Transforming Clinical Data into Actionable Prognosis Models: Machine-Learning Framework and Field-Deployable App to Predict Outcome of Ebola Patients
MetadataShow full item record
CitationColubri, Andres, Tom Silver, Terrence Fradet, Kalliroi Retzepi, Ben Fry, and Pardis Sabeti. 2016. “Transforming Clinical Data into Actionable Prognosis Models: Machine-Learning Framework and Field-Deployable App to Predict Outcome of Ebola Patients.” Edited by Thomas S. Churcher. PLOS Neglected Tropical Diseases 10 (3) (March 18): e0004549. doi:10.1371/journal.pntd.0004549.
AbstractWe introduce a machine-learning framework and field-deployable app to predict outcome of Ebola patients from their initial clinical symptoms. Recent work from other authors also points out to the clinical factors that can be used to better understand patient prognosis, but there is currently no predictive model that can be deployed in the field to assist health care workers. Mobile apps for clinical diagnosis and prognosis allow using more complex models than the scoring protocols that have been traditionally favored by clinicians, such as Apgar and MTS. Furthermore, the WHO Ebola Interim Assessment Panel has recently concluded that innovative tools for data collection, reporting, and monitoring are needed for better response in future outbreaks. However, incomplete clinical data will continue to be a serious problem until more robust and standardized data collection systems are in place. Our app demonstrates how systematic data collection could lead to actionable knowledge, which in turn would trigger more and better collection, further improving the prognosis models and the app, essentially creating a virtuous cycle.
Citable link to this pagehttp://nrs.harvard.edu/urn-3:HUL.InstRepos:27413721
- FAS Scholarly Articles