Health Monitoring ML Model – Download and Use in Your Project – CSE x Typhon

Want to learn Machine Learning? Download these models, test them on your own data, and create your own project.

Nowadays, everyone is conscious about their health. Smartwatches, fitness bands, and health apps track things like our heart rate, steps, and sleep.

But can this data tell us whether we’re at risk? Yes! Machine learning makes it possible. In this article, we bring you an ML model that

• Health Predict according to Age, Heart Rate, Steps, Sleep
• Use Random Forest Algorithm
• Download and Use in Your Project

What the model does?

Input	Output
Age	Healthy
Heart Rate (BPM)	Moderate Risk
Steps per Day	High Risk
Sleep Hours

How it works?

We’ve trained a Random Forest Classifier. It takes 4 inputs and produces one of 3 output categories.

Age	Heart Rate	Steps	Sleep	Label
25	75	10000	7.5	Healthy
50	100	2000	4.5	High Risk
35	85	7000	6.0	Moderate Risk

Code – which creates the model

# train_model.py
import pandas as pd
import numpy as np
from sklearn.ensemble import RandomForestClassifier
import joblib

# Dataset
data = {
    'Age': [25, 45, 35, 28, 50, 32, 22, 48, 38, 55],
    'HeartRate': [75, 95, 85, 70, 100, 82, 68, 98, 88, 102],
    'Steps': [10000, 3000, 7000, 12000, 2000, 8000, 11000, 3500, 6500, 1800],
    'Sleep': [7.5, 5.0, 6.0, 8.0, 4.5, 6.5, 7.8, 5.2, 6.2, 4.0],
    'Label': ['Healthy', 'High Risk', 'Moderate Risk', 'Healthy', 'High Risk', 
              'Moderate Risk', 'Healthy', 'High Risk', 'Moderate Risk', 'High Risk']
}

df = pd.DataFrame(data)
label_map = {'Healthy': 0, 'Moderate Risk': 1, 'High Risk': 2}
df['Label_Num'] = df['Label'].map(label_map)

X = df[['Age', 'HeartRate', 'Steps', 'Sleep']]
y = df['Label_Num']

model = RandomForestClassifier()
model.fit(X, y)

joblib.dump(model, 'health_model.pkl')
print("✅ Model Saved as health_model.pkl")

How to use the model in your project?

Step 1: Load the model

import joblib
import numpy as np

model = joblib.load('health_model.pkl')

Step 2: Make a prediction

# अपनी values यहाँ दो
user_data = np.array([[30, 80, 9000, 7.0]])  # Age, HR, Steps, Sleep

result = model.predict(user_data)
print(result)  # Output: 0 = Healthy, 1 = Moderate, 2 = High Risk

Step 3: Understand the result

status = {0: '✅ Healthy', 1: '⚠️ Moderate Risk', 2: '❌ High Risk'}
print(status[result[0]])

How to install it on your website? (Flask Example)

from flask import Flask, request, jsonify
import joblib
import numpy as np

app = Flask(__name__)
model = joblib.load('health_model.pkl')

@app.route('/predict', methods=['POST'])
def predict():
    data = request.get_json()
    input_data = np.array([[data['age'], data['heartRate'], data['steps'], data['sleep']]])
    pred = model.predict(input_data)[0]
    return jsonify({'status': ['Healthy', 'Moderate Risk', 'High Risk'][pred]})

if __name__ == '__main__':
    app.run(debug=True)

Model Accuracy and Improvement Tips

Problem	Solution
Less Data	download large dataset from Kaggle
Less Features	also add BP, Calories, Oxygen Level
Less Accuracy	XGBoost and Neural Network also try

what will you learn?

By downloading and using this model you

• understand real-life application of ML Model
• practically use of Random Forest algorithm
• you can make your own health monitoring app
• use in College project

Message from CSE x Typhon

This model is completely free. Download it, add it to your projects, and share it with friends.

Credits: CSE x Typhon Team License: MIT – anyone can use it anywhere

Links and Resources

• Model Download: health_model.pkl
• Complete Code: GitHub Repo
• Dataset Source: Kaggle – Heart Health Dataset

Questions?

If you have any doubts, leave a comment or ask on CSE x Typhon’s social media. We’ll answer.

Happy Coding!
CSE x Typhon – Learn, Build, Share.

Frequently Asked Questions (FAQs)