Abstract

Polycystic Ovary Syndrome (PCOS) is one of the most common hormonal disorders seen in women of reproductive age. Recently, PCOS has been renamed as Polyendocrine Metabolic Ovarian Syndrome (PMOS). In this research, a multimodal AI framework called PCOSense is proposed that can predict PCOS using clinical data and ovarian ultrasound images. For clinical prediction, a hybrid machine learning algorithm was applied. To classify ultrasound images for PCOS diagnosis, a deep learning algorithm that was built on MobileNetV2 with an attention and residual learning scheme was implemented. To enhance the accuracy level of the diagnosis, the probability outputs from both models were fused at the decision level to make a final prediction. According to the experimental results, it can be seen that the performance of the classifier for PCOS classification from ultrasound image is high. Moreover, a web application was designed based on the Streamlit framework to predict PCOS in real time using clinical variables and ultrasound images. This shows the practical usefulness of the proposed framework for intelligent healthcare support.

References

• K. Choudhary, R. Singh, A. Garg, N. Verma, A. Purohit, and D. Deora, “An Updated Overview of Polycystic Ovary Syndrome,” Innovare Journal of Medical Sciences, vol. 7, no. 3, pp. 1–13, 2019.
• P. Bhandari, “Polycystic Ovary Syndrome (PCOS): Causes, Symptoms, Diagnosis, and Treatment,” The American Journal of Patient Health Info, vol. 2, no. 2, 2025. DOI: https://doi.org/10.69512/ajphi.v2i2.83
• L. Shahmoradi, L. Azadbakht, J. Farzi, S. R. N. Kalhori, A. B. Yazdipour, and F. Solat, “Nutritional management recommendation systems in polycystic ovary syndrome: a systematic review,” BMC Women’s Health, vol. 24, no. 1, p. 234, 2024. DOI: https://doi.org/10.1186/s12905-024-03074-3
• S. Rajendran, R. Bama, and K. Maheswari, “A deep learning and machine learning-based hybrid approach for PCOS diagnosis using ultrasound images,” Scientific Reports, vol. 12, no. 1, p. 18141, 2022. DOI: https://doi.org/10.1038/s41598-022-18141-0
• S. J. Pulluparambil and S. Bhat, “Medical image processing: Detection and prediction of PCOS—a systematic literature review,” International Journal of Health Sciences and Pharmacy (IJHSP), vol. 5, no. 2, pp. 80–98, 2021. DOI: https://doi.org/10.47992/IJHSP.2581.6411.0075
• M. Priyadharshini, A. Srimathi, C. Sanjay, and K. Ramprakash, “PCOS disease prediction using machine learning algorithms,” International Research Journal of Advanced Engineering Hub (IRJAEH), vol. 2, no. 3, pp. 651–655, 2024. DOI: https://doi.org/10.47392/IRJAEH.2024.0094
• B. Yamini, V. R. Kaneti, M. Nalini, and S. Subramanian, “Machine learning-driven PCOS prediction for early detection and tailored interventions,” SSRG International Journal of Electrical and Electronics Engineering, vol. 10, no. 9, pp. 61–75, 2023. DOI: https://doi.org/10.14445/23488379/IJEEE-V10I9P106
• M. M. Rahman et al., “Empowering early detection: A web-based machine learning approach for PCOS prediction,” Informatics in Medicine Unlocked, vol. 47, p. 101500, 2024. DOI: https://doi.org/10.1016/j.imu.2024.101500
• Z. Zad et al., “Predicting polycystic ovary syndrome with machine learning algorithms from electronic health records,” Frontiers in Endocrinology, vol. 15, p. 1298628, 2024. DOI: https://doi.org/10.3389/fendo.2024.1298628
• B. Panjwani, J. Yadav, V. Mohan, N. Agarwal, and S. Agarwal, “Optimized machine learning for the early detection of polycystic ovary syndrome in women,” Sensors, vol. 25, no. 4, p. 1166, 2025. DOI: https://doi.org/10.3390/s25041166
• H. Elmannai et al., “Polycystic ovary syndrome detection machine learning model based on optimized feature selection and explainable artificial intelligence,” Diagnostics, vol. 13, no. 8, p. 1506, 2023. DOI: https://doi.org/10.3390/diagnostics13081506
• V. Sakthivel, P. Prakash, K. Vishnukumar, and D. Min, “Advanced diagnosis of polycystic ovarian syndrome using machine learning and multimodal data integration,” International Journal of Advanced Computer Science and Applications, vol. 15, no. 6, 2024. DOI: https://dx.doi.org/10.14569/IJACSA.2024.01506122
• S. A. Suha and M. N. Islam, “An extended machine learning technique for polycystic ovary syndrome detection using ovary ultrasound image,” Scientific Reports, vol. 12, no. 1, p. 17123, 2022. DOI: https://doi.org/10.1038/s41598-022-21724-0
• M. Sumathi, P. Chitra, R. S. Prabha, and K. Srilatha, “Study and detection of PCOS related diseases using CNN,” in IOP Conference Series: Materials Science and Engineering, vol. 1070, no. 1, p. 012062, Feb. 2021. DOI: https://doi.org/10.1088/1757-899X/1070/1/012062
• S. Ahmed et al., “A review on the detection techniques of polycystic ovary syndrome using machine learning,” IEEE Access, vol. 11, pp. 86522–86543, 2023. DOI: https://doi.org/10.1109/ACCESS.2023.3304536
• D. Rao, R. R. Dayma, S. K. Pendekanti, and A. K. Acharya, “Deep learning model for diagnosing polycystic ovary syndrome using a comprehensive dataset from Kerala hospitals,” International Journal of Electrical and Computer Engineering, vol. 14, no. 5, pp. 5715–5727, 2024. DOI: https://doi.org/10.11591/ijece.v14i5.pp5715-5727
• H. Pushkarini and M. A. Anusuya, “A prediction model for evaluating the risk of developing PCOS,” International Research Journal of Engineering and Technology (IRJET), vol. 7, no. 9, pp. 1150–1156, 2020. DOI: https://www.irjet.net/archives/V7/i9/IRJET-V7I9192.pdf
• F. J. Barrera et al., “Application of machine learning and artificial intelligence in the diagnosis and classification of polycystic ovarian syndrome: A systematic review,” Frontiers in Endocrinology, vol. 14, p. 1106625, 2023. DOI: https://doi.org/10.3389/fendo.2023.1106625
• T. Arunprasath, R. Ramalakshmi, R. Kottaimalai, and J. Alex Michael Raj, “Development of a machine learning model to classify polycystic ovarian syndrome,” Technology and Health Care, vol. 33, no. 3, pp. 1478–1488, 2025. DOI: https://doi.org/10.1177/09287329241296357
• R. Galagan, S. Andreiev, N. Stelmakh, Y. Rafalska, and A. Momot, “Automation of polycystic ovary syndrome diagnostics through machine learning algorithms in ultrasound imaging,” Applied Computer Science, vol. 20, no. 2, pp. 194–204, 2024. DOI: https://doi.org/10.35784/acs-2024-24
• R. Ahmad, L. A. Maghrabi, I. A. Khaja, L. A. Maghrabi, and M. Ahmad, “SMOTE-Based Automated PCOS Prediction Using Lightweight Deep Learning Models,” Diagnostics, vol. 14, no. 19, p. 2225, 2024. DOI: https://doi.org/10.3390/diagnostics14192225
• R. Mogos et al., “Predicting unfavorable pregnancy outcomes in polycystic ovary syndrome (PCOS) patients using machine learning algorithms,” Medicina, vol. 60, no. 8, p. 1298, 2024. DOI: https://doi.org/10.3390/medicina60081298
• N. Leslie, A. A. Permana, and A. T. Perdana, “Application of the K-Nearest Neighbor Algorithm for Polycystic Ovarian Syndrome (PCOS) Classification: A Diagnostic Tool,” Journal of Logistics, Informatics and Service Science, vol. 11, no. 10, 2024. DOI: https://doi.org/10.33168/JLISS.2024.1011
• K. P. Rakshitha and N. C. Naveen, “Op-RMSprop classification for prediction of polycystic ovary syndrome using hybrid machine learning technique,” International Journal of Advanced Computer Science and Applications, vol. 13, no. 6, 2022. DOI:https://dx.doi.org/10.14569/IJACSA.2022.0130671
• C. Khadse and C. Puri, “Early detection of polycystic ovary syndrome using a hybrid machine learning model,” International Journal of Advanced Multidisciplinary Research and Educational Development, vol. 1, no. 4, pp. 300–318, 2025. DOI: https://doi.org/10.1109/IDICAIHEI65991.2025.11379286
• S. Venkatalakshmi and M. Regina, “Leveraging hybrid machine learning models for early diagnosis and prediction of Polycystic Ovary Syndrome (PCOS),” Journal of Electrical Systems, vol. 20, no. 11S, pp. 1765–1775, 2024. Available: https://journal.esrgroups.org/jes/article/view/7586
• E. Alamoudi et al., “A deep learning fusion approach for diagnosis of Polycystic Ovary Syndrome (PCOS) using ultrasound images and clinical data,” Applied Computational Intelligence and Soft Computing, 2023. DOI: https://doi.org/10.1155/2023/9686697
• P. N. Sai et al., “Advanced diagnosis of Polycystic Ovary Syndrome using multimodal machine learning techniques,” International Journal of Engineering Research and Technology, 2023. DOI: https://dx.doi.org/10.14569/IJACSA.2024.01506122
• M. M. Hoque et al., “Vision models for medical imaging: A hybrid deep learning approach for PCOS detection using ultrasound images,” arXiv preprint, 2026. DOI: https://doi.org/10.48550/arXiv.2601.15119
• P. Moral, D. Mustafi, A. Mustafi, and S. K. Sahana, “CystNet: An AI-driven model for PCOS detection using multilevel thresholding of ultrasound images,” Scientific Reports, 2024. https://www.nature.com/articles/s41598-024-75964-3.pdf
• V. Lakshmi and B. Pushpa, “Explainable multimodal deep learning using cross-attention fusion of ultrasound and clinical features for PCOS classification,” Discover Computing, 2026. DOI: https://doi.org/10.1007/s10791-025-09901-x
• M. Sumathi, P. Chitra, S. Sheela, and C. Ishwarya, “Study and implementation of automated system for detection of PCOS from ultrasound scan images using artificial intelligence,” The Imaging Science Journal, 2023. DOI: https://doi.org/10.1080/13682199.2023.2229016
• J. Peng, Z. Guo, X. Chen, and M. Zhou, “Denoising degraded PCOS ultrasound images using an enhanced denoising diffusion probabilistic model,” Electronics, vol. 14, p. 4061, 2025. DOI: https://doi.org/10.3390/electronics14194061
• F. K. Sarguroh and R. Srivaramangai, “An analytical review of AI-driven techniques for Polycystic Ovary Syndrome prediction,” International Journal of Science and Research (IJSR), Dec. 2025. DOI: https://dx.doi.org/10.21275/SR251217131307.
• F. K. Sarguroh and S. Ramanujam, “Hybrid Machine Learning Framework for Clinical Diagnosis of Polycystic Ovary Syndrome,” International Journal of Innovative Technology and Exploring Engineering (IJITEE), 2026. DOI: https://doi.org/10.35940/ijitee.A8344.15040326