Cargando…

A modular approach to integrating multiple data sources into real-time clinical prediction for pediatric diarrhea

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...

Descripción completa

Detalles Bibliográficos
Autores principales: Brintz, Ben J, Haaland, Benjamin, Howard, Joel, Chao, Dennis L, Proctor, Joshua L, Khan, Ashraful I, Ahmed, Sharia M, Keegan, Lindsay T, Greene, Tom, Keita, Adama Mamby, Kotloff, Karen L, Platts-Mills, James A, Nelson, Eric J, Levine, Adam C, Pavia, Andrew T, Leung, Daniel T
Formato: Online Artículo Texto
Lenguaje:English
Publicado: eLife Sciences Publications, Ltd 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7853717/
https://www.ncbi.nlm.nih.gov/pubmed/33527894
http://dx.doi.org/10.7554/eLife.63009
_version_ 1783646018368176128
author Brintz, Ben J
Haaland, Benjamin
Howard, Joel
Chao, Dennis L
Proctor, Joshua L
Khan, Ashraful I
Ahmed, Sharia M
Keegan, Lindsay T
Greene, Tom
Keita, Adama Mamby
Kotloff, Karen L
Platts-Mills, James A
Nelson, Eric J
Levine, Adam C
Pavia, Andrew T
Leung, Daniel T
author_facet Brintz, Ben J
Haaland, Benjamin
Howard, Joel
Chao, Dennis L
Proctor, Joshua L
Khan, Ashraful I
Ahmed, Sharia M
Keegan, Lindsay T
Greene, Tom
Keita, Adama Mamby
Kotloff, Karen L
Platts-Mills, James A
Nelson, Eric J
Levine, Adam C
Pavia, Andrew T
Leung, Daniel T
author_sort Brintz, Ben J
collection PubMed
description 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.
format Online
Article
Text
id pubmed-7853717
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher eLife Sciences Publications, Ltd
record_format MEDLINE/PubMed
spelling pubmed-78537172021-02-04 A modular approach to integrating multiple data sources into real-time clinical prediction for pediatric diarrhea Brintz, Ben J Haaland, Benjamin Howard, Joel Chao, Dennis L Proctor, Joshua L Khan, Ashraful I Ahmed, Sharia M Keegan, Lindsay T Greene, Tom Keita, Adama Mamby Kotloff, Karen L Platts-Mills, James A Nelson, Eric J Levine, Adam C Pavia, Andrew T Leung, Daniel T eLife Epidemiology and Global Health 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. eLife Sciences Publications, Ltd 2021-02-02 /pmc/articles/PMC7853717/ /pubmed/33527894 http://dx.doi.org/10.7554/eLife.63009 Text en © 2021, Brintz et al http://creativecommons.org/licenses/by/4.0/ http://creativecommons.org/licenses/by/4.0/This article is distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use and redistribution provided that the original author and source are credited.
spellingShingle Epidemiology and Global Health
Brintz, Ben J
Haaland, Benjamin
Howard, Joel
Chao, Dennis L
Proctor, Joshua L
Khan, Ashraful I
Ahmed, Sharia M
Keegan, Lindsay T
Greene, Tom
Keita, Adama Mamby
Kotloff, Karen L
Platts-Mills, James A
Nelson, Eric J
Levine, Adam C
Pavia, Andrew T
Leung, Daniel T
A modular approach to integrating multiple data sources into real-time clinical prediction for pediatric diarrhea
title A modular approach to integrating multiple data sources into real-time clinical prediction for pediatric diarrhea
title_full A modular approach to integrating multiple data sources into real-time clinical prediction for pediatric diarrhea
title_fullStr A modular approach to integrating multiple data sources into real-time clinical prediction for pediatric diarrhea
title_full_unstemmed A modular approach to integrating multiple data sources into real-time clinical prediction for pediatric diarrhea
title_short A modular approach to integrating multiple data sources into real-time clinical prediction for pediatric diarrhea
title_sort modular approach to integrating multiple data sources into real-time clinical prediction for pediatric diarrhea
topic Epidemiology and Global Health
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7853717/
https://www.ncbi.nlm.nih.gov/pubmed/33527894
http://dx.doi.org/10.7554/eLife.63009
work_keys_str_mv AT brintzbenj amodularapproachtointegratingmultipledatasourcesintorealtimeclinicalpredictionforpediatricdiarrhea
AT haalandbenjamin amodularapproachtointegratingmultipledatasourcesintorealtimeclinicalpredictionforpediatricdiarrhea
AT howardjoel amodularapproachtointegratingmultipledatasourcesintorealtimeclinicalpredictionforpediatricdiarrhea
AT chaodennisl amodularapproachtointegratingmultipledatasourcesintorealtimeclinicalpredictionforpediatricdiarrhea
AT proctorjoshual amodularapproachtointegratingmultipledatasourcesintorealtimeclinicalpredictionforpediatricdiarrhea
AT khanashrafuli amodularapproachtointegratingmultipledatasourcesintorealtimeclinicalpredictionforpediatricdiarrhea
AT ahmedshariam amodularapproachtointegratingmultipledatasourcesintorealtimeclinicalpredictionforpediatricdiarrhea
AT keeganlindsayt amodularapproachtointegratingmultipledatasourcesintorealtimeclinicalpredictionforpediatricdiarrhea
AT greenetom amodularapproachtointegratingmultipledatasourcesintorealtimeclinicalpredictionforpediatricdiarrhea
AT keitaadamamamby amodularapproachtointegratingmultipledatasourcesintorealtimeclinicalpredictionforpediatricdiarrhea
AT kotloffkarenl amodularapproachtointegratingmultipledatasourcesintorealtimeclinicalpredictionforpediatricdiarrhea
AT plattsmillsjamesa amodularapproachtointegratingmultipledatasourcesintorealtimeclinicalpredictionforpediatricdiarrhea
AT nelsonericj amodularapproachtointegratingmultipledatasourcesintorealtimeclinicalpredictionforpediatricdiarrhea
AT levineadamc amodularapproachtointegratingmultipledatasourcesintorealtimeclinicalpredictionforpediatricdiarrhea
AT paviaandrewt amodularapproachtointegratingmultipledatasourcesintorealtimeclinicalpredictionforpediatricdiarrhea
AT leungdanielt amodularapproachtointegratingmultipledatasourcesintorealtimeclinicalpredictionforpediatricdiarrhea
AT brintzbenj modularapproachtointegratingmultipledatasourcesintorealtimeclinicalpredictionforpediatricdiarrhea
AT haalandbenjamin modularapproachtointegratingmultipledatasourcesintorealtimeclinicalpredictionforpediatricdiarrhea
AT howardjoel modularapproachtointegratingmultipledatasourcesintorealtimeclinicalpredictionforpediatricdiarrhea
AT chaodennisl modularapproachtointegratingmultipledatasourcesintorealtimeclinicalpredictionforpediatricdiarrhea
AT proctorjoshual modularapproachtointegratingmultipledatasourcesintorealtimeclinicalpredictionforpediatricdiarrhea
AT khanashrafuli modularapproachtointegratingmultipledatasourcesintorealtimeclinicalpredictionforpediatricdiarrhea
AT ahmedshariam modularapproachtointegratingmultipledatasourcesintorealtimeclinicalpredictionforpediatricdiarrhea
AT keeganlindsayt modularapproachtointegratingmultipledatasourcesintorealtimeclinicalpredictionforpediatricdiarrhea
AT greenetom modularapproachtointegratingmultipledatasourcesintorealtimeclinicalpredictionforpediatricdiarrhea
AT keitaadamamamby modularapproachtointegratingmultipledatasourcesintorealtimeclinicalpredictionforpediatricdiarrhea
AT kotloffkarenl modularapproachtointegratingmultipledatasourcesintorealtimeclinicalpredictionforpediatricdiarrhea
AT plattsmillsjamesa modularapproachtointegratingmultipledatasourcesintorealtimeclinicalpredictionforpediatricdiarrhea
AT nelsonericj modularapproachtointegratingmultipledatasourcesintorealtimeclinicalpredictionforpediatricdiarrhea
AT levineadamc modularapproachtointegratingmultipledatasourcesintorealtimeclinicalpredictionforpediatricdiarrhea
AT paviaandrewt modularapproachtointegratingmultipledatasourcesintorealtimeclinicalpredictionforpediatricdiarrhea
AT leungdanielt modularapproachtointegratingmultipledatasourcesintorealtimeclinicalpredictionforpediatricdiarrhea