Ethnic differences in quality of life and its association with survival in patients with heart failure.

BACKGROUND: Optimizing quality of life (QoL) is a key priority in the management of heart failure (HF). HYPOTHESIS: To investigate ethnic differences in QoL and its association with 1-year survival among patients with HF. METHODS: A prospective nationwide cohort (n = 1070, mean age: 62 years, 24.5% women) of Chinese (62.3%), Malay (26.7%) and Indian (10.9%) ethnicities from Singapore, QoL was assessed using the Minnesota Living with HF Questionnaire (MLHFQ) at baseline and 6 months. Patients were followed for all-cause mortality. RESULTS: At baseline, Chinese had a lower (better) mean MLHFQ total score (29.1 ± 21.6) vs Malays (38.5 ± 23.9) and Indians (41.7 ± 24.5); P < .001. NYHA class was the strongest independent predictor of MLHFQ scores (12.7 increment for class III/IV vs I/II; P < .001). After multivariable adjustment (including NT-proBNP levels, medications), ethnicity remained an independent predictor of QoL (P < .001). Crude 1-year mortality in the overall cohort was 16.5%. A 10-point increase of the physical component (of MLHFQ) was associated with a hazard (HR 1.22, 95% 1.03-1.43) of 1-year mortality (P = .018) in the overall cohort. An interaction between MLHFQ and ethnicity was found (P = .019), where poor MLHFQ score (per 10-point increase) predicted higher adjusted mortality only in Chinese (total score: HR 1.18 [95% CI 1.07-1.30]; physical: HR 1.44 [95% CI 1.17-1.75]; emotional score: HR 1.45 [95% CI 1.05-2.00]). CONCLUSIONS: Ethnicity is an independent determinant of QoL in HF. Despite better baseline QoL in Chinese, QoL was more strongly related to survival in Chinese vs Malays and Indians. These findings have implications for HF trials that use patient-reported outcomes as endpoints.

Machine Learning Approaches in Cardiovascular Imaging.

Cardiovascular imaging technologies continue to increase in their capacity to capture and store large quantities of data. Modern computational methods, developed in the field of machine learning, offer new approaches to leveraging the growing volume of imaging data available for analyses. Machine learning methods can now address data-related problems ranging from simple analytic queries of existing measurement data to the more complex challenges involved in analyzing raw images. To date, machine learning has been used in 2 broad and highly interconnected areas: automation of tasks that might otherwise be performed by a human and generation of clinically important new knowledge. Most cardiovascular imaging studies have focused on task-oriented problems, but more studies involving algorithms aimed at generating new clinical insights are emerging. Continued expansion in the size and dimensionality of cardiovascular imaging databases is driving strong interest in applying powerful deep learning methods, in particular, to analyze these data. Overall, the most effective approaches will require an investment in the resources needed to appropriately prepare such large data sets for analyses. Notwithstanding current technical and logistical challenges, machine learning and especially deep learning methods have much to offer and will substantially impact the future practice and science of cardiovascular imaging.