Recent advancements in cancer diagnosis using machine learning techniques - a systematic review of decades of research, comparisons, and problems

Aug 4, 2026

Upload by Maeve

Cancer is a non-communicable disease driven by uncontrolled cell growth, forming malignant tumors that undermine immune function and disrupt biological processes. Breast, lung, and cervical cancers can be screened at multiple stages, yet misdiagnosis from human error or data misinterpretation threatens outcomes. The study proposes an AI-supported machine learning framework using feature selection and classification on UCI repository datasets, comparing methods and feature-selection strategies with 10-fold cross-validation.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages11

Reading Time28 min

AccessFree to download

Introduction

Motivation and problem statement

Role of machine learning in cancer prediction

Review scope and proposed approach

Data sources and experimental design

Feature selection and classification methods

Methods and evaluation

Machine learning models considered

Feature selection strategies

Metrics and validation setup

Results overview

Reported accuracies across cancer types

Discussion and implications

Patterns extraction and limitations

ADBU-Journal of Engineering Technology Recent advancements in cancer diagnosis using machine learning techniques: a systematic review of decades of research, comparisons, and problems Prithwish Raymahapatra 1, Dr. Avijit Kumar Chaudhuri 2 1 UG -Computer Science and Engineering, Techno Engineering College Banipur, Habra, Kolkata Email: [prithsray@gmail.com](prithsray@gmail.com) 2 Associate Professor, Computer Science and Engineering, Brainware University, Barasat, Kolkata Email: [c.avijit@gmail.com](c.avijit@gmail.com) Abstract: Cancer is a non-communicable disease that spreads throughout the body through uncontrolled cell growth. The malignant cell grows into a tumor, which weakens the immune system and disrupts other biological processes. The most frequent types of cancer are breast, lung, and cervical cancer. Several screening methods are available to detect the presence of cancer at various stages. Misdiagnosis can occur in some circumstances owing to human mistakes or incorrect data interpretation, resulting in the loss of human lives. To address these issues, this research study proposes an effective machine learning-based review and diagnosis technique backed by intelligence learning models. Artificial intelligence-based feature selection and classification techniques are used to detect cancer atan earlier stage, improve prediction accuracy, and save lives. In this research study, breast, cervical, and lung cancer datasets from the University of California, Irvine repository was used in these experimental investigations. To train and validate the optimal features minimized by the proposed system, the authors used supervised machine learning approaches. There could be numerous features that may contribute to the occurrence of cancer, it is difficult to pinpoint the specific environmental and other diagnostic features that contribute to it, but it still plays a role in determining cancer occurrence. We can achieve our goal of estimating the probability of cancer occurrences by using machine learning algorithms and frequent diagnostic data. Cancer data sets contain a variety of patient information features, but not all of them are useful in cancer prognosis. In such cases, a feature selection approach plays a crucial role in identifying the relevant feature set. In this research, we compare the effects of feature selection approaches on the accuracy provided by existing machine learning algorithms. We investigated the following machine learning methods for this purpose: Logistic Regression(LR), Naive Bayes(NB), Random Forest(RF), Hoeffding Tree(HT), and Multi-Layer Perceptron(MLP). Information Gain(IF), Gain Ratio(GR), Relief-F(R-F), and One R(OR) were all evaluated as feature selection strategies.The training and performance models are validated using various accuracy matrices such as accuracy, sensitivity, specificity, f-measure, kappa score, and area under the ROC curve(AUC) using the 10-fold cross-validation approach. The accuracy of the proposed framework was 100%, 100%, and 91.30% on breast, cervical, and lung cancer datasets, respectively. Furthermore, this approach may serve as a versatile tool for extractingpatternsfrom several clinicaltrialsfor variousforms of cancer conditions. Keywords: Breast Cancer, Cervical Cancer, Lung Cancer, Data Mining, Machine Learning, Random Forest (Article history: Received: 20th October 2023 and accepted 16th July 2024) I. INTRODUCTION Cancer is a major cause of death that is frequently caused by the accumulation of hereditary disorders and a variety of pathological alterations. Cancerous cells are abnormal growths that can develop in any part of the human body and are potentially fatal. Cancer, also known as malignancy, must be detected early and accurately to determine what treatments may be effective. Even though each modality has its own sets of problem, the most common causes of mortality are convoluted historie

FAQs

What problem does the study address in cancer diagnosis?

The study targets inaccurate cancer detection caused by human mistakes or incorrect data interpretation, which can lead to severe clinical consequences. It aims to improve early-stage detection and prediction accuracy.

Which datasets and cancer types are used in the experiments?

Experiments use breast, cervical, and lung cancer datasets from the University of California, Irvine repository. These datasets support training and validation of the proposed framework.

How are feature selection and machine learning models evaluated?

The work compares multiple feature selection strategies and machine learning classifiers (e.g., Logistic Regression, Naive Bayes, Random Forest, Hoeffding Tree, and Multi-Layer Perceptron). Performance is measured using accuracy-related metrics with 10-fold cross-validation.

Aug 4, 2026

Upload by Maeve