刘军豪
阜外华中心血管病医院 内分泌科
BACKGROUND AND AIMS:Risk stratification for three-vessel coronary artery disease (3VD) remains an important clinical challenge. In this study, we utilized machine learning (ML), which can address the limitations of traditional regression-based models, to develop a novel model to assess mortality risk in patients with 3VD.METHODS:This study was based on a prospective cohort of 8943 participants with 3VD consecutively enrolled between 2004 and 2011. An ML-derived random forest model was trained and tested to predict 4-year mortality. The predictability of the model was compared with that of an established model, the Synergy Between Percutaneous Coronary Intervention With Taxus and Cardiac Surgery score II (SSII), among 3VD patients undergoing percutaneous coronary intervention (PCI), coronary artery bypass grafting (CABG), and medical therapy (MT) alone.RESULTS:The all-cause mortality was 7.5% (667 patients) over the 4-year follow-up period. The correlation-based feature selection algorithm selected 18 of the 94 features to develop the ML model. In the testing dataset, the ML-derived model achieved an area under the curve of 0.81 for 4-year mortality prediction. Its predictability was significantly better than that of the SSII among patients undergoing PCI (0.80 vs. 0.70, p < 0.001) or CABG (0.80 vs. 0.67, p < 0.001). The model also outperformed the SSII in patients receiving MT alone (ML: 0.75 vs. SSII for PCI: 0.70 or SSII for CABG: 0.66, p < 0.001).CONCLUSIONS:This ML-based approach exhibited better performance in risk stratification for 3VD compared with the conventional method. Further validation studies are needed to confirm these findings.
Atherosclerosis 2023
BACKGROUND:Three-vessel disease (TVD) with a SYNergy between PCI with TAXus and cardiac surgery (SYNTAX) score of ≥ 23 is one of the most severe types of coronary artery disease. We aimed to take advantage of machine learning to help in decision-making and prognostic evaluation in such patients.METHODS:We analyzed 3786 patients who had TVD with a SYNTAX score of ≥ 23, had no history of previous revascularization, and underwent either coronary artery bypass grafting (CABG) or percutaneous coronary intervention (PCI) after enrollment. The patients were randomly assigned to a training group and testing group. The C4.5 decision tree algorithm was applied in the training group, and all-cause death after a median follow-up of 6.6 years was regarded as the class label.RESULTS:The decision tree algorithm selected age and left ventricular end-diastolic diameter (LVEDD) as splitting features and divided the patients into three subgroups: subgroup 1 (age of ≤ 67 years and LVEDD of ≤ 53 mm), subgroup 2 (age of ≤ 67 years and LVEDD of > 53 mm), and subgroup 3 (age of > 67 years). PCI conferred a patient survival benefit over CABG in subgroup 2. There was no significant difference in the risk of all-cause death between PCI and CABG in subgroup 1 and subgroup 3 in both the training data and testing data. Among the total study population, the multivariable analysis revealed significant differences in the risk of all-cause death among patients in three subgroups.CONCLUSIONS:The combination of age and LVEDD identified by machine learning can contribute to decision-making and risk assessment of death in patients with severe TVD. The present results suggest that PCI is a better choice for young patients with severe TVD characterized by left ventricular dilation.
Journal of geriatric cardiology : JGC 2022
Hyperuricemia has been associated with mortality in patients with coronary artery disease (CAD). However, its prognostic value remains unknown in the context of severe CAD with heavy atherosclerotic burden in all 3 vessels. We used data from a large cohort of consecutive patients with severe CAD. The primary end point was all-cause death. Propensity score matching was used to identify 2 cohorts of patients with similar baseline characteristics. A total of 8,529 patients with available serum uric acid data were included in the study. Hyperuricemia was present in 1,207 (14.2%) patients. At baseline, hyperuricemic patients had more co-morbidities, and more often received medical therapy alone. During the median follow-up of 7.5 years, significantly more deaths occurred in hyperuricemic patients compared with normouricemic patients (22.5% vs 13.7%; p < 0.001). Multivariable analyses showed that hyperuricemia was associated with an increased risk of mortality (hazard ratio 1.33; 95% confidence interval 1.15 to 1.53; p < 0.001). Propensity score matching yielded similar results (hazard ratio 1.33; 95% confidence interval 1.11 to 1.61; p = 0.003). The association was relatively consistent across subgroups, except for an interaction between age and hyperuricemia. Addition of uric acid to SYNTAX score II provided significant improvements of reclassification and discrimination for mortality prediction. In conclusion, hyperuricemia is relatively common among patients with severe CAD and is independently associated with mortality. Moreover, uric acid can improve the predictability of a well-established risk score.
The American journal of cardiology 2019
AIMS:Risk assessment and treatment stratification for three-vessel disease (3VD) remain challenging. N-terminal pro-B-type natriuretic peptide (NT-proBNP) is an established biomarker for prognostication and treatment in heart failure. The present study aimed to evaluate the prognostic value of NT-proBNP beyond the SYNTAX score II (SSII), and its association with long-term outcome after three strategies [percutaneous coronary intervention (PCI), coronary artery bypass grafting (CABG), and medical therapy (MT)] in a cohort of patients with 3VD.METHODS AND RESULTS:A total of 6597 patients with available baseline NT-proBNP data were included in the study. Baseline, procedural, and follow-up data were collected. The primary endpoint was all-cause death. Secondary endpoints included cardiac death and major adverse cardiac and cerebrovascular events (MACCE), a composite of death, myocardial infarction, and stroke. During a median follow-up of 7.0 years, higher NT-proBNP levels were strongly associated with increased risks of all-cause death, cardiac death, and MACCE (all adjusted P < 0.01). Moreover, NT-proBNP significantly improved discrimination and reclassification of the SSII. Notably, there was a significant interaction between NT-proBNP quartiles and treatment strategies for MACCE (P = 0.004). Revascularization was associated with lower risks of MACCE than MT, except for patients in the lowest quartile wherein no such association was observed. Among patients in the highest quartile, PCI was associated with an increased risk of MACCE compared with CABG (hazard ratio 1.43, 95% confidence interval 1.09-1.87).CONCLUSION:N-terminal pro-BNP is a potential biomarker for risk stratification and therapeutic decision-making in patients with 3VD. Further randomized studies are needed to confirm these findings.
European heart journal 2019
AIM:To evaluate the prognostic value of plasma big endothelin-1 level in the context of three-vessel disease (TVD) with heavy atherosclerotic burden.METHODS:A total of 6,150 patients with TVD and available big endothelin-1 data were included in the study. Participants were divided into two groups according to the optimal cutoff value of big endothelin-1 for mortality prediction. The primary endpoint was all-cause death. C-index, net reclassification improvement (NRI), and integrated discrimination improvement (IDI) were calculated to evaluate the added prognostic value of plasma big endothelin-1 level beyond the SYNTAX score Ⅱ.RESULTS:On the basis of the optimal cutoff value of 0.79 pmol/L, 1,984 patients were assigned to the high big endothelin-1 group. During a median follow-up of 6.8 years, 818 patients experienced all-cause death. Plasma big endothelin-1 level was significantly higher in patients who died than in patients who survived. Multivariable analysis found that high big endothelin-1 level was independently associated with an increased risk of mortality (hazard ratio: 1.36, 95% confidence interval: 1.18-1.57, P＜0.001). The association of big endothelin-1 with all-cause death was relatively consistent across subgroups with no significant interactions. The predictive ability of the SYNTAX score Ⅱ was significantly enhanced by addition of plasma big endothelin-1 level (C-index: 0.723 vs.0.715, P =0.029; NRI: 0.304, P＜0.001; IDI: 0.009, P＜0.001).CONCLUSIONS:Plasma big endothelin-1 level is an independent predictor of long-term mortality in patients with TVD. It can improve the discrimination and reclassification of the SYNTAX score Ⅱ for mortality prediction.
Journal of atherosclerosis and thrombosis 2019
Stroke is a common complex trait and does not follow Mendelian pattern of inheritance. Gene-gene or gene-environment interactions may be responsible for the complex trait. How the interactions contribute to stroke is still under research. This study aimed to explore the association between gene-gene interactions and stroke in Chinese in a large case-control study. Nearly 4,000 participants were recruited from seven clinical centers. Eight variants in five candidate genes were examined for stroke risk. Gene-gene interactions were explored by using Generalized Multifactor Dimensionality Reduction (GMDR). A significant gene-gene interaction was found by GMDR. The best model including MTHFR C677T, ALOX5AP T2354A and NOTCH3 C381T scored 10 for Cross-Validation Consistency and 9 for Sign Test (P = 0.0107). The individuals with combination of MTHFR 677TT, ALOX5AP 2354AA and NOTCH3 381TT/TC had a significantly higher risk of thrombotic stroke (OR 3.165, 95% CI 1.461-6.858, P = 0.003). Our results show that combination of these alleles conferred higher risk for stroke than single risk allele. The gene-gene interaction may serve as a novel area for stroke research. The three-locus combination may change the susceptibility of particular subjects to the disease.
Human genetics 2009
