A modular approach to integrating multiple data sources into real-time clinical prediction for pediatric diarrhea
A modular approach to integrating multiple data sources into real-time clinical prediction for pediatric diarrhea
Abstract Traditional clinical prediction models focus on parameters of the individual patient. For infectious diseases, sources external to the patient, including characteristics of prior patients and seasonal factors, may improve predictive performance. We describe the development of a predictive model that integrates multiple sources of data in a principled statistical framework using a post-test odds formulation. Our method enables electronic real-time updating and flexibility, such that components can be included or excluded according to data availability. We apply this method to the prediction of etiology of pediatric diarrhea, where “pre-test” epidemiologic data may be highly informative. Diarrhea has a high burden in low-resource settings, and antibiotics are often over-prescribed. We demonstrate that our integrative method outperforms traditional prediction in accurately identifying cases with a viral etiology, and show that its clinical application, especially when used with an additional diagnostic test, could result in a 61% reduction in inappropriately prescribed antibiotics.
Brintz Ben J.、Howard Joel、Proctor Joshua L.、Khan Ashraful I.、Ahmed Sharia M.、Greene Tom、Nelson Eric J.、Chao Dennis L.、Kotloff Karen L.、Haaland Benjamin、Leung Daniel T.、Keegan Lindsay T.、Platts-Mills James A.、Levine Adam C.、Keita Adama Mamby、Pavia Andrew T.
Division of Epidemiology, Department of Internal Medicine, University of Utah||Division of Infectious Diseases, Department of Internal Medicine, University of UtahDivision of Pediatric Infectious Diseases, University of Utah, Salt Lake CityInstitute of Disease Modeling, Bill and Melinda Gates FoundationInternational Centre for Diarrhoeal Disease Research, Bangladesh (icddr,b)Division of Infectious Diseases, Department of Internal Medicine, University of UtahDivision of Epidemiology, Department of Internal Medicine, University of UtahDepartments of Pediatrics, University of Florida||Departments of Environmental and Global Health, University of FloridaInstitute of Disease Modeling, Bill and Melinda Gates FoundationDivision of Infectious Disease and Tropical Pediatrics, University of MarylandPopulation Health Sciences, University of UtahDivision of Infectious Diseases, Department of Internal Medicine, University of Utah||Division of Microbiology and Immunology, Department of Internal Medicine, University of UtahDivision of Epidemiology, Department of Internal Medicine, University of UtahDivision of Infectious Diseases and International Health, University of VirginiaDepartment of Emergency Medicine, Brown UniversityCentre Pour le D¨|veloppement des Vaccins-MaliDivision of Pediatric Infectious Diseases, University of Utah, Salt Lake City
医学研究方法儿科学临床医学
Brintz Ben J.,Howard Joel,Proctor Joshua L.,Khan Ashraful I.,Ahmed Sharia M.,Greene Tom,Nelson Eric J.,Chao Dennis L.,Kotloff Karen L.,Haaland Benjamin,Leung Daniel T.,Keegan Lindsay T.,Platts-Mills James A.,Levine Adam C.,Keita Adama Mamby,Pavia Andrew T..A modular approach to integrating multiple data sources into real-time clinical prediction for pediatric diarrhea[EB/OL].(2025-03-28)[2025-05-25].https://www.medrxiv.org/content/10.1101/2020.10.26.20210385.点此复制
评论