GitHub - sschwarcz/Diabetic-Re-admission-prediction: The goal of this project is to train a model using deep learning technics which will help to classify whether a diabetic patient will be re-admitted within 30 days, after 30 days and not at all, and to try to understand if the collected data is relevant. The dataset contains data from around 130 hospitals in the US, of over 100,000 diabetic patients that shows the treatments, medications etc. that they had, and the data of weather they were re-admitted, and if so when. The process includes processing the data to try and find the best features that can indicate the readmission, and then training a model with 70% of the data and evaluating the model with the rest of the data. The chosen model was MLP neural network

sschwarcz / Diabetic-Re-admission-prediction Public

Notifications You must be signed in to change notification settings
Fork 1
Star 0

The goal of this project is to train a model using deep learning technics which will help to classify whether a diabetic patient will be re-admitted within 30 days, after 30 days and not at all, and to try to understand if the collected data is relevant. The dataset contains data from around 130 hospitals in the US, of over 100,000 diabetic pati…