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
Comparative Analysis of Machine Learning Algorithms for the Diagnosis of Endometrial Cancer using MicroRNA data
University of Skövde, School of Bioscience.
2025 (English)Independent thesis Basic level (degree of Bachelor), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

Endometrial cancer (EC) is a type of cancer that has in recent years become one of the most common and deadly types of cancers among women worldwide. A rapid diagnosis has been shown to be crucial in the survival of patients with EC. In recent years, the use of machine learning (ML), for the diagnosis of EC has increased, allowing for earlier diagnosis than without ML. Data from 94 patients had been used to train three MLs, to discover which of them produce the best results and whether they could be further used for the diagnosis EC. The MLs tested were logistic regression, random forest and XGBoost. The performance of each of the MLs was measured using balanced accuracy and by generating a Receiver Operating Characteristic (ROC) curve. Of the three MLs, XGBoost performed the best, with a median balanced accuracy of 0.63 and median ROCvalue of 0.64. As XGBoost had not previously been used in the diagnosis of EC, these findings show the possibility of further testing XGBoost as a diagnostic tool for EC. The highest performing XGBoost model then generated a set of the micro RNAs (miRNA) with the highest importance values. These miRNAs were then inputted into miRNet, tofind the most significant pathways connected to the miRNAs. Based on a biological interpretation of the enrichment analysis, the pathways with the lowest false discovery rate (FDR), and the most significance, were Pathways in cancer, with RNA transport and Prostate cancer. The pathway to EC was still present and had an FDR lower than 0.05, making it a significant connection.

Place, publisher, year, edition, pages
2025. , p. 50
National Category
Bioinformatics (Computational Biology)
Identifiers
URN: urn:nbn:se:his:diva-25658OAI: oai:DiVA.org:his-25658DiVA, id: diva2:1986042
Subject / course
Bioinformatics
Supervisors
Examiners
Available from: 2025-07-29 Created: 2025-07-29 Last updated: 2025-09-29Bibliographically approved

Open Access in DiVA

fulltext(12393 kB)99 downloads
File information
File name FULLTEXT01.pdfFile size 12393 kBChecksum SHA-512
9e583c3f162d3e003d1960ef0176613811af3ac5177d2f16ad4d220ac9a4f25eb46435de80d4ef61382b9fbaee185ca78b9a414b77a547301c19dc155554996e
Type fulltextMimetype application/pdf

By organisation
School of Bioscience
Bioinformatics (Computational Biology)

Search outside of DiVA

GoogleGoogle Scholar
Total: 100 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: 427 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