RESUMO
OBJECTIVES: To calculate the coronary artery calcification score (CACS) obtained from coronary artery computed tomography angiography (CCTA) examination and combine it with the influencing factors of coronary artery calcification (CAC), which is then analyzed by machine learning (ML) to predict the probability of coronary heart disease(CHD). METHODS: All patients who were admitted to the Affiliated Hospital of Traditional Chinese Medicine of Southwest Medical University from January 2019 to March 2022, suspected of CHD, and underwent CCTA inspection were retrospectively selected. The degree of CAC was quantified based on the Agatston score. To compare the correlation between the CACS and clinical-related factors, we collected 31 variables, including hypertension, diabetes, smoking, hyperlipidemia, among others. ML models containing the random forest (RF), radial basis function neural network (RBFNN),support vector machine (SVM),K-Nearest Neighbor algorithm (KNN) and kernel ridge regression (KRR) were used to assess the risk of CHD based on CACS and clinical-related factors. RESULTS: Among the five ML models, RF achieves the best performance about accuracy (ACC) (78.96%), sensitivity (SN) (93.86%), specificity(Spe) (51.13%), and Matthew's correlation coefficient (MCC) (0.5192).It also has the best area under the receiver operator characteristic curve (ROC) (0.8375), which is far superior to the other four ML models. CONCLUSION: Computer ML model analysis confirmed the importance of CACS in predicting the occurrence of CHD, especially the outstanding RF model, making it another advancement of the ML model in the field of medical analysis.
Assuntos
Doença da Artéria Coronariana , Calcificação Vascular , Humanos , Calcificação Vascular/diagnóstico por imagem , Estudos Retrospectivos , Valor Preditivo dos Testes , Fatores de Risco , Doença da Artéria Coronariana/diagnóstico por imagem , Medição de Risco , Aprendizado de MáquinaRESUMO
Objective: To explore the diagnostic value of fragmented QRS (fQRS) for coronary atherosclerotic heart disease (CHD), and to analyze it's relationship with left ventricular remodeling. Methods: From Nov. 2016 to Oct. 2018, 498 hospitalized patients in the Department of Cardiovascular Medicine of Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine were selected consecutively. During the hospitalization, all the patients underwent coronary angiography. According to the angiographic results, the patients were divided into the control group (203 patients with negative or coronary stenosis < 30%), the mild to moderate stenosis group (155 patients with coronary stenosis 30% to 75%), and the severe stenosis group (140 patients with coronary stenosis≥75%). The incidences of fQRS(+) in the normal electrocardiogram among the three groups were compared by chi-square test of R×C contingency table. Two hundred and thirty patients with single-vessel stenosis≥30% were divided into the anterior descending branch group (128 cases), the right coronary branch group (59 cases), and the circumflex branch group (43 cases), and the relationship between fQRS(+) leads and diseased vessels was analyzed by nonparametric test. Finally, all the patients were divided into fQRS(+) group (86 cases) and fQRS(-) group (412 cases). The correlation between fQRS and left ventricular ejection fraction (LVEF), left ventricular end-diastolic volume (LVEDV), left ventricular end-systolic volume (LVESV), interventricular septum thickness (IVST) and left ventricular posterior wall thickness (LVPWT), respectively, were analyzed by binary Logistic regression model. Results: The chi-square test of R×C contingency table showed that the incidences of fQRS(+) in the three groups were 8.89%, 16.13% and 30.71%, respectively, with statistically significant differences (all P < 0.05). The nonparametric test showed that the fQRS(+) leads reflecting the anterior wall (V3, V4) were more common in the anterior descending branch group, and the fQRS(+) leads reflecting the interior wall and right ventricular (Ⅱ, III, AVF, V1, V2) were more common in the right coronary branch group, the fQRS(+) leads reflecting upper lateral wall (, AVL) were more common in the circumflex branch group, with statistically significant differences (all P<0.05). Binary Logistic regression analysis showed that fQRS was negatively correlated with LVEF (r=-0.030, OR=0.971, 95% CI 0.945-0.997, P=0.029), and positively correlated with LVESV (r=0.042, OR=1.043, 95% CI 1.005-1.082, P=0.026). Conclusion: fQRS has certain reference value in the clinical diagnosis of CHD, and left ventricular remodeling may be one of the mechanisms of fQRS.
RESUMO
Coronary atherosclerotic heart disease (CHD) remains the leading cause of morbidity and mortality in the world, with elevated low density lipoprotein-cholesterol (LDL-C) levels as a major risk factor. Lower levels of LDL-C can effectively reduce the risk of CHD. To date, lipid-lowering medicines such as statins are effective in lowering LDL-C, but a proportion of patients do not achieve lipid reduction target with statins or are intolerant to statins. Proprotein convertase subtilisin/kexin type 9 (PCSK9) inhibitors are a new class of agents reducing LDL-C which gain more and more concerns. Through inhibitory effect on PCSK9 and increasing low-density lipoprotein receptors recycling, they can significantly reduce serum LDL-C levels. PCSK9 inhibitors are currently in phase III of clinical trials, and the results showed that they had good lipid-lowering effects and tolerability. This review provided an overview of the latest advances and challenges about PCSK9 inhibitors.
RESUMO
Coronary atherosclerotic heart disease (CHD) remains the leading cause of morbidity and mortality in the world, with elevated low density lipoprotein-cholesterol (LDL-C) levels as a major risk factor. Lower levels of LDL-C can effectively reduce the risk of CHD. To date, lipid-lowering medicines such as statins are effective in lowering LDL-C, but a proportion of patients do not achieve lipid reduction target with statins or are intolerant to statins. Proprotein convertase subtilisin/kexin type 9 (PCSK9) inhibitors are a new class of agents reducing LDL-C which gain more and more concerns. Through inhibitory effect on PCSK9 and increasing low-density lipoprotein receptors recycling, they can significantly reduce serum LDL-C levels. PCSK9 inhibitors are currently in phase Ⅲ of clinical trials, and the results showed that they had good lipid-lowering effects and tolerability. This review provided an overview of the latest advances and challenges about PCSK9 inhibitors.
