Imperial College London
Portrait Picture

DrSophieYacoub

Faculty of Medicine, Department of Infectious Disease

Honorary Clinical Research Fellow
 
 
 
//

Contact

 

s.yacoub

 
 
//

Location

 

Commonwealth BuildingHammersmith Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Hernandez:2023:10.3389/fdgth.2023.1057467,
author = {Hernandez, Perez B and Stiff, O and Ming, D and Ho, Quang C and Vuong, Nguyen L and Tuan, Nguyen M and Chau, Nguyen VV and Nguyet, Nguyen M and Huy, Nguyen Q and Lam, Phung K and Tam, Dong Thi H and Trung, Dinh T and Trieu, Huynh T and Wills, B and Cameron, Paul S and Holmes, A and Yacoub, S and Georgiou, P},
doi = {10.3389/fdgth.2023.1057467},
journal = {Frontiers in Digital Health},
pages = {1--16},
title = {Learning meaningful latent space representations for patient risk stratification: model development and validation for dengue and other acute febrile illness},
url = {http://dx.doi.org/10.3389/fdgth.2023.1057467},
volume = {5},
year = {2023}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - Background: Increased data availability has prompted the creation of clinical decision support systems. These systems utilise clinical information to enhance health care provision, both to predict the likelihood of specific clinical outcomes or evaluate the risk of further complications. However, their adoption remains low due to concerns regarding the quality of recommendations, and a lack of clarity on how results are best obtained and presented.Methods: We used autoencoders capable of reducing the dimensionality of complex datasets in order to produce a 2D representation denoted as latent space to support understanding of complex clinical data. In this output, meaningful representations of individual patient profiles are spatially mapped in an unsupervised manner according to their input clinical parameters. This technique was then applied to a large real-world clinical dataset of over 12,000 patients with an illness compatible with dengue infection in Ho Chi Minh City, Vietnam between 1999 and 2021. Dengue is a systemic viral disease which exerts significant health and economic burden worldwide, and up to 5% of hospitalised patients develop life-threatening complications.Results: The latent space produced by the selected autoencoder aligns with established clinical characteristics exhibited by patients with dengue infection, as well as features of disease progression. Similar clinical phenotypes are represented close to each other in the latent space and clustered according to outcomes broadly described by the World Health Organisation dengue guidelines. Balancing distance metrics and density metrics produced results covering most of the latent space, and improved visualisation whilst preserving utility, with similar patients grouped closer together. In this case, this balance is achieved by using the sigmoid activation function and one hidden layer with three neurons, in addition to the latent dimension layer, which produces the output (Pearson, 0.840; Spearman
AU  - Hernandez,Perez B
AU  - Stiff,O
AU  - Ming,D
AU  - Ho,Quang C
AU  - Vuong,Nguyen L
AU  - Tuan,Nguyen M
AU  - Chau,Nguyen VV
AU  - Nguyet,Nguyen M
AU  - Huy,Nguyen Q
AU  - Lam,Phung K
AU  - Tam,Dong Thi H
AU  - Trung,Dinh T
AU  - Trieu,Huynh T
AU  - Wills,B
AU  - Cameron,Paul S
AU  - Holmes,A
AU  - Yacoub,S
AU  - Georgiou,P
DO  - 10.3389/fdgth.2023.1057467
EP  - 16
PY  - 2023///
SN  - 2673-253X
SP  - 1
TI  - Learning meaningful latent space representations for patient risk stratification: model development and validation for dengue and other acute febrile illness
T2  - Frontiers in Digital Health
UR  - http://dx.doi.org/10.3389/fdgth.2023.1057467
UR  - https://www.frontiersin.org/articles/10.3389/fdgth.2023.1057467/full
UR  - http://hdl.handle.net/10044/1/102711
VL  - 5
ER  -
Download