Breast Cancer Awareness and Menstrual Monitoring and Tracking System

Abstract

Breast cancer and menstrual health disorders are major concerns in women’s healthcare, often worsened by limited awareness, delayed self-monitoring, and fragmented digital solutions. Existing platforms typically address menstrual tracking or breast cancer awareness independently, lacking an integrated preventive approach. This paper presents an awareness-driven digital platform, with AI- based menstrual cycle prediction that combines breast cancer risk awareness, risk calculation, and self-assessment guidance with menstrual cycle tracking and monitoring in a unified system. The platform supports structured symptom logging, guided self-examination using visual aids, healthcare facility location personalized health recommendations, and AI-based menstrual cycle prediction. A questionnaire-based risk estimation model inspired by the Tyrer-Cuzick method provides risk categorization along with medical disclaimers. Additionally, the system generates exportable health reports and includes awareness modules on nutrition, exercise, and early warning signs. The proposed solution promotes preventive healthcare, enhances user engagement, and supports early risk recognition without replacing clinical diagnosis.

Introduction

The text presents a proposed integrated women’s health platform that combines breast cancer awareness and monitoring with menstrual health tracking. The main motivation is that breast cancer remains a major health concern, especially in developing countries, where late detection can result from low awareness, stigma, and limited access to screening. Similarly, menstrual problems such as irregular cycles and PCOD are often not consistently monitored.

The proposed system addresses the gap in existing health applications, which generally treat breast health and menstrual health separately. It provides guided breast self-assessment, awareness information, reminders, risk assessment, menstrual tracking, cycle prediction, personalized recommendations, and health reports. The system is intended to support early awareness and encourage medical consultation but does not replace professional diagnosis.

Literature Survey

Previous studies have explored:

• Breast cancer risk prediction using demographic, reproductive, genetic, and clinical factors.
• Machine learning and AI techniques for breast cancer detection.
• Menstrual and fertility tracking applications.
• The accuracy, usability, privacy, and clinical reliability of period-tracking apps.
• The relationship between reproductive factors and breast cancer risk.

However, the literature identifies a major gap: most existing systems focus on either breast cancer or menstrual health rather than integrating both into one comprehensive platform. Many also lack strong clinical validation, personalized prediction, preventive-awareness features, or broader healthcare integration.

Objectives

The project has two main components:

1. Breast Cancer Module

• Provide education about risk factors, warning signs, prevention, post-care, and HRT.
• Guide users through breast self-assessment with images/videos and monthly reminders.
• Calculate a non-diagnostic personalized risk score inspired by the Tyrer-Cuzick model.
• Alert users to potential abnormalities and encourage medical consultation.
• Generate AI-based health summary reports.
• Locate breast healthcare facilities and diagnostic centers using OpenStreetMap-based services.

2. Menstrual Health Module

• Educate users about menstrual phases, PCOS/PCOD, and menopause.
• Track periods, flow intensity, and symptoms.
• Provide reminders for periods, data entry, and medication.
• Predict upcoming menstrual cycles using AI/ML.
• Provide personalized diet, exercise, and symptom-management suggestions.
• Generate doctor-ready menstrual health reports.

Proposed Methodology

The system uses a modular architecture consisting of breast cancer and menstrual health modules. User information is processed using AI-based techniques to generate personalized insights and reports.

For menstrual prediction, a Random Forest Regressor uses data from the user's most recent three menstrual cycles, including cycle length, variability, stress, sleep quality, and health conditions such as PCOS. Multiple decision trees are combined to produce the predicted next cycle.

Conclusion

This paper presents an integrated and awareness-driven digital platform for breast cancer awareness and menstrual health monitoring. The proposed system addresses the limitations of existing solutions by combining both domains into a unified application, thereby promoting preventive healthcare and improving user engagement. The breast cancer module is based on the self-assessment, awareness generation, and questionnaire-based risk estimation inspired by Tyrer-Cuzick, healthcare facility locator and while the menstrual health module enables tracking and utilizes a Random Forest Regressor to predict future cycle patterns based on recent user data, improving prediction accuracy and adaptability by providing personalized recommendations, reminders, and exportable health reports, the system encourages early detection, consistent monitoring, and informed decision-making. The platform is designed to assist users in understanding their health conditions while clearly not replacing professional medical diagnosis. Future work will focus on incorporating larger and more diverse datasets , improving prediction models, and integrating real-time wearable data, strengthening privacy and security and exploring multilingual support for wider accessibility. The platform can be expanded to address overlooked aspects of men’s health ( including breast cancer in men and prostate health) ensuring the system evolves towards an inclusive,gender-neutral approach to preventive healthcare.

References

[1] R. Jose et al., “Development and validation of breast cancer risk model using logistic regression,” 2025. [2] L. Forer et al., “Multifactorial breast cancer risk assessment using polygenic risk scores,” 2025. [3] T. Arravalli et al., “Breast cancer detection using machine learning and explainable AI,” 2025 [Online]. Available : https://www.nature.com/articles/s41598-025-12644-w [4] “Menstrual Tracking Mobile App Review by Consumers and Health Care Providers: Quality Evaluations Study,” JMIR Mhealth and Uhealth, vol. 11, 2023.[Online]. Available : https://mhealth.jmir.org/2023/1/e40921 [5] Y. Lu et al., “AI-based mammography model for breast cancer detection using deep learning,” 2023 [6] L. Worsfold and L. Marriott, “Accuracy of period tracker applications using real-cycle data,” 2021. [7] S. Earle et al., “Fertility apps and menstrual tracking: A scoping review,” 2020. [8] R. A. Karasneh et al., “Evaluation of smartphone applications for period tracking: Systematic review,” 2020 [Online]. Available : https://onlinelibrary.wiley.com/doi/10.1155/2020/2192387 [9] Collaborative Group on Hormonal Factors in Breast Cancer, “Menarche, menopause, and breast cancer risk,” Lancet Oncology, vol. 13, pp. 1141–1151, 2012.. [10] J. Tyrer, S. W. Duffy, and J. Cuzick, “A breast cancer prediction model incorporating familial and personal risk factors,” Statistics in Medicine, vol. 23, pp. 1111–1130, 2004. [11] Magview : https://magview.com/ [12] http://cytecare.com/blog/breast-cancer/breast-cancer-symptoms [13] https://www.nationalbreastcancer.org/breast-self-exam/ [14] https://www.komen.org/breast-cancer/facts-statistics/what-is-breast-cancer/breast-anatomy [15] https://knowyourlemons.org/

Copyright

Copyright © 2026 Dr. Varsha Bodade, Kavita Chaudhari , Vaidehi Bhute, Anuja Sutar, Taniya Singh. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.