QRS detection and classification in Holter ECG data in one inference step
Abstract While various QRS detection and classification methods were developed in the past, the Holter ECG data acquired during daily activities by wearable devices represent new challenges such as increased noise and artefacts due to patient movements. Here, we present a deep-learning model to dete...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-07-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-022-16517-4 |
| _version_ | 1828375178221977600 |
|---|---|
| author | Adam Ivora Ivo Viscor Petr Nejedly Radovan Smisek Zuzana Koscova Veronika Bulkova Josef Halamek Pavel Jurak Filip Plesinger |
| author_facet | Adam Ivora Ivo Viscor Petr Nejedly Radovan Smisek Zuzana Koscova Veronika Bulkova Josef Halamek Pavel Jurak Filip Plesinger |
| author_sort | Adam Ivora |
| collection | DOAJ |
| description | Abstract While various QRS detection and classification methods were developed in the past, the Holter ECG data acquired during daily activities by wearable devices represent new challenges such as increased noise and artefacts due to patient movements. Here, we present a deep-learning model to detect and classify QRS complexes in single-lead Holter ECG. We introduce a novel approach, delivering QRS detection and classification in one inference step. We used a private dataset (12,111 Holter ECG recordings, length of 30 s) for training, validation, and testing the method. Twelve public databases were used to further test method performance. We built a software tool to rapidly annotate QRS complexes in a private dataset, and we annotated 619,681 QRS complexes. The standardised and down-sampled ECG signal forms a 30-s long input for the deep-learning model. The model consists of five ResNet blocks and a gated recurrent unit layer. The model's output is a 30-s long 4-channel probability vector (no-QRS, normal QRS, premature ventricular contraction, premature atrial contraction). Output probabilities are post-processed to receive predicted QRS annotation marks. For the QRS detection task, the proposed method achieved the F1 score of 0.99 on the private test set. An overall mean F1 cross-database score through twelve external public databases was 0.96 ± 0.06. In terms of QRS classification, the presented method showed micro and macro F1 scores of 0.96 and 0.74 on the private test set, respectively. Cross-database results using four external public datasets showed micro and macro F1 scores of 0.95 ± 0.03 and 0.73 ± 0.06, respectively. Presented results showed that QRS detection and classification could be reliably computed in one inference step. The cross-database tests showed higher overall QRS detection performance than any of compared methods. |
| first_indexed | 2024-04-14T07:43:10Z |
| format | Article |
| id | doaj.art-44423bbbbe444ed98dd755d5a2415439 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-14T07:43:10Z |
| publishDate | 2022-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-44423bbbbe444ed98dd755d5a24154392022-12-22T02:05:25ZengNature PortfolioScientific Reports2045-23222022-07-011211910.1038/s41598-022-16517-4QRS detection and classification in Holter ECG data in one inference stepAdam Ivora0Ivo Viscor1Petr Nejedly2Radovan Smisek3Zuzana Koscova4Veronika Bulkova5Josef Halamek6Pavel Jurak7Filip Plesinger8Institute of Scientific Instruments of the Czech Academy of SciencesInstitute of Scientific Instruments of the Czech Academy of SciencesInstitute of Scientific Instruments of the Czech Academy of SciencesInstitute of Scientific Instruments of the Czech Academy of SciencesInstitute of Scientific Instruments of the Czech Academy of SciencesMedical Data TransferInstitute of Scientific Instruments of the Czech Academy of SciencesInstitute of Scientific Instruments of the Czech Academy of SciencesInstitute of Scientific Instruments of the Czech Academy of SciencesAbstract While various QRS detection and classification methods were developed in the past, the Holter ECG data acquired during daily activities by wearable devices represent new challenges such as increased noise and artefacts due to patient movements. Here, we present a deep-learning model to detect and classify QRS complexes in single-lead Holter ECG. We introduce a novel approach, delivering QRS detection and classification in one inference step. We used a private dataset (12,111 Holter ECG recordings, length of 30 s) for training, validation, and testing the method. Twelve public databases were used to further test method performance. We built a software tool to rapidly annotate QRS complexes in a private dataset, and we annotated 619,681 QRS complexes. The standardised and down-sampled ECG signal forms a 30-s long input for the deep-learning model. The model consists of five ResNet blocks and a gated recurrent unit layer. The model's output is a 30-s long 4-channel probability vector (no-QRS, normal QRS, premature ventricular contraction, premature atrial contraction). Output probabilities are post-processed to receive predicted QRS annotation marks. For the QRS detection task, the proposed method achieved the F1 score of 0.99 on the private test set. An overall mean F1 cross-database score through twelve external public databases was 0.96 ± 0.06. In terms of QRS classification, the presented method showed micro and macro F1 scores of 0.96 and 0.74 on the private test set, respectively. Cross-database results using four external public datasets showed micro and macro F1 scores of 0.95 ± 0.03 and 0.73 ± 0.06, respectively. Presented results showed that QRS detection and classification could be reliably computed in one inference step. The cross-database tests showed higher overall QRS detection performance than any of compared methods.https://doi.org/10.1038/s41598-022-16517-4 |
| spellingShingle | Adam Ivora Ivo Viscor Petr Nejedly Radovan Smisek Zuzana Koscova Veronika Bulkova Josef Halamek Pavel Jurak Filip Plesinger QRS detection and classification in Holter ECG data in one inference step Scientific Reports |
| title | QRS detection and classification in Holter ECG data in one inference step |
| title_full | QRS detection and classification in Holter ECG data in one inference step |
| title_fullStr | QRS detection and classification in Holter ECG data in one inference step |
| title_full_unstemmed | QRS detection and classification in Holter ECG data in one inference step |
| title_short | QRS detection and classification in Holter ECG data in one inference step |
| title_sort | qrs detection and classification in holter ecg data in one inference step |
| url | https://doi.org/10.1038/s41598-022-16517-4 |
| work_keys_str_mv | AT adamivora qrsdetectionandclassificationinholterecgdatainoneinferencestep AT ivoviscor qrsdetectionandclassificationinholterecgdatainoneinferencestep AT petrnejedly qrsdetectionandclassificationinholterecgdatainoneinferencestep AT radovansmisek qrsdetectionandclassificationinholterecgdatainoneinferencestep AT zuzanakoscova qrsdetectionandclassificationinholterecgdatainoneinferencestep AT veronikabulkova qrsdetectionandclassificationinholterecgdatainoneinferencestep AT josefhalamek qrsdetectionandclassificationinholterecgdatainoneinferencestep AT paveljurak qrsdetectionandclassificationinholterecgdatainoneinferencestep AT filipplesinger qrsdetectionandclassificationinholterecgdatainoneinferencestep |