Resumo
The ever-growing usage and popularity of Internet of Things devices, coupled with Big Data technologies and machine learning algorithms, have allowed for data engineers to explore new opportunities in healthcare and continuous care. Furthermore, there is a need to reduce the gap on time from when information is created to when actions and insights can be offered. However, a challenge in implementing a large-scale data processing architecture is deciding which tools are appropriate, and how to apply them in the best way possible. For example, streaming systems are now mature enough that hospitals worldwide can use their extremely large datasets, along with data producers, to predict and influence future events. Thus, the main objective of this systematic review is to identify the state-of-the-art in data platforms on healthcare that allow the creation of metrics and actions in real-time. The PRISMA guideline for reporting systematic reviews was implemented to deliver a transparent and consistent report, validating the technological advances in a critical sector. Multiple pertinent articles and papers were retrieved from the SCOPUS abstract and citation database on May 13, 2022, using several relevant keywords to identify potentially relevant documents published from January 2020 onward. These documents must have already been published in English and been already published, and accessible through the B-ON consortium that allows Portuguese students to legally download from most publishers. Over seven studies have been selected for deeper discussion based on their relevance and impact for this review, showcasing their main objectives, data sources, and tools used, as well as their approaches for interoperability and support of machine learning algorithms for decision support. In closing, the collected articles have shown that while Big Data is currently in use at health institutions of all sizes, the ability of processing large amounts of data from sensors and events, and notifying stakeholders as quickly as possible is still in its infancy.
Links
BibTeX (Download)
@inproceedings{miranda2023data,
title = {Data Platforms for Real-time Insights in Healthcare: Systematic Review},
author = {Rui Miranda and Carlos Alves and António Abelha and José Machado},
doi = {https://doi.org/10.1016/j.procs.2023.03.110},
year = {2023},
date = {2023-03-17},
urldate = {2023-01-01},
booktitle = {Procedia Computer Science},
volume = {220},
number = {14th},
pages = {826–831},
organization = {Elsevier},
abstract = {The ever-growing usage and popularity of Internet of Things devices, coupled with Big Data technologies and machine learning algorithms, have allowed for data engineers to explore new opportunities in healthcare and continuous care. Furthermore, there is a need to reduce the gap on time from when information is created to when actions and insights can be offered. However, a challenge in implementing a large-scale data processing architecture is deciding which tools are appropriate, and how to apply them in the best way possible. For example, streaming systems are now mature enough that hospitals worldwide can use their extremely large datasets, along with data producers, to predict and influence future events. Thus, the main objective of this systematic review is to identify the state-of-the-art in data platforms on healthcare that allow the creation of metrics and actions in real-time. The PRISMA guideline for reporting systematic reviews was implemented to deliver a transparent and consistent report, validating the technological advances in a critical sector. Multiple pertinent articles and papers were retrieved from the SCOPUS abstract and citation database on May 13, 2022, using several relevant keywords to identify potentially relevant documents published from January 2020 onward. These documents must have already been published in English and been already published, and accessible through the B-ON consortium that allows Portuguese students to legally download from most publishers. Over seven studies have been selected for deeper discussion based on their relevance and impact for this review, showcasing their main objectives, data sources, and tools used, as well as their approaches for interoperability and support of machine learning algorithms for decision support. In closing, the collected articles have shown that while Big Data is currently in use at health institutions of all sizes, the ability of processing large amounts of data from sensors and events, and notifying stakeholders as quickly as possible is still in its infancy.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
