| 1. |
- Agarwal, Anubha, et al.
(författare)
-
Toward a Universal Definition of Etiologies in Heart Failure : Categorizing Causes and Advancing Registry Science
- 2024
-
Ingår i: Circulation Heart Failure. - : American Heart Association. - 1941-3289 .- 1941-3297. ; 17:4
-
Forskningsöversikt (refereegranskat)abstract
- Heart failure (HF) is a well-described final common pathway for a broad range of diseases however substantial confusion exists regarding how to describe, study, and track these underlying etiologic conditions. We describe (1) the overlap in HF etiologies, comorbidities, and case definitions as currently used in HF registries led or managed by members of the global HF roundtable; (2) strategies to improve the quality of evidence on etiologies and modifiable risk factors of HF in registries; and (3) opportunities to use clinical HF registries as a platform for public health surveillance, implementation research, and randomized registry trials to reduce the global burden of noncommunicable diseases. Investment and collaboration among countries to improve the quality of evidence in global HF registries could contribute to achieving global health targets to reduce noncommunicable diseases and overall improvements in population health.
|
|
| 2. |
- Myhre, Peder L., et al.
(författare)
-
External validation of a deep learning algorithm for automated echocardiographic strain measurements
- 2024
-
Ingår i: EUROPEAN HEART JOURNAL - DIGITAL HEALTH. - 2634-3916. ; 5:1, s. 60-68
-
Tidskriftsartikel (refereegranskat)abstract
- Aims Echocardiographic strain imaging reflects myocardial deformation and is a sensitive measure of cardiac function and wall-motion abnormalities. Deep learning (DL) algorithms could automate the interpretation of echocardiographic strain imaging.Methods and results We developed and trained an automated DL-based algorithm for left ventricular (LV) strain measurements in an internal dataset. Global longitudinal strain (GLS) was validated externally in (i) a real-world Taiwanese cohort of participants with and without heart failure (HF), (ii) a core-lab measured dataset from the multinational prevalence of microvascular dysfunction-HF and preserved ejection fraction (PROMIS-HFpEF) study, and regional strain in (iii) the HMC-QU-MI study of patients with suspected myocardial infarction. Outcomes included measures of agreement [bias, mean absolute difference (MAD), root-mean-squared-error (RMSE), and Pearson's correlation (R)] and area under the curve (AUC) to identify HF and regional wall-motion abnormalities. The DL workflow successfully analysed 3741 (89%) studies in the Taiwanese cohort, 176 (96%) in PROMIS-HFpEF, and 158 (98%) in HMC-QU-MI. Automated GLS showed good agreement with manual measurements (mean +/- SD): -18.9 +/- 4.5% vs. -18.2 +/- 4.4%, respectively, bias 0.68 +/- 2.52%, MAD 2.0 +/- 1.67, RMSE = 2.61, R = 0.84 in the Taiwanese cohort; and -15.4 +/- 4.1% vs. -15.9 +/- 3.6%, respectively, bias -0.65 +/- 2.71%, MAD 2.19 +/- 1.71, RMSE = 2.78, R = 0.76 in PROMIS-HFpEF. In the Taiwanese cohort, automated GLS accurately identified patients with HF (AUC = 0.89 for total HF and AUC = 0.98 for HF with reduced ejection fraction). In HMC-QU-MI, automated regional strain identified regional wall-motion abnormalities with an average AUC = 0.80.Conclusion DL algorithms can interpret echocardiographic strain images with similar accuracy as conventional measurements. These results highlight the potential of DL algorithms to democratize the use of cardiac strain measurements and reduce time-spent and costs for echo labs globally. Graphical Abstract
|
|
