1. A modular approach to integrating multiple data sources into real-time clinical prediction for pediatric diarrhea
- Author
-
Karen L. Kotloff, Adam C. Levine, James A Platts-Mills, Sharia M Ahmed, Dennis L. Chao, Eric J. Nelson, Benjamin Haaland, Adama Mamby Keita, Tom Greene, Lindsay T Keegan, Joel Howard, Ashraful Islam Khan, Joshua L. Proctor, Andrew T. Pavia, Ben J Brintz, and Daniel T. Leung
- Subjects
clinical decision support ,Computer science ,QH301-705.5 ,Science ,030231 tropical medicine ,diarrhea ,enteric infection ,antibiotic stewardship ,Clinical prediction rule ,Machine learning ,computer.software_genre ,Communicable Diseases ,Clinical decision support system ,General Biochemistry, Genetics and Molecular Biology ,Decision Support Techniques ,Odds ,Antimicrobial Stewardship ,03 medical and health sciences ,0302 clinical medicine ,clinical prediction rule ,medicine ,Humans ,030212 general & internal medicine ,Biology (General) ,Child ,Viral etiology ,Flexibility (engineering) ,General Immunology and Microbiology ,Diagnostic Tests, Routine ,business.industry ,General Neuroscience ,General Medicine ,Modular design ,Decision Support Systems, Clinical ,Anti-Bacterial Agents ,Virus ,Diarrhea ,Multiple data ,Epidemiology and Global Health ,Etiology ,Medicine ,Artificial intelligence ,medicine.symptom ,business ,computer ,Predictive modelling ,Research Article - 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.
- Published
- 2021