Imperial College London
Portrait Picture

DrIlariaDorigatti

Faculty of Medicine, School of Public Health

Senior Lecturer
 
 
 
//

Contact

 

+44 (0)20 7594 1451i.dorigatti

 
 
//

Location

 

G24Norfolk PlaceSt Mary's Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Forna:2021:10.1371/journal.pone.0257005,
author = {Forna, A and Dorigatti, I and Nouvellet, P and Donnelly, C},
doi = {10.1371/journal.pone.0257005},
journal = {PLoS One},
title = {Comparison of machine learning methods for estimating case fatality ratios: an Ebola outbreak simulation study},
url = {http://dx.doi.org/10.1371/journal.pone.0257005},
volume = {16},
year = {2021}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - BackgroundMachine learning (ML) algorithms are now increasingly used in infectious disease epidemiology. Epidemiologists should understand how ML algorithms behave within the context of outbreak data where missingness of data is almost ubiquitous.MethodsUsing simulated data, we use a ML algorithmic framework to evaluate data imputation performance and the resulting case fatality ratio (CFR) estimates, focusing on the scale and type of data missingness (i.e., missing completely at random—MCAR, missing at random—MAR, or missing not at random—MNAR).ResultsAcross ML methods, dataset sizes and proportions of training data used, the area under the receiver operating characteristic curve decreased by 7% (median, range: 1%–16%) when missingness was increased from 10% to 40%. Overall reduction in CFR bias for MAR across methods, proportion of missingness, outbreak size and proportion of training data was 0.5% (median, range: 0%–11%).ConclusionML methods could reduce bias and increase the precision in CFR estimates at low levels of missingness. However, no method is robust to high percentages of missingness. Thus, a datacentric approach is recommended in outbreak settings—patient survival outcome data should be prioritised for collection and random-sample follow-ups should be implemented to ascertain missing outcomes.
AU  - Forna,A
AU  - Dorigatti,I
AU  - Nouvellet,P
AU  - Donnelly,C
DO  - 10.1371/journal.pone.0257005
PY  - 2021///
SN  - 1932-6203
TI  - Comparison of machine learning methods for estimating case fatality ratios: an Ebola outbreak simulation study
T2  - PLoS One
UR  - http://dx.doi.org/10.1371/journal.pone.0257005
UR  - http://hdl.handle.net/10044/1/92162
VL  - 16
ER  -
Download