BLSF: Adaptive Learning for Small-Sample Medical Data With Broad Learning System Forest Integration

Abstract

The Broad Learning System Forest (BLSF) model proved to be the preeminent classifier across all assessed datasets, demonstrating outstanding performance and efficiency. In the dataset, BLSF attained an accuracy of 94.53%, markedly exceeding standard BLS at 84.32%, Fuzzy BLS at 79.88%, and Intuitionistic Fuzzy BLS, which obtained just 15.55%. BLSF’s efficacy is exemplified by its recall of 0.9452, accuracy of 0.9524, and F1-Score of 0.9481, emphasizing its ability to accurately categorize both positive and negative samples. Despite Tree BLS demonstrating a superior accuracy of 97.19%, its substantial memory use (789,862 MB) constrains its usability. In the Breast cancer dataset, BLSF attained a notable accuracy of 98.24%, trailing only Tree BLS at 98.75%, and markedly surpassing BLS (94.95%) and Fuzzy BLS (78.68%). The AUC-ROC score of BLSF at 0.9817 further substantiates its exceptional categorization capability. Although Incremental Weighted Ensemble BLS achieved a commendable performance of 98.57%, BLSF exhibited enhanced memory efficiency and a somewhat improved F1-Score of 0.9827. The Cardiovascular disease dataset revealed that BLSF achieved an accuracy of 76.61%, surpassing BLS at 71.38% and Fuzzy BLS at 53.23%. Although Tree BLS attained a superior accuracy of 91.75%, its considerable memory demands made BLSF the more efficient option. Incremental Weighted Ensemble BLS exhibited enhanced accuracy (81.99%) but required greater memory utilization. In imbalanced datasets such as PIDD (73.60%), Kidney failure (100%), and Heart disease (91.12%), BLSF consistently surpassed Fuzzy BLS and Intuitionistic Fuzzy BLS. It got a flawless score on the Kidney failure dataset, demonstrating its proficiency in managing difficult classifications with exceptional accuracy. BLSF excelled in accuracy, precision, recall, and efficiency across many datasets. In conclusion, the Broad Learning System Forest (BLSF) is a pioneering model that excels in accuracy and efficiency while exhibiting exceptional adaptability to complex and imbalanced datasets, marking a significant advancement in medical data classification.

Keywords

• Broad learning system forest
• feature mapping
• adaptive learning
• medical data classification
• small-sample classification
• enhanced predictive modeling