Imperial College London
Portrait Picture

ProfessorPaulFreemont

Faculty of Medicine, Department of Infectious Disease

Chair in Protein Crystallography
 
 
 
//

Contact

 

+44 (0)20 7594 5327p.freemont

 
 
//

Location

 

259Sir Alexander Fleming BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@unpublished{Li:2020,
author = {Li, H and Barnaghi, P and Skillman, S and Sharp, D and Nilforooshan, R and Rostill, H},
publisher = {arXiv},
title = {Machine learning for risk analysis of Urinary Tract Infection in people  with dementia},
url = {http://arxiv.org/abs/2011.13916v1},
year = {2020}
}
Download

RIS format (EndNote, RefMan)

TY  - UNPB
AB  - The Urinary Tract Infections (UTIs) are one of the top reasons for unplannedhospital admissions in people with dementia, and if detected early, they can betimely treated. However, the standard UTI diagnosis tests, e.g. urine tests,will be only taken if the patients are clinically suspected of having UTIs.This causes a delay in diagnosis and treatment of the conditions and in somecases like people with dementia, the symptoms can be difficult to observe.Delay in detection and treatment of dementia is one of the key reasons forunplanned hospital admissions in people with dementia. To address these issues,we have developed a technology-assisted monitoring system, which is a Class 1medical device. The system uses off-the-shelf and low-cost in-home sensorydevices to monitor environmental and physiological data of people with dementiawithin their own homes. We have designed a machine learning model to use thedata and provide risk analysis for UTIs. We use a semi-supervised learningmodel which leverage the environmental data, i.e. the data collected from themotion sensors, smart plugs and network-connected body temperature monitoringdevices in the home, to detect patterns that can show the risk of UTIs. Sincethe data is noisy and partially labelled, we combine the neural networks andprobabilistic neural networks to train an auto-encoder, which is to extract thegeneral representation of the data. We will demonstrate our smart homemanagement by videos/online, and show how our model can pick up the UTI relatedpatterns.
AU  - Li,H
AU  - Barnaghi,P
AU  - Skillman,S
AU  - Sharp,D
AU  - Nilforooshan,R
AU  - Rostill,H
PB  - arXiv
PY  - 2020///
TI  - Machine learning for risk analysis of Urinary Tract Infection in people  with dementia
UR  - http://arxiv.org/abs/2011.13916v1
UR  - http://hdl.handle.net/10044/1/85218
ER  -
Download