Multi‐Model Prediction of West Nile Virus Neuroinvasive Disease With Machine Learning for Identification of Important Regional Climatic Drivers
Abstract West Nile virus (WNV) is the leading cause of mosquito‐borne illness in the continental United States (CONUS). Spatial heterogeneity in historical incidence, environmental factors, and complex ecology make prediction of spatiotemporal variation in WNV transmission challenging. Machine learn...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
American Geophysical Union (AGU)
2023-11-01
|
| Series: | GeoHealth |
| Subjects: | |
| Online Access: | https://doi.org/10.1029/2023GH000906 |
| _version_ | 1797449789507371008 |
|---|---|
| author | Karen M. Holcomb J. Erin Staples Randall J. Nett Charles B. Beard Lyle R. Petersen Stanley G. Benjamin Benjamin W. Green Hunter Jones Michael A. Johansson |
| author_facet | Karen M. Holcomb J. Erin Staples Randall J. Nett Charles B. Beard Lyle R. Petersen Stanley G. Benjamin Benjamin W. Green Hunter Jones Michael A. Johansson |
| author_sort | Karen M. Holcomb |
| collection | DOAJ |
| description | Abstract West Nile virus (WNV) is the leading cause of mosquito‐borne illness in the continental United States (CONUS). Spatial heterogeneity in historical incidence, environmental factors, and complex ecology make prediction of spatiotemporal variation in WNV transmission challenging. Machine learning provides promising tools for identification of important variables in such situations. To predict annual WNV neuroinvasive disease (WNND) cases in CONUS (2015–2021), we fitted 10 probabilistic models with variation in complexity from naïve to machine learning algorithm and an ensemble. We made predictions in each of nine climate regions on a hexagonal grid and evaluated each model's predictive accuracy. Using the machine learning models (random forest and neural network), we identified the relative importance and variation in ranking of predictors (historical WNND cases, climate anomalies, human demographics, and land use) across regions. We found that historical WNND cases and population density were among the most important factors while anomalies in temperature and precipitation often had relatively low importance. While the relative performance of each model varied across climatic regions, the magnitude of difference between models was small. All models except the naïve model had non‐significant differences in performance relative to the baseline model (negative binomial model fit per hexagon). No model, including the ensemble or more complex machine learning models, outperformed models based on historical case counts on the hexagon or region level; these models are good forecasting benchmarks. Further work is needed to assess if predictive capacity can be improved beyond that of these historical baselines. |
| first_indexed | 2024-03-09T14:30:07Z |
| format | Article |
| id | doaj.art-ca143f64a797489f89bbe0bf3af92899 |
| institution | Directory Open Access Journal |
| issn | 2471-1403 |
| language | English |
| last_indexed | 2024-03-09T14:30:07Z |
| publishDate | 2023-11-01 |
| publisher | American Geophysical Union (AGU) |
| record_format | Article |
| series | GeoHealth |
| spelling | doaj.art-ca143f64a797489f89bbe0bf3af928992023-11-28T02:35:46ZengAmerican Geophysical Union (AGU)GeoHealth2471-14032023-11-01711n/an/a10.1029/2023GH000906Multi‐Model Prediction of West Nile Virus Neuroinvasive Disease With Machine Learning for Identification of Important Regional Climatic DriversKaren M. Holcomb0J. Erin Staples1Randall J. Nett2Charles B. Beard3Lyle R. Petersen4Stanley G. Benjamin5Benjamin W. Green6Hunter Jones7Michael A. Johansson8Global Systems Laboratory National Oceanic and Atmospheric Administration Boulder CO USADivision of Vector‐Borne Diseases Centers for Disease Control and Prevention Fort Collins CO USADivision of Vector‐Borne Diseases Centers for Disease Control and Prevention Fort Collins CO USADivision of Vector‐Borne Diseases Centers for Disease Control and Prevention Fort Collins CO USADivision of Vector‐Borne Diseases Centers for Disease Control and Prevention Fort Collins CO USAGlobal Systems Laboratory National Oceanic and Atmospheric Administration Boulder CO USAGlobal Systems Laboratory National Oceanic and Atmospheric Administration Boulder CO USAClimate Prediction Office National Oceanic and Atmospheric Administration Silver Spring MD USADivision of Vector‐Borne Diseases Centers for Disease Control and Prevention San Juan PR USAAbstract West Nile virus (WNV) is the leading cause of mosquito‐borne illness in the continental United States (CONUS). Spatial heterogeneity in historical incidence, environmental factors, and complex ecology make prediction of spatiotemporal variation in WNV transmission challenging. Machine learning provides promising tools for identification of important variables in such situations. To predict annual WNV neuroinvasive disease (WNND) cases in CONUS (2015–2021), we fitted 10 probabilistic models with variation in complexity from naïve to machine learning algorithm and an ensemble. We made predictions in each of nine climate regions on a hexagonal grid and evaluated each model's predictive accuracy. Using the machine learning models (random forest and neural network), we identified the relative importance and variation in ranking of predictors (historical WNND cases, climate anomalies, human demographics, and land use) across regions. We found that historical WNND cases and population density were among the most important factors while anomalies in temperature and precipitation often had relatively low importance. While the relative performance of each model varied across climatic regions, the magnitude of difference between models was small. All models except the naïve model had non‐significant differences in performance relative to the baseline model (negative binomial model fit per hexagon). No model, including the ensemble or more complex machine learning models, outperformed models based on historical case counts on the hexagon or region level; these models are good forecasting benchmarks. Further work is needed to assess if predictive capacity can be improved beyond that of these historical baselines.https://doi.org/10.1029/2023GH000906West Nile virusmachine learningpredictionclimatevariable importance |
| spellingShingle | Karen M. Holcomb J. Erin Staples Randall J. Nett Charles B. Beard Lyle R. Petersen Stanley G. Benjamin Benjamin W. Green Hunter Jones Michael A. Johansson Multi‐Model Prediction of West Nile Virus Neuroinvasive Disease With Machine Learning for Identification of Important Regional Climatic Drivers GeoHealth West Nile virus machine learning prediction climate variable importance |
| title | Multi‐Model Prediction of West Nile Virus Neuroinvasive Disease With Machine Learning for Identification of Important Regional Climatic Drivers |
| title_full | Multi‐Model Prediction of West Nile Virus Neuroinvasive Disease With Machine Learning for Identification of Important Regional Climatic Drivers |
| title_fullStr | Multi‐Model Prediction of West Nile Virus Neuroinvasive Disease With Machine Learning for Identification of Important Regional Climatic Drivers |
| title_full_unstemmed | Multi‐Model Prediction of West Nile Virus Neuroinvasive Disease With Machine Learning for Identification of Important Regional Climatic Drivers |
| title_short | Multi‐Model Prediction of West Nile Virus Neuroinvasive Disease With Machine Learning for Identification of Important Regional Climatic Drivers |
| title_sort | multi model prediction of west nile virus neuroinvasive disease with machine learning for identification of important regional climatic drivers |
| topic | West Nile virus machine learning prediction climate variable importance |
| url | https://doi.org/10.1029/2023GH000906 |
| work_keys_str_mv | AT karenmholcomb multimodelpredictionofwestnilevirusneuroinvasivediseasewithmachinelearningforidentificationofimportantregionalclimaticdrivers AT jerinstaples multimodelpredictionofwestnilevirusneuroinvasivediseasewithmachinelearningforidentificationofimportantregionalclimaticdrivers AT randalljnett multimodelpredictionofwestnilevirusneuroinvasivediseasewithmachinelearningforidentificationofimportantregionalclimaticdrivers AT charlesbbeard multimodelpredictionofwestnilevirusneuroinvasivediseasewithmachinelearningforidentificationofimportantregionalclimaticdrivers AT lylerpetersen multimodelpredictionofwestnilevirusneuroinvasivediseasewithmachinelearningforidentificationofimportantregionalclimaticdrivers AT stanleygbenjamin multimodelpredictionofwestnilevirusneuroinvasivediseasewithmachinelearningforidentificationofimportantregionalclimaticdrivers AT benjaminwgreen multimodelpredictionofwestnilevirusneuroinvasivediseasewithmachinelearningforidentificationofimportantregionalclimaticdrivers AT hunterjones multimodelpredictionofwestnilevirusneuroinvasivediseasewithmachinelearningforidentificationofimportantregionalclimaticdrivers AT michaelajohansson multimodelpredictionofwestnilevirusneuroinvasivediseasewithmachinelearningforidentificationofimportantregionalclimaticdrivers |