Early Detection and Diagnosis of Chronic Kidney and Breast Cancer Using Multi-level Machine Learning - A Hybrid Prediction Model

Aug 3, 2026

Upload by Logic

A multilevel machine learning framework is developed for early detection and diagnosis of chronic kidney disease (CKD) and breast cancer. The hybrid prediction model combines supervised and unsupervised techniques, leveraging Long Short-Term Memory (LSTM) and random forest algorithms, alongside a feature selection stage to retain the most informative attributes. Model performance is tested on a patient information dataset and benchmarked against other machine learning approaches and traditional diagnostic methods. Results indicate superior accuracy, sensitivity, and specificity for both conditions, supporting potential clinical use to improve patient outcomes and reduce diagnostic burden.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages6

Reading Time15 min

AccessFree to download

Introduction

Research context and motivation

Limitations of existing models

Research Methodology

Hybrid predictive model design

Feature extraction and selection

Proposed Model for Breast Cancer Prediction

Model structure and layers

Early Detection and Diagnosis of Chronic Kidney and Breast Cancer Using Multi-level Machine Learning: A Hybrid Prediction Model Sun Hujuna*, Ang Ling Weayb a,bMalaysia University of Science and Technology, Petaling Jaya, Malaysia aEmail: [sun.hujun@phd.must.edu.my](sun.hujun@phd.must.edu.my), [b](bEmail: dr.ang@must.edu.my)[Email: dr.ang@must.edu.my](bEmail: dr.ang@must.edu.my) Abstract In this study, a multilevel machine learning approach is proposed for the early detection and diagnosis of chronic kidney disease (CKD) and breast cancer. The proposed hybrid prediction model uses a combination of supervised and unsupervised machine learning techniques, including Long Short-Term Memory (LSTM) and random forest algorithms, to improve the early detection and diagnosis of these diseases. The model also includes a feature selection process to extract the most relevant features from the data. The performance of the proposed model was evaluated on a dataset of patient information and compared with other machine learning models and traditional diagnostic methods. The results show that the proposed model outperforms traditional diagnostic methods and other machine learning models in terms of accuracy, sensitivity, and specificity in the early detection and diagnosis of CKD and breast cancer. The proposed multilevel machine learning approach provides an effective way to improve the early detection and diagnosis of CKD and breast cancer and has the potential to be used in clinical practice to improve patient outcomes. Keywords: Chronic kidney disease (CKD); Breast cancer; Multi-level machine learning; Hybrid prediction model; Early detection and diagnosis) . * Corresponding author. 1. Introduction Cancer is one of the leading causes of death worldwide, and early detection and diagnosis are critical to improving treatment outcomes. Chronic kidney disease (CKD) and breast cancer are two of the most common cancers, and early detection can significantly improve treatment options and outcomes. Machine learning has the potential to improve early detection and diagnosis of these diseases by analyzing large amounts of data and identifying patterns that may not be apparent to the human eye. In this study, we propose a multilevel machine learning approach that combines different machine learning techniques to improve the early detection and diagnosis of CKD and breast cancer. Previous research has made significant progress in chronic disease prediction and classification, but there are still areas that require further attention [1] . One of the main weaknesses of current models is their limited scope, often focusing on a single disease and not properly extracting relevant features, resulting in lower prediction accuracy [2] . In addition, models based on deep learning and neural networks tend to overfit and underfit [3] . These limitations can be addressed by adjusting the training data (citation needed) . In this study, we applied Long Short-Term Memory (LSTM) and Random Forest algorithms to predict several chronic diseases. Our main contribution is to improve the prediction accuracy by including a feature extraction module [4] . This improved prediction accuracy not only shortens the diagnosis time for physicians, allowing them to treat more patients, but also reduces the burden on hospital resources [5] . 2. Research Methodology Our proposed hybrid predictive model uses a combination of supervised and unsupervised machine learning techniques. The model first uses unsupervised learning to extract features from the data, such as demographic information and laboratory results. These features then serve as inputs to a supervised learning algorithm, such as a support vector machine or random forest, to predict the probability of CKD or breast cancer. The model also includes a level of feature selection, where the most relevant features are selected for use in the prediction algorithms. The prediction of breast cancer and ch

FAQs

What diseases does the proposed multilevel model target?

The study targets chronic kidney disease (CKD) and breast cancer, aiming to support early detection and diagnosis for both conditions.

Which machine learning techniques are used in the hybrid prediction model?

The model combines unsupervised feature extraction with supervised prediction, using Long Short-Term Memory (LSTM) and random forest algorithms, along with a feature selection process.

How is the model evaluated and what performance improvements are reported?

The approach is evaluated on a dataset of patient information and compared with other machine learning models and traditional diagnostic methods, showing higher accuracy, sensitivity, and specificity for early detection and diagnosis.

Aug 3, 2026

Upload by Logic