Overview of the Artificial Intelligence Methods and Analysis of Their Application Potential
release_3c6ditgfsbfofitka7r7lazdyy
by
Dalia Kriksciuniene, Virgilijus Sakalauskas
2022 p167-183
Abstract
<jats:title>Abstract</jats:title>The medical industry collects a huge amount of data, most of which is electronic health records. These data cannot be processed and analyzed using traditional statistical or data analysis methods because of the complexity and a volume of the data. So the knowledge discovery from raw clinical data is a big challenge for healthcare system. In this chapter we introduce the issue of data mining in healthcare, i.e. how to use the raw clinical data to ensure a systematic approach to health problems, highlight good practices, reveal inefficiencies, and improve healthcare efficiency. We identify the data sources used in healthcare, discuss its adequacy, interpretation, transformation and cleansing challenges. Also we consider the variety characteristics and specific capacities of methods, applied in the areas of data mining. Particular attention is paid to the diversity of Machine Learning and Artificial intelligence methods, analytical health data analysis models, its testing and evaluation capabilities.
In application/xml+jats
format
Archived Files and Locations
application/pdf 293.4 kB
file_xlxtajjyu5fojpsyk33z6otrd4
|
link.springer.com (publisher) web.archive.org (webarchive) |
chapter
Stage
published
Year 2022
access all versions, variants, and formats of this works (eg, pre-prints)
Crossref Metadata (via API)
Worldcat
SHERPA/RoMEO (journal policies)
wikidata.org
CORE.ac.uk
Semantic Scholar
Google Scholar