The Asian system for cardiac operative risk evaluation for predicting mortality after isolated coronary artery bypass graft surgery (ASCORE‐C)

Luo, Hai; Teoh, Leok-Kheng Kristine; Gaudino, Mario; Fremes, Stephen E.; Kofidis, Theo

doi:10.1111/jocs.14836

Cited by 7 publications

(9 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, several studies have reported that these scores have limitations in some surgeries or patient subgroups ( 11 – 13 ). Recently, a growing number of studies have focused on mid-term or long-term mortality after cardiac surgery ( 32 – 36 ). For example, Wu et al ( 37 ) created a risk score predicting long-term mortality following isolated CABG surgery with the C-statistics ranging from 0.768 to 0.783 for mortality at 1, 3, 5, and 7 years of follow-up.…”

Section: Discussionmentioning

confidence: 99%

Machine Learning Methods for Predicting Long-Term Mortality in Patients After Cardiac Surgery

Peng²,

Zhang³

et al. 2022

Front. Cardiovasc. Med.

View full text Add to dashboard Cite

Objective:This study aims to construct and validate several machine learning (ML) algorithms to predict long-term mortality and identify risk factors in unselected patients post-cardiac surgery.MethodsThe Medical Information Mart for Intensive Care (MIMIC-III) database was used to perform a retrospective administrative database study. Candidate predictors consisted of the demographics, comorbidity, vital signs, laboratory test results, scoring systems, and treatment information on the first day of ICU admission. Four-year mortality was set as the study outcome. We used the ML methods of logistic regression (LR), artificial neural network (NNET), naïve bayes (NB), gradient boosting machine (GBM), adapting boosting (Ada), random forest (RF), bagged trees (BT), and eXtreme Gradient Boosting (XGB). The prognostic capacity and clinical utility of these ML models were compared using the area under the receiver operating characteristic curves (AUC), calibration curves, and decision curve analysis (DCA).ResultsOf 7,368 patients in MIMIC-III included in the final cohort, a total of 1,337 (18.15%) patients died during a 4-year follow-up. Among 65 variables extracted from the database, a total of 25 predictors were selected using recursive feature elimination and included in the subsequent analysis. The Ada model performed best among eight models in both discriminatory ability with the highest AUC of 0.801 and goodness of fit (visualized by calibration curve). Moreover, the DCA shows that the net benefit of the RF, Ada, and BT models surpassed that of other ML models for almost all threshold probability values. Additionally, through the Ada technique, we determined that red blood cell distribution width (RDW), blood urea nitrogen (BUN), SAPS II, anion gap (AG), age, urine output, chloride, creatinine, congestive heart failure, and SOFA were the Top 10 predictors in the feature importance rankings.ConclusionsThe Ada model performs best in predicting 4-year mortality after cardiac surgery among the eight ML models, which might have significant application in the development of early warning systems for patients following operations.

show abstract

Section: Discussionmentioning

confidence: 99%

Machine Learning Methods for Predicting Long-Term Mortality in Patients After Cardiac Surgery

Peng²,

Zhang³

et al. 2022

Front. Cardiovasc. Med.

View full text Add to dashboard Cite

show abstract

“…11,20 Other studies in Asia have the same consideration, seeing the lack of representation of Asian races in the development of EuroSCORE II. [21][22][23] Although both were conducted in Indonesia, the multicenter study by Kurniawaty, et al (2022) found that EuroSCORE II had poor calibration for the Indonesian population, whereas Sembiring, et al (2021) found otherwise. 19,20 Due to the limited research related to the validation of EuroSCORE II in Indonesia, it is certainly not possible to conclude whether or not this scoring system is suitable to be applied in Indonesia.…”

Section: Discussionmentioning

confidence: 99%

“…Singapore and China have even proposed separate scoring systems for Asian populations, such as the Asian System for Cardiac Operative Risk Evaluation (ASCORE-C) and the Sino System for Coronary Operative Risk Evaluation (SinoSCORE), based on the characteristics of their countries. 21,22 Thus, they have better discrimination and calibration abilities than EuroSCORE II. 21,22 In addition, a study in France assessed that EuroSCORE II significantly underestimated the mortality rate of elderly patients undergoing cardiac surgery.…”

Section: Discussionmentioning

confidence: 99%

“…21,22 Thus, they have better discrimination and calibration abilities than EuroSCORE II. 21,22 In addition, a study in France assessed that EuroSCORE II significantly underestimated the mortality rate of elderly patients undergoing cardiac surgery. 24 This study also found that the death of elderly patients who underwent CABG in this study was mostly caused by septic shock (53.3%).…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Success Rate of Coronary Artery Bypass Grafting on Elderly Patients in Dr. Soetomo General Academic Hospital, Surabaya

Tombokan,

Sembiring,

Dharmadjati

et al. 2024

JUXTA

View full text Add to dashboard Cite

Highlights: CABG is the most performed cardiac surgery in Indonesia, and most patients undergoing this surgery are above 60 years old. CABG success rate is not significantly influenced solely by the patient’s age but also by several perioperative characteristics such as gender, comorbidities, and other variables included in the calculation of EuroSCORE II. Abstract Introduction: Coronary artery disease (CAD) causes more than a quarter of deaths in Indonesia and is found to be more prevalent in the elderly (≥60 years old). Treatment includes coronary artery bypass grafting (CABG), the most-performed cardiac surgery in Indonesia. This study aimed to determine the short-term and one-year postoperative success, morbidity, and mortality rates with their causes in Dr. Soetomo General Academic Hospital, Surabaya. Methods: This was a cross-sectional retrospective study using secondary data obtained from 85 medical records of CABG patients aged ≥60 years old in the Department of Thoracic, Cardiac, and Vascular Surgery, Dr. Soetomo General Academic Hospital, Surabaya, from January 2018 to December 2020. Aside from descriptive statistics, logistic regression was conducted to assess the relationship between EuroSCORE II and the success of CABG in elderly patients. Results: Patients were mostly male in their sixties with a mean of 65.5 ± 4.9 years old, had three-vessel disease, and had a predicted mortality rate of 1.6%. The average number of grafts used was 3.3 ± 0.7, and the average length of hospital stay was 7.4 ± 2.4 days. The morbidity rate was 71.8%, with bleeding as the most common complication, a 17.6% mortality rate with septic shock as the most frequent cause, and a success rate of 82.4% (short-term) and 80% (one-year postoperative). Higher EuroSCORE II was found to significantly decrease the probability of both short-term and one-year postoperative success. Conclusion: The success rates of CABG in Dr. Soetomo General Academic Hospital, Surabaya, were 82.4% (short-term) and 80% (one-year postoperative), negatively correlated with EuroSCORE II.

show abstract

“…There's been a lot of research similar to heart disease prediction with different data learning approaches are specified (Senouci et al 2021). The paper focuses on the accuracy of evaluating Heart Disease Prediction in each of the 50 states using Classification Function Algorithms (CFA) and Long Short-Term Memory (LSTM), two different forecasting techniques developed and used to predict the accurate prediction of heart diseases (Luo et al 2020). The accurate prediction of the algorithm is used to get better accuracy.…”

Section: Introductionmentioning

confidence: 99%

Heart Disease Prediction Based on Age Detection using Novel Logistic Regression over Decision Tree

Karthi¹,

Kalaivani²

2023

View full text Add to dashboard Cite

Aim: To improve the accuracy in Heart Disease Prediction using Novel Logistic Regression and Decision tree Materials and Methods: This study contains 2 groups i.e Novel Logistic Regression and Decision tree Each group consists of a sample size of 10 and the study parameters include alpha value 0.01, beta value 0.2, and the Gpower value 0.8. Results: The Novel Logistic Regression (91.60) achieved improved accuracy than the Decision Tree (89.42) in Heart Disease Prediction. The statistical significance difference is 0.01 (p<0.05). Conclusion: The Novel Logistic Regression model is significantly better than the Decision Tree in Heart Disease Prediction. It can be also considered as a better option for Heart Disease Prediction.

show abstract

The Asian system for cardiac operative risk evaluation for predicting mortality after isolated coronary artery bypass graft surgery (ASCORE‐C)

Cited by 7 publications

References 25 publications

Machine Learning Methods for Predicting Long-Term Mortality in Patients After Cardiac Surgery

Machine Learning Methods for Predicting Long-Term Mortality in Patients After Cardiac Surgery

Success Rate of Coronary Artery Bypass Grafting on Elderly Patients in Dr. Soetomo General Academic Hospital, Surabaya

Heart Disease Prediction Based on Age Detection using Novel Logistic Regression over Decision Tree

Contact Info

Product

Resources

About