Precise prediction of the trend of the pandemic has been crucial in COVID-19, as it allows the governments and healthcare systems to effectively distribute and prioritize resource allocations. In this issue, Jo et al. present a neural network model to make quantile predictions on COVID-19 death tolls at the county level. This fine geographical scale, which is rare in publicly available models, can benefit state-level officials to coordinate resources within the state. The qua[Detail] ...
Background: Modern machine learning-based models have not been harnessed to their total capacity for disease trend predictions prior to the COVID-19 pandemic. This work is the first use of the conditional RNN model in predicting disease trends that we know of during development that complemented classical epidemiological approaches.
Methods: We developed the long short-term memory networks with quantile output (condLSTM-Q) model for making quantile predictions on COVID-19 death tolls.
Results: We verified that the condLSTM-Q was accurately predicting fine-scale, county-level daily deaths with a two-week window. The model’s performance was robust and comparable to, if not slightly better than well-known, publicly available models. This provides unique opportunities for investigating trends within the states and interactions between counties along state borders. In addition, by analyzing the importance of the categorical data, one could learn which features are risk factors that affect the death trend and provide handles for officials to ameliorate the risks.
Conclusion: The condLSTM-Q model performed robustly, provided fine-scale, county-level predictions of daily deaths with a two-week window. Given the scalability and generalizability of neural network models, this model could incorporate additional data sources with ease and could be further developed to generate other valuable predictions such as new cases or hospitalizations intuitively.
Background: The analysis of COVID-19 infection data through the eye of Physics-inspired Artificial Intelligence leads to a clearer understanding of the infection dynamics and assists in predicting future evolution. The spreading of the pandemic during the first half of 2020 was curtailed to a larger or lesser extent through social distancing measures imposed by most countries. In the context of the standard Susceptible-Infected-Recovered (SIR) model, changes in social distancing enter through time-dependent infection rates.
Methods: In this work we use machine learning and the infection dynamical equations of SIR to extract from the infection data the degree of social distancing and, through it, assess the effectiveness of the imposed measures.
Results: Quantitative machine learning analysis is applied to eight countries with infection data from the first viral wave. We find as two extremes Greece and USA where the measures were successful and unsuccessful, respectively, in limiting spreading. This physics-based neural network approach is employed to the second wave of the infection, and by training the network with the new data, we extract the time-dependent infection rate and make short-term predictions with a week-long or even longer horizon. This algorithmic approach is applied to all eight countries with good short-term results. The data for Greece is analyzed in more detail from August to December 2020.
Conclusions: The model captures the essential spreading dynamics and gives useful projections for the spreading, both in the short-term but also for a more intermediate horizon, based on specific social distancing measures that are extracted directly from the data.
Background: The purpose of our study is to develop a quite precise mathematical model which describes epidemics spread in a country with non-uniform population density. This model gives explanation of quite long duration of the peak of a respiratory infection such as the coronavirus disease 2019 (COVID-19).
Methods: The theory of kinetic equations and fractal analysis are used in our mathematical model. According to our model, COVID-19 spreading takes the form of several spatio-temporal waves developing almost independently and simultaneously in areas with different population density. The intensity of each wave is described by a power-law dependence. The parameters of the dependence are determined by real statistical data at the initial stage of the disease spread.
Results: The results of the model simulation were verified using statistical data for the Republic of Belarus. Based on the developed model, a forecast calculation was made at the end of May, 2020. It was shown that the epidemiological situation in the Republic of Belarus is well described by three waves, which spread respectively in large cities with the highest population density (the first wave), in medium-sized cities with a population of 50−200 thousands people (the second wave), in small towns and rural areas (the third wave). It was shown that a new wave inside a subpopulation with a lower density was born 20−25 days after the appearance of the previous wave. Comparison with actual data several months later showed that the accuracy of forecasting the total number of cases for a period of 3 months for total population in the proposed approach was approximately 3%.
Conclusions: The high accuracy mathematical model is proposed. It describes the development of a respiratory epidemic in a country non-uniform population density without quarantine. The model is useful for predicting the development of possible epidemics in the future. An accurate forecast allows to correctly allocating available resources to effectively withstand the epidemic.
Background: Mathematical models are essential to predict the likely outcome of an epidemic. Various models have been proposed in the literature for disease spreads. Some are individual based models and others are compartmental models. In this study, discrete mathematical models are developed for the spread of the coronavirus disease 2019 (COVID-19).
Methods: The proposed models take into account the known special characteristics of this disease such as the latency and incubation periods, and the different social and infectiousness conditions of infected people. In particular, they include a novel approach that considers the social structure, the fraction of detected cases over the real total infected cases, the influx of undetected infected people from outside the borders, as well as contact-tracing and quarantine period for travelers. The first model is a simplified model and the second is a complete model.
Results: From a numerical point of view, the particular case of Lebanon has been studied and its reported data have been used to estimate the complete discrete model parameters using optimization techniques. Moreover, a parameter analysis and several prediction scenarios are presented in order to better understand the role of the parameters.
Conclusions: Understanding the role of the parameters involved in the models help policy makers in deciding the appropriate mitigation measures. Also, the proposed approach paves the way for models that take into account societal factors and complex human behavior without an extensive process of data collection.
Background: In this paper, we conduct an analysis of the COVID-19 data in the United States in 2020 via functional data analysis methods. Through this research, we investigate the effectiveness of the practice of public health measures, and assess the correlation between infections and deaths caused by the COVID-19. Additionally, we look into the relationship between COVID-19 spread and geographical locations, and propose a forecasting method to predict the total number of confirmed cases nationwide.
Methods: The functional data analysis methods include functional principal analysis methods, functional canonical correlation analysis methods, an expectation-maximization (EM) based clustering algorithm and a functional time series model used for forecasting.
Results: It is evident that the practice of public health measures helps to reduce the growth rate of the epidemic outbreak over the nation. We have observed a high canonical correlation between confirmed and death cases. States that are geographically close to the hot spots are likely to be clustered together, and population density appears to be a critical factor affecting the cluster structure. The proposed functional time series model gives more reliable and accurate predictions of the total number of confirmed cases than standard time series methods.
Conclusions: The results obtained by applying the functional data analysis methods provide new insights into the COVID-19 data in the United States. With our results and recommendations, the health professionals can make better decisions to reduce the spread of the epidemic, and mitigate its negative effects to the national public health.
Background: Due to the limited availability and high cost of the reverse transcription-polymerase chain reaction (RT- PCR) test, many studies have proposed machine learning techniques for detecting COVID-19 from medical imaging. The purpose of this study is to systematically review, assess and synthesize research articles that have used different machine learning techniques to detect and diagnose COVID-19 from chest X-ray and CT scan images.
Methods: A structured literature search was conducted in the relevant bibliographic databases to ensure that the survey solely centered on reproducible and high-quality research. We selected papers based on our inclusion criteria.
Results: In this survey, we reviewed 98 articles that fulfilled our inclusion criteria. We have surveyed a complete pipeline of chest imaging analysis techniques related to COVID-19, including data collection, pre-processing, feature extraction, classification, and visualization. We have considered CT scans and X-rays as both are widely used to describe the latest developments in medical imaging to detect COVID-19.
Conclusions: This survey provides researchers with valuable insights into different machine learning techniques and their performance in the detection and diagnosis of COVID-19 from chest imaging. At the end, the challenges and limitations in detecting COVID-19 using machine learning techniques and the future direction of research are discussed.
Background: Coronavirus disease (COVID-19) is a contagious infection caused by severe acute respiratory syndrome coronavirus-2 (SARS-COV-2) and it has infected and killed millions of people across the globe.
Objective: In the absence or inadequate provision of therapeutic treatments of COVID-19 and the limited convenience of diagnostic techniques, there is a necessity for some alternate spontaneous screening systems that can easily be used by the physicians to rapidly recognize and isolate the infected patients to circumvent onward surge. A chest X-ray (CXR) image can effortlessly be used as a substitute modality to diagnose the COVID-19.
Method: In this study, we present an automatic COVID-19 diagnostic and severity prediction system (COVIDX) that uses deep feature maps of CXR images along with classical machine learning algorithms to identify COVID-19 and forecast its severity. The proposed system uses a three-phase classification approach (healthy vs unhealthy, COVID-19 vs pneumonia, and COVID-19 severity) using different conventional supervised classification algorithms.
Results: We evaluated COVIDX through 10-fold cross-validation, by using an external validation dataset, and also in a real setting by involving an experienced radiologist. In all the adopted evaluation settings, COVIDX showed strong generalization power and outperforms all the prevailing state-of-the-art methods designed for this purpose.
Conclusions: Our proposed method (COVIDX), with vivid performance in COVID-19 diagnosis and its severity prediction, can be used as an aiding tool for clinical physicians and radiologists in the diagnosis and follow-up studies of COVID-19 infected patients.
Availability: We made COVIDX easily accessible through a cloud-based webserver and python code available at the site of google and the website of Github.