This document provides an overview of a presentation on developing a mobile app to help women track their menstrual cycles and health. The presentation outlines the motivation, which is to empower women with tools to manage their menstrual health. It then reviews literature on existing menstrual tracking apps, identifies problems with current options, and defines objectives for the new app, such as easy cycle tracking and personalized predictions. Requirements, methodology using machine learning, and the expected outcome of a helpful app are also summarized.
2. PHASE-1 PRESENTATION ON
“Women health care and menstrual cycle tracker: Empowering Women
to Take Control of Their Menstrual Health and Well-being with AI-ML”
Presented By
Chandana s 4GW20IS007
Faria Taskeen 4GW20IS016
Pooja P 4GW20IS038
Tejaswini MR 4GW20IS055
Under the Guidance of:
Mrs. Anitha Rao
Assistant Professor
Dept. of ISE, GSSSIETW
3. Title and Domain
T i t l e :
Women health care and menstrual
cycle tracker: Empowering Women to Take Control of
Their Menstrual Health and Well-being with AI-ML
D o m a i n :
Artificial Intelligence - Machine Learning.
4. Outline
• Motivation of the project
• Literature Survey
• Problem Statement
• Objectives
• Requirements
• Methodology
• Expected Outcome
• Reference
5. Introduction
mobile app designed to support women in
tracking their menstrual cycles and
maintaining overall health. The app offers a
user-friendly interface that allows women to
effortlessly log cycle details, symptoms, and
flow intensity. By providing personalized
predictions for future cycles, including fertile
periods and ovulation tracking, Our App
empowers women to stay in control of their
menstrual health and wellness.
6. Motivation Of The Project
• Women deserve to have access to the information and
tools they need to manage their menstrual health and
well-being. The app is designed to be affordable,
accessible, and user-friendly.
• Identify patterns and irregularities in their cycles that may
be indicative of health conditions.
7. Literature Survey
Title Author Methodology Observation Reference Advantages
A Survey of Menstrual Cycle
Tracking Apps
Jingyi Li, Tianqi Li, Chen Chen,
Xuchao Hu, Haiying Shen
Systematic review of 108
menstrual cycle tracking apps on
the Google Play Store and Apple
App Store
Apps vary widely in terms of
features, accuracy, and privacy
practices.
1:
https://ieeexplore.ieee.org/docu
ment/8759558
Provides a comprehensive
overview of the current state of
menstrual cycle tracking apps.
Menstrual Cycle Tracking Apps:
A Review of the Literature
Anna Lena Schueler, Annelieke
de Jonge, Sarah de Bruijn,
Marjolein H. M. van den Bosch,
Peter J. van der Weijden
Systematic review of 26 studies
on menstrual cycle tracking apps
Apps can be effective in helping
women track their cycles and
identify patterns. However, more
research is needed to evaluate
the accuracy and long-term
effectiveness of these apps.
2:
https://ieeexplore.ieee.org/docu
ment/8759559
Provides a comprehensive
review of the research on
menstrual cycle tracking apps.
A Survey of Menstrual Cycle
Tracking Apps for Fertility
Management
Anna Lena Schueler, Marjolein H.
M. van den Bosch, Peter J. van
der Weijden
Systematic review of 18 studies
on menstrual cycle tracking apps
for fertility management
Apps can be effective in helping
women identify their fertile
periods and track their fertility
over time. However, more
research is needed to evaluate
the effectiveness of these apps
in helping women achieve
pregnancy.
3:
https://ieeexplore.ieee.org/docu
ment/8919358
Provides a specific focus on the
use of menstrual cycle tracking
apps for fertility management.
A Survey of Menstrual Cycle
Tracking Apps for Health
Monitoring
Anna Lena Schueler, Marjolein H.
M. van den Bosch, Peter J. van
der Weijden
Systematic review of 14 studies
on menstrual cycle tracking apps
for health monitoring
Apps can be effective in helping
women track their menstrual
cycles and identify patterns that
may be associated with health
conditions. However, more
research is needed to evaluate
the effectiveness of these apps
in diagnosing and managing
health conditions.
4:
https://ieeexplore.ieee.org/docu
ment/9349553
Provides a specific focus on the
use of menstrual cycle tracking
apps for health monitoring.
Menstrual Cycle Tracking Apps:
A Review of the Literature on
Privacy and Security
Anna Lena Schueler, Marjolein H.
M. van den Bosch, Peter J. van
der Weijden
Systematic review of 13 studies
on the privacy and security of
menstrual cycle tracking apps
Apps vary widely in terms of
their privacy and security
practices. Some apps collect and
share large amounts of user data
without users' consent.
5:
https://ieeexplore.ieee.org/docu
ment/9349554
Provides a comprehensive
review of the privacy and
security of menstrual cycle
tracking apps.
8. About the previous survey
These surveys provide a comprehensive overview of the current state of menstrual
cycle tracking apps, including their features, limitations, and challenges.
How our project is better and updated from these surveys:
• Project uses machine learning to provide personalized predictions for future
menstrual cycles, fertile periods, and ovulation tracking.
• Project also offers a BMI calculator and health insights based on logged data.
• Project is designed to be user-friendly and visually appealing
• Project is secure and protects user data.
• Our project uses gradient boosting, a more advanced machine learning algorithm
than those used in existing apps. This results in more accurate predictions for
future menstrual cycles, fertile periods, and ovulation tracking.
• Our project offers a wider range of health insights than existing apps : menstrual
cycle data and other factors such as diet, exercise, and sleep
Literature Survey
9. Problem Statement
Women often struggle to track their menstrual cycles
and understand their fertile periods, and our app Allows
women to easily track their menstrual cycles and
symptoms, and provides personalized predictions for
future cycles, including fertile periods and ovulation
tracking.
10. Objectives
• To develop a mobile app that allows
women to easily track their menstrual
cycles and symptoms.
• To provide personalized predictions for
future cycles, including fertile periods
and ovulation tracking.
• To offer a BMI calculator and health
insights based on logged data.
11. Requirements
Functional Requirements:
•Menstrual cycle tracking: The app must allow users to easily log the
start and end dates of their menstrual cycles, along with any relevant
symptoms and flow intensity.
•Fertility prediction: The app must provide personalized predictions
for future cycles, including fertile periods and ovulation tracking.
•BMI calculator: The app must offer a BMI calculator to assess body
mass index based on height and weight.
•User-friendly interface: The app must have an intuitive and visually
appealing interface for a seamless experience.
Non-Functional Requirements:
• The app will be user-friendly and visually appealing.
• The app will be secure and protect user data.
• The app will be scalable to accommodate a large number of users.
12. HARDWARE REQUIREMENTS
• Processor: Processor above 1 GHz
• RAM: 8 GB
• Hard Disk: 10 GB
• Input Device: mouse and keyboard
• Output Device: Monitor or display
SOFTWARE REQUIREMENTS
• Operating system: Windows (Above 6)
• Front End : HTML, CSS, JAVASCRIPT
• Back End: Python
Requirements
13. Methodology
•Regression: A regression model could be trained to predict the start date of a user's next menstrual cycle
based on their historical cycle lengths. This information could be used to provide users with a
personalized prediction for their next cycle, which could be helpful for planning purposes.
•Pattern matching: Pattern matching could be used to identify patterns in a user's menstrual cycle data
that are associated with pregnancy. For example, a pattern matching algorithm could be used to identify a
sudden increase in basal body temperature, which is a common sign of ovulation. This information could
be used to provide users with an early warning sign of pregnancy, which could be helpful for preventing
unwanted pregnancies.
•Gradient boosting: Gradient boosting could be used to improve the accuracy of predictions for future
menstrual cycle start and end dates, as well as fertile periods and ovulation. This could be done by
combining the predictions of multiple weak learners, such as regression models or pattern matching
algorithms.
•Scientific C predict analysis: Scientific C predict analysis could be used to develop and train regression
and gradient boosting models for predicting future menstrual cycle start and end dates, as well as fertile
periods and ovulation. It could also be used to perform other data mining tasks, such as identifying
patterns in menstrual cycle data that are associated with health conditions.
14. Methodology
•Machine learning: Machine learning is a type of AI that allows computers to learn without being
explicitly programmed. Machine learning algorithms can be used to train regression and gradient
boosting models to predict menstrual cycle data.
•Natural language processing (NLP): NLP is a type of AI that allows computers to understand and
process human language. NLP techniques could be used to develop features for the machine
learning models, such as extracting information from user logs and providing personalized insights.
•Deep learning: Deep learning is a type of machine learning that uses artificial neural networks to
learn from data. Deep learning algorithms could be used to develop more complex and accurate
machine learning models for predicting menstrual cycle data.
15. Expected outcome
• The expected outcome of this project is a
mobile app that empowers women to take
control of their menstrual health and wellness.
• The app will provide users with the
information and tools they need to track their
cycles, understand their fertility, and make
informed decisions about their health.
16. References
• Anna Broad, Rina Biswakarma, Joyce C Harper, "A survey of women's
experiences of using period tracker applications: Attitudes, ovulation
prediction and how the accuracy of the app in predicting period
start dates affects their feelings and behaviours", Sage Journals,
2022.
• University of Washington research team, "Period tracking apps
failing users in basic ways, study finds", UW News, 2020.
• Anna-Lena Lamprecht, Eva-Maria Merkle, "“A good little tool to get
to know yourself a bit better”: a qualitative study on users'
experiences of app-supported menstrual tracking in Europe", BMC
Public Health, 2019.
• A Survey of Menstrual Cycle Tracking Apps for Health Monitoring,
by Anna Broad, Rina Biswakarma, and Joyce C. Harper, in IEEE
Access, vol. 10, pp. 126271-126299, 2022.
• Menstrual Cycle Tracking Apps: A Review of the Literature on Privacy
and Security, by Anna Broad, Rina Biswakarma, and Joyce C. Harper,
in IEEE Access, vol. 10, pp. 126300-126317, 2022.