Clardia: Type 2 Diabetes (T2D) Prediction Using Short-PPG Signals and Physiological Characteristics.
This repository contains the code related to the project: Use of Machine Learning for the Prediction of Diabetes from Photoplethysmography (PPG) Measurements & Physiological Characteristics.
The Original Dataset: Liang,Yongbo,etal."Anew,short-recordedphotoplethysmogramdatasetforbloodpres- sure monitoring in China." Scientific data 5 (2018): 180020.
The main features identified in literature related to the PPG signal have been extracted using the Matlab software. To Run the matlab scripts download the original dataset and run the script to extract features related to Diabetes, Normal and Hypertension patients.
The extracted features are used as the input to the models.
The code related to the paper: Hettiarachchi, Chirath, and Charith Chitraranjan. "A Machine Learning Approach to Predict Diabetes Using Short Recorded Photoplethysmography and Physiological Characteristics." Conference on Artificial Intelligence in Medicine in Europe. Springer, Cham, 2019.
Link: https://link.springer.com/chapter/10.1007/978-3-030-21642-9_41
Code related to the Fasting Blood Glucose Prediction using PPG signals.
Note: Data is not provided.