Skip to content

README.md

Latest commit

 

History

History
56 lines (45 loc) · 1.97 KB

README.md

File metadata and controls

56 lines (45 loc) · 1.97 KB
Raw

AI-Powered Pharmacovigilance: Predicting Adverse Drug Reactions (ADRs)

This project uses a machine learning model to predict Adverse Drug Reactions (ADRs) based on patient and drug-related features. It is developed as part of a B.Pharm final-year research project to demonstrate the integration of AI in drug safety and pharmacovigilance.

Table of Contents

Overview

The goal of this project is to train and evaluate a binary classification model to detect the likelihood of an ADR occurring. This project explores how AI can revolutionize pharmacovigilance systems in the healthcare sector.

Project Structure

  • adr_prediction_model.pkl: Trained machine learning model.
  • adr_prediction.ipynb: Google Colab notebook for training and testing the model.
  • dataset.csv: Cleaned dataset used for training.
  • README.md: Project documentation.

How to Run

  1. Upload all files to your Google Colab or local environment.
  2. Open adr_prediction.ipynb.
  3. Run the cells to:
    • Load dataset
    • Preprocess data
    • Train model
    • Evaluate performance
  4. The model is saved as adr_prediction_model.pkl.

Dataset

A sample synthetic/real dataset was used containing anonymized data such as:

  • Age, gender, drug name
  • Side effects or symptoms
  • Outcome (ADR occurred or not)

Model Performance

  • Accuracy: ~50%
  • Precision & Recall balanced (Needs improvement)
  • Tools for visualization: Confusion matrix, ROC curve

Technologies Used

  • Python
  • Scikit-learn
  • Pandas, NumPy, Matplotlib, Seaborn
  • Google Colab

Usage

This project shows a proof-of-concept for students or researchers in pharmacy, healthcare, or AI domains to understand AI’s impact in ADR prediction.

License

This project is open for academic and non-commercial use.