{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T21:33:58Z","timestamp":1786484038063,"version":"build-2736575974"},"reference-count":42,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Med Inform"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Accurate forecasting of influenza-like illness (ILI) is crucial for public health. Integrating novel digital data streams (eg, internet searches and human mobility) with traditional surveillance can improve accuracy, but optimal modeling frameworks are underexplored.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aimed to develop and compare multisource data-driven models for forecasting ILI incidence trends.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n \n Weekly ILI incidence data and multisource variables for Hubei Province from 2020 to 2023 were collected. Multisource predictors included mean temperature, relative humidity, air quality index, a synthesized Baidu Search Index for influenza-related queries, the Baidu Migration Scale Index for population mobility, and the Oxford Stringency Index (SI) for nonpharmaceutical interventions. Predictive models evaluated were Seasonal Autoregressive Integrated Moving Average (SARIMA), long short-term memory (LSTM), a hybrid convolutional neural network\u2013long short-term memory (CNN-LSTM), Transformer, and random forest. Models were constructed using an 85:15 training-test split and optimized via grid search with 5-fold cross-validation. Performance was assessed using mean absolute error, root-mean-squared error (RMSE), mean absolute percentage error, and coefficient of determination (\n R<\/jats:italic>\n \u00b2).\n <\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n All models incorporating multisource data substantially outperformed univariate time-series benchmarks. Among univariate models, CNN-LSTM achieved superior performance (\n R<\/jats:italic>\n \u00b2=0.7623) over SARIMA (\n R<\/jats:italic>\n \u00b2=\u22120.2645). In multisource configurations, the LSTM model demonstrated the strongest predictive capability and feature integration, attaining an optimal\n R<\/jats:italic>\n \u00b2 of 0.8350 when combining environmental, mobility (Baidu Migration Scale), and internet search (synthetic Baidu index [SBI]) data. The inclusion of the Oxford SI consistently reduced prediction error across all models, with mean absolute percentage error decreasing by up to 84.87% in the LSTM model. The Baidu Search Index emerged as the most influential single external predictor, notably enhancing model fit. In contrast, model performance varied with feature composition: the Transformer model excelled with full feature sets, while CNN-LSTM performed best primarily with SBI integration. Over a 26-week prospective projection, the optimal LSTM model forecasted a \u201crapid decline\u2013gradual decline\u2013stabilization\u201d trend, indicating a return to baseline ILI activity, and demonstrated robust external validation performance (\n R<\/jats:italic>\n 2<\/jats:sup>\n =0.7707).\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n Deep learning models, particularly LSTM, can effectively leverage heterogeneous digital data to improve ILI forecasting. Internet search behavior and policy stringency are critical external predictors. The proposed model demonstrated good external validation performance, and the findings may be applicable to other temperate regions in central China exhibiting similar epidemic characteristics.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/91844","type":"journal-article","created":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T18:35:10Z","timestamp":1781721310000},"page":"e91844-e91844","source":"Crossref","is-referenced-by-count":0,"title":["Influenza-Like Illness Forecasting Using Multisource Data: Comparative Deep Learning Study"],"prefix":"10.2196","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-5276-1329","authenticated-orcid":false,"given":"Caixia","family":"Dang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5652-0564","authenticated-orcid":false,"given":"Yeqing","family":"Tong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5816-5118","authenticated-orcid":false,"given":"Yanquan","family":"Mo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5307-0583","authenticated-orcid":false,"given":"Ziqian","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1646-5963","authenticated-orcid":false,"given":"Shanhui","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4398-3665","authenticated-orcid":false,"given":"Feng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0189-0562","authenticated-orcid":false,"given":"Huiqun","family":"Jia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0355-2992","authenticated-orcid":false,"given":"Jingya","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9709-6881","authenticated-orcid":false,"given":"Yuanyong","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2218-3982","authenticated-orcid":false,"given":"Hui","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,8,11]]},"reference":[{"issue":"10127","key":"R1","doi-asserted-by":"publisher","first-page":"1285","DOI":"10.1016\/S0140-6736(17)33293-2","article-title":"Estimates of global seasonal influenza-associated respiratory mortality: a modelling study","volume":"391","author":"Iuliano","journal-title":"Lancet"},{"issue":"3","key":"R2","doi-asserted-by":"publisher","DOI":"10.3390\/v15030594","article-title":"Association between Temperature and Influenza Activity across Different Regions of China during 2010-2017","volume":"15","author":"Wang","journal-title":"Viruses"},{"issue":"11","key":"R3","doi-asserted-by":"publisher","first-page":"704","DOI":"10.1016\/S1473-3099(04)01177-6","article-title":"Seasonality of infectious diseases and severe acute respiratory syndrome-what we don\u2019t know can hurt us","volume":"4","author":"Dowell","journal-title":"Lancet Infect Dis"},{"issue":"1","key":"R4","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-25120-6","article-title":"Etiological and epidemiological features of acute respiratory infections in China","volume":"12","author":"Li","journal-title":"Nat Commun"},{"key":"R5","unstructured":"China NICC National Influenza Centre of China. Title: China National Influenza Center (CNIC) \u2013 Influenza Surveillance Website. URL: https:\/\/ivdc.chinacdc.cn\/cnic\/ [Accessed 13-07-2026]"},{"issue":"1","key":"R6","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-23440-1","article-title":"Impact of COVID-19 outbreaks and interventions on influenza in China and the United States","volume":"12","author":"Feng","journal-title":"Nat Commun"},{"issue":"1","key":"R7","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-48201-8","article-title":"Temporal shifts in 24 notifiable infectious diseases in China before and during the COVID-19 pandemic","volume":"15","author":"Li","journal-title":"Nat Commun"},{"key":"R8","doi-asserted-by":"publisher","DOI":"10.1016\/j.scitotenv.2021.151724","article-title":"Influenza seasonality and its environmental driving factors in mainland China and Hong Kong","volume":"818","author":"Ali","journal-title":"Sci Total Environ"},{"issue":"6","key":"R9","doi-asserted-by":"publisher","DOI":"10.1128\/AEM.02426-18","article-title":"Effects of Absolute Humidity, Relative Humidity, Temperature, and Wind Speed on Influenza Activity in Toronto, Ontario, Canada","volume":"85","author":"Peci","journal-title":"Appl Environ Microbiol"},{"issue":"11","key":"R10","doi-asserted-by":"publisher","DOI":"10.3390\/v14112563","article-title":"The Impact of Urbanization and Human Mobility on Seasonal Influenza in Northern China","volume":"14","author":"Yang","journal-title":"Viruses"},{"issue":"12","key":"R11","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.aau5294","article-title":"Urbanization affects peak timing, prevalence, and bimodality of influenza pandemics in Australia: Results of a census-calibrated model","volume":"4","author":"Zachreson","journal-title":"Sci Adv"},{"issue":"10","key":"R12","doi-asserted-by":"publisher","DOI":"10.2196\/14276","article-title":"The Fever Coach Mobile App for Participatory Influenza Surveillance in Children: Usability Study","volume":"7","author":"Kim","journal-title":"JMIR Mhealth Uhealth"},{"key":"R13","doi-asserted-by":"publisher","DOI":"10.3389\/fpubh.2023.1203628","article-title":"Using the Baidu index to predict trends in the incidence of tuberculosis in Jiangsu Province, China","volume":"11","author":"Wang","journal-title":"Front Public Health"},{"issue":"1","key":"R14","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-35685-w","article-title":"Using Baidu Search Engine to Monitor AIDS Epidemics Inform for Targeted intervention of HIV\/AIDS in China","volume":"9","author":"Li","journal-title":"Sci Rep"},{"issue":"1","key":"R15","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0280834","article-title":"Influenza surveillance with Baidu index and attention-based long short-term memory model","volume":"18","author":"Dai","journal-title":"PLoS One"},{"key":"R16","doi-asserted-by":"publisher","DOI":"10.7717\/peerj.10139","article-title":"Regional infectious risk prediction of COVID-19 based on geo-spatial data","volume":"8","author":"Cheng","journal-title":"PeerJ"},{"issue":"1","key":"R17","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-39871-2","article-title":"Predicting seasonal influenza epidemics using cross-hemisphere influenza surveillance data and local internet query data","volume":"9","author":"Zhang","journal-title":"Sci Rep"},{"key":"R18","doi-asserted-by":"publisher","DOI":"10.2196\/45085","article-title":"Influenza Epidemic Trend Surveillance and Prediction Based on Search Engine Data: Deep Learning Model Study","volume":"25","author":"Yang","journal-title":"J Med Internet Res"},{"issue":"3","key":"R19","doi-asserted-by":"publisher","DOI":"10.1007\/s11113-023-09780-4","article-title":"Influence Mechanism Analysis of the Spatial Evolution of Inter-Provincial Population Flow in China Based on Epidemic Prevention and Control","volume":"42","author":"Lan","journal-title":"Popul Res Policy Rev"},{"issue":"4","key":"R20","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/s41562-021-01079-8","article-title":"A global panel database of pandemic policies (Oxford COVID-19 Government Response Tracker)","volume":"5","author":"Hale","journal-title":"Nat Hum Behav"},{"issue":"1","key":"R21","doi-asserted-by":"publisher","DOI":"10.1038\/s43856-023-00424-4","article-title":"Forecasting influenza hospital admissions within English sub-regions using hierarchical generalised additive models","volume":"3","author":"Mellor","journal-title":"Commun Med (Lond)"},{"issue":"23","key":"R22","doi-asserted-by":"publisher","DOI":"10.1097\/MD.0000000000029317","article-title":"The research of SARIMA model for prediction of hepatitis B in mainland China","volume":"101","author":"Zhao","journal-title":"Medicine (Baltimore)"},{"key":"R23","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2023.04.026","article-title":"Long short-term memory with activation on gradient","volume":"164","author":"Qin","journal-title":"Neural Netw"},{"key":"R24","doi-asserted-by":"publisher","DOI":"10.1016\/j.csbj.2021.09.001","article-title":"Machine learning and deep learning methods that use omics data for metastasis prediction","volume":"19","author":"Albaradei","journal-title":"Comput Struct Biotechnol J"},{"issue":"8","key":"R25","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","journal-title":"Neural Comput"},{"issue":"1","key":"R26","doi-asserted-by":"publisher","DOI":"10.1186\/s12889-024-19590-8","article-title":"Forecasting and analyzing influenza activity in Hebei Province, China, using a CNN-LSTM hybrid model","volume":"24","author":"Li","journal-title":"BMC Public Health"},{"key":"R27","doi-asserted-by":"publisher","DOI":"10.7717\/peerj.17811","article-title":"Prediction of PM concentration based on a CNN-LSTM neural network algorithm","volume":"12","author":"Bai","journal-title":"PeerJ"},{"key":"R28","unstructured":"Vaswani A Shazeer N Parmar N Uszkoreit J Jones L Gomez AN et al. Attention is all you need. arXiv. Preprint posted online on Jun 12, 2017. [doi: 10.48550\/arXiv.1706.03762]"},{"key":"R29","doi-asserted-by":"publisher","DOI":"10.2196\/67847","article-title":"Evaluation of a Machine Learning Model Based on Laboratory Parameters for the Prediction of Influenza A and B in Chongqing, China: Multicenter Model Development and Validation Study","volume":"27","author":"Hu","journal-title":"J Med Internet Res"},{"issue":"1","key":"R30","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random Forests","volume":"45","author":"Breiman","journal-title":"Mach Learn"},{"key":"R31","doi-asserted-by":"publisher","DOI":"10.1016\/j.ebiom.2019.08.024","article-title":"Forecasting influenza activity using self-adaptive AI model and multi-source data in Chongqing, China","volume":"47","author":"Su","journal-title":"EBioMedicine"},{"issue":"3","key":"R32","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1111\/irv.12226","article-title":"A systematic review of studies on forecasting the dynamics of influenza outbreaks","volume":"8","author":"Nsoesie","journal-title":"Influenza Other Respir Viruses"},{"key":"R33","doi-asserted-by":"publisher","DOI":"10.2196\/71786","article-title":"A Deep Learning Framework for Using Search Engine Data to Predict Influenza-Like Illness and Distinguish Epidemic and Nonepidemic Seasons: Multifeature Time Series Analysis","volume":"27","author":"Li","journal-title":"J Med Internet Res"},{"issue":"1","key":"R34","doi-asserted-by":"publisher","first-page":"19","DOI":"10.2991\/ijndc.k.201218.003","article-title":"The Prediction of COVID-19 Using LSTM Algorithms","volume":"9","author":"Kim","journal-title":"IJNDC"},{"issue":"5","key":"R35","doi-asserted-by":"publisher","first-page":"e279","DOI":"10.1016\/S2468-2667(20)30090-6","article-title":"Impact assessment of non-pharmaceutical interventions against coronavirus disease 2019 and influenza in Hong Kong: an observational study","volume":"5","author":"Cowling","journal-title":"Lancet Public Health"},{"issue":"1","key":"R36","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-27326-w","article-title":"Evaluation of climate prediction models in Yunnan, China: traditional methods and AI approaches","volume":"15","author":"Zhao","journal-title":"Sci Rep"},{"issue":"1","key":"R37","doi-asserted-by":"publisher","DOI":"10.1186\/s12889-024-17978-0","article-title":"The prediction of influenza-like illness using national influenza surveillance data and Baidu query data","volume":"24","author":"Wei","journal-title":"BMC Public Health"},{"issue":"1","key":"R38","doi-asserted-by":"publisher","DOI":"10.1186\/s12879-023-08594-1","article-title":"Impact of non-pharmaceutical interventions during COVID-19 on future influenza trends in Mainland China","volume":"23","author":"Liu","journal-title":"BMC Infect Dis"},{"key":"R39","doi-asserted-by":"publisher","DOI":"10.3389\/fpubh.2024.1336077","article-title":"The effect of nonpharmaceutical interventions on influenza virus transmission","volume":"12","author":"Chen","journal-title":"Front Public Health"},{"key":"R40","doi-asserted-by":"publisher","DOI":"10.3389\/fpubh.2024.1344306","article-title":"The impact of population influx on infectious diseases - from the mediating effect of polluted air transmission","volume":"12","author":"Fu","journal-title":"Front Public Health"},{"key":"R41","doi-asserted-by":"crossref","unstructured":"Lai G Chang WC Yang Y Liu H . Modeling long- and short-term temporal patterns with deep neural networks. Presented at: 41st International ACM SIGIR Conference on Research & Development in Information Retrieval; Jul 8-12, 2018:95-104; Ann Arbor. Jun 27, 2018.[doi: 10.1145\/3209978.3210006]","DOI":"10.1145\/3209978.3210006"},{"issue":"1","key":"R42","doi-asserted-by":"publisher","first-page":"388","DOI":"10.1016\/j.ijforecast.2020.06.008","article-title":"Recurrent Neural Networks for Time Series Forecasting: Current status and future directions","volume":"37","author":"Hewamalage","journal-title":"Int J Forecast"}],"container-title":["JMIR Medical Informatics"],"original-title":[],"language":"en","deposited":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T21:15:07Z","timestamp":1786482907000},"score":1,"resource":{"primary":{"URL":"https:\/\/medinform.jmir.org\/2026\/1\/e91844"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,11]]},"references-count":42,"URL":"https:\/\/doi.org\/10.2196\/91844","relation":{},"ISSN":["2291-9694"],"issn-type":[{"value":"2291-9694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,11]]},"article-number":"v14i10127e91844"}}