{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T16:14:11Z","timestamp":1785428051605,"version":"3.56.0"},"reference-count":43,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T00:00:00Z","timestamp":1775779200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72274210"],"award-info":[{"award-number":["72274210"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"award":["72274210"],"award-info":[{"award-number":["72274210"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"publisher"}]},{"name":"Capital\u2019s Funds for Health Improvement and Research of China","award":["2024-1G-5011"],"award-info":[{"award-number":["2024-1G-5011"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Pathogens"],"abstract":"<jats:p>Background: Pneumonia of unknown etiology (PUE), defined as pneumonia cases without an identified pathogen at the time of clinical presentation, represents a critical clinical warning signal for emerging infectious disease (EID) outbreaks with pandemic potential. Yet, conventional pathogen-centric surveillance systems suffer from an inherent blind spot: they cannot detect early clustering signals before the causative agent is identified, creating a window of vulnerability during novel pathogen emergence. To address this gap, this study aims to develop a deep learning model that leverages unstructured chest imaging text\u2014a routinely available clinical data stream\u2014to enable real-time, automated screening of PUE cases and early warning of EID clusters, independent of prior pathogen knowledge, within an integrated multi-pathogen surveillance framework. Methods: We retrospectively collected data from 8860 patients with respiratory illnesses at a tertiary hospital in Beijing, China, including 980 PUE cases (11.1%) and 7880 known-etiology pneumonia cases. A deep learning model (RoBERTa with attention enhancement) was developed using unstructured chest imaging reports. The Matthews correlation coefficient (MCC) curve was employed to determine the optimal decision threshold. Model performance was assessed for PUE case identification and clustering signal detection on a test set. Results: The model achieved an area under the receiver operating characteristic curve of 0.986 (95% CI: 0.981\u20130.991). At the optimal threshold of 0.08, selected by maximizing the Matthews correlation coefficient (MCC)\u2014a balanced metric that accounts for all four confusion matrix outcomes\u2014sensitivity was 89.8%, and specificity was 97.0% for identifying PUE cases. In a simulated surveillance exercise, the model showed a high correlation between the predicted and actual case counts (Pearson\u2019s r = 0.901), suggesting its potential to detect abnormal clustering signals prior to pathogen identification. Conclusions: The developed model demonstrates potential to detect clustering signals of PUE caused by unknown pathogens and can be integrated with hospital information systems, providing a feasible, low-cost tool for integrated surveillance of pathogens with pandemic potential. This approach enables earlier outbreak detection and supports public health decision-making during the critical window before pathogen identification.<\/jats:p>","DOI":"10.3390\/pathogens15040413","type":"journal-article","created":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T12:01:52Z","timestamp":1775822512000},"page":"413","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Integrated Deep Learning Surveillance of Unknown Pathogens with Pandemic Potential Using Pneumonia of Unknown Etiology"],"prefix":"10.3390","volume":"15","author":[{"given":"Xiao","family":"Yang","sequence":"first","affiliation":[{"name":"The Fifth Clinical College, Anhui Medical University, Hefei 230032, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui","family":"Ma","sequence":"additional","affiliation":[{"name":"The Fifth Clinical College, Anhui Medical University, Hefei 230032, China"},{"name":"Graduate School, Medical School of Chinese PLA, Beijing 100853, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min","family":"Zhu","sequence":"additional","affiliation":[{"name":"Graduate School, Medical School of Chinese PLA, Beijing 100853, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyu","family":"Song","sequence":"additional","affiliation":[{"name":"Graduate School, Medical School of Chinese PLA, Beijing 100853, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiahao","family":"Feng","sequence":"additional","affiliation":[{"name":"Graduate School, Medical School of Chinese PLA, Beijing 100853, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,4,10]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1206","DOI":"10.3201\/eid1007.030703","article-title":"SARS control and psychological effects of quarantine, Toronto, Canada","volume":"10","author":"Hawryluck","year":"2004","journal-title":"Emerg. Infect. Dis."},{"key":"ref_2","first-page":"1843","article-title":"Detection of SARS-CoV-2 in Different Types of Clinical Specimens","volume":"323","author":"Wang","year":"2020","journal-title":"JAMA"},{"key":"ref_3","first-page":"891","article-title":"The middle east respiratory syndrome (MERS)","volume":"33","author":"Azhar","year":"2019","journal-title":"Infect. Dis. Clin."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"453","DOI":"10.1007\/s41885-020-00070-3","article-title":"Socio-economic impacts of COVID-19 on household consumption and poverty","volume":"4","author":"Martin","year":"2020","journal-title":"Econ. Disasters Clim. Change"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Thiam, M.-M., Pontais, I., Forgeot, C., Pedrono, G., Paget, L.-M., Fouillet, A., and Caserio-Sch\u00f6nemann, C. (2022). Syndromic surveillance: A key component of population health monitoring during the first wave of the COVID-19 outbreak in France, February\u2013June 2020. PLoS ONE, 17.","DOI":"10.1371\/journal.pone.0260150"},{"key":"ref_6","first-page":"1197","article-title":"Syndromic surveillance and bioterrorism-related epidemics","volume":"7","author":"Buehler","year":"2001","journal-title":"Emerg. Infect. Dis."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Dai, Y., and Wang, J. (2020). Identifying the outbreak signal of COVID-19 before the response of the traditional disease monitoring system. PLoS Negl. Trop. Dis., 14.","DOI":"10.1371\/journal.pntd.0008758"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"100003","DOI":"10.1016\/j.ijidoh.2023.100003","article-title":"Looking in all the wrong places: A rationale for signal detection for pandemics based on existing data sources","volume":"1","author":"Dogra","year":"2023","journal-title":"IJID One Health"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"100102","DOI":"10.1016\/j.soh.2024.100102","article-title":"Integrated surveillance and early warning system of emerging infectious diseases in China at community level: Current status, gaps and perspectives","volume":"4","author":"Zhou","year":"2025","journal-title":"Sci. One Health"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"102621","DOI":"10.1016\/j.jiph.2024.102621","article-title":"Does syndromic surveillance assist public health practice in early detecting respiratory epidemics? Evidence from a wide Italian retrospective experience","volume":"18","author":"Corrao","year":"2025","journal-title":"J. Infect. Public Health"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Proverbio, D., Kemp, F., Magni, S., and Goncalves, J. (2022). Performance of early warning signals for disease re emergence: A case study on COVID-19 data. PLoS Comput. Biol., 18.","DOI":"10.1371\/journal.pcbi.1009958"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"19795","DOI":"10.1038\/s41598-021-98781-4","article-title":"Change sign detection with differential MDL change statistics and its applications to COVID-19 pandemic analysis","volume":"11","author":"Yamanishi","year":"2021","journal-title":"Sci. Rep."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"41","DOI":"10.4103\/jgid.jgid_90_23","article-title":"State of the Globe: Navigating the Impact of SARS-CoV-2 Mutations on COVID-19 Testing","volume":"15","author":"Varshney","year":"2023","journal-title":"J. Glob. Infect. Dis."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1407","DOI":"10.1093\/infdis\/jix148","article-title":"Viral Pathogen Detection by Metagenomics and Pan-Viral Group Polymerase Chain Reaction in Children With Pneumonia Lacking Identifiable Etiology","volume":"215","author":"Schlaberg","year":"2017","journal-title":"J. Infect. Dis."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Villanueva-Miranda, I., Xiao, G., and Xie, Y. (2025). Artificial intelligence in early warning systems for infectious disease surveillance: A systematic review. Front. Public Health, 13.","DOI":"10.3389\/fpubh.2025.1609615"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"558","DOI":"10.1080\/21505594.2015.1040975","article-title":"New technologies in predicting, preventing and controlling emerging infectious diseases","volume":"6","author":"Christaki","year":"2015","journal-title":"Virulence"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"e101153","DOI":"10.1136\/bmjhci-2024-101153","article-title":"Patient perspective on predictive models in healthcare: Translation into practice, ethical implications and limitations?","volume":"32","author":"Markham","year":"2025","journal-title":"BMJ Health Care Inform."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"6176855","DOI":"10.1155\/ipid\/6176855","article-title":"Identifying Early Signals From Emerging Public Health Events Using Natural Language Processing","volume":"2026","author":"Peterson","year":"2026","journal-title":"Interdiscip. Perspect. Infect. Dis."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Rani, S., Kumar, R., Panda, B.S., Kumar, R., Muften, N.F., Abass, M.A., and Lozanovi\u0107, J. (2025). Machine Learning-Powered Smart Healthcare Systems in the Era of Big Data: Applications, Diagnostic Insights, Challenges, and Ethical Implications. Diagnostics, 15.","DOI":"10.3390\/diagnostics15151914"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"E115","DOI":"10.1148\/radiol.2020200432","article-title":"Sensitivity of chest CT for COVID-19: Comparison to RT-PCR","volume":"296","author":"Fang","year":"2020","journal-title":"Radiology"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1038\/s42256-020-0180-7","article-title":"An interpretable mortality prediction model for COVID-19 patients","volume":"2","author":"Yan","year":"2020","journal-title":"Nat. Mach. Intell."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1016\/j.cell.2020.05.032","article-title":"Proteomic and metabolomic characterization of COVID-19 patient sera","volume":"182","author":"Shen","year":"2020","journal-title":"Cell"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"4080","DOI":"10.1038\/s41467-020-17971-2","article-title":"Artificial intelligence for the detection of COVID-19 pneumonia on chest CT using multinational datasets","volume":"11","author":"Harmon","year":"2020","journal-title":"Nat. Commun."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"3543","DOI":"10.1038\/s41467-020-17280-8","article-title":"Early triage of critically ill COVID-19 patients using deep learning","volume":"11","author":"Liang","year":"2020","journal-title":"Nat. Commun."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"19196","DOI":"10.1038\/s41598-020-76282-0","article-title":"Deep learning-based model for detecting 2019 novel coronavirus pneumonia on high-resolution computed tomography","volume":"10","author":"Chen","year":"2020","journal-title":"Sci. Rep."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"19549","DOI":"10.1038\/s41598-020-76550-z","article-title":"Covid-Net: A tailored deep convolutional neural network design for detection of covid-19 cases from chest x-ray images","volume":"10","author":"Wang","year":"2020","journal-title":"Sci. Rep."},{"key":"ref_27","first-page":"105251","article-title":"Early detection of COVID-19 outbreaks using textual analysis of electronic medical records","volume":"155","author":"Shapiro","year":"2022","journal-title":"Int. J. Infect. Dis."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"e53367","DOI":"10.2196\/53367","article-title":"Moving biosurveillance beyond coded data using AI for symptom detection from physician notes: Retrospective cohort study","volume":"26","author":"McMurry","year":"2024","journal-title":"J. Med. Internet Res."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1097\/PEC.0000000000002648","article-title":"Machine Learning-Based Prediction of Hospital Admission Among Children in an Emergency Care Center","volume":"39","author":"Hatachi","year":"2023","journal-title":"Pediatr. Emerg. Care"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Kurita, Y., Meguro, S., Tsuyama, N., Kosugi, I., Enomoto, Y., Kawasaki, H., Uemura, T., Kimura, M., and Iwashita, T. (2023). Accurate deep learning model using semi-supervised learning and Noisy Student for cervical cancer screening in low magnification images. PLoS ONE, 18.","DOI":"10.1371\/journal.pone.0285996"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"e71229","DOI":"10.2196\/71229","article-title":"A Machine Learning-Based Prognostication Model Enhances Prediction of Early Hepatic Encephalopathy in Patients With Noncancer-Related Cirrhosis: Multicenter Longitudinal Cohort Study in Taiwan","volume":"13","author":"Chen","year":"2025","journal-title":"JMIR Med. Inform."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"11257","DOI":"10.1038\/s41598-025-95794-1","article-title":"An ensemble learning model to predict lymph node metastasis in early gastric cancer","volume":"15","author":"Song","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"e403","DOI":"10.1016\/j.wneu.2024.08.137","article-title":"Exploring the Combination of Computer Vision and Surgical Neuroanatomy: A Workflow Involving Artificial Intelligence for the Identification of Skull Base Foramina","volume":"191","author":"Payman","year":"2024","journal-title":"World Neurosurg."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1706","DOI":"10.1002\/jso.27854","article-title":"Development of Machine Learning Models for Predicting the 1-Year Risk of Reoperation After Lower Limb On-cological Resection and Endoprosthetic Reconstruction Based on Data From the PARITY Trial","volume":"130","author":"Deng","year":"2024","journal-title":"J. Surg. Oncol."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Yang, Z., Yang, D., Dyer, C., He, X., Smola, A., and Hovy, E. (2016). Hierarchical attention networks for document classification. Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Association for Computational Linguistics.","DOI":"10.18653\/v1\/N16-1174"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1089\/hs.2023.0070","article-title":"Navigating uncertainty in public health decisionmaking: The role of a value of information framework in threat agnostic biosurveillance","volume":"22","author":"Awan","year":"2024","journal-title":"Health Secur."},{"key":"ref_37","first-page":"e495","article-title":"Refined selection of individuals for preventive cardiovascular disease treatment with a transformer-based risk model","volume":"7","author":"Rao","year":"2025","journal-title":"Lancet Digit. Health"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"e42324","DOI":"10.2196\/42324","article-title":"Classifying COVID-19 Patients From Chest X-ray Images Using Hybrid Machine Learning Techniques: Development and Evaluation","volume":"7","author":"Phumkuea","year":"2023","journal-title":"JMIR Form. Res."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1177\/17511437251344068","article-title":"Biomarkers for pneumonia after major trauma: A systematic review and meta-analysis","volume":"27","author":"Howroyd","year":"2025","journal-title":"J. Intensive Care Soc."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"11779322251356563","DOI":"10.1177\/11779322251356563","article-title":"Machine Learning Techniques in Chronic Kidney Diseases: A Comparative Study of Classification Model Performance","volume":"19","author":"Phuong","year":"2025","journal-title":"Bioinform. Biol. Insights"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"797","DOI":"10.1007\/s40264-023-01324-1","article-title":"Serially combining epidemiological designs does not improve overall signal detection in vaccine safety surveillance","volume":"46","author":"Arshad","year":"2023","journal-title":"Drug Saf."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Anto\u00f1anzas, J.M., Perramon, A., L\u00f3pez, C., Boneta, M., Aguilera, C., Capdevila, R., Gatell, A., Serrano, P., Poblet, M., and Canadell, D. (2022). Symptom-Based Predictive Model of COVID-19 Disease in Children. Viruses, 14.","DOI":"10.3390\/v14010063"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1038\/s41591-021-01506-3","article-title":"Federated learning for predicting clinical outcomes in patients with COVID-19","volume":"27","author":"Dayan","year":"2021","journal-title":"Nat. Med."}],"container-title":["Pathogens"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2076-0817\/15\/4\/413\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T12:13:58Z","timestamp":1775823238000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2076-0817\/15\/4\/413"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,10]]},"references-count":43,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["pathogens15040413"],"URL":"https:\/\/doi.org\/10.3390\/pathogens15040413","relation":{},"ISSN":["2076-0817"],"issn-type":[{"value":"2076-0817","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,10]]}}}