Conference Paper2025Cited by 2

Integrating Supervised and Self-Supervised Models for an Enhanced PCOS Detection: A Data-Driven Approach with Machine Learning Perspective

Tasmia Tahmida, Syed Tangim Pasha, Mehedi Hassan, Ashraful Islam, M. Ashraful Amin

2025 6th International Conference on Artificial Intelligence, Robotics and Control (AIRC)

IEEE, pp. 499-503

  • Good Health and Well-being — Relevance: 94%
  • Gender Equality — Relevance: 64%
DOI: 10.1109/airc64931.2025.11077542URL

Abstract

Polycystic Ovary Syndrome (PCOS) is a common ovarian dysfunction that leads to various difficulties, including missed or irregular menstrual periods, acne, depression, mood swings, and excessive facial hair. Due to the wide range of symptoms, diagnosing PCOS can be challenging. In addition, the process can be costly, and there is a high rate of false positives in PCOS diagnoses. Machine Learning (ML) can aid both patients and clinicians in diagnosing PCOS by using labeled data to analyze patient history effectively. However, the Self-Supervised model uses labeled and unlabeled data to understand new patient cases better. Incorporating unlabeled information during model training has become increasingly reliable for identifying a new patient case study. In this study, we employed the publicly available KagglePCOS tabular dataset to evaluate various modeling approaches. Our findings indicated that the Support Vector Classifier (SVC) model achieved a commendable accuracy of$\mathbf{9 3. 8 \%}$. In comparison, the Gaussian Naive Bayes (GNB) model exhibited notably lower performance, with an accuracy of 54.1%. Among the Self-Supervised models, the Autoencoder showcased the most effective balance between accuracy and recall, achieving an accuracy of$\mathbf{8 2. 7 \%}$. Although other models, such as Simple Contrastive Learning of Representations (SimCLR) and Bootstrap Your Own Latent (BYOL), demonstrated lower F1 scores and accuracy, they highlighted the potential of Self-Supervised methods in identifying new cases within unlabeled datasets. While traditional Supervised models remain highly effective, SelfSupervised learning offers a promising direction, especially for diagnosing cases where labeled data is unavailable.

Keywords

  • polycystic ovary syndrome
  • BYOL
  • Autoencoder
  • self-supervised learning
  • PCOS diagnosis
  • Gaussian naive Bayes
  • Supervised learning
  • SimCLR
  • unlabeled data
  • support vector classifier

CCDS Authors

Syed Tangim Pasha
Syed Tangim Pasha

Syed Tangim Pasha

  • Collaborator, HCI Wing

Lecturer

Department of Computing and Information System

Daffodil International University

Published at

UbiComp

Research Interests

Health Informatics, Affective Computing, Digital Health, Wearable Computing

Mehedi Hassan, PhD
Mehedi Hassan, PhD

Mehedi Hassan, PhD

  • Collaborator, HCI Wing

Instructor

+1 more affiliation

University of Arkansas

Ashraful Islam, PhD
Ashraful Islam

Ashraful Islam, PhD

  • Center Director, CCDS
  • Director, HCI Wing

Assistant Professor

Department of Computer Science and Engineering

Independent University, Bangladesh (IUB)

Published at

CHI, UIST, UbiComp, IJCNN, ICIP, HCII, ICDMW, BLP, IEEE Internet of Things Journal, JMIR, JMIR Human Factors, JMIR Formative Research, IEEE Access, Smart Agricultural Technology, Diabetes Research and Clinical Practice, PLOS ONE

Research Interests

Human-Computer Interaction, AI for Social Good, AI for Public Health, AI for Impact

Prof. M Ashraful Amin, PhD
M Ashraful Amin, PhD

Prof. M Ashraful Amin, PhD

  • Founder Director, CCDS
  • Director, AI/ML, HCI & DS Wings

Professor

+1 more affiliation

Department of Information Sciences and Technology

George Mason University, USA

Published at

ACL, CHI, UbiComp, ECAI, WACV, PAKDD, IJCNN, ICPR, ICIP, HCII, CLEF, BLP, Scientific Reports, JMIR, IEEE Access, Smart Agricultural Technology, Frontiers in Computational Neuroscience, Diabetes Research and Clinical Practice, PLOS ONE

Research Interests

Machine Learning, Cognitive & Vision Science, Cybernetics, Surveillance & Security, ICT in Education, Health, & Agriculture, Human-Computer Interaction, Internet of Things, Robotics

References

  1. 1.Kathleen M. Hoeger, Anuja Dokras, Terhi Piltonen. (2020). Update on PCOS: Consequences, Challenges, and Guiding Treatment. The Journal of Clinical Endocrinology & Metabolism, 106(3), e1071–e1083[10.1210/clinem/dgaa839]
  2. 2.Jan Egger, Christina Gsaxner, Antonio Pepe, Kelsey L. Pomykala, Frederic Jonske, Manuel Kurz, Jianning Li, Jens Kleesiek. (2022). Medical deep learning—A systematic meta-review. Computer Methods and Programs in Biomedicine, 221, 106874[10.1016/j.cmpb.2022.106874]
  3. 3.Yvonne V. Louwers, Joop S.E. Laven. (2020). Characteristics of polycystic ovary syndrome throughout life. Therapeutic Advances in Reproductive Health, 14, 2633494120911038[10.1177/2633494120911038]
  4. 4.Ashwini Kodipalli, Susheela Devi. (2021). Prediction of PCOS and Mental Health Using Fuzzy Inference and SVM. Frontiers in Public Health, 9, 789569[10.3389/fpubh.2021.789569]
  5. 5.Abrar Alamoudi, Irfan Ullah Khan, Nida Aslam, Nourah Alqahtani, Hind S. Alsaif, Omran Al Dandan, Mohammed Al Gadeeb, Ridha Al Bahrani. (2023). A Deep Learning Fusion Approach to Diagnosis the Polycystic Ovary Syndrome (PCOS). Applied Computational Intelligence and Soft Computing, 2023, 1–15[10.1155/2023/9686697]
  6. 6.Hiya Islam, Jaasia Masud, Yushe Nazrul Islam, Fahim Kabir Monjurul Haque. (2022). An update on polycystic ovary syndrome: A review of the current state of knowledge in diagnosis, genetic etiology, and emerging treatment options. Women s Health, 18, 17455057221117966[10.1177/17455057221117966]
  7. 7.Błażej Męczekalski, Olga Niwczyk, Anna Kostrzak, Marzena Maciejewska-Jeske, Gregory Bala, Anna Szeliga. (2023). PCOS in Adolescents—Ongoing Riddles in Diagnosis and Treatment. Journal of Clinical Medicine, 12(3), 1221[10.3390/jcm12031221]
  8. 8.Anju E. Joham, Terhi Piltonen, Marla E. Lujan, Sylvia Kiconco, Chau Thien Tay. (2022). Challenges in diagnosis and understanding of natural history of polycystic ovary syndrome. Clinical Endocrinology, 97(2), 165–173[10.1111/cen.14757]
  9. 9.Ananya Chaudhuri. (2023). Polycystic ovary syndrome: Causes, symptoms, pathophysiology, and remedies. Obesity Medicine, 39, 100480[10.1016/j.obmed.2023.100480]
  10. 10.Chandana Rayasandra Satish, XinYing Chew, Khai Wah Khaw. (2020). Polycystic Ovarian Syndrome (PCOS) classification and feature selection by machine learning techniques.
  11. 11.S. Sowmiya, U. Snekhalatha, Omar Alhajlah, Fadiyah Almutairi, Shabnam Mohamed Aslam, R. K. Ahalya. (2024). F-Net: Follicles Net an efficient tool for the diagnosis of polycystic ovarian syndrome using deep learning techniques. PLoS ONE, 19(8), e0307571[10.1371/journal.pone.0307571]
  12. 12.Tessa Copp, Danielle Marie Muscat, Jolyn Hersch, Kirsten McCaffery, Jenny Doust, Ben W. Mol, Anuja Dokras, Jesse Jansen. (2020). Clinicians’ perspectives on diagnosing polycystic ovary syndrome in Australia: a qualitative study. Human Reproduction, 35(3), 660–668[10.1093/humrep/deaa005]
  13. 13.Tracy N. H. Harrison, R. Jeffrey Chang. (2022). Ovarian response to follicle‐stimulating hormone in women with polycystic ovary syndrome is diminished compared to ovulatory controls. Clinical Endocrinology, 97(3), 310–318[10.1111/cen.14708]
  14. 14.Vaidehi Mendpara, Narendranath Reddy Ganampet, Sabah Afroze, Sulochana Gnanasekaran, Sweta Sahu, Rahmatulhusna Atikah, Shreyaa Rajpal, Prithvi Raghavan, Krithika Ajith, Mihirkumar P Parmar, Vishal Venugopal. (2023). Long-Term Effects of Treatment Modalities on Metabolic Health, Fertility Outcomes, and Cardiovascular Risks in Lean Women with Polycystic Ovary Syndrome (PCOS): A Systematic Review. Research Square[10.21203/rs.3.rs-3360467/v1]
  15. 15.National Diabetes Information Clearinghouse (NDIC). (2020). Polycystic ovary syndrome (PCOS). Definitions[10.32388/1jsned]

Cited By

  1. 1.Retika S, Umarani Srikanth G, Shaarmi G. (2026). MSRD-PCOS: A Multi-Source Risk Discrepancy Framework for Early Screening of Polycystic Ovary Syndrome. , 1–9[10.1109/icdca69396.2026.11620043]
  2. 2.Mathu Mozhi S P, Nithyasri B, Hepsi Ajibah A S. (2026). Mamba-SHAP Hybrid Framework for Explainable PCOS Detection from Clinical and Hormonal Data. , 1–7[10.1109/icbdml68582.2026.11544669]
← All publications