To address this gap, we validated the previously developed AI algorithm by Cho et al. Despite advancement in AI-based LVSD diagnosis, an AI algorithm to identify LVSD patients with an EF < 40% has not been validated in a clinical population of patients with symptomatic HF regardless of EF. Various AI algorithms have been developed and performed based on different definitions of LVSD (e.g., ejection fraction (EF) < 35% 7, 10, 14, < 40% 8, 9, 11, 12, 13, or < 50% 12) and for distinct study populations 9, 13. The use of ECG for LVSD diagnosis has been ongoing since 1996, from identification of simple abnormalities on ECG to the more recent development of artificial intelligence (AI) algorithms 5, 7, 8, 9, 10, 11, 12, 13, 14, 15. Thus, the development of alternative screening tools for LVSD has been attempted, such as biochemical options and electrocardiogram (ECG) 4, 5, 6, 7, 8, 9. These limitations restrict the routine use of echocardiography in a resource-limited medical setting. While echocardiography is the standard tool for LVSD diagnosis, the results are highly influenced by operator-dependent factors and its interpretation is subjective, resulting in high dependence to assessor’s expertise 3. showed a decline in asymptomatic LVSD over the past three decades, the prognosis of LVSD has remained unchanged, emphasizing the importance of early diagnosis and adequate management of LVSD 2. Left ventricular systolic dysfunction (LVSD) increases the risk of systemic embolism, stroke, and death compared to heart failure (HF) with preserved LV systolic function 1.
The DeepECG-HFrEF algorithm may help in identification of LVSD and of patients at risk of worse survival in resource-limited settings.
HFrEF (+) was associated with higher mortality rates. The DeepECG-HFrEF algorithm can discriminate HFrEF in a real-world HF cohort with acceptable performance. Those classified as HFrEF (+) showed lower survival rates than HFrEF (−) (log-rank p < 0.001). The AUC value was 0.844 for identifying HFrEF among patients with acute symptomatic HF. HFrEF (+) identified an EF < 40% and HFrEF (−) identified EF ≥ 40%. A total of 690 patients contributing 18,449 ECGs were included with final 1291 ECGs eligible for the study (mean age 67.8 ± 14.4 years men, 56%). The 5-year mortality according to DeepECG-HFrEF results was analyzed using the Kaplan–Meier method. The performance of DeepECG-HFrEF was determined using the area under the receiver operating characteristic curve (AUC) values. Symptomatic HF patients admitted at Seoul National University Hospital between 20 were included. The DeepECG-HFrEF algorithm was trained to identify left ventricular systolic dysfunction (LVSD), defined by an ejection fraction (EF) < 40%. The performance and clinical implications of the deep learning aided algorithm using electrocardiogram of heart failure (HF) with reduced ejection fraction (DeepECG-HFrEF) were evaluated in patients with acute HF.
0 kommentar(er)
