Time series forecasting of Valley fever infection in Maricopa County, AZ using LSTMResearch in context

Summary: Background: Coccidioidomycosis (CM), also known as Valley fever, is a respiratory infection. Recently, the number of confirmed cases of CM has been increasing. Precisely defining the influential factors and forecasting future infection can assist in public health messaging and treatment de...

Full description

Saved in:
Bibliographic Details
Main Authors: Xueting Jin, Fangwu Wei, Srinivasa Srivatsav Kandala, Tejas Umesh, Kayleigh Steele, John N. Galgiani, Manfred D. Laubichler
Format: Article
Language:English
Published: Elsevier 2025-03-01
Series:The Lancet Regional Health. Americas
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2667193X25000201
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832087368898707456
author Xueting Jin
Fangwu Wei
Srinivasa Srivatsav Kandala
Tejas Umesh
Kayleigh Steele
John N. Galgiani
Manfred D. Laubichler
author_facet Xueting Jin
Fangwu Wei
Srinivasa Srivatsav Kandala
Tejas Umesh
Kayleigh Steele
John N. Galgiani
Manfred D. Laubichler
author_sort Xueting Jin
collection DOAJ
description Summary: Background: Coccidioidomycosis (CM), also known as Valley fever, is a respiratory infection. Recently, the number of confirmed cases of CM has been increasing. Precisely defining the influential factors and forecasting future infection can assist in public health messaging and treatment decisions. Methods: We utilized Long Short-Term Memory (LSTM) networks to forecast CM cases, based on the daily pneumonia cases in Maricopa County, Arizona from 2020 to 2022. Besides weather and climate variables, we examined the impact of people's lifestyle change during COVID-19. Factors, including temperature, precipitation, wind speed, PM10 and PM2.5 concentration, drought, and stringency index, were included in LSTM networks, considering their association with CM prevalence, time-lag effect, and correlation with other factors. Findings: LSTM can predict CM prevalence with accurate trend and low mean squared error (MSE). We also found a tradeoff between the length of the forecasting period and the performance of the forecasting model. The models with longer forecasting periods have less accurate trends over time and higher MSEs. Two models with different lengths of forecasting periods, 10 days and 30 days, are identified with good prediction. Interpretation: LSTM algorithms, combined with traditional statistical methods, could help with the forecasting of CM cases. By predicting the CM prevalence, our results can inform researchers, epidemiologists, clinicians, and the public in order to assist public health. Funding: “Getting to the Source of Arizona's Valley Fever Problem: A Tri-University Collaboration to Map and Characterize the Pathogen Where It Grows” funded by the Arizona Board of Regents.
format Article
id doaj-art-5e59b9ec309a42c2832dc88c1d29e005
institution Kabale University
issn 2667-193X
language English
publishDate 2025-03-01
publisher Elsevier
record_format Article
series The Lancet Regional Health. Americas
spelling doaj-art-5e59b9ec309a42c2832dc88c1d29e0052025-02-06T05:13:01ZengElsevierThe Lancet Regional Health. Americas2667-193X2025-03-0143101010Time series forecasting of Valley fever infection in Maricopa County, AZ using LSTMResearch in contextXueting Jin0Fangwu Wei1Srinivasa Srivatsav Kandala2Tejas Umesh3Kayleigh Steele4John N. Galgiani5Manfred D. Laubichler6Decision Theater, Knowledge Enterprise, Arizona State University, Tempe, AZ, USA; School of Geographical Sciences and Urban Planning, Arizona State University, Tempe, AZ, USADecision Theater, Knowledge Enterprise, Arizona State University, Tempe, AZ, USA; Corresponding author. Arizona State University, Tempe, AZ, USA.Decision Theater, Knowledge Enterprise, Arizona State University, Tempe, AZ, USABarrow Neurological Institute, St Joseph's Hospital, Phoenix, AZ, USADecision Theater, Knowledge Enterprise, Arizona State University, Tempe, AZ, USAValley Fever Center for Excellence and the Departments of Medicine and Immunobiology, University of Arizona College of Medicine-Tucson, Tucson, AZ, USA; BIO5 Institute, University of Arizona, Tucson, AZ, USADecision Theater, Knowledge Enterprise, Arizona State University, Tempe, AZ, USASummary: Background: Coccidioidomycosis (CM), also known as Valley fever, is a respiratory infection. Recently, the number of confirmed cases of CM has been increasing. Precisely defining the influential factors and forecasting future infection can assist in public health messaging and treatment decisions. Methods: We utilized Long Short-Term Memory (LSTM) networks to forecast CM cases, based on the daily pneumonia cases in Maricopa County, Arizona from 2020 to 2022. Besides weather and climate variables, we examined the impact of people's lifestyle change during COVID-19. Factors, including temperature, precipitation, wind speed, PM10 and PM2.5 concentration, drought, and stringency index, were included in LSTM networks, considering their association with CM prevalence, time-lag effect, and correlation with other factors. Findings: LSTM can predict CM prevalence with accurate trend and low mean squared error (MSE). We also found a tradeoff between the length of the forecasting period and the performance of the forecasting model. The models with longer forecasting periods have less accurate trends over time and higher MSEs. Two models with different lengths of forecasting periods, 10 days and 30 days, are identified with good prediction. Interpretation: LSTM algorithms, combined with traditional statistical methods, could help with the forecasting of CM cases. By predicting the CM prevalence, our results can inform researchers, epidemiologists, clinicians, and the public in order to assist public health. Funding: “Getting to the Source of Arizona's Valley Fever Problem: A Tri-University Collaboration to Map and Characterize the Pathogen Where It Grows” funded by the Arizona Board of Regents.http://www.sciencedirect.com/science/article/pii/S2667193X25000201CoccidioidomycosisValley feverDeep learningLSTMTime series forecasting
spellingShingle Xueting Jin
Fangwu Wei
Srinivasa Srivatsav Kandala
Tejas Umesh
Kayleigh Steele
John N. Galgiani
Manfred D. Laubichler
Time series forecasting of Valley fever infection in Maricopa County, AZ using LSTMResearch in context
The Lancet Regional Health. Americas
Coccidioidomycosis
Valley fever
Deep learning
LSTM
Time series forecasting
title Time series forecasting of Valley fever infection in Maricopa County, AZ using LSTMResearch in context
title_full Time series forecasting of Valley fever infection in Maricopa County, AZ using LSTMResearch in context
title_fullStr Time series forecasting of Valley fever infection in Maricopa County, AZ using LSTMResearch in context
title_full_unstemmed Time series forecasting of Valley fever infection in Maricopa County, AZ using LSTMResearch in context
title_short Time series forecasting of Valley fever infection in Maricopa County, AZ using LSTMResearch in context
title_sort time series forecasting of valley fever infection in maricopa county az using lstmresearch in context
topic Coccidioidomycosis
Valley fever
Deep learning
LSTM
Time series forecasting
url http://www.sciencedirect.com/science/article/pii/S2667193X25000201
work_keys_str_mv AT xuetingjin timeseriesforecastingofvalleyfeverinfectioninmaricopacountyazusinglstmresearchincontext
AT fangwuwei timeseriesforecastingofvalleyfeverinfectioninmaricopacountyazusinglstmresearchincontext
AT srinivasasrivatsavkandala timeseriesforecastingofvalleyfeverinfectioninmaricopacountyazusinglstmresearchincontext
AT tejasumesh timeseriesforecastingofvalleyfeverinfectioninmaricopacountyazusinglstmresearchincontext
AT kayleighsteele timeseriesforecastingofvalleyfeverinfectioninmaricopacountyazusinglstmresearchincontext
AT johnngalgiani timeseriesforecastingofvalleyfeverinfectioninmaricopacountyazusinglstmresearchincontext
AT manfreddlaubichler timeseriesforecastingofvalleyfeverinfectioninmaricopacountyazusinglstmresearchincontext