Sushmitha Suresh, Meena G, Pragna P S, Niswana N Swamy
Abstract
OVARIA is a web-based system designed to estimate the risk of Polycystic Ovarian Disease in women by analyzing nonclinical health and lifestyle information. The application collects data like age, body mass index, menstrual history, and general symptoms through a structured questionnaire and preprocesses these inputs by standard cleaning, encoding, and scaling. A Random Forest classifier trained on this dataset categorizes users into three groups: likely PCOD, no PCOD, and at risk while providing lifestyle changes to maintain PCOD.
This model is integrated on a Flask-based web interface that enables users to sign up, submit their details, view their risk predictions, and review educational content on PCOD. Additionally, the system provides basic lifestyle guidance on diet, physical activity, and self-monitoring to help users balance PCOD. OVARIA is designed to support the early identification of PCOD risk through machine learning integrated into a user-friendly web platform, in particular for young women with little access to specialist healthcare services.
Keywords
PCOD (Polycystic Ovarian Disease), Random Forest Classifier, Flask web-interface
Conclusion
OVARIA illustrates the benefit of the integration of machine learning techniques within an easy-to- use web platform for early risk prediction of PCOD. The collection of basic health and lifestyle data and the use of a Random Forest classifier allow the system to screen individuals efficiently, even outside clinical settings. OVARIA offers users personalized risk assessments, along with practical lifestyle suggestions and educational resources to facilitate proactive health choices for women. This digital method fills gaps in awareness and access, which otherwise might not be sought in a timely manner, especially for young women. Further refinement and wider dissemination of such technology-driven innovations have the potential to enhance preventive healthcare and ensure early intervention in conditions like PCOD.
References
[1][1] Srinithi, V. & Rekha, R., (2023) “Machine Learning for Diagnosis of Polycystic Ovarian Syndrome (PCOS/PCOD)”, Proc. Int. Conf. Intelligent Systems for Communication, IoT and Security (ICISCoIS).
[2][2] Kapadia, D. & Jain, R., (2023) “PCOS Prediction: Advancements in Medical Informatics Using Artificial Intelligence”, Proc. 2nd Int. Conf. Futuristic Technologies (INCOFT).
[3][3] Kaushik, S. & Mishra, S. K., (2023) “Prediction of PCOD using Machine Learning Algorithms”, Proc. 14th Int. Conf. Computing Communication and Networking.
[4][4] Venkatachalam, C. & Rani, V., (2024) “Detection of PCOS/PCOD and Prediction of Infertility at the Early Stage Based on RF-ELM Technique”, Proc. Asian Conf. Intelligent Technologies (ACOIT).
[5][5] Patel, D., Mhaskar, M., Shendage, R., Modi, R., Sarvade, R. & Ram, A., (2024) “Machine Learning-Enhanced Solutions for Mitigating PCOS/PCOD-Related Women’s Health Disparities in Rural Areas: A Holistic Telemedicine System Design and Implementation”, Proc. Int. Conf. Brain Computer Interface & Healthcare Technologies (iCon- BCIHT).
[6][6] Dutta, P., Paul, S. & Majumder, M., (2021) “An Efficient SMOTE Based Machine Learning Classification for Prediction & Detection of PCOD”, Research Square.
[7][7] Bharati, S., Podder, P. & Mondal, M. R. H., (2020) “Diagnosis of Polycystic Ovary Disease Using Machine Learning Algorithms”, 2020 IEEE Region 10 Symposium (TENSYMP), Dhaka, Bangladesh.
[8][8] Denny, A., Raj, A., Ashok, A., Ram, C. M. & George, R., (2019) “i- HOPE: Detection and Prediction System for Polycystic Ovary Syndrome (PCOS) Using Machine Learning Techniques”, TENCON 2019 – 2019 IEEE Region 10 Conference (TENCON), Kochi, India.
[9][9] Saravanan, A. & Sathiamoorthy, S., (2018) “Detection of Polycystic Ovarian Syndrome: A Literature Survey”, Asian Journal of Engineering and Applied Technology.
[10][10] Satish, C. R., Nandipati, C. R., Chew, X. Y. & Khaw, K. W., (2020) “Polycystic Ovarian Syndrome (PCOD) Classification and Feature Selection by Machine Learning Techniques”.
How to Cite This Paper
Sushmitha Suresh, Meena G, Pragna P S, Niswana N Swamy (2026). OVARIA – A Smart Approach for Early PCOD Prediction. International Journal of Computer Techniques, 13(2). ISSN: 2394-2231.
