• Je něco špatně v tomto záznamu ?

Exploring novel algorithms for atrial fibrillation detection by driving graduate level education in medical machine learning

M. Rohr, C. Reich, A. Höhl, T. Lilienthal, T. Dege, F. Plesinger, V. Bulkova, G. Clifford, M. Reyna, C. Hoog Antink

. 2022 ; 43 (7) : . [pub] 20220707

Jazyk angličtina Země Anglie, Velká Británie

Typ dokumentu časopisecké články

Perzistentní odkaz   https://www.medvik.cz/link/bmc22025259

During the lockdown of universities and the COVID-Pandemic most students were restricted to their homes. Novel and instigating teaching methods were required to improve the learning experience and so recent implementations of the annual PhysioNet/Computing in Cardiology (CinC) Challenges posed as a reference. For over 20 years, the challenges have proven repeatedly to be of immense educational value, besides leading to technological advances for specific problems. In this paper, we report results from the class 'Artificial Intelligence in Medicine Challenge', which was implemented as an online project seminar at Technical University Darmstadt, Germany, and which was heavily inspired by the PhysioNet/CinC Challenge 2017 'AF Classification from a Short Single Lead ECG Recording'. Atrial fibrillation is a common cardiac disease and often remains undetected. Therefore, we selected the two most promising models of the course and give an insight into the Transformer-based DualNet architecture as well as into the CNN-LSTM-based model and finally a detailed analysis for both. In particular, we show the model performance results of our internal scoring process for all submitted models and the near state-of-the-art model performance for the two named models on the official 2017 challenge test set. Several teams were able to achieve F1scores above/close to 90% on a hidden test-set of Holter recordings. We highlight themes commonly observed among participants, and report the results from the self-assessed student evaluation. Finally, the self-assessment of the students reported a notable increase in machine learning knowledge.

Citace poskytuje Crossref.org

000      
00000naa a2200000 a 4500
001      
bmc22025259
003      
CZ-PrNML
005      
20221031100135.0
007      
ta
008      
221017s2022 enk f 000 0|eng||
009      
AR
024    7_
$a 10.1088/1361-6579/ac7840 $2 doi
035    __
$a (PubMed)35697013
040    __
$a ABA008 $b cze $d ABA008 $e AACR2
041    0_
$a eng
044    __
$a enk
100    1_
$a Rohr, Maurice $u KIS*MED - AI Systems in Medicine, Technische Universität Darmstadt, Darmstadt, Germany $1 https://orcid.org/0000000260536558
245    10
$a Exploring novel algorithms for atrial fibrillation detection by driving graduate level education in medical machine learning / $c M. Rohr, C. Reich, A. Höhl, T. Lilienthal, T. Dege, F. Plesinger, V. Bulkova, G. Clifford, M. Reyna, C. Hoog Antink
520    9_
$a During the lockdown of universities and the COVID-Pandemic most students were restricted to their homes. Novel and instigating teaching methods were required to improve the learning experience and so recent implementations of the annual PhysioNet/Computing in Cardiology (CinC) Challenges posed as a reference. For over 20 years, the challenges have proven repeatedly to be of immense educational value, besides leading to technological advances for specific problems. In this paper, we report results from the class 'Artificial Intelligence in Medicine Challenge', which was implemented as an online project seminar at Technical University Darmstadt, Germany, and which was heavily inspired by the PhysioNet/CinC Challenge 2017 'AF Classification from a Short Single Lead ECG Recording'. Atrial fibrillation is a common cardiac disease and often remains undetected. Therefore, we selected the two most promising models of the course and give an insight into the Transformer-based DualNet architecture as well as into the CNN-LSTM-based model and finally a detailed analysis for both. In particular, we show the model performance results of our internal scoring process for all submitted models and the near state-of-the-art model performance for the two named models on the official 2017 challenge test set. Several teams were able to achieve F1scores above/close to 90% on a hidden test-set of Holter recordings. We highlight themes commonly observed among participants, and report the results from the self-assessed student evaluation. Finally, the self-assessment of the students reported a notable increase in machine learning knowledge.
650    _2
$a algoritmy $7 D000465
650    _2
$a umělá inteligence $7 D001185
650    12
$a fibrilace síní $x diagnóza $7 D001281
650    12
$a COVID-19 $x diagnóza $7 D000086382
650    _2
$a kontrola infekčních nemocí $7 D003140
650    _2
$a elektrokardiografie $x metody $7 D004562
650    _2
$a lidé $7 D006801
650    _2
$a strojové učení $7 D000069550
655    _2
$a časopisecké články $7 D016428
700    1_
$a Reich, Christoph $u KIS*MED - AI Systems in Medicine, Technische Universität Darmstadt, Darmstadt, Germany $1 https://orcid.org/0000000286161627
700    1_
$a Höhl, Andreas $u KIS*MED - AI Systems in Medicine, Technische Universität Darmstadt, Darmstadt, Germany
700    1_
$a Lilienthal, Timm $u KIS*MED - AI Systems in Medicine, Technische Universität Darmstadt, Darmstadt, Germany
700    1_
$a Dege, Tizian $u KIS*MED - AI Systems in Medicine, Technische Universität Darmstadt, Darmstadt, Germany
700    1_
$a Plesinger, Filip $u Institute of Scientific Instruments of the Czech Academy of Sciences, Brno, Czech Republic $1 https://orcid.org/0000000328753541
700    1_
$a Bulkova, Veronika $u Medical Data Transfer, s.r.o., Brno, Czech Republic
700    1_
$a Clifford, Gari $u Department of Biomedical Informatics, Emory University, United States of America $u Department of Biomedical Engineering, Georgia Institute of Technology, United States of America $1 https://orcid.org/000000025709201X
700    1_
$a Reyna, Matthew $u Department of Biomedical Informatics, Emory University, United States of America $1 https://orcid.org/0000000346887965
700    1_
$a Hoog Antink, Christoph $u KIS*MED - AI Systems in Medicine, Technische Universität Darmstadt, Darmstadt, Germany $1 https://orcid.org/0000000179488181
773    0_
$w MED00181057 $t Physiological measurement $x 1361-6579 $g Roč. 43, č. 7 (2022)
856    41
$u https://pubmed.ncbi.nlm.nih.gov/35697013 $y Pubmed
910    __
$a ABA008 $b sig $c sign $y p $z 0
990    __
$a 20221017 $b ABA008
991    __
$a 20221031100133 $b ABA008
999    __
$a ok $b bmc $g 1854788 $s 1176549
BAS    __
$a 3
BAS    __
$a PreBMC
BMC    __
$a 2022 $b 43 $c 7 $e 20220707 $i 1361-6579 $m Physiological measurement $n Physiol Meas $x MED00181057
LZP    __
$a Pubmed-20221017

Najít záznam

Citační ukazatele

Možnosti archivace