Abstract:
Pediatric neuroblastoma is deadly. Treatment plans depend on neuroblastoma survival prediction. We proposed a heterogeneous ensemble learning method to predict neuroblastoma patient survival and extracted decision rules to help doctors make decisions. Five heterogeneous base learners—decision tree, random forest, genetic algorithm-based support vector machine, extreme gradient boosting, and light gradient boosting—were created after data preprocessing. After that, a heterogeneous feature selection method was used to find the optimal feature subset of each base learner, which guided their construction as a priori knowledge. An area under curve-based ensemble mechanism was suggested to integrate the five heterogeneous base learners. Finally, the proposed method was compared to mainstream machine learning methods from different indicators, and the partial dependency plot analysis and rule-extracted methods from the proposed method extracted valuable information. The proposed method achieves 91.64% accuracy, 91.14% recall, and 91.35% AUC, outperforming mainstream machine learning methods. The proposed method also extracts interpretable rules with accuracy above 0.900 and predicted responses. Our study can improve neuroblastoma patient survival by improving the clinical decision support system.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
