Högskolan i Skövde

his.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • apa-cv
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Empowering cardiovascular disease diagnosis with machine and deep learning approaches
University of Skövde, School of Bioscience.
2024 (English)Independent thesis Basic level (degree of Bachelor), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

Cardiovascular diseases are the leading cause of death worldwide, and their diagnosis can be a complex process which involves several tests and medical procedures. The addition of artificial intelligence (AI) models aims to help clinicians to make informed decisions by comparing available models, identifying critical variables, and diagnosing heart diseases; further support can be given by the implementation of a user interface. Clinical data from 35,021 healthy and 34,979 affected adults including information on eleven variables, was used to train and test the AI models. Decision trees and random forests were the machine learning algorithms utilized and compared with convolutional and artificial neural networks as deep learning algorithms. The most relevant variables in the diagnosis of cardiovascular diseases, based on the analysis with the four models, were systolic and diastolic blood pressure, weight, and height. Furthermore, regarding the actual diagnosis, the random forest model showed great accuracy and potential as diagnostic tool in the medical field. The potential of AI models to enhance diagnostic accuracy and maximally utilize the capacity of clinical settings is highlighted, laying the foundation for future advances in AI-based diagnosis. Additionally, the implementation of a user interface performed in this study is intended to assist clinicians by making these AI models more accessible and easier to use in practical settings. This study also points out the importance of incorporating more specific and detailed health data to fully leverage the abilities of modern AI technologies. 

Place, publisher, year, edition, pages
2024. , p. ii, 36
National Category
Bioinformatics and Computational Biology
Identifiers
URN: urn:nbn:se:his:diva-24296OAI: oai:DiVA.org:his-24296DiVA, id: diva2:1883247
Subject / course
Bioinformatics
Educational program
Molekylär bioinformatik
Supervisors
Examiners
Available from: 2024-07-09 Created: 2024-07-09 Last updated: 2025-02-07Bibliographically approved

Open Access in DiVA

fulltext(2270 kB)189 downloads
File information
File name FULLTEXT01.pdfFile size 2270 kBChecksum SHA-512
05029a45e45952d6356f28f1a197e69d9b483bf8e44873e932587b3ab5fc70fead174c70f0a9627e162c8f0b368d39cabdd8c1de2dcd8922409dd97251eb9d95
Type fulltextMimetype application/pdf

By organisation
School of Bioscience
Bioinformatics and Computational Biology

Search outside of DiVA

GoogleGoogle Scholar
Total: 189 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 370 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • apa-cv
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf