Gaussian Naïve Bayes Algorithm: A Reliable Technique Involved in the Assortment of the Segregation in Cancer

Mobile Information Systems, Journal Year: 2022, Volume and Issue: 2022, P. 1 - 7

Published: June 17, 2022

Cancer is a disease caused by uncontrollable cell growth. The constant subject of concern due to unavailability treatment at severe level. Patients who have suffered from the chance getting saved if this fatal illness identified in beginning stage. survival will be very low it detected final stage cancer. As patients could not survive their last stage, cure disease, an early diagnosis key issue and vital. For classification cancer, Gaussian Naïve Bayes implemented work. By exerting on two datasets, algorithm tested, which Wisconsin Breast Dataset (WBCD) considered as earliest one next Lung Dataset. assessment result suggested attained 90% accuracy prediction lung predicting breast 98%.

Language: Английский

---

A Review of the Recent Advances in Alzheimer’s Disease Research and the Utilization of Network Biology Approaches for Prioritizing Diagnostics and Therapeutics

Diagnostics, Journal Year: 2022, Volume and Issue: 12(12), P. 2975 - 2975

Published: Nov. 28, 2022

Alzheimer’s disease (AD) is a polygenic multifactorial neurodegenerative that, after decades of research and development, still without cure. There are some symptomatic treatments to manage the psychological symptoms but none these drugs can halt progression. Additionally, over last few years, many anti-AD failed in late stages clinical trials hypotheses surfaced explain failures, including lack clear understanding pathways processes. Recently, different epigenetic factors have been implicated AD pathogenesis; thus, they could serve as promising diagnostic biomarkers. network biology approaches suggested effective tools study on systems level discover multi-target-directed ligands novel for AD. Herein, we provide comprehensive review pathophysiology better pathogenesis decipher role genetic development We also an overview biomarkers drug targets suggest new identifying drugs. posit that application machine learning artificial intelligence mining multi-omics data will facilitate biomarker discovery efforts lead individualized anti-Alzheimer treatments.

Language: Английский

---

The role of machine learning in advancing precision medicine with feedback control

Cell Reports Physical Science, Journal Year: 2022, Volume and Issue: 3(11), P. 101149 - 101149

Published: Nov. 1, 2022

The capacity of machine-learning methods to handle large and complex datasets makes them suitable for applications in precision medicine. Current automate data analysis predict physiological outcomes patients with various types clinical inform treatment strategies. In this perspective, we propose ways which machine learning can be leveraged even further advance optimizing patient treatment. Namely, used expand feedback control direct the response biological systems predictably automatically. This paves way highly sophisticated treatments that continuously adapt an individual patient's response. elements improved using include sensor analysis, modeling, reconfiguring algorithm "on fly." We discuss challenges unique analysis/control systems, existing work, areas remain underdeveloped.

Language: Английский

---

Explainable Artificial Intelligence of Multi-Level Stacking Ensemble for Detection of Alzheimer’s Disease Based on Particle Swarm Optimization and the Sub-Scores of Cognitive Biomarkers

IEEE Access, Journal Year: 2023, Volume and Issue: 11, P. 123173 - 123193

Published: Jan. 1, 2023

Alzheimer's disease (AD) is a progressive neurological disorder characterized by memory loss and cognitive decline, affecting millions worldwide. Early detection crucial for effective treatment, as it can slow progression improve quality of life. Machine learning has shown promise in AD using various medical modalities. In this paper, we propose novel multi-level stacking model that combines heterogeneous models modalities to predict different classes AD. The include sub-scores (e.g., clinical dementia rating – sum boxes, assessment scale) from the Disease Neuroimaging Initiative dataset. proposed approach, level 1, used six base (Random Forest (RF), Decision Tree (DT), Support Vector (SVM), Logistic Regression (LR), K-nearest Neighbors (KNN), Native Bayes (NB)to train each modality (ADAS, CDR, FQA). Then, build training outputs set staking testing outcomes set. 2, three are produced trains evaluates based on output 6 (RF, LR, DT, SVM, KNN, NB) combined Stacking meta-learners evaluate (RF). Finally, 3, prediction FQA) datasets merged new dataset, which testing. Training meta-learner, meta-learner produce final prediction. Our research also aims provide explanations, ensuring efficiency, effectiveness, trust through explainable artificial intelligence (XAI). Feature selection optimization Particle Swarm Optimization select most appropriate sub-scores. shows significant potential improving early diagnosis. results demonstrate multi-modality approach outperforms single-modality approaches. Moreover, achieve highest performance with selected features compared regular ML classifiers full multi-modalities, achieving accuracy, precision, recall, F1-scores 92.08%, 92.07%, 92.01% two classes, 90.03%, 90.19%, 90.05% respectively.

Language: Английский

---

An Approach to Binary Classification of Alzheimer’s Disease Using LSTM

Bioengineering, Journal Year: 2023, Volume and Issue: 10(8), P. 950 - 950

Published: Aug. 9, 2023

In this study, we use LSTM (Long-Short-Term-Memory) networks to evaluate Magnetic Resonance Imaging (MRI) data overcome the shortcomings of conventional Alzheimer's disease (AD) detection techniques. Our method offers greater reliability and accuracy in predicting possibility AD, contrast cognitive testing brain structure analyses. We used an MRI dataset that downloaded from Kaggle source train our network. Utilizing temporal memory characteristics LSTMs, network was created efficiently capture sequential patterns inherent scans. model scored a remarkable AUC 0.97 98.62%. During training process, Stratified Shuffle-Split Cross Validation make sure findings were reliable generalizable. study adds significantly body knowledge by demonstrating potential specific field AD prediction extending variety methods investigated for image classification research. have also designed user-friendly Web-based application help with accessibility developed model, bridging gap between research actual deployment.

Language: Английский

---