A recent study showed that machine learning algorithms are trained to diagnose the disease in accurate manner. The stroke prediction of people based on various features is identified effectively using machine learning models. The main objective of this work is to use an optimized model for breast cancer and stroke prediction in patients. Two different datasets are collected and their results were obtained. In the first phase, the square static method is applied to find the correlation among the features and this enhances the dimensionality reduction in the dataset. In the second phase, Deep Hyper Optimization and Genetic Meta-Learning Model (DHO-GML) are applied to perform the classification efficiently by selecting the optimized model. The performance of the proposed work is compared with the models such as Logistic Regression (LR), XGBClassifier, Support Vector Machine (SVM), K Nearest Neighbors (KNN), Bernouli NB and Ada Boost classifier. As shown in the analysis the proposed model produces an accuracy above 99% with the metrics precision, recall, F1 score, Area under Curve (AUC) and elapsed time.
The machine learning techniques can be used for clinical investigations in breast cancer diagnosis. The researchers investigated various machine learning algorithms, such as Support Vector Machine, Naïve Bayes, Logistic Regression (LR), Random Forest, Decision Tree and K Nearest Neighbor to diagnose the disease. Early detection of breast cancer cells from the features is essential. Feature selection is the process of reducing the input features to improve the performance of the model. This research aims to increase the accuracy, sensitivity, specificity and to reduce the False Positive Rate (FPR) and False Negative Rate (FNR) by feature selection. The proposed feature selection technique is comprised of two phases: feature grouping and feature selection. In the first phase, feature grouping uses the Pearson correlation techniques to identify the correlation among the features and group the features based on high-, medium- and low- level ranking. In the second phase, Triplet Feature Selection (TFS) method has been proposed to avoid collinearity among the features. In this, the features are selected based on the correlation differences in each subset when satisfying the race condition. Finally, select the features in the triplet group and apply LR classification technique to diagnose the disease. The proposed classifier achieved an accuracy (95.4%), FPR (1%), FNR (4%), sensitivity (97%) and specificity (96%) to detect the benign and malign ones. The effects of TFS feature selection with LR classifier were used and the performance of the proposed framework was compared with the existing feature selection methods and classifiers.
9 December 2023 in Signal, Image and Video Processing
Disease classification using Artificial Intelligence (AI) is one of the emerging areas for medical professionals to diagnose the disease. Thyroid is a common disease which is faced by most of the people that produce severe health problems. As a second opinion to medical professionals, various classification models are used such as Logistic Regression, Decision Tree, Random Forest, K Nearest Neighbor and gradient boosting algorithms.An Artificial Neural Network (ANN) is a part of AI mainly used to identify the nonlinear relationship among the features for better prediction. However, there are some common problems like under fitting and overfitting that occur during the analysis and prediction. The present study suggests the Deep Hyper Optimization (DHO) - Genetic Meta Learning (GML) technique to increase the accuracy and reduce the elapsed time of execution without overfitting. In the first phase, DHO is used to fine tune the weight, bias and identify the optimal number of parameters in the hidden layer using DHO. The performance of various algorithms are observed and compared with Deep Hyper Optimization (DHO) technique. It chooses the best parameter for classification based on the highest probability of particular value in the parameters after performing the divide and conquer approach. In the second phase, GML technique is used to identify the optimal model for classification. It uses the crossover to select the best model and generate offspring population. The performance of each method is observed based on the accuracy, elapsed time, precision, recall, and F1 score, FPR, FNR, TNR and Area under Curve (AUC).
15 September 2026 in Journal of Membrane Computing
Early detection of cardiovascular diseases (CVD) is critical for improving patient outcomes and preventing severe cardiac complications. However, traditional heart sound classification methods often suffer from limitations such as low accuracy, inefficient signal processing, and high computational cost. These shortcomings hinder the timely and accurate diagnosis of CVD. To address these challenges, a novel two-phase evaluation framework is proposed. In the first phase, a strong method for breaking down and identifying features is created by combining Dolphin Echolocation Optimization (DEO) with the Onset technique, which is improved using Modified Blackman Windowing (MBW) to reduce unwanted noise in the data. Mel Frequency Cepstral Coefficients (MFCC), DEO, and onset features are jointly utilized to accurately segment heart sounds for each cardiac cycle. In the second phase, a hybrid deep learning architecture combining Separable Convolutional Neural Network and Bidirectional Long Short-Term Memory (SEPCNN-BiLSTM) is proposed to improve classification accuracy and minimize prediction loss. The proposed model demonstrates superior performance over existing approaches, achieving a peak classification accuracy of 94.8% at batch size 32, with a total model training time of 90 s and an inference response time of 140 ms per sample, outperforming all evaluated baseline architectures.