• Refine Query
  • Source
  • Publication year
  • to
  • Language
  • 1
  • Tagged with
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • About
  • The Global ETD Search service is a free service for researchers to find electronic theses and dissertations. This service is provided by the Networked Digital Library of Theses and Dissertations.
    Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.
1

Risk Stratification of Endometriosis through Machine Learning using Lifestyle Data : An Extensive Analysis on Lifestyle Data to Reveal Patterns in People with Endometriosis / Riskstratifiering av Endometrios genom Maskininlärning med hjälp av Livsstilsdata

Carrera Jeri, Patrick January 2023 (has links)
Endometriosis affect 11% of women of reproductive years worldwide. The project made use of lifestyle factors coming from the Lucy application. The Pearson correlation test was used to find linear correlation between endometriosis and lifestyle factors, while different machine learning models and logistic regression was used for finding non-linear correlations. The strongest linear correlation found (-0.23) was irregular menstruation however, the score does suggest a weak linear correlation. Decision Tree, Gradient boosted DT, XgBoost, Random Forest, and Logistic regression were usedto find patterns within the dataset. Risk stratification results proved to be unreliable. Decision Tree and its variants show strong evidence of correlation between endometriosis and the following features: weight, irregular menstruation, menstruation length, height, cycle length, irregular cycle, age, pregnancy, and daily symptoms. Additional analysis on those features could give more insight on what may be correlated as well as cause endometriosis. / Endometrios är en sjukdom som påverkar 11% av kvinnor i fortplantningsålder över hela världen. Det här projektet kommer använda livsstilsfaktorer som kommer från Lucy applikationen. Pearsons korrelations test används för att leta efter linjära korrelationer medans maskininlärnings modeller samt logistiskregression användes för att hitta icke-linjära korrelationer. Den starkaste linjärakorrelationen som hittades (-0.23) var oregelbunden menstruation, däremot tydervärdet på en svag linjär korrelation. Decision Tree, Gradient boosted DT, XgBoost, Random Forest, and Logistisk regressionsanalys användes för att hitta samband i datamängden. Riskstratifiering visades sig vara opålitliga. Decision Tree och deras varianter visade starka bevis på att det finns korrelationer mellan endometrios och följande egenskaper: vikt, oregelbunden menstruation, menstruationslängd, längd, cykellängd, oregelbunden cykel, ålder, graviditet samt dagliga symtomer. Mera analyser med dessa egenskaper kan ge mer insikt om vad som är korrelerat men även vad som orsakar endometrios

Page generated in 0.0448 seconds