DigitalBiomarkerDiscoveryPipeline

Digital_Health_Data_Repository

The DHDR (Digital Health Data Repository) is a repository with sample data for use with the DBDP.

DBDP

Start here!

Pre-process

Pre-processing methods for mHealth and wearables data.

cgmquantify

Functions to calculate glucose summary metrics, glucose variability metrics (as defined in clinical publications), and visualizations to visualize trends in CGM data.

Exploratory-Data-Analysis

Tools for exploratory data analysis of wearables and mHealth data.

Data-Compression-Toolbox

The Wearables Data Compression Toolbox is designed to share data compression algorithms that have been evaluated on wearables data.

Sleep

Resting-Heart-Rate

Estimation of resting heart rate.

CovIdentify

Functions to extract features from wearable data to track and predict infectious disease status.

nutritionSearchTool

nutrition search tool that uses food2vec

wearablecompute

wearablecompute is an open source Python package containing over 50 data and domain-driven features that can be computed from wearables and mHealth sensor data.

Case_Studies

DBDP Case Studies

flirt

Are you ready to FLIRT with your wearable data?

dbdpy

DigitalBiomarkerDiscoveryPipeline.github.io

Check out our website at dbdp.org! It is hosted here on GitHub pages.

Model-Development

General methods for machine learning for digital biomarker discovery.

systematic-digital-biomarker-literature-search

this contains a file which was used to filter authors from a pubmed search for a systematic review based on the location of the author (requiring 50% USA led) and that one author from the USA was an academic

DBDP-GUI

An interactive GUI that allows users of any skill level to develop biomarkers off wearables data

feature-engineering-and-extraction

Awesome-CGM

List of CGM datasets

cgmquantify-R

Functions to calculate glucose summary metrics, glucose variability metrics (as defined in clinical publications), and visualizations to visualize trends in CGM data. (In R)

DBDP-Ed

DeepPostures

Deep Learning Methods for Identifying Human Postures from Hip-Worn Accelerometer Data

devicely

Devicely: A Python package for reading, timeshifting and writing sensor data

fasting

A Python package to interact with fasting logs from apps like Zero.

iglu

R package for Interpreting GLUcose data from CGMs (Continuous Glucose Monitors)

iglu-py

latentcor

latentcor is an R package provides estimation for latent correlation with mixed data types (continuous, binary, truncated and ternary).

SGCTools

Analysis tools for multivariate mixed data and continous/truncated/discrete functional data using Semiparametric Gaussian Copula (SGC)

tidyfun

Clean, wholesome, tidy fun with functional data in R