Diagnostic Expert Advisor: A platform for developing machine learning models on medical time-series data

Setting up data structures, parallelizing code, and creating visualizations are tasks in almost any project aiming to develop healthcare AI solutions based on heterogeneous, high-dimensional data structures. While toolkits for individual parts of this workflow exist, a solution that provides integra...

Full description

Saved in:
Bibliographic Details
Published in:SoftwareX 2023-07, Vol.23, p.101517, Article 101517
Main Authors: Polzin, Richard, Fritsch, Sebastian, Sharafutdinov, Konstantin, Marx, Gernot, Schuppert, Andreas
Format: Article
Language:English
Subjects:
AI model development
Heterogeneous medical data
Machine learning
Python
Time-series
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Setting up data structures, parallelizing code, and creating visualizations are tasks in almost any project aiming to develop healthcare AI solutions based on heterogeneous, high-dimensional data structures. While toolkits for individual parts of this workflow exist, a solution that provides integration of all steps is rarely found. We present the Diagnostic Expert Advisor, a platform for machine learning research on heterogeneous medical time-series data that aims to provide a robust environment for the rapid development of AI applications. It integrates a local web app through which whole patient cohorts, as well as the disease evolution of individual patients, can be analyzed with integrated tools for data handling, visualization, and parallelization. The platform provides sensible defaults while being flexible and extensible to fit various projects and working styles.
ISSN:2352-7110
2352-7110
DOI:10.1016/j.softx.2023.101517