An Optimized HCC Recurrence Prediction Using APO Algorithm Multiple Time Series Clinical Liver Cancer Dataset.

Area of Science:

• Oncology
• Medical Informatics
• Machine Learning

Background:

• Classifying Hepato Cellular Carcinoma (HCC) recurrence post-radiofrequency ablation is crucial for patient management.
• Existing methods face challenges with imbalanced datasets and high computational costs for feature and parameter selection.

Purpose of the Study:

• To develop an efficient and effective method for classifying HCC recurrence and non-recurrence.
• To overcome the class imbalance issue in clinical liver cancer datasets.
• To reduce computation time for feature and classifier parameter selection.

Main Methods:

• A merging algorithm was used to integrate multi-source, multi-temporal clinical data, preserving information with statistical measures.
• An Inverse Random Under Sampling (IRUS) approach was employed to address the class imbalance problem.
• The Artificial Plant Optimization (APO) algorithm was utilized for optimal feature and classifier parameter selection.
• Support Vector Machine (SVM) and Random Forest (RF) classifiers were used for patient classification.

Main Results:

• The proposed IRUS method effectively addresses class imbalance by under-sampling the majority class.
• APO algorithm significantly reduced iterations and computation time for feature and parameter optimization.
• The combined approach demonstrated superior performance in accuracy, specificity, sensitivity, and balanced accuracy compared to existing methods.

Conclusions:

• The proposed method offers an efficient and effective solution for classifying HCC recurrence.
• IRUS combined with APO provides a robust approach for handling imbalanced datasets in medical predictions.
• This technique can improve the accuracy and efficiency of predicting HCC outcomes after radiofrequency ablation.