Heart Failure and Structural Heart Disease Unit

Lead: Jeffrey Chan

Dr Jeffrey Chan discusses his original study looking at the prognostic value of fragmented QRS in heart failure patients using automated ECG waveform extraction

Dr Jeffrey Chan investigates the use of clustering analysis to aid risk stratification in heart failure


Dr Chan presents at ESC Asia on his project aiming to predict incident heart failure using visit-to-visit variability in cholesterol levels

Heart failure is the common final pathway of many cardiovascular conditions, with an estimated 70 million people worldwide suffering from it. Many of the heart failure patients are frail, and are at greater risks of acute decompensation events. Therefore, there is a pressing need to accurately forecast such events before they occur, which would allow timely intervention to improve clinical outcomes and qualify of life. With this in mind, the team has worked towards greater precision and accuracy in phenotyping and prediction of adverse outcomes in heart failure. An exemplar is the development of a multimodality risk score, which included atrial and ventricular measurements from electrocardiography and echocardiography, blood inflammatory marker [neutrophil-to-lymphocyte ratio (NLR)], and prognostic nutritional index (PNI) and comorbidity records, to improve the prediction of atrial fibrillation, stroke and mortality. The application of multilayer perceptron and multi-task learning improved the F1-score from 0.81 to 0.89 and 0.94.


Moreover, frailty assessment is highly time-consuming and there have been increasing efforts globally to develop surrogate markers of frailty, as exemplified by electronic frailty indices. Subsequent data-driven explorations in a larger cohort resulted in the development of a heart failure-specific electronic frailty index, which did not require clinical assessment, electrocardiographic or echocardiographic testing. This index, computed from comorbidity and laboratory data, showed an excellent performance with an area under the receiver operating characteristic curve of 0.86 with logistic regression, which was significantly improved to 0.88 and 0.91 by decision tree and gradient boosting methods for short-term mortality prediction.

Publications


1. Chan, J.S.K., Zhou, J., Lee, S., Li, A., Tan, M., Leung, K.S.K., Jeevaratnam, K., Liu, T., Roever, L., Liu, Y., Tse, G., Zhang, Q. (2021) Fragmented QRS is independently predictive of long-term adverse clinical outcomes in Asian patients hospitalized for heart failure: a retrospective cohort study. Front Cardiovasc Med. 8: 1634. doi: https://doi.org/10.3389/fcvm.2021.738417. Impact factor: 6.050.


2. Ju, C., Zhou, J., Lee, S., Tan, M.S., Liu, T., Bazoukis, G., Jeevaratnam, K., Chan, E.W.Y., Wong, I.C.K., Wei, L., Zhang, Q., Tse, G. (2021) Derivation of an electronic frailty index for predicting short-term mortality in heart failure: a machine learning approach. ESC Heart Failure. PMID: 34080784. https://doi.org/10.1002/ehf2.13358. Impact factor: 3.9.


3. Sun, Y., Wang, N., Zhang, Y., Yang, J., Tse, G., Liu, Y. (2021) Predictive value of H2FPEF score in patients with heart failure with preserved ejection fraction. ESC Heart Failure. 8(2):1244-1252. PMID: 33403825. https://doi.org/10.1002/ehf2.13187. Impact factor: 3.9.


4. Tse, G., Zhou, J., Woo, S.W.D., Ko, C.H., Lai, R.W.C., Liu, T., Liu, Y., Leung, K.S.K., Li, A., Lee, S., Li, K.H.C., Lakhani, I., Zhang, Q. (2020) Multi-modality machine-learning approach for risk stratification in heart failure with left ventricular ejection fraction ≤ 45%. ESC Heart Failure. 7(6):3716-25. PMID: 33094925. https://doi.org/10.1002/ehf2.12929. Impact factor: 3.9.


5. Wang, Y., Xiao, G., Zhang, G., Wang, B., Lin, Z., Saiwha, H.D., You, H., Lai, K., Su, M., Wen, H., Wang, J., Annest, L., Tse, G. (2020) Early Results of the Revivent TC Procedure for Treatment of Left Ventricular Aneurysm and Heart Failure Due to Ischemic Cardiomyopathy. EuroIntervention. 2020 Jan 28:EIJ-D-19-00225. PMID: 31985453. https://doi.org/10.4244/eij-d-19-00225. 5-year impact factor: 3.8.


6. Zhang, Y., Yuan, M., Gong, M., Li, G., Liu, T., Tse, G. (2018) Letter to the Editor: Associations between prefrailty or frailty components and clinical outcomes in heart failure: a follow-up meta-analysis. J Am Med Dir Assoc. pii: S1525-8610(18)30609-1. PMID: 30541690. https://doi.org/10.1016/j.jamda.2018.10.029. 5-year impact factor: 6.3.


7. Zhang, Y., Yuan, M., Gong, M., Tse, G., Li, G., Liu, T. (2018) Frailty and clinical outcomes in heart failure: a systematic review with meta-analysis. J Am Med Dir Assoc. S1525-8610(18)30329-3. PMID: 30076123. https://doi.org/10.1016/j.jamda.2018.06.009. 5-year impact factor: 6.3.


8. Tse, G., Gong, M., Wong, S.H., Wu, W.K.K., Bazoukis, G., Lampropoulos, K., Wong, W.T., Xia, Y., Wong, M.C.S., Liu, T., Woo, J. (2017) Frailty and clinical outcomes in advanced heart failure patients undergoing left ventricular assist device implantation: a systematic review and meta-analysis. J Am Med Dir Assoc. pii: S1525-8610(17)30545-5. PMID: 29129497. http://dx.doi.org/10.1016/j.jamda.2017.09.022. Impact factor: 5.




Collaborating Institutions