Early-Stage Detection of Ovarian Cancer Based on Clinical Data Using Machine Learning Approaches

Aug 3, 2026

Upload by Miles

Ovarian cancer remains a lethal cancer type with limited curative drug options, making earlier detection crucial for improving patient life expectancy. This study applies machine learning models together with statistical methods to clinical data from 349 patients, enabling predictive analytics for early diagnosis. Student’s t-test and log fold-change comparisons identify significant blood biomarkers between groups, while Random Forest, SVM, Decision Tree, XGBoost, Logistic Regression, GBM, and LGBM classify benign versus malignant patients. Results highlight key biomarkers and support classification performance up to 91% accuracy.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages16

Reading Time40 min

AccessFree to download

Introduction

Clinical problem and need for early detection

Biomarkers used for differentiating ovarian cancer and benign tumors

Materials and Methods

Statistical analysis for biomarkers

Machine learning models for classification

Results and Discussion

Significant biomarkers identified

Predictive performance for benign vs malignant

Article Early-Stage Detection of Ovarian Cancer Based on Clinical Data Using Machine Learning Approaches Md. Martuza Ahamad 1, Sakifa Aktar 1, Md. Jamal Uddin 1, Tasnia Rahman 2, Salem A. Alyami 3, Samer Al-Ashhab 3, Hanan Fawaz Akhdar 4, AKM Azad 5,6 and Mohammad Ali Moni 7, * Citation: Ahamad, M.M.; Aktar, S.; Uddin, M.J.; Rahman, T.; Alyami, S.A.; Al-Ashhab, S.; Akhdar, H.F.; Azad, A.K.M.; Moni, M.A. Early-Stage Detection of Ovarian Cancer Based on Clinical Data Using Machine Learning Approaches. J. Pers. Med. 2022, 12, 1211. [https://](https://)[ ](https://)[doi.org/10.3390/jpm12081211](doi.org/10.3390/jpm12081211) Academic Editor: Christian Singer Received: 25 June 2022 Accepted: 21 July 2022 Published: 25 July 2022 Publisher's Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional afﬁliations. Copyright: © 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) . 1 Department of Computer Science and Engineering, Bangabandhu Sheikh Mujibur Rahman Science and Technology University, Gopalganj 8100, Bangladesh; [martuza.cse@bsmrstu.edu.bd](martuza.cse@bsmrstu.edu.bd) (M.M.A.); [sakifa.cse@bsmrstu.edu.bd](sakifa.cse@bsmrstu.edu.bd) (S.A.); [jamal.bsmrstu@gmail.com](jamal.bsmrstu@gmail.com) (M.J.U) 2 Department of Computer Science and Engineering, Rajshahi University of Engineering and Technology, Rajshahi 6200, Bangladesh; [sruti.cse13.ruet@gmail.com](sruti.cse13.ruet@gmail.com) 3 Department of Mathematics and Statistics, Faculty of Science, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh 13318, Saudi Arabia; [saalyami@imamu.edu.sa](saalyami@imamu.edu.sa) (S.A.A.); [ssashhab@imamu.edu.sa](ssashhab@imamu.edu.sa) (S.A.-A.) 4 Department of Physics, Faculty of Science, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh 13318, Saudi Arabia; [hfakdar@imamu.edu.sa](hfakdar@imamu.edu.sa) 5 Faculty of Science, Engineering & Technology, Swinburne University of Technology, Sydney, NSW 2150, Australia; [aazad@swin.edu.au or aazad@cmri.org.au](aazad@swin.edu.au or aazad@cmri.org.au) 6 ProCan®, Children's Medical Research Institute, Faculty of Medicine and Health, The University of Sydney, Westmead, NSW 2145, Australia 7 School of Health and Rehabilitation Sciences, Faculty of Health and Behavioural Sciences, The University of Queensland, St Lucia, QLD 4072, Australia * [Correspondence: m.moni@uq.edu.au](Correspondence: m.moni@uq.edu.au) Abstract: One of the common types of cancer for women is ovarian cancer. Still, at present, there are no drug therapies that can properly cure this deadly disease. However, early-stage detection could boost the life expectancy of the patients. The main aim of this work is to apply machine learning models along with statistical methods to the clinical data obtained from 349 patient individuals to conduct predictive analytics for early diagnosis. In statistical analysis, Student's t-test as well as log fold changes of two groups are used to ﬁnd the signiﬁcant blood biomarkers. Furthermore, a set of machine learning models including Random Forest (RF), Support Vector Machine (SVM), Decision Tree (DT), Extreme Gradient Boosting Machine (XGBoost), Logistic Regression (LR), Gradient Boosting Machine (GBM) and Light Gradient Boosting Machine (LGBM) are used to build classiﬁcation models tostratify benign-vs.-malignant ovarian cancer patients. Both of the analysis techniques recognized that the serumsamples carbohydrate antigen 125, carbohydrate antigen 19-9, carcinoembryonic antigen and human epididymis protein 4 are the top-most signiﬁcant biomarkers as well as neutrophil ratio, thrombocytocrit, hematocrit blood samples, alanine amino

FAQs

What is the main goal of the study?

To use machine learning models and statistical methods on clinical data to support predictive analytics for early diagnosis of ovarian cancer.

How were significant biomarkers identified?

The study uses Student’s t-test and log fold-change comparisons between two patient groups to find significant blood biomarkers.

Which machine learning models were used for classification?

Random Forest, Support Vector Machine, Decision Tree, XGBoost, Logistic Regression, Gradient Boosting Machine, and Light Gradient Boosting Machine are used to build benign-vs-malignant classification models.

Aug 3, 2026

Upload by Miles