DoctorAI

Your own AI Doctor.

The DoctorAI repository is a project that aims to develop a deep learning-based virtual assistant for doctors to improve their efficiency and productivity.

TODO: The repository plans to include code for the virtual assistant's frontend, backend, and machine learning models.

The frontend is a web application that doctors can use to input patient data and receive recommendations from the virtual assistant. The backend is responsible for processing the input data, calling the appropriate machine learning model, and returning the recommendations to the frontend. The machine learning models are trained on patient data and are designed to perform tasks such as various diagnosis (Heart Failure, Pneumonia, Mortality).

The project is still in the early stages of development, and the repository is being regularly updated with new features and improvements. The project is open-source and welcomes contributions from the community.

Installation

Clone the repository.

git clone https://github.com/siripragadashashank/DoctorAI.git

Install the required packages through requirements.txt.

# --user is optional
python3 -m pip install -r requirements.txt --user

Install the source code for doctorai.

python3 setup.py install

Datasets

• Heart Failure:
• MIMIC-III:
• Chest X-Ray:

Models

• Heart Failure prediction
  • SVM
  • MLP
• MIMIC-III data for mortality prediction
  • MLP
  • CNN
  • RNN
• Pneumonia prediction from Chest X-Rays
  • CNN
  • RNN

Project Organization

├── LICENSE
├── Makefile           <- Makefile with commands like `make data` or `make train`
├── README.md          <- The top-level README.
├── datasets
│   ├── hf             <- Heart failure dataset.
│   └── mimic          <- MIMIC-III toy dataset for Mortality.
│   └── pneumonia      <- Chest X-ray dataset for Pneumonia.
│
├── docs               <- A default Sphinx project; see sphinx-doc.org for details
│
├── models             <- Trained and serialized models, model predictions, or model summaries
│
├── notebooks          <- Jupyter notebooks.
│
├── requirements.txt   <- The requirements file for reproducing the analysis environment, e.g.
│                         generated with `pip freeze > requirements.txt`
│
├── setup.py           <- makes project pip installable (pip install -e .) so src can be imported
├── doctorai           <- Source code for use in this project.
│   ├── __init__.py    <- Makes doctorai a Python module.
│   │
│   └── data           <- Scripts to generate MIMIC, Pneumonia and HF data.
│   │
│   ├── features       <- Scripts to turn raw data into features for modeling.
│   │
│   ├── models         <- Scripts to train doctorai models.
│   │   │                 
│   │   ├── hf         <- Train Heart Failure binary classifier using hf dataset.
│   │   └── mimic      <- Train Mortality binary classifier using MIMIC-III dataset.
│   │   └── pneumonia  <- Train Pneumonia binary classifier model using Chest X-ray dataset. 
│   │
│   └── visualization  <- Scripts to create exploratory and results oriented visualizations.
│
└── tox.ini            <- tox file with settings for running tox; see tox.readthedocs.io

---

Project based on the cookiecutter data science project template. #cookiecutterdatascience