An integrated decision support system for heart failure prediction based on feature transformation using grid of stacked autoencoders

Bhat

Computational and Mathematical Methods in Medicine

et al. 2023

The leading cause of death worldwide today is heart disease (HD). The heart is recognised as the second-most significant organ behind the brain. A successful outcome of treatment can be improved by an early diagnosis which can significantly reduce the chance of death in health care. In this paper, we proposed a method to predict heart disease. We used various machine learning algorithms (MLA), namely, logistic regression (LR), k-nearest neighbor (KNN), support vector machine (SVM), Naive Bayes (NB), random forest (RF), and decision tree (DT). With the testing data set, we evaluated the model’s accuracy in heart disease prediction. When compared to the other five models, the random forest and k-nearest neighbor approaches perform better. With a 99.04% accuracy rate, the k-nearest neighbor algorithm and random forest provide the best match to the data as compared to other algorithms. Six feature selection algorithms were used for the performance evaluation matrix. MCC parameters for accuracy, precision, recall, and F measure are used to evaluate models.

Section: Introductionmentioning

confidence: 99%

Performance Evaluation of Machine Learning Techniques (MLT) for Heart Disease Prediction

Bhat

Computational and Mathematical Methods in Medicine

et al. 2023

“…At last, the empirical findings of the designed method have confirmed its effectiveness and also it was utilized to enhance the transmission power and network lifetime. Researchers [ 22 ] have developed the first robust optimization model for routing in BAN over traffic uncertainty and tuning of network topology. It has utilized appropriate linear mitigations to conduct a randomized fixing of the constraints, and also it has been supported by an accurate large variable neighborhood search.…”

Section: Literature Workmentioning

confidence: 99%

“…Researchers [ 22 ] have promoted a more robust technique that fused a grid of stacked autoencoders with deep learning strategies. The recommended stacked autoencoders were utilized to attain the robust set of features and also the neural network was categorized as the recently acquired set of features.…”

Section: Literature Workmentioning

confidence: 99%

Intelligent Bi-LSTM with Architecture Optimization for Heart Disease Prediction in WBAN through Optimal Channel Selection and Feature Selection

Nithiyanantham¹,

Sivaraman²

2023

Biomedicines

Wireless Body Area Network (WBAN) is a trending technology of Wireless Sensor Networks (WSN) to enhance the healthcare system. This system is developed to monitor individuals by observing their physical signals to offer physical activity status as a wearable low-cost system that is considered an unremarkable solution for continuous monitoring of cardiovascular health. Various studies have discussed the uses of WBAN in Personal Health Monitoring systems (PHM) based on real-world health monitoring models. The major goal of WBAN is to offer early and fast analysis of the individuals but it is not able to attain its potential by utilizing conventional expert systems and data mining. Multiple kinds of research are performed in WBAN based on routing, security, energy efficiency, etc. This paper suggests a new heart disease prediction under WBAN. Initially, the standard patient data regarding heart diseases are gathered from benchmark datasets using WBAN. Then, the channel selections for data transmission are carried out through the Improved Dingo Optimizer (IDOX) algorithm using a multi-objective function. Through the selected channel, the data are transmitted for the deep feature extraction process using One Dimensional-Convolutional Neural Networks (ID-CNN) and Autoencoder. Then, the optimal feature selections are done through the IDOX algorithm for getting more suitable features. Finally, the IDOX-based heart disease prediction is done by Modified Bidirectional Long Short-Term Memory (M-BiLSTM), where the hyperparameters of BiLSTM are tuned using the IDOX algorithm. Thus, the empirical outcomes of the given offered method show that it accurately categorizes a patient’s health status founded on abnormal vital signs that is useful for providing the proper medical care to the patients.

“…However, the improvement in accuracy on test data is not followed by training data. This study proposes a more robust approach that integrates stacked autoencoder grids with neural network models to address the problem [46]. Most feature engineering in the input space relies on manually defined transformation functions.…”

Section: A Feature Transformation Techniquementioning

confidence: 99%

Separability-based Quadratic Feature Transformation to Improve Classification Performance

Sudibyo,

Rustad,

Andono

et al. 2023

IJACSA

Feature transformation is an essential part of data preprocessing to improve the predictive performance of machine learning (ML) algorithms. Box-Cox transformation with the goal of separability is proven to align with the performance improvement of ML algorithms. However, the features mapped using Box-Cox transformation preserve the order of the data, so it is ineffective when used to improve the separability of multimodal distributed features. This research aims to build a feature transformation method using quadratic functions to improve class separability that can adaptively change the order of the data when necessary. Fisher score (Fs) measures the separability level by maximizing the Fisher's Criteria of the quadratic function. In addition to increasing the Fs value of each feature, this method can also make the feature more informative, as evidenced by the increasing value of information gain, information gain ratio, Gini decrease, ANOVA, Chi-Square, reliefF, and FCBF. The increase in Fs is particularly significant for bimodally distributed features. Experiments were conducted on 11 public datasets with two statistical-based machine learning algorithms representing linear and nonlinear ML algorithms to validate the success of this method, namely LDA and QDA. The experimental results show an improvement in accuracy in almost all datasets and ML algorithms, where the highest accuracy improvement is 0.268 for LDA and 0.188 for QDA.