disease-prediction

Disease Prediction Using Machine Learning

This project uses multiple machine learning algorithms to predict diseases based on patient symptoms or medical attributes. It compares the performance of the following classifiers:

• Random Forest Classifier
• XGBoost Classifier
• K-Nearest Neighbors (KNN)
• Logistic Regression

📊 Algorithms Used

1. Random Forest Classifier
   Ensemble-based algorithm that builds multiple decision trees and outputs the majority vote for classification.

2. XGBoost Classifier
   A gradient boosting algorithm that improves accuracy by minimizing error with boosting techniques.

3. K-Nearest Neighbors (KNN)
   A distance-based algorithm that classifies data points based on the majority label among the k-nearest neighbors.

4. Logistic Regression (LR)
   A linear model used for binary and multi-class classification problems.

---

📁 Dataset

• The dataset includes symptoms or health-related metrics of patients and the corresponding diagnosed disease.
• Make sure your dataset is cleaned, preprocessed, and encoded before feeding it into ML models.

📈 Evaluation Metrics Accuracy

Precision

Recall

F1-Score

Confusion Matrix

These metrics help compare performance across different models.

📚 Dependencies pandas, numpy, matplotlib, scikit-learn, xgboost

✅ Results Each model's performance is evaluated, and the most accurate model is recommended for production use.

👩‍💻 Author: Isha Rane – MSc Data Science Student

LinkedIn: (https://www.linkedin.com/in/isha-rane-a19274167)