Home / Current Issue / Paper 1719237
Smart AI PCOD/PCOS Detection System
Subject area: Science,Engineering and Technology · Area of research: AI-Based PCOS Detection Systems
DOI: 10.64388/IREV9I12-1719237
Abstract
Polycystic Ovary Syndrome (PCOS) and Polycystic Ovarian Disease (PCOD) are one of the most common hormonal disorders in women in the world. It causes irregular menstrual cycle, infertility, metabolic disorder, insulin resistance, obesity and psychological stress. Major challenges for early detection and continuous monitoring are still limited awareness, delayed diagnosis and unaffordable personalized healthcare systems. This paper presents a Smart AI PCOD/PCOS Detection System, a web-based health care platform that uses integrated AI and IoT to help in early symptom analysis, menstrual cycle tracking, lifestyle monitoring and real-time physiological parameter analysis. The system incorporates two levels of diagnostics. Level 1 provides AI-assisted analysis of the menstrual and hormonal symptoms via a responsive web application. The users perform medically relevant questionnaire-based assessments related to menstrual irregularities, PMS symptoms, weight fluctuations, acne, hirsutism, bloating, sleep irregularities, and ovulation abnormalities. The gathered data is processed using a Machine learning prediction pipeline with a Random Forest classifier trained on real PCOS datasets to predict the risk probability. The level 2 is IoT based physiological monitoring, which includes temperature sensors, heartbeat sensors, insulin detection module, microcontroller unit and LCD display system for acquiring real-time biological readings. The sensor data is transmitted wirelessly to a backend server based on Flask and synchronized to Firebase Real-time Database. The system is equipped with Responsive Dashboards, Live Analytics using Chart.js, Professional PDF Medical Report Generation using Report Lab, Notification Systems, Multi-Language Support, AI Chatbot Assistance and Wellness Recommendation modules for Diet, Yoga, Hydration and Sleep Tracking. The collected data is processed through a Machine Learning prediction pipeline where a Random Forest classifier trained on real PCOS datasets is used to predict the risk probability. The second level entails IoT-based biological monitoring with the use of temperature sensors, heartbeat sensors, insulin detector, microcontroller units, and LCD screen displays for gathering real-time information. The sensor data is relayed via wireless means to the server built on Flask architecture and then synchronized through Firebase Real-time Database. There are also dashboards with live analytics based on Chart.js, professional PDF reports using Report Lab, notifications, multiple language support, AI chatbots, and health recommendation services such as dietary, yoga, hydration, and sleep management services. The mentioned platform will be evidence of the implementation of Artificial Intelligence, IoT, Machine Learning, web technology, and healthcare data analysis to create a menstruation health platform that will enhance the PCOD/PCOS early warning and healthcare monitoring system.
Keywords
PCOD, PCOS, Machine Learning, IoT, Flask, Firebase, Women’s Healthcare, Menstrual Tracking, Random Forest, AI Healthcare System, Ovulation Prediction, Real-Time Monitoring., Polycystic Ovary Syndrome, Polycystic Ovarian Disease, Irregular Menstrual Cycle, Infertility, Integrated AI, IoT, Web Application, PMS Symptoms, Hirsutism, Random Forest Classifier, IoT Based Physiological Monitoring, Firebase Real-Time Database, Temperature Sensors, Heartbeat Sensors, Insulin Detector, Microcontroller Units, LCD Screen Displays
References
[1] Patel, R., Sharma, P., and Gupta, A., “Machine Learning Approaches for PCOS Prediction,” International Journal of Healthcare Informatics, vol. 8, no. 2, pp. 112–120, 2021.
[2] Khan, S. U., Islam, N., and Jan, Z., “IoT-Based Healthcare Monitoring Framework,” Future Generation Computer Systems, vol. 82, pp. 708–719, 2018.
[3] Marques, A., Pitarma, S., Garcia, N., and Pombo, N., “IoT Architectures and Technologies for Healthcare Systems,” IEEE Access, vol. 7, pp. 67491–67516, 2019.
[4] Rani, M., Kumar, V., and Singh, A., “Menstrual Cycle Prediction Using Calendar Analytics,” Journal of Women’s Healthcare Technology, vol. 5, no. 3, pp. 55–64, 2020.
[5] Kumar, P., and Lee, B. K., “Security Issues in Healthcare Sensor Networks,” Sensors, vol. 12, no. 1, pp. 55–91, 2012.
[6] Dr. J. Narendra Babu "SMART WASTE IMAGE DETECTION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 12, page no. e469-e472, December-2025. URL: http://www.jetir.org/papers/JETIR2512457.pdf
[7] Dr. J. Narendra Babu, et.al, "Traffic Violation Fine Tracker", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 12, page no.c608-c611, December-2025, URL: http://www.jetir.org/papers/JETIR2512268.pdf
[8] Dr. J. Narendra Babu, et.al, Journal of Internet Services and information security, AI-Enabled Forecasting and Isolation Forest-Based Detection of CBF Flow Anomalies in Secure Internet Architectures, Year 2025, Volume: 15, number: 3 (
[9] J. Narendra Babu, et.al– Indian License Plate Recognition System Based on Fuzzy Theory and BP Neural Network, IJECT Vol. 4, Issue 1, Jan - March 2013, ISSN: 2230-7109 (Online) | ISSN: 2230-9543 (Print)
[10] Flask Documentation, “Flask Web Framework,” 2025. [Online]. Available: https://flask.palletsprojects.com
[11] Firebase Documentation, “Firebase Realtime Database,” 2025. [Online]. Available: https://firebase.google.com
[12] Chart.js Documentation, “Chart.js Visualization Library,” 2025. [Online]. Available: https://www.chartjs.org
[13] Pedregosa, F. et al., “Scikit-learn: Machine Learning in Python,” Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011
[14] Chen, M., Mao, S., and Liu, Y., “Artificial Intelligence in Healthcare Systems,” Mobile Networks and Applications, vol. 19, no. 2, pp. 171–209, 2014.
How to cite this paper
@article{1719237,
author = {Anjali B S Naik, Bindu D R, Ankitha A, Archana G; Anushree V, Dr. J. Narendra Babu ; Karthik N S},
title = {Smart AI PCOD/PCOS Detection System},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {9},
number = {12},
pages = {3700-3705},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1719237.pdf},
abstract = {Polycystic Ovary Syndrome (PCOS) and Polycystic Ovarian Disease (PCOD) are one of the most common hormonal disorders in women in the world. It causes irregular menstrual cycle, infertility, metabolic disorder, insulin resistance, obesity and psychological stress. Major challenges for early detection and continuous monitoring are still limited awareness, delayed diagnosis and unaffordable personalized healthcare systems. This paper presents a Smart AI PCOD/PCOS Detection System, a web-based health care platform that uses integrated AI and IoT to help in early symptom analysis, menstrual cycle tracking, lifestyle monitoring and real-time physiological parameter analysis. The system incorporates two levels of diagnostics. Level 1 provides AI-assisted analysis of the menstrual and hormonal symptoms via a responsive web application. The users perform medically relevant questionnaire-based assessments related to menstrual irregularities, PMS symptoms, weight fluctuations, acne, hirsutism, bloating, sleep irregularities, and ovulation abnormalities. The gathered data is processed using a Machine learning prediction pipeline with a Random Forest classifier trained on real PCOS datasets to predict the risk probability. The level 2 is IoT based physiological monitoring, which includes temperature sensors, heartbeat sensors, insulin detection module, microcontroller unit and LCD display system for acquiring real-time biological readings. The sensor data is transmitted wirelessly to a backend server based on Flask and synchronized to Firebase Real-time Database. The system is equipped with Responsive Dashboards, Live Analytics using Chart.js, Professional PDF Medical Report Generation using Report Lab, Notification Systems, Multi-Language Support, AI Chatbot Assistance and Wellness Recommendation modules for Diet, Yoga, Hydration and Sleep Tracking. The collected data is processed through a Machine Learning prediction pipeline where a Random Forest classifier trained on real PCOS datasets is used to predict the risk probability. The second level entails IoT-based biological monitoring with the use of temperature sensors, heartbeat sensors, insulin detector, microcontroller units, and LCD screen displays for gathering real-time information. The sensor data is relayed via wireless means to the server built on Flask architecture and then synchronized through Firebase Real-time Database. There are also dashboards with live analytics based on Chart.js, professional PDF reports using Report Lab, notifications, multiple language support, AI chatbots, and health recommendation services such as dietary, yoga, hydration, and sleep management services. The mentioned platform will be evidence of the implementation of Artificial Intelligence, IoT, Machine Learning, web technology, and healthcare data analysis to create a menstruation health platform that will enhance the PCOD/PCOS early warning and healthcare monitoring system.},
keywords = {PCOD, PCOS, Machine Learning, IoT, Flask, Firebase, Women’s Healthcare, Menstrual Tracking, Random Forest, AI Healthcare System, Ovulation Prediction, Real-Time Monitoring., Polycystic Ovary Syndrome, Polycystic Ovarian Disease, Irregular Menstrual Cycle, Infertility, Integrated AI, IoT, Web Application, PMS Symptoms, Hirsutism, Random Forest Classifier, IoT Based Physiological Monitoring, Firebase Real-Time Database, Temperature Sensors, Heartbeat Sensors, Insulin Detector, Microcontroller Units, LCD Screen Displays},
month = {June},
doi = {https://doi.org/10.64388/IREV9I12-1719237}
}