We introduce Disease Informed Neural Networks (DINNs) — neural networks capable of learning how diseases spread, forecasting their progression, and finding their unique parameters (e.g. death rate). Here, we used DINNs to identify the dynamics of 11 highly infectious and deadly diseases. These systems vary in their complexity, ranging from 3D to 9D ODEs, and from a few parameters to over a dozen. The diseases include COVID, Anthrax, HIV, Zika, Smallpox, Tuberculosis, Pneumonia, Ebola, Dengue, Polio, and Measles.

Disease Informed Neural Network Sample Architecture

COVID Model: 1 Month Future Predictions

The easiest way to get started is to first install the necessary packages:

For a quick setup follow the next steps:

conda create -n dinn python=3.6

conda activate dinn

git clone https://github.com/Shaier/DINN.git

cd DINN

pip install -r requirements.txt

Once the packages are install, the next recommendation is to explore the tutorial.ipynb file.

Other than that, the experiments folder has all the experiments I ran for the paper. The diseases folder has all the diseases DINN was trained on.