A nomogram for predicting CRT response based on multi-parameter features
Yuxuan Lou1,2, Yang Hua2, Jiaming Yang2
1Southeast University, Nanjing, 210009, Jiangsu, China.
Insights
This study developed a nomogram to predict cardiac resynchronization therapy (CRT) response in heart failure patients. The tool accurately identifies patients likely to benefit from CRT, aiding treatment decisions.
Area of Science:
- Cardiology
- Medical Imaging
- Biostatistics
Background:
- Chronic heart failure (CHF) poses a significant health burden.
- Cardiac resynchronization therapy (CRT) is a treatment option for select CHF patients.
- Predicting CRT responsiveness is crucial for optimizing patient outcomes.
Purpose of the Study:
- To develop and validate a nomogram for predicting CRT responsiveness in CHF patients.
- To identify key factors influencing CRT response.
Main Methods:
- Retrospective analysis of 109 CHF patients who received CRT.
- Utilized LASSO and multivariate logistic regression to identify predictive factors.
- Constructed a nomogram and evaluated its performance using ROC, calibration curves, and DCA.
Main Results:
- The nomogram incorporated left ventricular end-systolic volume, diffuse fibrosis, and left bundle branch block (LBBB).
- Achieved an AUC of 0.865, indicating high predictive accuracy.
- Demonstrated good calibration and excellent clinical net benefit.
Conclusions:
- The developed nomogram effectively predicts CRT responsiveness in CHF patients.
- The tool offers high discrimination and calibration for clinical application.
- This nomogram can aid clinicians in patient selection for CRT.
Objective:
To construct a nomogram for predicting the responsiveness of cardiac resynchronization therapy (CRT) in patients with chronic heart failure and verify its predictive efficacy.
Method:
A retrospective study was conducted including 109 patients with chronic heart failure who successfully received CRT from January 2018 to December 2022. According to patients after six months of the CRT preoperative improving acuity in the left ventricular ejection fraction is 5% or at least improve grade 1 NYHA heart function classification, divided into responsive group and non-responsive group. Clinical data of patients were collected, and LASSO regression analysis and multivariate logistic regression analysis were used to explore relative factors. A nomogram was constructed, and the predictive performance of the nomogram was evaluated using the calibration curve and decision curve analysis (DCA).
Results:
Among the 109 patients, 61 were assigned to the CRT-responsive group, while 48 were assigned to the non-responsive group. LASSO regression analysis showed that left ventricular end-systolic volume, diffuse fibrosis, and left bundle branch block (LBBB) were independent factors for CRT responsiveness in patients with heart failure (P < 0.05). Based on the above three predictive factors, a nomogram was constructed. The ROC curve analysis showed that the area under the curve (AUC) was 0.865 (95% CI 0.794-0.935). The calibration curve analysis showed that the predicted probability of the nomogram is consistent with the actual occurrence rate. DCA showed that the line graph model has an excellent clinical net benefit rate.
Conclusion:
The nomogram constructed based on clinical features, laboratory, and imaging examinations in this study has high discrimination and calibration in predicting CRT responsiveness in patients with chronic heart failure.
Related Concept Videos
01:16Response Surface Methodology
The process of RSM involves several key steps:
01:15Receiver Operating Characteristic Plot