RESEARCH ARTICLE
Artificial Intelligence Approaches in Healthcare Informatics Toward Advanced Computation and Analysis
E.B. Priyanka1, *, S. Thangavel1, R Mohanasundaram2, Shamala Subramaniam3
Article Information
Identifiers and Pagination:
Year: 2024Volume: 18
E-location ID: e18741207281491
Publisher ID: e18741207281491
DOI: 10.2174/0118741207281491240118060019
Article History:
Received Date: 10/09/2023Revision Received Date: 29/12/2023
Acceptance Date: 09/01/2024
Electronic publication date: 29/01/2024
Collection year: 2024
open-access license: This is an open access article distributed under the terms of the Creative Commons Attribution 4.0 International Public License (CC-BY 4.0), a copy of which is available at: https://creativecommons.org/licenses/by/4.0/legalcode. This license permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Abstract
Introduction
Automated Machine Learning or AutoML is a set of approaches and processes to make machine learning accessible for non-experts. AutoML can exhibit optimized enhancement of an existing model or suggest the best models for precise datasets. In the field of computerized Artificial Intelligence (AI), medical experts better utilize AI models with available encrypted information science ability.
Methods
This paper aims to characterize and summarize the stage-wise design of Automated Machine Learning (AutoML) analysis e-healthcare platform starting from the sensing layer and transmission to the cloud using IoT (Internet of Things). To support the AutoML concept, the Auto Weka2.0 package, which serves as the open-source software platform, holds the predominant priority for experimental analysis to generate statistical reports.
Results
To validate the entire framework, a case study on Glaucoma diagnosis using the AutoML concept is carried out, and its identification of best-fit model configuration rates is also presented. The Auto-ML built-in model possesses a higher influence factor to generate population-level statistics from the available individual patient histories.
Conclusion
Further, AutoML is integrated with the Closed-loop Healthcare Feature Store (CHFS) to support data analysts with an automated end-to-end ML pipeline to help clinical experts provide better medical examination through automated mode.
