Background: Machine learning can be used to predict the different onset of human cancers. Highly dimensional data have enormous, complicated problems. One of these is an excessive number of genes plus over-fitting, fitting time, and classification accuracy. Recursive Feature Elimination (RFE) is a wrapper method for selecting the best subset of features that cause the best accuracy. Despite the high performance of RFE, time computation and over-fitting are two disadvantages of this algorithm. Random forest for selection (RFS) proves its effectiveness in selecting the effective features and improving the over-fitting problem. Method: This paper proposed a method, namely, positions first bootstrap step (PFBS) random forest selection recursive feature elimination (RFS-RFE) and its abbreviation is PFBS- RFS-RFE to enhance cancer classification performance. It used a bootstrap with many positions included in the outer first bootstrap step (OFBS), inner first bootstrap step (IFBS), and outer/ inner first bootstrap step (O/IFBS). In the first position, OFBS is applied as a resampling method (bootstrap) with replacement before selection step. The RFS is applied with bootstrap = false i.e., the whole datasets are used to build each tree. The importance features are hybrid with RFE to select the most relevant subset of features. In the second position, IFBS is applied as a resampling method (bootstrap) with replacement during applied RFS. The importance features are hybrid with RFE. In the third position, O/IFBS is applied as a hybrid of first and second positions. RFE used logistic regression (LR) as an estimator. The proposed methods are incorporated with four classifiers to solve the feature selection problems and modify the performance of RFE, in which five datasets with different size are used to assess the performance of the PFBS-RFS-RFE. Results: The results showed that the O/IFBS-RFS-RFE achieved the best performance compared with previous work and enhanced the accuracy, variance and ROC area for RNA gene and dermatology erythemato-squamous diseases datasets to become 99.994%, 0.0000004, 1.000 and 100.000%, 0.0 and 1.000, respectively. Conclusion: High dimensional datasets and RFE algorithm face many troubles in cancers classification performance. PFBS-RFS-RFE is proposed to fix these troubles with different positions. The importance features which extracted from RFS are used with RFE to obtain the effective features.

Machine learning (ML) has been increasingly used in disease prediction, leveraging both phenotype and genotype data. However, genotype data have received comparatively less attention due to limited availability, whereas phenotype data have been more extensively studied. While breast cancer research is abundant, studies on other cancers, such as bladder cancer, and neurological diseases like Parkinson’s disease, remain limited. High-dimensional datasets pose challenges, including lengthy processing times, overfitting, an excess of features, and difficulties in classification. This study introduces a framework that integrates phenotype and genotype data for cancer prediction, aiming for high accuracy with a minimal number of relevant features. The framework consists of three main procedures: feature selection (FS), cancer prediction (CP), and identification of cancer-associated genes/features (CAG/F). FS employs a hybrid LEDF approach, combining the empirical distribution function (EDF) with three embedded methods: lasso regression selection (LRS), ridge regression selection (RRS), and random forest selection (RFS). EDF acts as a resampling tool with external (EEDF) and internal (IEDF) components that merge as E/IEDF. Features are selected based on classification accuracy using both union and intersection methods. CP applies multiple ML models with cross-validation to enhance prediction accuracy. Lastly, CAG/F identifies cancer-associated genes/features following the FS and CP steps. The algorithms E/IEDF-RFS, E/IEDF-LRS, and E/IEDF-RRS demonstrated excellent performance for RNA gene and dermatology datasets, achieving 100\% accuracy. E/IEDF-RFS reached 94.58\% accuracy for Parkinson’s Disease2, while EEDF-LRS performed best for DNA data with 94.85\% accuracy. E/IEDF-RRS showed 96.43\% accuracy for Parkinson’s Disease1 using RF classifiers, and IED-RFS and E/IEDF-LRS achieved 98.42\% accuracy for the BreastEw dataset.