Non-invasive diagnosis of deep vein thrombosis from ultrasound imaging with machine learning

Abstract Deep vein thrombosis (DVT) is a blood clot most commonly found in the leg, which can lead to fatal pulmonary embolism (PE). Compression ultrasound of the legs is the diagnostic gold standard, leading to a definitive diagnosis. However, many patients with possible symptoms are not found to h...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Bernhard Kainz, Mattias P. Heinrich, Antonios Makropoulos, Jonas Oppenheimer, Ramin Mandegaran, Shrinivasan Sankar, Christopher Deane, Sven Mischkewitz, Fouad Al-Noor, Andrew C. Rawdin, Andreas Ruttloff, Matthew D. Stevenson, Peter Klein-Weigel, Nicola Curry
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Computer applications to medicine. Medical informatics R858-859.7
Acceso en línea:	https://doaj.org/article/ab23f06ff7e846daaf92380021bbe382
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:ab23f06ff7e846daaf92380021bbe382
record_format	dspace
spelling	oai:doaj.org-article:ab23f06ff7e846daaf92380021bbe3822021-12-02T15:15:44ZNon-invasive diagnosis of deep vein thrombosis from ultrasound imaging with machine learning10.1038/s41746-021-00503-72398-6352https://doaj.org/article/ab23f06ff7e846daaf92380021bbe3822021-09-01T00:00:00Zhttps://doi.org/10.1038/s41746-021-00503-7https://doaj.org/toc/2398-6352Abstract Deep vein thrombosis (DVT) is a blood clot most commonly found in the leg, which can lead to fatal pulmonary embolism (PE). Compression ultrasound of the legs is the diagnostic gold standard, leading to a definitive diagnosis. However, many patients with possible symptoms are not found to have a DVT, resulting in long referral waiting times for patients and a large clinical burden for specialists. Thus, diagnosis at the point of care by non-specialists is desired. We collect images in a pre-clinical study and investigate a deep learning approach for the automatic interpretation of compression ultrasound images. Our method provides guidance for free-hand ultrasound and aids non-specialists in detecting DVT. We train a deep learning algorithm on ultrasound videos from 255 volunteers and evaluate on a sample size of 53 prospectively enrolled patients from an NHS DVT diagnostic clinic and 30 prospectively enrolled patients from a German DVT clinic. Algorithmic DVT diagnosis performance results in a sensitivity within a 95% CI range of (0.82, 0.94), specificity of (0.70, 0.82), a positive predictive value of (0.65, 0.89), and a negative predictive value of (0.99, 1.00) when compared to the clinical gold standard. To assess the potential benefits of this technology in healthcare we evaluate the entire clinical DVT decision algorithm and provide cost analysis when integrating our approach into diagnostic pathways for DVT. Our approach is estimated to generate a positive net monetary benefit at costs up to £72 to £175 per software-supported examination, assuming a willingness to pay of £20,000/QALY.Bernhard KainzMattias P. HeinrichAntonios MakropoulosJonas OppenheimerRamin MandegaranShrinivasan SankarChristopher DeaneSven MischkewitzFouad Al-NoorAndrew C. RawdinAndreas RuttloffMatthew D. StevensonPeter Klein-WeigelNicola CurryNature PortfolioarticleComputer applications to medicine. Medical informaticsR858-859.7ENnpj Digital Medicine, Vol 4, Iss 1, Pp 1-18 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Computer applications to medicine. Medical informatics R858-859.7
spellingShingle	Computer applications to medicine. Medical informatics R858-859.7 Bernhard Kainz Mattias P. Heinrich Antonios Makropoulos Jonas Oppenheimer Ramin Mandegaran Shrinivasan Sankar Christopher Deane Sven Mischkewitz Fouad Al-Noor Andrew C. Rawdin Andreas Ruttloff Matthew D. Stevenson Peter Klein-Weigel Nicola Curry Non-invasive diagnosis of deep vein thrombosis from ultrasound imaging with machine learning
description	Abstract Deep vein thrombosis (DVT) is a blood clot most commonly found in the leg, which can lead to fatal pulmonary embolism (PE). Compression ultrasound of the legs is the diagnostic gold standard, leading to a definitive diagnosis. However, many patients with possible symptoms are not found to have a DVT, resulting in long referral waiting times for patients and a large clinical burden for specialists. Thus, diagnosis at the point of care by non-specialists is desired. We collect images in a pre-clinical study and investigate a deep learning approach for the automatic interpretation of compression ultrasound images. Our method provides guidance for free-hand ultrasound and aids non-specialists in detecting DVT. We train a deep learning algorithm on ultrasound videos from 255 volunteers and evaluate on a sample size of 53 prospectively enrolled patients from an NHS DVT diagnostic clinic and 30 prospectively enrolled patients from a German DVT clinic. Algorithmic DVT diagnosis performance results in a sensitivity within a 95% CI range of (0.82, 0.94), specificity of (0.70, 0.82), a positive predictive value of (0.65, 0.89), and a negative predictive value of (0.99, 1.00) when compared to the clinical gold standard. To assess the potential benefits of this technology in healthcare we evaluate the entire clinical DVT decision algorithm and provide cost analysis when integrating our approach into diagnostic pathways for DVT. Our approach is estimated to generate a positive net monetary benefit at costs up to £72 to £175 per software-supported examination, assuming a willingness to pay of £20,000/QALY.
format	article
author	Bernhard Kainz Mattias P. Heinrich Antonios Makropoulos Jonas Oppenheimer Ramin Mandegaran Shrinivasan Sankar Christopher Deane Sven Mischkewitz Fouad Al-Noor Andrew C. Rawdin Andreas Ruttloff Matthew D. Stevenson Peter Klein-Weigel Nicola Curry
author_facet	Bernhard Kainz Mattias P. Heinrich Antonios Makropoulos Jonas Oppenheimer Ramin Mandegaran Shrinivasan Sankar Christopher Deane Sven Mischkewitz Fouad Al-Noor Andrew C. Rawdin Andreas Ruttloff Matthew D. Stevenson Peter Klein-Weigel Nicola Curry
author_sort	Bernhard Kainz
title	Non-invasive diagnosis of deep vein thrombosis from ultrasound imaging with machine learning
title_short	Non-invasive diagnosis of deep vein thrombosis from ultrasound imaging with machine learning
title_full	Non-invasive diagnosis of deep vein thrombosis from ultrasound imaging with machine learning
title_fullStr	Non-invasive diagnosis of deep vein thrombosis from ultrasound imaging with machine learning
title_full_unstemmed	Non-invasive diagnosis of deep vein thrombosis from ultrasound imaging with machine learning
title_sort	non-invasive diagnosis of deep vein thrombosis from ultrasound imaging with machine learning
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/ab23f06ff7e846daaf92380021bbe382
work_keys_str_mv	AT bernhardkainz noninvasivediagnosisofdeepveinthrombosisfromultrasoundimagingwithmachinelearning AT mattiaspheinrich noninvasivediagnosisofdeepveinthrombosisfromultrasoundimagingwithmachinelearning AT antoniosmakropoulos noninvasivediagnosisofdeepveinthrombosisfromultrasoundimagingwithmachinelearning AT jonasoppenheimer noninvasivediagnosisofdeepveinthrombosisfromultrasoundimagingwithmachinelearning AT raminmandegaran noninvasivediagnosisofdeepveinthrombosisfromultrasoundimagingwithmachinelearning AT shrinivasansankar noninvasivediagnosisofdeepveinthrombosisfromultrasoundimagingwithmachinelearning AT christopherdeane noninvasivediagnosisofdeepveinthrombosisfromultrasoundimagingwithmachinelearning AT svenmischkewitz noninvasivediagnosisofdeepveinthrombosisfromultrasoundimagingwithmachinelearning AT fouadalnoor noninvasivediagnosisofdeepveinthrombosisfromultrasoundimagingwithmachinelearning AT andrewcrawdin noninvasivediagnosisofdeepveinthrombosisfromultrasoundimagingwithmachinelearning AT andreasruttloff noninvasivediagnosisofdeepveinthrombosisfromultrasoundimagingwithmachinelearning AT matthewdstevenson noninvasivediagnosisofdeepveinthrombosisfromultrasoundimagingwithmachinelearning AT peterkleinweigel noninvasivediagnosisofdeepveinthrombosisfromultrasoundimagingwithmachinelearning AT nicolacurry noninvasivediagnosisofdeepveinthrombosisfromultrasoundimagingwithmachinelearning
_version_	1718387528530132992

Non-invasive diagnosis of deep vein thrombosis from ultrasound imaging with machine learning

Ejemplares similares