Effective Handling of Missing Values in Datasets for Classification Using Machine Learning Methods

Abstract

The existence of missing values reduces the amount of knowledge learned by the machine learning models in the training stage thus affecting the classification accuracy negatively. To address this challenge, we introduce the use of Support Vector Machine (SVM) regression for imputing the missing values. Additionally, we propose a two-level classification process to reduce the number of false classifications. Our evaluation of the proposed method was conducted using the PIMA Indian dataset for diabetes classification. We compared the performance of five different machine learning models: Naive Bayes (NB), Support Vector Machine (SVM), k-Nearest Neighbours (KNN), Random Forest (RF), and Linear Regression (LR). The results of our experiments show that the SVM classifier achieved the highest accuracy of 94.89%. The RF classifier had the highest precision (98.80%) and the SVM classifier had the highest recall (85.48%). The NB model had the highest F1-Score (95.59%). Our proposed method provides a promising solution for detecting diabetes at an early stage by addressing the issue of missing values in the dataset. Our results show that the use of SVM regression and a two-level classification process can notably improve the performance of machine learning models for diabetes classification. This work provides a valuable contribution to the field of diabetes research and highlights the importance of addressing missing values in machine learning applications.

Prediction of diabetes disease using an ensemble of machine learning multi-classifier models

“…( 1 ) and ( 2 ), convert the values of these attributes to the numerical values. Handling Missing or Null Values Missing or null values are values that may lead to incorrect predictions or inference for each class in the classification [ 29 , 30 ], so here, a little number of attribute values were completing (missing values) with the consultation of a doctor specializing in endocrinology and metabolism using the k-NN Imputation method. The result of this process is shown in Fig.…”

Imputation Validation Mean Squared Error: a novel measurement to evaluate the performance of missing value imputation

“…No explicit solution exists to minimize (4); an iterative algorithm Expectation Maximization-PCA (EM-PCA) 25 is proposed to solve it. The EM-PCA algorithm is also called iterative PCA, and the missing values are generated as a fixed structure having a low-rank representation in 𝑆 dimensions corrupted by noise as (5).…”

“…Although there are now larger, more complex diabetes datasets, the Pima Indian Diabetes dataset has remained a benchmark for diabetes classification research. As the Pima Indian Diabetes dataset is challenging to classify due to its missing values, much research has been done on the Pima Indian Diabetes dataset missing values imputation to improve the classification accuracy, such as using the fuzzy feature selection method 4 , Support Vector Machine (SVM) method 5 , and tree-based method to impute the missing values 6 . In this literature, we compared four machine learning missing value imputation models (Clustering, K Nearest Neighbors, Markov Chain Monte Carlo, and Principal Component Analysis) to find the lowest imputation test-validation mean square error with its optimal tuning parameter in the Pima Indian Diabetes dataset.…”

Simplifying Data Analysis in Biomedical Research: An Automated, User-Friendly Tool

“…Properly addressing missing data ensures the robustness and validity of research findings, enabling accurate interpretation and generalization of results. Techniques to manage missing values range from simple imputation to more complex statistical models, each carrying different implications for the integrity of the dataset and the reliability of subsequent findings [ 6 , 7 , 8 ].…”