Machine Learning for Genetic Studies - Exploring the Potential of Machine Learning Models for Predicting Preterm Delivery using Genetic Markers - Master’s Thesis 2023

Aug 4, 2026

Upload by Aria

Preterm delivery (PTD) is a major driver of infant mortality and morbidity worldwide, shaped by both environmental and genetic factors. Prior genetic studies have linked variants to PTD and gestational duration, yet small effect sizes leave much inherited variation unexplained. This master’s thesis evaluates machine learning methods to extract additional predictive insight from genetic data, using the MoBa cohort and Norway’s Medical Birth Registry, with a focus on previously reported loci.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages96

Reading Time4 h 2 min

AccessFree to download

Abstract

Background and Aim

Research Questions and Data

Theory and Methods

Results and Conclusions

Acknowledgements

Machine Learning for Genetic Studies Exploring the Potential of Machine Learning Models for Predicting Preterm Delivery using Genetic Markers Master’s thesis in Biomedical Engineering HEDVIG SUNDELIN DEPARTMENT OF ELECTRICAL ENGINEERING CHALMERS UNIVERSITY OF TECHNOLOGY Gothenburg, Sweden 2023 [www.chalmers.se](www.chalmers.se) Master’s thesis 2023 Machine Learning for Genetic Studies Exploring the Potential of Machine Learning Models for Predicting Preterm Delivery using Genetic Markers Hedvig Sundelin Department of Electrical Engineering Division of Biomedical Engineering Chalmers University of Technology Gothenburg, Sweden 2023 Machine Learning for Genetic Studies Exploring the Potential of Machine Learning Models for Predicting Preterm Delivery using Genetic Markers Hedvig Sundelin © Hedvig Sundelin, 2023 . Supervisor: Julius Juodakis, Department of Obstetrics and Gynecology, Institute of Clinical Sciences, Sahlgrenska Academy, University of Gothenburg Examiner: Andreas Fhager, Department of Electrical Engineering, Chalmers University of Technology Master’s Thesis 2023 Department of Electrical Engineering Division of Biomedical Engineering Chalmers University of Technology SE-412 96 Gothenburg Telephone +46 31 772 1000 Cover: Pregnant woman and baby with DNA structures stretching over to a computer performing machine [learning. Created with BioRender.com](learning. Created with BioRender.com) Typeset in LATEX Printed by Chalmers Reproservice Gothenburg, Sweden 2023 Machine Learning for Genetic Studies Hedvig Sundelin Department of Electrical Engineering Chalmers University of Technology Abstract Preterm delivery (PTD) is a significant contributor to infant mortality and morbidity worldwide, influenced by environmental and genetic factors. Although previous studies have identified genetic variants associated with PTD and gestational duration, their effect sizes remain relatively small, leaving a substantial portion of the hereditary variation unexplained. This thesis explores the potential of machine learning (ML) techniques to uncover additional insights into PTD and gestational duration using genetic data. The background section underscores the global impact of preterm birth on child mortality and long-term health outcomes, emphasising the role of genetics with an estimated heritability of around 30% . This project aims to apply ML techniques to improve the prediction of gestational duration and PTD based on genetic data. Research questions address ML model selection, the impact of variables on prediction performance, and a comparison to previous studies. The study is based on the Norwegian Mother, Father and Child Cohort Study (MoBa) and uses data from the Medical Birth Registry of Norway (MBRN) . The scope includes the use of genetic data and a focus on the 23 loci previously identified in a related study. The theory chapter provides an overview of genetics and its application in studying complex conditions like preterm delivery. It also introduces ML and explains the theoretical foundations of different ML models. Subsequently, the methods and materials chapter describes the data acquisition process, preprocessing steps, employed ML classifiers, and model evaluation methods. The chapter highlights the use of neural networks, classic ML algorithms, and libraries for implementation. Results reveal varying AUC scores among classic models, with logistic regression (LR) performing the best. The choice of variables had a significant impact, with the maternal genome and the Top 23 set, offering the best conditions. Network models achieved comparative scores for binary classification. Additional analyses on the predicted probabilities demonstrated higher AUC scores compared to binary classifications, identifying RMSprop as the best-performing network model. The study reveals a slight improvement in results compared to Polygenic Risk Scores (PRS) but a modest predictive

FAQs

What problem does this thesis address?

The thesis addresses prediction of preterm delivery and gestational duration, focusing on how genetic variation can improve predictive performance when earlier genetic effects explain only a limited portion of heritability.

Which dataset and genetic scope are used?

The study uses data from the Norwegian Mother, Father and Child Cohort Study (MoBa) and the Medical Birth Registry of Norway (MBRN), focusing on genetic data and 23 loci previously identified in a related study.

Which machine learning approaches perform best?

Logistic regression (LR) achieves the best overall AUC among classic models. Among network models, RMSprop performs best when evaluating predicted probabilities.

Aug 4, 2026

Upload by Aria