RutuChakra - Smart PCOD Risk Prediction System
Bringing Balance to Women’s Wellness
Created on 11th February 2026
•
RutuChakra - Smart PCOD Risk Prediction System
Bringing Balance to Women’s Wellness
The problem RutuChakra - Smart PCOD Risk Prediction System solves
Polycystic Ovarian Disorder (PCOD) is often underdiagnosed in its early stages due to lack of awareness, irregular health monitoring, and limited access to preventive screening tools. Many women ignore early symptoms such as irregular menstrual cycles, weight gain, acne, and hormonal imbalance until the condition becomes severe. Traditional diagnosis typically requires multiple clinical tests, ultrasound scans, and specialist consultations, which may not always be accessible or affordable.
Rutuchakra addresses this gap by providing an AI-powered early risk assessment tool that helps users identify potential PCOD risk based on lifestyle and symptom inputs. Instead of replacing medical diagnosis, it acts as a preventive screening assistant.
What People Can Use It For:
Early PCOD risk estimation using symptom and lifestyle data
Monitoring menstrual health patterns over time
Identifying warning signs before complications increase
Receiving basic lifestyle recommendations for risk reduction
Encouraging timely medical consultation
How It Makes Existing Tasks Easier & Safer:
Reduces dependency on immediate clinical testing for preliminary screening
Promotes early awareness and proactive healthcare behaviour makes menstrual health tracking structured and data-driven provides accessible health insights without stigma or hesitation by combining machine learning with structured health inputs, Rutuchakra simplifies early screening, empowers women with data-backed insights, and supports preventive healthcare decision-making
Challenges we ran into
One of the major challenges we faced was ensuring proper integration between the machine learning model and the full-stack application. Since the ML model was built in Python while the backend was developed using Node.js and Express, connecting both systems required careful API structuring and data formatting. We initially encountered issues with inconsistent data types and mismatched feature ordering, which resulted in incorrect predictions.
Another hurdle was handling missing or unstructured health data in the dataset. We had to clean the data, remove null values, and ensure that the input format used in the frontend matched the structure expected by the trained model.
We overcame these challenges by standardizing the feature pipeline, validating input data before prediction, and thoroughly testing the API using sample requests. Clear team role distribution and version control through GitHub also helped us debug integration issues efficiently.
Tracks Applied (1)
Ethereum Track
ETHIndia
Technologies used
