Performance evaluation of linear discriminant analysis and support vector machines to classify cesarean section

Abstract

Currently the hospital is a place that is very vulnerable to the transmission of Covid-19, so giving birth in a hospital is very risky. In addition, the hospital currently only accepts cesarean deliveries, while mothers who can give birth vaginally are recommended to give birth in a midwife because the chances of being exposed to Covid-19 are much lower. In general, this study aims to examine the performance of the LDA-SVM method in predicting whether a prospective mother needs to undergo a C-section or simply give birth normally. The aims of this study are: 1) to determine the best parameters for building the detection model; 2) to determine the best accuracy from the model; 3) to compare the accuracies with the other methods. The data used in this study is the dataset of caesarian section. This data consists of the results of 80 pregnant women following C-section with the most important characteristics of labor problems in the clinical field. Based on the results of the experiments that have been carried out, several parameter values that provide the best results for building the detection model are obtained, namely σ (sigma) –5.9 for 70 % training data, σ=4, –6.1 and ‑6.6 for 80 % training data and σ=4 and 16 for 90 % training data. Besides, the results obtained show that the LDA-SVM method is able to classify the C-section method properly with an accuracy of up to 100 %. This research is also able to surpass the methods in previous studies. The results show that LDA-SVM for this case study generates an accuracy of 100.00 %. This method has great potential to be used by doctors used as an early detection to determine whether a mother needs to go through a C-section or simply give birth vaginally. So that mothers can prevent the transmission of Covid-19 in the hospital

A Clinical Decision Support System (CDSS) for Unbiased Prediction of Caesarean Section Based on Features Extraction and Optimized Classification

“…Table 5 provides a brief description of these ML-based methods which were presented in the past. Our proposed ROSE-PCA-RF model has shown significant improved performance in comparison to the recently proposed method of Abdillah et al [ 35 ] and Rahman et al [ 34 ]. Furthermore, Abdillah et al [ 35 ] had used several data partition schemes for training and testing purposes of their proposed LDA-SVM model.…”

“…Our proposed ROSE-PCA-RF model has shown significant improved performance in comparison to the recently proposed method of Abdillah et al [ 35 ] and Rahman et al [ 34 ]. Furthermore, Abdillah et al [ 35 ] had used several data partition schemes for training and testing purposes of their proposed LDA-SVM model. But for the holdout validation scheme, their proposed LDA-SVM model obtained an accuracy of 70% on testing dataset while 67.86% on training dataset, while our proposed model obtained the accuracy of 96.26% on training data and 97.12% on testing data which means the newly proposed ROSE-PCA-RF model does not suffer from the problem of overfitting as the model has shown better performance on both training and testing data.…”

“…In holdout validation scheme, a dataset is divided into two parts where one part is used for the training purpose, while the rest part is used for testing of ML model. Moreover, Souza et al [ 6 ] and Abdillah et al [ 35 ] had used holdout validation schemes to evaluate their prediction models for CS. They had divided the dataset into two parts where 70% of the data had been used for training purpose of the ML model while 30% data are used for testing the predictive model.…”

“…Moreover, Abdillah et al proposed a novel method using linear discernment analysis (LDA) and SVM for the classification of CS and they had used various evaluation metrics to test the proposed LDA-SVM model. According to experimental results, they had obtained the accuracy of 74.5% using the holdout validation scheme [ 35 ].…”

“…On the other side, if a ML model performs better on a testing dataset but degrades in performance on a training dataset, this is referred to as overfitting. These issues typically arise, when datasets contained a small number of samples and imbalance classes such that Rahman et al [ 34 ] and Abdillah et al [ 35 ] have used in their proposed models. Additionally, feature preprocessing is a critical component of ML models for attaining superior outcomes, but researchers have given little attention to this facet in their suggested ML models for CS prediction in the past.…”