Introduction to the Special Track on Artificial Intelligence and COVID-19

The human race is facing one of the most meaningful public health emergencies in the modern era caused by the COVID-19 pandemic. This pandemic introduced various challenges, from lock-downs with significant economic costs to fundamentally altering the way of life for many people around the world. The battle to understand and control the virus is still at its early stages yet meaningful insights have already been made. The uncertainty of why some patients are infected and experience severe symptoms, while others are infected but asymptomatic, and others are not infected at all, makes managing this pandemic very challenging. Furthermore, the development of treatments and vaccines relies on knowledge generated from an ever evolving and expanding information space. Given the availability of digital data in the modern era, artificial intelligence (AI) is a meaningful tool for addressing the various challenges introduced by this unexpected pandemic. Some of the challenges include: outbreak prediction, risk modeling including infection and symptom development, testing strategy optimization, drug development, treatment repurposing, vaccine development, and others. © 2023 AI Access Foundation. All rights reserved.

Informing Building Strategies to Reduce Infectious Aerosol Transmission Risk by Integrating DNA Aerosol Tracers with Quantitative Microbial Risk Assessment.

Using aerosol-based tracers to estimate risk of infectious aerosol transmission aids in the design of buildings with adequate protection against aerosol transmissible pathogens, such as SARS-CoV-2 and influenza. We propose a method for scaling a SARS-CoV-2 bulk aerosol quantitative microbial risk assessment (QMRA) model for impulse emissions, coughing or sneezing, with aerosolized synthetic DNA tracer concentration measurements. With point-of-emission ratios describing relationships between tracer and respiratory aerosol emission characteristics (i.e., volume and RNA or DNA concentrations) and accounting for aerosolized pathogen loss of infectivity over time, we scale the inhaled pathogen dose and risk of infection with time-integrated tracer concentrations measured with a filter sampler. This tracer-scaled QMRA model is evaluated through scenario testing, comparing the impact of ventilation, occupancy, masking, and layering interventions on infection risk. We apply the tracer-scaled QMRA model to measurement data from an ambulatory care room to estimate the risk reduction resulting from HEPA air cleaner operation. Using DNA tracer measurements to scale a bulk aerosol QMRA model is a relatively simple method of estimating risk in buildings and can be applied to understand the impact of risk mitigation efforts.

Precision recruitment for high-risk participants in a COVID-19 cohort study.

Background: Studies for developing diagnostics and treatments for infectious diseases usually require observing the onset of infection during the study period. However, when the infection base rate incidence is low, the cohort size required to measure an effect becomes large, and recruitment becomes costly and prolonged. We developed a model for reducing recruiting time and resources in a COVID-19 detection study by targeting recruitment to high-risk individuals. Methods: We conducted an observational longitudinal cohort study at individual sites throughout the U.S., enrolling adults who were members of an online health and research platform. Through direct and longitudinal connection with research participants, we applied machine learning techniques to compute individual risk scores from individually permissioned data about socioeconomic and behavioral data, in combination with predicted local prevalence data. The modeled risk scores were then used to target candidates for enrollment in a hypothetical COVID-19 detection study. The main outcome measure was the incidence rate of COVID-19 according to the risk model compared with incidence rates in actual vaccine trials. Results: When we used risk scores from 66,040 participants to recruit a balanced cohort of participants for a COVID-19 detection study, we obtained a 4- to 7-fold greater COVID-19 infection incidence rate compared with similar real-world study cohorts. Conclusion: This risk model offers the possibility of reducing costs, increasing the power of analyses, and shortening study periods by targeting for recruitment participants at higher risk.

Impact of COVID-19 lockdown and health risk modeling of polycyclic aromatic hydrocarbons in Onne, Nigeria.

The people living in Onne are highly vulnerable to PAH exposure due to constant exposure to black soot through oral, dermal, and inhalation routes. This work aims to determine the PAHs profile of selected soils in Onne, to determine the health risks associated with PAHs exposure through the soil, and to determine the impact of reduced industrial and other activities on the PAHs profile and associated public health risks. This study evaluated 16 priority polycyclic aromatic hydrocarbon (PAHs) pollutants in soil samples from the four (4) major clans in Onne using a gas chromatography flame ionization detector (GC-FID) during and after the COVID-19 lockdown. The results showed a differential presence of PAHs during and after the lockdown. Of the 16 priority PAHs, 10 and 8 PAHs were respectively detected during and after the COVID-19 lockdown. High molecular weight PAHs such as benzo(k)fluoranthene and benzo(a)anthracene were major contributors during the lockdown, while low molecular weight PAHs such as naphthalene, acenaphthylene, and fluorene were present at higher levels after the lockdown. An assessment of health risk by incremental lifetime cancer risks revealed that the entire population of Onne might be at risk of cancer development across periods, though a higher risk was presented during the lockdown. In addition, children under the age of 18 may be at greater risk. To the best of our knowledge, there is no previous report on the impact of the COVID-19 lockdown on soil PAH profile and health risks, with particular attention to the Onne industrial host community. Earlier work considered the ecological risks of heavy metals on dumpsites in Onne. Taken together, the PAH-contaminated soil in Onne poses an immediate health concern. Therefore, reduced anthropological activities, as evident during the COVID-19 lockdown, may play a role in exposure and cancer risk reduction. While there may not be another lockdown due to the challenging impacts associated with a physical lockdown, firmly controlled economic activity can be a solution if embraced by stakeholders. The COVID-19-lockdown was encumbered with restricted movements and security checks, which limited the number of samples collected. However, the Local Government Council (Department of the Environment) granted permission for the researchers to work with a minimal threat to their lives.

Credit Risk Models in the Mexican Context Using Machine Learning

The Default Rate is related to the period of the economic cycle in which they are observed, during expansion periods of the economy the default rate tends to be lower. But in contraction periods, the default rate tends to increase and this could be a risk for the stability of a country’s economy. Therefore, it is important to monitor the perspective of the economy in case it is expected to decrease or have abrupt movements. This work aims to identify the economic variables that determine the default rate of the Mexican Financial System and to find a machine learning model that forecasts the default rate. For this, we aggregate a dataset based on three official Mexican sources that compile data from 2013 to 2022, including the COVID-19 pandemic time frame. Then, we propose the analysis using two machine learning models. After the analysis, the results confirm that the artificial neural networks model shows better predictive power for the default rate values. We also implement an easy to use web application to estimate the default rate based on three simple variables. We anticipate this work might help on estimating the default rate and might impact on the strategic policies in the Mexican economy. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Spatial-temporal monitoring risk analysis and decision-making of COVID-19 distribution by region

The purpose of this study is to model, map, and identify why some areas present a completely different dispersion pattern of COVID-19, as well as creating a risk model, composed of variables such as probability, susceptibility, danger, vulnerability, and potential damage, that characterises each of the defined regions. The model is based on a risk conceptual model proposed by Bachmann and Allgower in 2001, based on the wildfire terminology, analysing the spatial distribution. Additionally, a model based on population growth, chaotic maps, and turbulent flows is applied in the calculation of the variable probability, based on the work of Bonasera (2020). The results for the Portuguese case are promising, regarding the fitness of the said models and the outcome results of a conceptual model for the epidemiological risk assessment for the spread of coronavirus for each region. © 2022 Inderscience Enterprises Ltd.. All rights reserved.

Using a Deep Neural Network in a Relative Risk Model to Estimate Vaccination Protection for COVID-19

The proportional hazard Cox model is traditionally used in survival analysis to estimate the effect of several variables on the hazard rate of an event. Recently, neural networks were proposed to improve the flexibility of the Cox model. In this work, we focus on an extension of the Cox model, namely on a non-proportional relative risk model, where the neural network approximates a non-linear time-dependent risk function. We address the issue of the lack of time-varying variables in this model, and to this end, we design a deep neural network model capable of time-varying regression. The target application of our model is the waning of post-vaccination and post-infection immunity in COVID-19. This task setting is challenging due to the presence of multiple time-varying variables and different epidemic intensities at infection times. The advantage of our model is that it enables a fine-grained analysis of risks depending on the time since vaccination and/or infection, all approximated using a single non-linear function. A case study on a data set containing all COVID-19 cases in the Czech Republic until the end of 2021 has been performed. The vaccine effectiveness for different age groups, vaccine types, and the number of doses received was estimated using our model as a function of time. The results are in accordance with previous findings while allowing greater flexibility in the analysis due to a continuous representation of the waning function. © 2022, Springer Nature Switzerland AG.

Analytic modeling and risk assessment of aerial transmission of SARS-CoV-2 virus through vaping expirations in shared micro-environments.

It is well known that airborne transmission of COVID-19 in indoor spaces occurs through various respiratory activities: breathing, vocalizing, coughing, and sneezing. However, there is a complete lack of knowledge of its possible transmission through exhalations of e-cigarette aerosol (ECA), which is also a respiratory activity. E-cigarettes have become widely popular among smokers seeking a much safer way of nicotine consumption than smoking. Due to restrictive lockdown measures taken during the COVID-19 pandemic, many smokers and vapers (e-cigarette users) were confined to shared indoor spaces, making it necessary to assess the risk of SARS-CoV-2 virus aerial transmission through their exhalations. We summarize inferred knowledge of respiratory particles emission and transport through ECA, as well as a theoretical framework for explaining the visibility of exhaled ECA, which has safety implications and is absent in other respiratory activities (apart from smoking). We also summarize and briefly discuss the effects of new SARS-CoV-2 variants, vaccination rates, and environmental factors that may influence the spread of COVID-19. To estimate the risk of SARS-CoV-2 virus aerial transmission associated with vaping exhalations, we adapt a theoretical risk model that has been used to analyze the risks associated with other respiratory activities in shared indoor spaces. We consider home and restaurant scenarios, with natural and mechanical ventilation, with occupants wearing and not wearing face masks. We consider as "control case" or baseline risk scenario an indoor space (home and restaurant) where respiratory droplets and droplet nuclei are uniformly distributed and aerial contagion risk might originate exclusively from occupants exclusively rest breathing, assuming this to be the only (unavoidable) respiratory activity they all carry on. If an infected occupant uses an e-cigarette in a home or restaurant scenarios, bystanders not wearing face masks exposed to the resulting ECA expirations face a [Formula: see text] increase of risk of contagion with respect the control case. This relative added risk with respect to the control case becomes [Formula: see text] for high-intensity vaping, [Formula: see text], and over [Formula: see text] for speaking for various periods or coughing (all without vaping). Infectious emissions are significantly modified by mechanical ventilation, face mask usage, vaccination, and environmental factors, but given the lack of empiric evidence, we assume as a working hypothesis that all basic parameters of respiratory activities are equally (or roughly equally) affected by these factors. Hence, the relative risk percentages with respect to the control state should remain roughly the same under a wide range of varying conditions. By avoiding direct exposure to the visible exhaled vaping jet, wearers of commonly used face masks are well protected from respiratory droplets and droplet nuclei directly emitted by mask-less vapers. Compared to the control case of an already existing (unavoidable) risk from continuous breathing, vaping emissions in shared indoor spaces pose just a negligible additional risk of COVID-19 contagion. We consider that it is not necessary to take additional preventive measures beyond those already prescribed (1.5 m separation and wearing face masks) in order to protect bystanders from this contagion.

Optimizing operational strategies for mass transit systems in response to a global pandemic

This study analyzes the risk involved in riding various transit modes during and after a global pandemic. The goal is to identify which factors are related to this risk, how such a relationship can be represented in a manner amenable to analysis, and what a transit operator can do to mitigate the risk while running its service as efficiently as possible. The resulting infection risk model is sensitive to such factors as prevalence of infection, baseline transmission probability, social distance, and expected number of human contacts. Built on this model, we formulate, analyze and test three versions of a transit operator's design problem. In the first, the operator seeks to jointly optimize vehicle capacity and staff testing frequency while keeping the original service schedule and satisfying a predefined infection risk requirement. The second model assumes the operator is obligated to meet the returning demand after the peak of the pandemic. The third allows the operator to run more than one transit line and to allocate limited resources between the lines, subject to the penalty of unserved passengers. We find: (i) The optimal profit, as well as the testing frequency and the vehicle capacity, decreases when passengers expect to come in close contact with more fellow riders in a trip;(ii) Using a larger bus and/or reducing the testing cost enables the operator to both test drivers more frequently and allow more passengers in each bus;(iii) If passengers weigh the risk of riding bus relative to taxi, a higher prevalence of infection has a negative effect on transit operation, whereas a higher baseline transmission probability has a positive effect;(iv) The benefit of improving service capacity and/or testing more frequently is limited given the safety requirement. When the demand rises beyond the range of the capacity needed to maintain sufficient social distancing, the operator has no choice but to increase the service frequency;and (v) In the multi-line case, the lines that have a larger pre-pandemic demand, a higher penalty for each unserved passenger, or a greater exposure risk should be prioritized. © 2022 Elsevier Ltd

EU-27 bank failure prediction with C5.0 decision trees and deep learning neural networks

This article provides evidence that machine learning methods are suitable for reliably predicting the failure risk of European Union-27 banks from the experiences of the past decade. It demonstrates that earnings, capital adequacy, and management capability are the strongest predictors of bank failure. Critical and relevant field research is presented in the context of economic uncertainties arising from the COVID-19 pandemic. The results suggest that the developed models possess high predictive power, with the C5.0 decision tree model providing the best performance. The findings have policy implications for bank supervisory authorities, bank executives, risk management professionals, and policymakers working in finance. The models can be used to recognize bank weaknesses in time to take appropriate mitigating actions.

Identification of Maritime Education and Training Institutions (METIs) risk in pandemic restrictions

The unprecedented COVID-19 crisis apparently has questioned our systems' survivability nationally or even in a global context. The pandemic has proven the indispensable role of international shipping in our societies’ sustainability. Still, one of the main challenges for the shipping industry is to secure the supply of competent seafarers. Typically, Maritime Education and Training Institutions' (METIs’) core mission revolves around keeping such demand supplied, however in restrictive situations, METIs' capability to achieve their mission is still questionable. During the pandemic restrictions, METIs are likely exposed to many uncertainties that directly threaten their role and may lead to hazardous consequences. In such scenarios, many questions arise to challenge whether the institution/organizational levels of control are sufficient or additional barriers to keep the risk as low as reasonably practicable are needed. Consequently, this research investigates the possible threats exposed to METIs under such conditions, the potential consequences if they lose control of their operations, and the required barriers to prevent, detect, or protect the METIs from such a failure. To achieve this aim, a survey was designed to capture the expertise of a group of Maritime Education and Training (MET) experts. The survey responses have been quantified and statistically analysed to comprehensively identify these risk factors, their contribution, and their effectiveness. © 2021 21st Annual General Assembly, IAMU AGA 2021 - Proceedings of the International Association of Maritime Universities ,IAMU Conference. All rights reserved.

Remuneration Review: Risk, Planning, and Modelling beyond the Covid Crisis

Organisations that have survived Covid-19 jolts, uncertainties and lockdowns now require business intelligence and information system integration for decision support. Risks and market challenges have shifted as the pandemic progresses. Crisis management repositioning has left many firms cash-poor. Now, firms are facing labour shortages. Standard remuneration policies and practices need revision to keep core talent, stabilise teams from burn-out and to move forward strategically. This paper revises essential remuneration review considerations for crisis management in a new Covid-19 context. Current trends are discussed, as restrictions and pandemic uncertainties lift, allowing greater accuracy in risk scenario planning. Reliable data, fit for analytics and complex modelling, are making results more meaningful. The unique contribution of this research is the Covid-19 post-survival organisational perspective that can transform remuneration modelling. The scope extends beyond the governance level, and considers semantics and dynamic risk planning. Specific scenarios are updated from lessons learned from financial crisis management. Conclusions take a holistic view of how data can enhance remuneration practices to add value for organisations in the current Covid-19 climate. The paper advocates post crisis remuneration review that includes complex modelling with dynamic risk analysis for strategic planning in mid-term scenarios. © 2021 IEEE.

A Novel Predictor for Micro-Scale COVID-19 Risk Modeling: An Empirical Study from a Spatiotemporal Perspective.

Risk assessments for COVID-19 are the basis for formulating prevention and control strategies, especially at the micro scale. In a previous risk assessment model, various "densities" were regarded as the decisive driving factors of COVID-19 in the spatial dimension (population density, facility density, trajectory density, etc.). However, this conclusion ignored the fact that the "densities" were actually an abstract reflection of the "contact" frequency, which is a more essential determinant of epidemic transmission and lacked any means of corresponding quantitative correction. In this study, based on the facility density (FD), which has often been used in traditional research, a novel micro-scale COVID-19 risk predictor, facility attractiveness (FA, which has a better ability to reflect "contact" frequency), was proposed for improving the gravity model in combination with the differences in regional population density and mobility levels of an age-hierarchical population. An empirical analysis based on spatiotemporal modeling was carried out using geographically and temporally weighted regression (GTWR) in the Qingdao metropolitan area during the first wave of the pandemic. The spatiotemporally nonstationary relationships between facility density (attractiveness) and micro-risk of COVID-19 were revealed in the modeling results. The new predictors showed that residential areas and health-care facilities had more reasonable impacts than traditional "densities". Compared with the model constructed using FDs (0.5159), the global prediction ability (adjusted R2) of the FA model (0.5694) was increased by 10.4%. The improvement in the local-scale prediction ability was more significant, especially in high-risk areas (rate: 107.2%) and densely populated areas (rate in Shinan District: 64.4%; rate in Shibei District: 57.8%) during the outset period. It was proven that the optimized predictors were more suitable for use in spatiotemporal infection risk modeling in the initial stage of regional epidemics than traditional predictors. These findings can provide methodological references and model-optimized ideas for future micro-scale spatiotemporal infection modeling.

A dynamic risk assessment model to assess the impact of the coronavirus (COVID-19) on the sustainability of the biomass supply chain: A case study of a U.S. biofuel industry.

The novel coronavirus (COVID-19) is highly detrimental, and its death distribution peculiarity has severely affected people's health and the operations of businesses. COVID-19 has wholly undermined the global economy, including inflicting significant damage to the ever-emerging biomass supply chain; its sustainability is disintegrating due to the coronavirus. The biomass supply chain must be sustainable and robust enough to adapt to the evolving and fluctuating risks of the market due to the coronavirus or any potential future pandemics. However, no such study has been performed so far. To address this issue, investigating how COVID-19 influences a biomass supply chain is vital. This paper presents a dynamic risk assessment methodological framework to model biomass supply chain risks due to COVID-19. Using a dynamic Bayesian network (DBN) formalism, the impacts of COVID-19 on the performance of biomass supply chain risks have been studied. The proposed model has been applied to the biomass supply chain of a U.S.-based Mahoney Environmental® company in Washington, USA. The case study results show that it would take one year to recover from the maximum damage to the biomass supply chain due to COVID-19, while full recovery would require five years. Results indicate that biomass feedstock gate availability (FGA) is 2%, due to pandemic and lockdown conditions. Due to the availability of vaccination and gradual business reopenings, this availability increases to 92% in the second year. Results also indicate that the price of fossil-based fuel will gradually increase after one year of the pandemic; however, the market prices of fossil-based fuel will not revert to pre-coronavirus conditions even after nine years. K-fold cross-validation is used to validate the DBN. Results of validation indicate a model accuracy of 95%. It is concluded that the pandemic has caused risks to the sustainability of biomass feedstock, and the current study can help develop risk mitigation strategies.

Modeling the impact of delaying surgery for early esophageal cancer in the era of COVID-19.

BACKGROUND: Surgical society guidelines have recommended changing the treatment strategy for early esophageal cancer during the novel coronavirus (COVID-19) pandemic. Delaying resection can allow for interim disease progression, but the impact of this delay on mortality is unknown. The COVID-19 infection rate at which immediate operative risk exceeds benefit is unknown. We sought to model immediate versus delayed surgical resection in a T1b esophageal adenocarcinoma. METHODS: A decision analysis model was developed, and sensitivity analyses performed. The base case was a 65-year-old male smoker presenting with cT1b esophageal adenocarcinoma scheduled for esophagectomy during the COVID-19 pandemic. We compared immediate surgical resection to delayed resection after 3 months. The likelihood of key outcomes was derived from the literature where available. The outcome was 5-year overall survival. RESULTS: Proceeding with immediate esophagectomy for the base case scenario resulted in slightly improved 5-year overall survival when compared to delaying surgery by 3 months (5-year overall survival 0.74 for immediate and 0.73 for delayed resection). In sensitivity analyses, a delayed approach became preferred when the probability of perioperative COVID-19 infection increased above 7%. CONCLUSIONS: Immediate resection of early esophageal cancer during the COVID-19 pandemic did not decrease 5-year survival when compared to resection after 3 months for the base case scenario. However, as the risk of perioperative COVID-19 infection increases above 7%, a delayed approach has improved 5-year survival. This balance should be frequently re-examined by surgeons as infection risk changes in each hospital and community throughout the COVID-19 pandemic.

Modeling the Impact of Delaying Bariatric Surgery due to COVID-19: a Decision Analysis.

We developed a decision analysis model to evaluate risks and benefits of delaying scheduled bariatric surgery during the novel coronavirus disease (COVID-19) pandemic. Our base case was a 45-year-old female with diabetes and a body mass index of 45 kg/m2. We compared immediate with delayed surgery after 6 months to allow for COVID-19 prevalence to decrease. We found that immediate and delayed bariatric surgeries after 6 months resulted in similar 20-year overall survival. When the probability of COVID-19 infection exceeded 4%, then delayed surgery improved survival. If future COVID-19 infection rates were at least half those in the immediate scenario, then immediate surgery was favored and local infection rates had to exceed 9% before surgical delay improved survival. Surgeons should consider local disease prevalence and patient comorbidities associated with increased mortality before resuming bariatric surgery programs.

Predicting Coronavirus Disease 2019 Infection Risk and Related Risk Drivers in Nursing Homes: A Machine Learning Approach.

OBJECTIVE: Inform coronavirus disease 2019 (COVID-19) infection prevention measures by identifying and assessing risk and possible vectors of infection in nursing homes (NHs) using a machine-learning approach. DESIGN: This retrospective cohort study used a gradient boosting algorithm to evaluate risk of COVID-19 infection (ie, presence of at least 1 confirmed COVID-19 resident) in NHs. SETTING AND PARTICIPANTS: The model was trained on outcomes from 1146 NHs in Massachusetts, Georgia, and New Jersey, reporting COVID-19 case data on April 20, 2020. Risk indices generated from the model using data from May 4 were prospectively validated against outcomes reported on May 11 from 1021 NHs in California. METHODS: Model features, pertaining to facility and community characteristics, were obtained from a self-constructed dataset based on multiple public and private sources. The model was assessed via out-of-sample area under the receiver operating characteristic curve (AUC), sensitivity, and specificity in the training (via 10-fold cross-validation) and validation datasets. RESULTS: The mean AUC, sensitivity, and specificity of the model over 10-fold cross-validation were 0.729 [95% confidence interval (CI) 0.690‒0.767], 0.670 (95% CI 0.477‒0.862), and 0.611 (95% CI 0.412‒0.809), respectively. Prospective out-of-sample validation yielded similar performance measures (AUC 0.721; sensitivity 0.622; specificity 0.713). The strongest predictors of COVID-19 infection were identified as the NH's county's infection rate and the number of separate units in the NH; other predictors included the county's population density, historical Centers of Medicare and Medicaid Services cited health deficiencies, and the NH's resident density (in persons per 1000 square feet). In addition, the NH's historical percentage of non-Hispanic white residents was identified as a protective factor. CONCLUSIONS AND IMPLICATIONS: A machine-learning model can help quantify and predict NH infection risk. The identified risk factors support the early identification and management of presymptomatic and asymptomatic individuals (eg, staff) entering the NH from the surrounding community and the development of financially sustainable staff testing initiatives in preventing COVID-19 infection.