidemic in Wuhan, China

The epidemic of COVID-19 displays a declining trend in China with the enhanced containment and mitigation strategies, and public's normal demand for medical treatment is increasing sharply.The current focus is to ensure the daily medical services needed by non-COVID-19 patients while preventing and controlling the epidemic of COVID-19.Although ophthalmologists do not work on the front lines of COVID-19 outbreak, due to their area of expertise, a variety of situations, such as infection consultations or ophthalmic emergency treatments, can lead to the exposure of ophthalmologists to high-risk environments.This paper mainly analyzes the problems existing in work and life of ophthalmic medical staffs in a fixed-point treatment hospital for non-COVID-19 patients in later stages of the epidemic, and make recommendations and responses, which is helpful to us to obtain guarantee in both safety and quality of medical services, avoid cross-contamination in clinical practice, reduce infectious risk among ophthalmic medical staffs and lessen the mental and spiritual stress for medical staffs.