National incidence of coccidioidomycosis in the United States estimated through machine learning integration of epidemiological, veterinary, and socioecological data
- 1University of California, Berkeley
Abstract
Key pointsO_ST_ABSQuestionC_ST_ABSIn the absence of nationwide reporting for coccidioidomycosis, can alternative data sources be integrated to enable estimates of monthly, county-level incidence across the US?
FindingsIn this cross-sectional study of 3,108 counties, the model identified 60 counties in non-reporting states with predicted incidence [≥]2 cases per 100,000 population (considered moderate to high incidence). In states with mandatory reporting outside of Arizona and California, the models predicted county-level incidence rates were, on average, 28% higher than those captured in national surveillance.
MeaningOur predictions highlight the extent of case under-ascertainment for coccidioidomycosis relative to Arizona and California, both in states with mandatory reporting and in non-reporting states.
ImportanceCoccidioidomycosis, also known as Valley fever, is a serious fungal disease caused by inhaling Coccidioides spores aerosolized from the soil. Despite rising public health concern, the distribution and incidence of coccidioidomycosis in the US remain poorly characterized as not all states are required to report cases, and case under-ascertainment is presumed to be high, particularly outside of the endemic region.
ObjectiveTo estimate monthly, county-level coccidioidomycosis incidence across the US while accounting for widespread under-ascertainment.
Design, Setting, and ParticipantsWe integrated multisource data, including human cases diagnosed in electronic health records, serological testing of dogs, and ecological and sociodemographic predictors, in a machine learning model estimating monthly, county-level coccidioidomycosis incidence. The model was trained on surveillance data from Arizona and California from 2013 to 2023, then applied to predict incidence in states across the contiguous US over the same time period.
Main Outcomes and MeasuresIncidence of coccidioidomycosis at the monthly county level.
ResultsThe model predicted coccidioidomycosis incidence from 2013 to 2023 for 3,108 counties from all states in the contiguous US. The model identified 60 counties in non-reporting states where predicted incidence was [≥]2 cases per 100,000 population (considered moderate to high incidence). In states with mandatory reporting outside of Arizona and California, the model predicted county-level incidence rates that were 28% higher (95% bootstrap interval, 0.1%-69.8%) than those captured in national surveillance, equating to a total of 608 potentially missed cases per year (95% bootstrap interval, 340-964).
Conclusions and RelevanceIn this cross-sectional study, the model quantified case under-ascertainment for coccidioidomycosis relative to Arizona and California, and highlighted the potential for alternative data sources to fill in gaps in mandatory reporting. Estimating incidence while accounting for under-ascertainment and non-reporting may help efforts to improve public and physician awareness and to detect emergence in new regions.
Related
- Accelerating research to keep pace with the rising incidence of coccidioidomycosis
- Cancer Incidence, Healthcare Access, and Support Resource Distribution in Delaware : A Statewide Epidemiological Analysis, 2018-2022.
- A retrospective epidemiological study of screening-derived solid cancer incidence proxy rates in South Korea before and after COVID-19 using Korean National Health Insurance Service data
- Epidemiological trend comparison and incidence prediction for elderly lung cancer in 204 countries and territories: a retrospective study.
- Epidemiological Characteristics and Incidence Trends of Hemorrhagic Fever With Renal Syndrome in Shandong Province, China: Retrospective Observational Study With Forecasting
BibTeX
@misc{couper2026national,
title = {{National incidence of coccidioidomycosis in the United States estimated through machine learning integration of epidemiological, veterinary, and socioecological data}},
author = {L. I. Couper and S. K. Camponuri and J. E. Sykes and X. Li and A. E. Hubbard and B. L. M. Bustamante and T. Williamson and I. Ruberto and G. Sondermeyer-Cooksey and E. N. Karmarkar and A. T. Yu and A. K. Heaney and J. R. Head and J. V. Remais},
howpublished = {medRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.14.26365564},
url = {https://www.medrxiv.org/content/10.64898/2026.10.14.26365564v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - National incidence of coccidioidomycosis in the United States estimated through machine learning integration of epidemiological, veterinary, and socioecological data
AU - L. I. Couper
AU - S. K. Camponuri
AU - J. E. Sykes
AU - X. Li
AU - A. E. Hubbard
AU - B. L. M. Bustamante
AU - T. Williamson
AU - I. Ruberto
AU - G. Sondermeyer-Cooksey
AU - E. N. Karmarkar
AU - A. T. Yu
AU - A. K. Heaney
AU - J. R. Head
AU - J. V. Remais
PY - 2026
DA - 2026/10/14
PB - medRxiv
DO - 10.64898/2026.10.14.26365564
UR - https://www.medrxiv.org/content/10.64898/2026.10.14.26365564v1
AB - Key pointsO_ST_ABSQuestionC_ST_ABSIn the absence of nationwide reporting for coccidioidomycosis, can alternative data sources be integrated to enable estimates of monthly, county-level incidence across the US? FindingsIn this cross-sectional study of 3,108 counties, the model identified 60 counties in non-reporting states with predicted incidence [≥]2 cases per 100,000 population (considered moderate to high incidence). In states with mandatory reporting outside of Arizona and California, the models predicted county-level incidence rates were, on average, 28% higher than those captured in national surveillance. MeaningOur predictions highlight the extent of case under-ascertainment for coccidioidomycosis relative to Arizona and California, both in states with mandatory reporting and in non-reporting states. ImportanceCoccidioidomycosis, also known as Valley fever, is a serious fungal disease caused by inhaling Coccidioides spores aerosolized from the soil. Despite rising public health concern, the distribution and incidence of coccidioidomycosis in the US remain poorly characterized as not all states are required to report cases, and case under-ascertainment is presumed to be high, particularly outside of the endemic region. ObjectiveTo estimate monthly, county-level coccidioidomycosis incidence across the US while accounting for widespread under-ascertainment. Design, Setting, and ParticipantsWe integrated multisource data, including human cases diagnosed in electronic health records, serological testing of dogs, and ecological and sociodemographic predictors, in a machine learning model estimating monthly, county-level coccidioidomycosis incidence. The model was trained on surveillance data from Arizona and California from 2013 to 2023, then applied to predict incidence in states across the contiguous US over the same time period. Main Outcomes and MeasuresIncidence of coccidioidomycosis at the monthly county level. ResultsThe model predicted coccidioidomycosis incidence from 2013 to 2023 for 3,108 counties from all states in the contiguous US. The model identified 60 counties in non-reporting states where predicted incidence was [≥]2 cases per 100,000 population (considered moderate to high incidence). In states with mandatory reporting outside of Arizona and California, the model predicted county-level incidence rates that were 28% higher (95% bootstrap interval, 0.1%-69.8%) than those captured in national surveillance, equating to a total of 608 potentially missed cases per year (95% bootstrap interval, 340-964). Conclusions and RelevanceIn this cross-sectional study, the model quantified case under-ascertainment for coccidioidomycosis relative to Arizona and California, and highlighted the potential for alternative data sources to fill in gaps in mandatory reporting. Estimating incidence while accounting for under-ascertainment and non-reporting may help efforts to improve public and physician awareness and to detect emergence in new regions.
ER -