Machine Learning in the Model Space for Metabolomics - Time Series in an Adrenal Steroid Hormone Study - Doctor of Philosophy Thesis

Aug 5, 2026

Learning in the model space (LiMS) represents complex data subjects such as sparse and/or noisy time series using an appropriate model or a posterior distribution over models, incorporating mechanistic information during model building. The thesis introduces a topographic mapping approach and a time series classification method in the model space, validated on real measurements from an adrenal steroid hormone study. Proposed self-organising maps directly formulated in the model space (SOMiMS) and an extended generative topographic mapping (GTM) improve interpretability via heat maps and parameter plots. Model-space classification enhances disease diagnosis accuracy with mechanistic and biomedical interpretability.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages178

Reading Time7 h 29 min

AccessFree to download

Contents

1 Introduction

2 Literature review

3 Clinical and biomedical background

Machine Learning in the Model Space for Metabolomics Time Series in an adrenal steroid hormone study by XINYUE CHEN Lead Supervisor: Prof. Peter Tino Co-Supervisor: Dr. Yuan Shen and Prof. David Smith A thesis submitted to the University of Birmingham for the degree of DOCTOR OF PHILOSOPHY School of Computer Science University of Birmingham February 2023 University of Birmingham Research Archive e-theses repository This unpublished thesis/dissertation is copyright of the author and/or third parties. The intellectual property rights of the author or third parties in respect of this work are as defined by The Copyright Designs and Patents Act 1988 or as modified by any successor legislation. Any use made of information contained in this thesis/dissertation must be in accordance with that legislation and must be properly acknowledged. Further distribution or reproduction in any format is prohibited without the permission of the copyright holder. Abstract Learning in the model space (LiMS) aims to represent each complex data subject such as sparse and/or noisy time series with an appropriate model, or a full posterior distribution over models. LiMS approaches include mechanistic information on how the data is generated in the machine learning model-building stage. Hence, it can improve the interpretability of chosen machine learning tools. This thesis proposes a new topographic mapping approach as well as a time series classification application in the model space. Both of them are demonstrated on a real-world data set of measurements taken on subjects in an adrenal steroid hormone study. Topographic visualisation methods such as self-organisation maps are important tools in data mining. In order to cluster and visualise sparse and/or noisy time series data, a novel self-organising map directly formulated in the model space termed as SOMiMS is proposed, together with an extension of generative topographic mapping (GTM) to the model space. Both maps are demonstrated on the adrenal steroid hormone data set with a good degree of separation of conditions. Compared to classic approaches in the signal space, they take the mechanistic information into account by providing interpretable readily data visualisations and parameter plots in the form of heat maps. In biomedical settings, time series classification is one of the most important techniques to improve the accuracy of disease diagnosis. The time series classification in the model space is developed not only to improve the diagnosis accuracy but also to provide mechanistic and biomedical model interpretability. It is applied to the adrenal steroid hormone data set showing satisfying classification performance in both signal and model space. Two classifier models, support vector machine (SVM) and logistic regression are employed. In addition, a hybrid model which significantly improves the accuracy is also created. Through feature selection, important time periods (signal space) and model parameters (model space) are extracted, which are crucial and valuable information from the biomedical point of view. In the data preprocessing stage, the missing value and initial value problems, which are two common problems of biomedical data are solved by using the univariate Gaussian process and adjoint method. Analyses and evaluations are concluded along with mechanistic and biomedical knowledge and case studies of some additional subjects. Acknowledgement First and foremost, I would like to express my deepest gratitude to my lead supervisor Prof. Peter Tino for his unlimited support and unconditional guidance during my Ph.D. journey. I would also like to extend my sincere thanks to my second supervisor Dr. Yuan Shen for his assistance and insightful suggestions at every stage of my research. I thank my co-supervisor Prof. David Smith. Without their encouragement and constant feedback this research would not be achievable. In addition, I would like to

FAQs

What is Learning in the model space (LiMS) and what problem does it target?

LiMS represents complex subjects such as sparse and/or noisy time series using an appropriate model or a posterior distribution over models, incorporating mechanistic information in the model-building stage.

Which topographic mapping methods does the thesis propose for model-space visualization and clustering?

It proposes SOMiMS, a self-organising map directly formulated in the model space, and an extension of generative topographic mapping (GTM) to the model space.

How is time series classification carried out and what improvements are reported?

Model-space time series classification is developed to improve diagnostic accuracy and provide mechanistic and biomedical interpretability, using classifiers such as SVM and logistic regression plus a hybrid model that increases accuracy.

Aug 5, 2026

Upload by Ava Thompson