Application of a data-driven XGBoost model for the prediction of COVID-19 in the USA: a time-series study.
Ontology highlight
ABSTRACT: Objective
The COVID-19 outbreak was first reported in Wuhan, China, and has been acknowledged as a pandemic due to its rapid spread worldwide. Predicting the trend of COVID-19 is of great significance for its prevention. A comparison between the autoregressive integrated moving average (ARIMA) model and the eXtreme Gradient Boosting (XGBoost) model was conducted to determine which was more accurate for anticipating the occurrence of COVID-19 in the USA.Design
Time-series study.Setting
The USA was the setting for this study.Main outcome measures
Three accuracy metrics, mean absolute error (MAE), root mean square error (RMSE) and mean absolute percentage error (MAPE), were applied to evaluate the performance of the two models.Results
In our study, for the training set and the validation set, the MAE, RMSE and MAPE of the XGBoost model were less than those of the ARIMA model.Conclusions
The XGBoost model can help improve prediction of COVID-19 cases in the USA over the ARIMA model.
SUBMITTER: Fang ZG
PROVIDER: S-EPMC9251895 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:In light of the COVID-19 pandemic that has struck the world since the end of 2019, many endeavors have been carried out to overcome this crisis. Taking into consideration the uncertainty as a feature of forecasting, this data article introduces long-term time-series predictions for the virus's daily infections in Brazil by training forecasting models on limited raw data (30 time-steps and 40 time-steps alternatives). The primary reuse potential of this forecasting data is to enable decision-makers to develop action plans against the pandemic, and to help researchers working in infection prevention and control to: (1) explore limited data usage in predicting infections. (2) develop a reinforcement learning model on top of this data-lake, which can perform an online game between the trained models to generate a new capable model for predicting future true data. The prediction data was generated by training 4200 recurrent neural networks (54 to 84 days validation periods) on raw data from Johns Hopkins University's online repository, to pave the way for generating reliable extended long-term predictions.
| S-EPMC7437445 | biostudies-literature
Project description:Pakistan is currently facing the fourth wave of the deadly coronavirus, which was first reported in Wuhan, China, in December 2019. This work utilizes the epidemiological models to analyze Pakistan's COVID-19 data. The basic susceptible, infected, and recovered (SIR) model is studied assuming Bayesian and time-series SIR (tSIR) approaches. Many studies have been conducted from different perspectives, but to the best of our knowledge, no study is available using the SIR models for Pakistan. The coronavirus incubation period has been set to 14 days across the globe; however, this study noticed that the assumption of 14 days is not suitable for Pakistan's data. Furthermore, on the basis of R 0, we infer that COVID-19 is not a pandemic in Pakistan, as it was in other nations, such as the United States, India, Brazil, and Italy, among others. We attribute this to the best strategy adopted by the Government of Pakistan to minimize the burden of COVID-19 cases in Pakistani hospitals. It is also noticed that the posterior-based SIR (pSIR) model with uniform prior toR 0 and Poisson distribution (of log-likelihood) provides better results as compared to other distributions. From time-series SIR (tSIR), we observed that the value of the reporting rate (ρ) is less than 1 which means that cases are underreported.
| S-EPMC9256309 | biostudies-literature
Project description:Understanding the local dynamics of COVID-19 transmission calls for an approach that characterizes the incidence curve in a small geographical unit. Given that incidence curves exhibit considerable day-to-day variation, the fractal structure of the time series dynamics is investigated for the Flanders and Brussels Regions of Belgium. For each statistical sector, the smallest administrative geographical entity in Belgium, fractal dimensions of COVID-19 incidence rates, based on rolling time spans of 7, 14, and 21 days were estimated using four different estimators: box-count, Hall-Wood, variogram, and madogram. We found varying patterns of fractal dimensions across time and location. The fractal dimension is further summarized by its mean, variance, and autocorrelation over time. These summary statistics are then used to cluster regions with different incidence rate patterns using k-means clustering. Fractal dimension analysis of COVID-19 incidence thus offers important insight into the past, current, and arguably future evolution of an infectious disease outbreak.
| S-EPMC10016183 | biostudies-literature
Project description:The effective reproduction number Reff is a critical epidemiological parameter that characterizes the transmissibility of a pathogen. However, this parameter is difficult to estimate in the presence of silent transmission and/or significant temporal variation in case reporting. This variation can occur due to the lack of timely or appropriate testing, public health interventions and/or changes in human behavior during an epidemic. This is exactly the situation we are confronted with during this COVID-19 pandemic. In this work, we propose to estimate Reff for the SARS-CoV-2 (the etiological agent of the COVID-19), based on a model of its propagation considering a time-varying transmission rate. This rate is modeled by a Brownian diffusion process embedded in a stochastic model. The model is then fitted by Bayesian inference (particle Markov Chain Monte Carlo method) using multiple well-documented hospital datasets from several regions in France and in Ireland. This mechanistic modeling framework enables us to reconstruct the temporal evolution of the transmission rate of the COVID-19 based only on the available data. Except for the specific model structure, it is non-specifically assumed that the transmission rate follows a basic stochastic process constrained by the observations. This approach allows us to follow both the course of the COVID-19 epidemic and the temporal evolution of its Reff(t). Besides, it allows to assess and to interpret the evolution of transmission with respect to the mitigation strategies implemented to control the epidemic waves in France and in Ireland. We can thus estimate a reduction of more than 80% for the first wave in all the studied regions but a smaller reduction for the second wave when the epidemic was less active, around 45% in France but just 20% in Ireland. For the third wave in Ireland the reduction was again significant (>70%).
| S-EPMC8341713 | biostudies-literature
Project description:Complex systems are challenging to understand, especially when they defy manipulative experiments for practical or ethical reasons. Several fields have developed parallel approaches to infer causal relations from observational time series. Yet, these methods are easy to misunderstand and often controversial. Here, we provide an accessible and critical review of three statistical causal discovery approaches (pairwise correlation, Granger causality, and state space reconstruction), using examples inspired by ecological processes. For each approach, we ask what it tests for, what causal statement it might imply, and when it could lead us astray. We devise new ways of visualizing key concepts, describe some novel pathologies of existing methods, and point out how so-called 'model-free' causality tests are not assumption-free. We hope that our synthesis will facilitate thoughtful application of methods, promote communication across different fields, and encourage explicit statements of assumptions. A video walkthrough is available (Video 1 or https://youtu.be/AIV0ttQrjK8).
| S-EPMC9391047 | biostudies-literature
Project description:ObjectiveHyperglycemia has emerged as an important clinical manifestation of coronavirus disease 2019 (COVID-19) in diabetic and nondiabetic patients. Whether these glycemic changes are specific to a subgroup of patients and persist following COVID-19 resolution remains to be elucidated. This work aimed to characterize longitudinal random blood glucose in a large cohort of nondiabetic patients diagnosed with COVID-19.Materials and methodsDe-identified electronic medical records of 7502 patients diagnosed with COVID-19 without prior diagnosis of diabetes between January 1, 2020, and November 18, 2020, were accessed through the TriNetX Research Network. Glucose measurements, diagnostic codes, medication codes, laboratory values, vital signs, and demographics were extracted before, during, and after COVID-19 diagnosis. Unsupervised time-series clustering algorithms were trained to identify distinct clusters of glucose trajectories. Cluster associations were tested for demographic variables, COVID-19 severity, glucose-altering medications, glucose values, and new-onset diabetes diagnoses.ResultsTime-series clustering identified a low-complexity model with 3 clusters and a high-complexity model with 19 clusters as the best-performing models. In both models, cluster membership differed significantly by death status, COVID-19 severity, and glucose levels. Clusters membership in the 19 cluster model also differed significantly by age, sex, and new-onset diabetes mellitus.Discussion and conclusionThis work identified distinct longitudinal blood glucose changes associated with subclinical glucose dysfunction in the low-complexity model and increased new-onset diabetes incidence in the high-complexity model. Together, these findings highlight the utility of data-driven techniques to elucidate longitudinal glycemic dysfunction in patients with COVID-19 and provide clinical evidence for further evaluation of the role of COVID-19 in diabetes pathogenesis.
| S-EPMC8364667 | biostudies-literature
Project description:BackgroundThe COVID-19 pandemic has led to a high interest in mathematical models describing and predicting the diverse aspects and implications of the virus outbreak. Model results represent an important part of the information base for the decision process on different administrative levels. The Robert-Koch-Institute (RKI) initiated a project whose main goal is to predict COVID-19-specific occupation of beds in intensive care units: Steuerungs-Prognose von Intensivmedizinischen COVID-19 Kapazitäten (SPoCK). The incidence of COVID-19 cases is a crucial predictor for this occupation.MethodsWe developed a model based on ordinary differential equations for the COVID-19 spread with a time-dependent infection rate described by a spline. Furthermore, the model explicitly accounts for weekday-specific reporting and adjusts for reporting delay. The model is calibrated in a purely data-driven manner by a maximum likelihood approach. Uncertainties are evaluated using the profile likelihood method. The uncertainty about the appropriate modeling assumptions can be accounted for by including and merging results of different modelling approaches. The analysis uses data from Germany describing the COVID-19 spread from early 2020 until March 31st, 2021.ResultsThe model is calibrated based on incident cases on a daily basis and provides daily predictions of incident COVID-19 cases for the upcoming three weeks including uncertainty estimates for Germany and its subregions. Derived quantities such as cumulative counts and 7-day incidences with corresponding uncertainties can be computed. The estimation of the time-dependent infection rate leads to an estimated reproduction factor that is oscillating around one. Data-driven estimation of the dark figure purely from incident cases is not feasible.ConclusionsWe successfully implemented a procedure to forecast near future COVID-19 incidences for diverse subregions in Germany which are made available to various decision makers via an interactive web application. Results of the incidence modeling are also used as a predictor for forecasting the need of intensive care units.
| S-EPMC9019290 | biostudies-literature
Project description:Compositional data analysis (CoDA) methods have increased in popularity as a new framework for analyzing next-generation sequencing (NGS) data. CoDA methods, such as the centered log-ratio (clr) transformation, adjust for the compositional nature of NGS counts, which is not addressed by traditional normalization methods. CoDA has only been sparsely applied to NGS data generated from microbial communities or to multiple 'omics' datasets. In this study, we applied CoDA methods to analyze NGS and untargeted metabolomic datasets obtained from bacterial and fungal communities. Specifically, we used clr transformation to reanalyze NGS amplicon and metabolomics data from a study investigating the effects of building material type, moisture and time on microbial and metabolomic diversity. Compared to analysis of untransformed data, analysis of clr-transformed data revealed novel relationships and stronger associations between sample conditions and microbial and metabolic community profiles.
| S-EPMC7671389 | biostudies-literature
Project description:ObjectivesHuman brucellosis is a public health problem endangering health and property in China. Predicting the trend and the seasonality of human brucellosis is of great significance for its prevention. In this study, a comparison between the autoregressive integrated moving average (ARIMA) model and the eXtreme Gradient Boosting (XGBoost) model was conducted to determine which was more suitable for predicting the occurrence of brucellosis in mainland China.DesignTime-series study.SettingMainland China.MethodsData on human brucellosis in mainland China were provided by the National Health and Family Planning Commission of China. The data were divided into a training set and a test set. The training set was composed of the monthly incidence of human brucellosis in mainland China from January 2008 to June 2018, and the test set was composed of the monthly incidence from July 2018 to June 2019. The mean absolute error (MAE), root mean square error (RMSE) and mean absolute percentage error (MAPE) were used to evaluate the effects of model fitting and prediction.ResultsThe number of human brucellosis patients in mainland China increased from 30 002 in 2008 to 40 328 in 2018. There was an increasing trend and obvious seasonal distribution in the original time series. For the training set, the MAE, RSME and MAPE of the ARIMA(0,1,1)×(0,1,1)12 model were 338.867, 450.223 and 10.323, respectively, and the MAE, RSME and MAPE of the XGBoost model were 189.332, 262.458 and 4.475, respectively. For the test set, the MAE, RSME and MAPE of the ARIMA(0,1,1)×(0,1,1)12 model were 529.406, 586.059 and 17.676, respectively, and the MAE, RSME and MAPE of the XGBoost model were 249.307, 280.645 and 7.643, respectively.ConclusionsThe performance of the XGBoost model was better than that of the ARIMA model. The XGBoost model is more suitable for prediction cases of human brucellosis in mainland China.
| S-EPMC7722837 | biostudies-literature
Project description:BackgroundVisualization plays an important role in epidemic time series analysis and forecasting. Viewing time series data plotted on a graph can help researchers identify anomalies and unexpected trends that could be overlooked if the data were reviewed in tabular form; these details can influence a researcher's recommended course of action or choice of simulation models. However, there are challenges in reviewing data sets from multiple data sources - data can be aggregated in different ways (e.g., incidence vs. cumulative), measure different criteria (e.g., infection counts, hospitalizations, and deaths), or represent different geographical scales (e.g., nation, HHS Regions, or states), which can make a direct comparison between time series difficult. In the face of an emerging epidemic, the ability to visualize time series from various sources and organizations and to reconcile these datasets based on different criteria could be key in developing accurate forecasts and identifying effective interventions. Many tools have been developed for visualizing temporal data; however, none yet supports all the functionality needed for easy collaborative visualization and analysis of epidemic data.ResultsIn this paper, we present EpiViewer, a time series exploration dashboard where users can upload epidemiological time series data from a variety of sources and compare, organize, and track how data evolves as an epidemic progresses. EpiViewer provides an easy-to-use web interface for visualizing temporal datasets either as line charts or bar charts. The application provides enhanced features for visual analysis, such as hierarchical categorization, zooming, and filtering, to enable detailed inspection and comparison of multiple time series on a single canvas. Finally, EpiViewer provides several built-in statistical Epi-features to help users interpret the epidemiological curves.ConclusionEpiViewer is a single page web application that provides a framework for exploring, comparing, and organizing temporal datasets. It offers a variety of features for convenient filtering and analysis of epicurves based on meta-attribute tagging. EpiViewer also provides a platform for sharing data between groups for better comparison and analysis. Our user study demonstrated that EpiViewer is easy to use and fills a particular niche in the toolspace for visualization and exploration of epidemiological data.
| S-EPMC6251172 | biostudies-literature