This repository contains the codebase and documentation for a Pharmacist’s Assistant, leverages AI to automate the interpretation of handwritten prescriptions. By integrating a custom trained CNN + BiLSTM model with CTC loss, my solution converts prescription images into structured orders and flags potential dosage errors or conflicting medications. This not only streamlines pharmacy operations but also reduces manual errors, ultimately enhancing patient safety and operational efficiency.
The solution Approach can be summarized as follows:
- Automates reading handwritten prescriptions:
- Converts prescriptions into structured orders:
- Alerts on dosage errors and conflicts:
lables of dataset
results of model after training
To use the disaster relief and response solution, follow these steps:
Use deployed app for Medical Prescription generation: https://med-sarthi.streamlit.app/
- Clone the repository to your local machine. Use this link - https://github.com/SapanaDashoni15/MedSarthi.git
- Install all necessary dependencies and libraries as specified in the repository.
- Install requirements for streamlit app pip install -r requirements.txt
- Set up the environment and configure the solution parameters according to your requirements.
- To Check results run - streamlit run app.py or python -m streamlit run app.py (if python version not 3.1 or less)
This project is licensed under the MIT License.
We would like to acknowledge the contributions of the open-source community and the support of our partners and collaborators in developing and testing this disaster relief and response solution. Thank you for your support!