InDetector – Automatic detection of infected driveline regions

Shravan Aras, Thienne Johnson, Christopher Gniady, Rinku Skaria, Zain I Khalpey

Research output: Contribution to journalArticle

Abstract

Although there have been significant advancements in Left Ventricular Assist Device(LVAD) technology and improvements in mortality rates, infection remains one of the major complications associated with LVAD therapy with an incidence of 25-80% cases annually. Amongst such infections driveline infections are the most common and account for 14-28% according to the RE-MATCH trial of the total of LVAD related infections. If a patient is diagnosed with LVAD infection, it is important to initiate antibiotic therapy as early as possible. If left untreated it can lead to sepsis with multi-organ failure, longer hospital stay, delay heart transplant or early mortality. To improve infection detection and monitoring we propose InDetector, a driveline infection detection system that allows at-home patients to use a smartphone to capture images of their driveline regions to check for infections. InDetector uses a Convolutional Neural Network along with image augmentation techniques for inferring infected images and achieves an overall classification accuracy of 93.75% on our validation dataset.

Original languageEnglish (US)
Pages (from-to)170-178
Number of pages9
JournalSmart Health
Volume9-10
DOIs
StatePublished - Dec 1 2018

Fingerprint

Left ventricular assist devices
Heart-Assist Devices
Infection
Transplants
Smartphones
Antibiotics
Neural networks
Mortality
Monitoring
Length of Stay
Sepsis
Anti-Bacterial Agents
Technology

ASJC Scopus subject areas

  • Medicine (miscellaneous)
  • Health Informatics
  • Computer Science Applications
  • Information Systems
  • Health Information Management

Cite this

InDetector – Automatic detection of infected driveline regions. / Aras, Shravan; Johnson, Thienne; Gniady, Christopher; Skaria, Rinku; Khalpey, Zain I.

In: Smart Health, Vol. 9-10, 01.12.2018, p. 170-178.

Research output: Contribution to journalArticle

Aras, Shravan ; Johnson, Thienne ; Gniady, Christopher ; Skaria, Rinku ; Khalpey, Zain I. / InDetector – Automatic detection of infected driveline regions. In: Smart Health. 2018 ; Vol. 9-10. pp. 170-178.
@article{c5a6e869fcef481192e8b6df21f0f61f,
title = "InDetector – Automatic detection of infected driveline regions",
abstract = "Although there have been significant advancements in Left Ventricular Assist Device(LVAD) technology and improvements in mortality rates, infection remains one of the major complications associated with LVAD therapy with an incidence of 25-80{\%} cases annually. Amongst such infections driveline infections are the most common and account for 14-28{\%} according to the RE-MATCH trial of the total of LVAD related infections. If a patient is diagnosed with LVAD infection, it is important to initiate antibiotic therapy as early as possible. If left untreated it can lead to sepsis with multi-organ failure, longer hospital stay, delay heart transplant or early mortality. To improve infection detection and monitoring we propose InDetector, a driveline infection detection system that allows at-home patients to use a smartphone to capture images of their driveline regions to check for infections. InDetector uses a Convolutional Neural Network along with image augmentation techniques for inferring infected images and achieves an overall classification accuracy of 93.75{\%} on our validation dataset.",
author = "Shravan Aras and Thienne Johnson and Christopher Gniady and Rinku Skaria and Khalpey, {Zain I}",
year = "2018",
month = "12",
day = "1",
doi = "10.1016/j.smhl.2018.07.016",
language = "English (US)",
volume = "9-10",
pages = "170--178",
journal = "Smart Health",
issn = "2352-6483",
publisher = "Elsevier BV",

}

TY - JOUR

T1 - InDetector – Automatic detection of infected driveline regions

AU - Aras, Shravan

AU - Johnson, Thienne

AU - Gniady, Christopher

AU - Skaria, Rinku

AU - Khalpey, Zain I

PY - 2018/12/1

Y1 - 2018/12/1

N2 - Although there have been significant advancements in Left Ventricular Assist Device(LVAD) technology and improvements in mortality rates, infection remains one of the major complications associated with LVAD therapy with an incidence of 25-80% cases annually. Amongst such infections driveline infections are the most common and account for 14-28% according to the RE-MATCH trial of the total of LVAD related infections. If a patient is diagnosed with LVAD infection, it is important to initiate antibiotic therapy as early as possible. If left untreated it can lead to sepsis with multi-organ failure, longer hospital stay, delay heart transplant or early mortality. To improve infection detection and monitoring we propose InDetector, a driveline infection detection system that allows at-home patients to use a smartphone to capture images of their driveline regions to check for infections. InDetector uses a Convolutional Neural Network along with image augmentation techniques for inferring infected images and achieves an overall classification accuracy of 93.75% on our validation dataset.

AB - Although there have been significant advancements in Left Ventricular Assist Device(LVAD) technology and improvements in mortality rates, infection remains one of the major complications associated with LVAD therapy with an incidence of 25-80% cases annually. Amongst such infections driveline infections are the most common and account for 14-28% according to the RE-MATCH trial of the total of LVAD related infections. If a patient is diagnosed with LVAD infection, it is important to initiate antibiotic therapy as early as possible. If left untreated it can lead to sepsis with multi-organ failure, longer hospital stay, delay heart transplant or early mortality. To improve infection detection and monitoring we propose InDetector, a driveline infection detection system that allows at-home patients to use a smartphone to capture images of their driveline regions to check for infections. InDetector uses a Convolutional Neural Network along with image augmentation techniques for inferring infected images and achieves an overall classification accuracy of 93.75% on our validation dataset.

UR - http://www.scopus.com/inward/record.url?scp=85059786705&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85059786705&partnerID=8YFLogxK

U2 - 10.1016/j.smhl.2018.07.016

DO - 10.1016/j.smhl.2018.07.016

M3 - Article

VL - 9-10

SP - 170

EP - 178

JO - Smart Health

JF - Smart Health

SN - 2352-6483

ER -