Publications

BibTex format

@article{Kainz:2021:10.1038/s41746-021-00503-7,
author = {Kainz, B and Makropoulos, A and Oppenheimer, J and Deane, C and Mischkewitz, S and Al-Noor, F and Rawdin, AC and Stevenson, MD and Mandegaran, R and Heinrich, MP and Curry, N and Sankar, S and Ruttloff, A and Klein-Weigel, P},
doi = {10.1038/s41746-021-00503-7},
journal = {npj Digital Medicine},
pages = {1--15},
title = {Non-invasive diagnosis of deep vein thrombosis from ultrasound imaging with machine learning},
url = {http://dx.doi.org/10.1038/s41746-021-00503-7},
volume = {4},
year = {2021}
}

Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - 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.
AU  - Kainz,B
AU  - Makropoulos,A
AU  - Oppenheimer,J
AU  - Deane,C
AU  - Mischkewitz,S
AU  - Al-Noor,F
AU  - Rawdin,AC
AU  - Stevenson,MD
AU  - Mandegaran,R
AU  - Heinrich,MP
AU  - Curry,N
AU  - Sankar,S
AU  - Ruttloff,A
AU  - Klein-Weigel,P
DO  - 10.1038/s41746-021-00503-7
EP  - 15
PY  - 2021///
SN  - 2398-6352
SP  - 1
TI  - Non-invasive diagnosis of deep vein thrombosis from ultrasound imaging with machine learning
T2  - npj Digital Medicine
UR  - http://dx.doi.org/10.1038/s41746-021-00503-7
UR  - http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000696208600003&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=1ba7043ffcc86c417c072aa74d649202
UR  - https://www.nature.com/articles/s41746-021-00503-7
UR  - http://hdl.handle.net/10044/1/92288
VL  - 4
ER  -

Download

DR BERNHARD KAINZ

Contact

Location

Summary

Citation

BibTex format

RIS format (EndNote, RefMan)