This repository contains code for a natural language processing (NLP) trained model that detects key words and predicts medical conditions. The model is designed to predict one out of four trained conditions: Depression, High Blood Pressure, Diabetes (Type 2), and Birth Control whilst giving three drug recommendations
The dataset used for training the model consists of text data related to the four medical conditions: Depression, High Blood Pressure, Diabetes (Type 2), and Birth Control. The dataset has been preprocessed and labeled to facilitate the training process. Dataset for training is found here
The NLP model utilizes advanced techniques for keyword detection and medical condition prediction. It employs a combination of text preprocessing, feature extraction, and machine learning algorithms to analyze input text and make predictions.
The implementation of the model is done in Python using popular NLP libraries and machine learning frameworks. Ensure that you have the following dependencies installed:
Python 3.x Natural Language Toolkit (NLTK) Scikit-learn Other necessary libraries (NumPy, Pandas, etc.)