GLORIA

GEOMAR Library Ocean Research Information Access

X

Your email was sent successfully. Check your inbox.

An error occurred while sending the email. Please try again.

Proceed reservation?

Export
  • 1
    Online Resource
    Online Resource
    Discovering and Visualizing Disease-Specific Electrocardiogram Features Using Deep Learning : Proof-of-Concept in Phospholamban Gene Mutation Carriers
    Ovid Technologies (Wolters Kluwer Health) ; 2021
    In:  Circulation: Arrhythmia and Electrophysiology Vol. 14, No. 2 ( 2021-02)
    Details
    In: Circulation: Arrhythmia and Electrophysiology, Ovid Technologies (Wolters Kluwer Health), Vol. 14, No. 2 ( 2021-02)
    Abstract: ECG interpretation requires expertise and is mostly based on physician recognition of specific patterns, which may be challenging in rare cardiac diseases. Deep neural networks (DNNs) can discover complex features in ECGs and may facilitate the detection of novel features which possibly play a pathophysiological role in relatively unknown diseases. Using a cohort of PLN (phospholamban) p.Arg14del mutation carriers, we aimed to investigate whether a novel DNN-based approach can identify established ECG features, but moreover, we aimed to expand our knowledge on novel ECG features in these patients. Methods: A DNN was developed on 12-lead median beat ECGs of 69 patients and 1380 matched controls and independently evaluated on 17 patients and 340 controls. Differentiating features were visualized using Guided Gradient Class Activation Mapping++. Novel ECG features were tested for their diagnostic value by adding them to a logistic regression model including established ECG features. Results: The DNN showed excellent discriminatory performance with a c-statistic of 0.95 (95% CI, 0.91–0.99) and sensitivity and specificity of 0.82 and 0.93, respectively. Visualizations revealed established ECG features (low QRS voltages and T-wave inversions), specified these features (eg, R- and T-wave attenuation in V2/V3) and identified novel PLN-specific ECG features (eg, increased PR-duration). The logistic regression baseline model improved significantly when augmented with the identified features ( P 〈 0.001). Conclusions: A DNN-based feature detection approach was able to discover and visualize disease-specific ECG features in PLN mutation carriers and revealed yet unidentified features. This novel approach may help advance diagnostic capabilities in daily practice.
    Type of Medium: Online Resource
    ISSN: 1941-3149 , 1941-3084
    URL: Article
    DOI: 10.1161/CIRCEP.120.009056
    Language: English
    Publisher: Ovid Technologies (Wolters Kluwer Health)
    Publication Date: 2021
    detail.hit.zdb_id: 2425487-3
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 2
    Online Resource
    Online Resource
    Interatrial Block Predicts Life‐Threatening Arrhythmias in Dilated Cardiomyopathy
    Ovid Technologies (Wolters Kluwer Health) ; 2022
    In:  Journal of the American Heart Association Vol. 11, No. 14 ( 2022-07-19)
    Details
    In: Journal of the American Heart Association, Ovid Technologies (Wolters Kluwer Health), Vol. 11, No. 14 ( 2022-07-19)
    Abstract: Interatrial block (IAB) has been associated with supraventricular arrhythmias and stroke, and even with sudden cardiac death in the general population. Whether IAB is associated with life‐threatening arrhythmias (LTA) and sudden cardiac death in dilated cardiomyopathy (DCM) remains unknown. This study aimed to determine the association between IAB and LTA in ambulant patients with DCM. Methods and Results A derivation cohort (Maastricht Dilated Cardiomyopathy Registry; N=469) and an external validation cohort (Utrecht Cardiomyopathy Cohort; N=321) were used for this study. The presence of IAB (P‐wave duration 〉 120 milliseconds) or atrial fibrillation (AF) was determined using digital calipers by physicians blinded to the study data. In the derivation cohort, IAB and AF were present in 291 (62%) and 70 (15%) patients with DCM, respectively. LTA (defined as sudden cardiac death, justified shock from implantable cardioverter‐defibrillator or anti‐tachypacing, or hemodynamic unstable ventricular fibrillation/tachycardia) occurred in 49 patients (3 with no IAB, 35 with IAB, and 11 patients with AF, respectively; median follow‐up, 4.4 years [2.1; 7.4]). The LTA‐free survival distribution significantly differed between IAB or AF versus no IAB (both P 〈 0.01), but not between IAB versus AF ( P =0.999). This association remained statistically significant in the multivariable model (IAB: HR, 4.8 (1.4–16.1), P =0.013; AF: HR, 6.4 (1.7–24.0), P =0.007). In the external validation cohort, the survival distribution was also significantly worse for IAB or AF versus no IAB ( P =0.037; P =0.005), but not for IAB versus AF ( P =0.836). Conclusions IAB is an easy to assess, widely applicable marker associated with LTA in DCM. IAB and AF seem to confer similar risk of LTA. Further research on IAB in DCM, and on the management of IAB in DCM is warranted.
    Type of Medium: Online Resource
    ISSN: 2047-9980
    URL: Article
    DOI: 10.1161/JAHA.121.025473
    Language: English
    Publisher: Ovid Technologies (Wolters Kluwer Health)
    Publication Date: 2022
    detail.hit.zdb_id: 2653953-6
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 3
    Online Resource
    Online Resource
    Deep neural network-based clustering of deformation curves reveals novel disease features in PLN pathogenic variant carriers
    Springer Science and Business Media LLC ; 2023
    In:  The International Journal of Cardiovascular Imaging Vol. 39, No. 11 ( 2023-08-11), p. 2149-2161
    Details
    In: The International Journal of Cardiovascular Imaging, Springer Science and Business Media LLC, Vol. 39, No. 11 ( 2023-08-11), p. 2149-2161
    Abstract: Echocardiographic deformation curves provide detailed information on myocardial function. Deep neural networks (DNNs) may enable automated detection of disease features in deformation curves, and improve the clinical assessment of these curves. We aimed to investigate whether an explainable DNN-based pipeline can be used to detect and visualize disease features in echocardiographic deformation curves of phospholamban ( PLN ) p.Arg14del variant carriers. A DNN was trained to discriminate PLN variant carriers (n = 278) from control subjects (n = 621) using raw deformation curves obtained by 2D-speckle tracking in the longitudinal axis. A visualization technique was used to identify the parts of these curves that were used by the DNN for classification. The PLN variant carriers were clustered according to the output of the visualization technique. The DNN showed excellent discriminatory performance (C-statistic 0.93 [95% CI 0.87–0.97]). We identified four clusters with PLN -associated disease features in the deformation curves. Two clusters showed previously described features: apical post-systolic shortening and reduced systolic strain. The two other clusters revealed novel features, both reflecting delayed relaxation. Additionally, a fifth cluster was identified containing variant carriers without disease features in the deformation curves, who were classified as controls by the DNN. This latter cluster had a very benign disease course regarding development of ventricular arrhythmias. Applying an explainable DNN-based pipeline to myocardial deformation curves enables automated detection and visualization of disease features. In PLN variant carriers, we discovered novel disease features which may improve individual risk stratification. Applying this approach to other diseases will further expand our knowledge on disease-specific deformation patterns. Graphical abstract Overview of the deep neural network-based pipeline for feature detection in myocardial deformation curves. Firstly, phospholamban ( PLN ) p.Arg14del variant carriers and controls were selected and a deep neural network (DNN) was trained to detect the PLN variant carriers. Subsequently, a clustering-based approach was performed on the attention maps of the DNN, which revealed 4 distinct phenotypes of PLN variant carriers with different prognoses. Moreover, a cluster without features and a benign prognosis was detected.
    Type of Medium: Online Resource
    ISSN: 1875-8312
    URL: Article
    DOI: 10.1007/s10554-023-02924-9
    Language: English
    Publisher: Springer Science and Business Media LLC
    Publication Date: 2023
    detail.hit.zdb_id: 2008950-8
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
Close ⊗
This website uses cookies and the analysis tool Matomo. More information can be found here...