A spatiotemporal machine learning approach to forecasting COVID-19 incidence at the county level in the United States

• URL: http://arxiv.org/abs/2109.12094v2
• Date: Mon, 27 Sep 2021 17:38:37 GMT
• Title: A spatiotemporal machine learning approach to forecasting COVID-19 incidence at the county level in the United States
• Authors: Benjamin Lucas, Behzad Vahedi, and Morteza Karimzadeh
• Abstract summary: We present COVID-LSTM, a data-driven model based on a Long Short-term memory architecture for forecasting COVID-19 incidence at the county-level in the US. We use the weekly number of new cases as temporal input, and hand-engineered spatial features from Facebook to capture the spread of the disease in time and space. Over the 4-week forecast horizon, our model is on average 50 cases per county more accurate than the COVIDhub-ensemble.
• Score: 2.9822184411723645
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: With COVID-19 affecting every country globally and changing everyday life, the ability to forecast the spread of the disease is more important than any previous epidemic. The conventional methods of disease-spread modeling, compartmental models, are based on the assumption of spatiotemporal homogeneity of the spread of the virus, which may cause forecasting to underperform, especially at high spatial resolutions. In this paper we approach the forecasting task with an alternative technique - spatiotemporal machine learning. We present COVID-LSTM, a data-driven model based on a Long Short-term Memory deep learning architecture for forecasting COVID-19 incidence at the county-level in the US. We use the weekly number of new positive cases as temporal input, and hand-engineered spatial features from Facebook movement and connectedness datasets to capture the spread of the disease in time and space. COVID-LSTM outperforms the COVID-19 Forecast Hub's Ensemble model (COVIDhub-ensemble) on our 17-week evaluation period, making it the first model to be more accurate than the COVIDhub-ensemble over one or more forecast periods. Over the 4-week forecast horizon, our model is on average 50 cases per county more accurate than the COVIDhub-ensemble. We highlight that the underutilization of data-driven forecasting of disease spread prior to COVID-19 is likely due to the lack of sufficient data available for previous diseases, in addition to the recent advances in machine learning methods for spatiotemporal forecasting. We discuss the impediments to the wider uptake of data-driven forecasting, and whether it is likely that more deep learning-based models will be used in the future.

Related papers

• MedDiffusion: Boosting Health Risk Prediction via Diffusion-based Data Augmentation [58.93221876843639]
  This paper introduces a novel, end-to-end diffusion-based risk prediction model, named MedDiffusion. It enhances risk prediction performance by creating synthetic patient data during training to enlarge sample space. It discerns hidden relationships between patient visits using a step-wise attention mechanism, enabling the model to automatically retain the most vital information for generating high-quality data.
  arXiv  Detail & Related papers  (2023-10-04T01:36:30Z)
• Strict baselines for Covid-19 forecasting and ML perspective for USA and Russia [105.54048699217668]
  Covid-19 allows researchers to gather datasets accumulated over 2 years and to use them in predictive analysis. We present the results of a consistent comparative study of different types of methods for predicting the dynamics of the spread of Covid-19 based on regional data for two countries: the United States and Russia.
  arXiv  Detail & Related papers  (2022-07-15T18:21:36Z)
• Back2Future: Leveraging Backfill Dynamics for Improving Real-time Predictions in Future [73.03458424369657]
  In real-time forecasting in public health, data collection is a non-trivial and demanding task. 'Backfill' phenomenon and its effect on model performance has been barely studied in the prior literature. We formulate a novel problem and neural framework Back2Future that aims to refine a given model's predictions in real-time.
  arXiv  Detail & Related papers  (2021-06-08T14:48:20Z)
• Modeling the geospatial evolution of COVID-19 using spatio-temporal convolutional sequence-to-sequence neural networks [48.7576911714538]
  Portugal was the country in the world with the largest incidence rate, with 14-days incidence rates per 100,000 inhabitants in excess of 1000. Despite its importance, accurate prediction of the geospatial evolution of COVID-19 remains a challenge.
  arXiv  Detail & Related papers  (2021-05-06T15:24:00Z)
• COUnty aggRegation mixup AuGmEntation (COURAGE) COVID-19 Prediction [29.919578191688274]
  This paper proposes a method named COURAGE to generate a short-term prediction of 2-week-ahead COVID-19 related deaths for each county in the United States. Our model fully utilizes publicly available information of COVID-19 related confirmed cases, deaths, community mobility trends and demographic information, and can produce state-level prediction as an aggregation of the corresponding county-level predictions.
  arXiv  Detail & Related papers  (2021-05-03T04:00:59Z)
• STELAR: Spatio-temporal Tensor Factorization with Latent Epidemiological Regularization [76.57716281104938]
  We develop a tensor method to predict the evolution of epidemic trends for many regions simultaneously. STELAR enables long-term prediction by incorporating latent temporal regularization through a system of discrete-time difference equations. We conduct experiments using both county- and state-level COVID-19 data and show that our model can identify interesting latent patterns of the epidemic.
  arXiv  Detail & Related papers  (2020-12-08T21:21:47Z)
• Examining Deep Learning Models with Multiple Data Sources for COVID-19 Forecasting [10.052302234274256]
  We design and analysis of deep learning-based models for COVID-19 forecasting. We consider multiple sources such as COVID-19 confirmed and death case count data and testing data for better predictions. We propose clustering-based training for high-temporal forecasting.
  arXiv  Detail & Related papers  (2020-10-27T17:52:02Z)
• Inter-Series Attention Model for COVID-19 Forecasting [23.58411106491221]
  We develop a new neural forecasting model, called Attention Crossing Time Series (textbfACTS), that makes forecasts via comparing patterns across time series obtained from multiple regions. Among 13 out of 18 testings including forecasting newly confirmed cases, hospitalizations and deaths, textbfACTS outperforms all the leading COVID-19 forecasters highlighted by CDC.
  arXiv  Detail & Related papers  (2020-10-25T00:11:49Z)
• Backtesting the predictability of COVID-19 [0.0]
  We use historical data of COVID-19 infections from 253 regions from the period of 22nd January 2020 until 22nd June 2020. Prediction errors are substantially higher in early stages of the pandemic, resulting from limited data. The more confirmed cases a country exhibits at any point in time, the lower the error in forecasting future confirmed cases.
  arXiv  Detail & Related papers  (2020-07-22T13:18:00Z)
• A Recurrent Neural Network and Differential Equation Based Spatiotemporal Infectious Disease Model with Application to COVID-19 [3.464871689508835]
  We develop an integrated disease model based on epidemic differential equations (SIR) and recurrent neural networks (RNN) We trained and tested our model on CO-19 data in Italy, and show that it out-performs existing temporal models (fully connected NN, SIR, ARIMA) in 1-day, 3-day, and 1-week ahead forecasting.
  arXiv  Detail & Related papers  (2020-07-14T07:04:57Z)
• A machine learning methodology for real-time forecasting of the 2019-2020 COVID-19 outbreak using Internet searches, news alerts, and estimates from mechanistic models [53.900779250589814]
  Our method is able to produce stable and accurate forecasts 2 days ahead of current time. Our model's predictive power outperforms a collection of baseline models in 27 out of the 32 Chinese provinces.
  arXiv  Detail & Related papers  (2020-04-08T14:39:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.