About This System

A machine learning system built to assist in early detection of common sleep disorders using everyday health metrics.

Why This System?

Built with precision for medical professionals and health-conscious individuals alike.

🎯

High Accuracy

Random Forest achieves 95.2% classification accuracy on the sleep health dataset, outperforming single decision tree models.

🧠

ML Powered

Uses ensemble of 100 decision trees trained on 11 health parameters including BMI, heart rate, stress level, and sleep duration.

🔒

Privacy First

All data is processed client-side. No personal health information is stored on our servers.

Methodology

The model is trained on the Sleep Health and Lifestyle Dataset, containing health data from 400 subjects across various occupations and demographics.

Random Forest was chosen for its ability to handle non-linear relationships, provide feature importance rankings, and generalize well on small to medium datasets without overfitting.

1
Data Collection & Cleaning
2
Feature Engineering & Normalization
3
Random Forest Training (100 trees)
4
Cross-Validation & Accuracy Testing
5
Deployment & Real-time Prediction

Input Parameters

GenderBiological sex of the patient
AgePatient age in years
OccupationType of daily work/profession
Sleep DurationAverage hours of sleep per night
Quality of SleepSelf-rated sleep quality (1–10)
Physical Activity LevelDaily exercise duration (min/day)
Stress LevelSelf-rated stress level (1–10)
BMI CategoryBody Mass Index classification
Blood PressureSystolic/Diastolic blood pressure
Heart RateResting heart rate (bpm)
Daily StepsAverage daily step count

Ready to try the system?

Input your health data and get an instant sleep disorder classification powered by Random Forest ML.

Start Prediction →