Raman Spectroscopy with Machine Learning in the Assessment of a FIT-Positive Bowel Screening Population - Assessing the Feasibility of Detecting Colorectal Cancer and Adenomas Using Human Serum Samples

Aug 6, 2026

Upload by Hazel

This thesis investigates Raman spectroscopy combined with machine learning to support non-invasive diagnosis of colorectal cancer and colorectal adenomas in a bowel screening population identified as FIT-positive. The work reviews blood-based biomarker literature, then details study methods and results using pre-processed Raman spectra from 400 human serum samples. Statistical spectral comparisons and feature ranking identify candidate biomolecular classes, while multiple supervised models are evaluated via AUC performance. Findings suggest limited diagnostic discrimination currently, despite potential future clinical utility as an adjunct or replacement for faecal testing.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages284

Reading Time11 h 56 min

AccessFree to download

Contents

Summary (Abstract)

Declaration and Statements

Acknowledgements

Figures and Tables

Abbreviations and Definitions

1. Introduction

2. Systematic Literature Review – Blood-Based Biomarkers

3. Raman Spectroscopy in a Bowel Cancer Screening Population

Raman Spectroscopy with Machine Learning in the Assessment of a FIT-Positive Bowel Screening Population: Assessing the Feasibility of Detecting Colorectal Cancer and Adenomas Using Human Serum Samples Drew Samuel Magowan MBChB (hons), MRCS (Ed) Submitted to Swansea University in fulfilment of the requirements for the Degree of Doctor of Medicine Swansea University Faculty of Medicine, Health and Life Science – 2025 1 Copyright: The Author, Drew Samuel Magowan, 2025. Summary (Abstract) This thesis describes Raman spectroscopy combined with machine learning models for the non-invasive diagnosis of colorectal cancer and colorectal adenomas in a bowel screening population who have tested positive using a standard faecal immunochemical test. The aims were to review relevant current literature in blood-based biomarkers for colorectal cancer and colorectal adenomas, and to describe study methods and results including population characteristics, Raman spectral comparative analysis and machine learning model diagnostic classification outcomes. A literature review identified a growing field of diagnostic tests with acceptable sensitivity and specificity, comparable or superior to faecal-based testing. However, studies demonstrated a broad range of heterogenous tests, techniques and reporting quality which made objective comparisonsand selecting the best candidates difficult. For this reason, a narrative literature review was preferred to a systematic review and meta-analysis. Supervised and unsupervised analysis was undertaken for pre-processed Raman spectral data from 400 serum samples using principal component analysis, random forest ranked features of importance and Mann-Whitney U testing of mean spectra. These analyses were chosen to reduce data dimensionality, highlight spectral patterns and to test asymmetrical data for statistically significant differences between spectra. Spectral variance was low, however, multiple wavenumber regions of interest were identified and cross-referenced with known Raman peak assignments to identify potential underlying biomolecules involved in group differentiation. Biomolecule classes of interest included fatty acids, carbohydrates, amino acids, nucleotides and other molecules including lipids. Machine learning models including random forest, extreme gradient boost, logistic regression (with and without elastic net regularisation) and support vector machine were trained using preprocessed Raman spectral data for each set of diagnostic groups. These models were chosen due to their proven classification ability in other studies involving biological samples. Diagnostic classification area under the curve (AUC) ranged from 0.348 (95%CI 0.260 to 0 .436) to 0.583 (95%CI 424 to 0 .694) . These results likely arose from low classification power resultant from low spectral variance between groups, a high number of training variables, inadequate sample size, biologically complex samples, a lack of significantly advanced cancersand the dilutional effect of a large colorectal adenoma population. There remains potential clinical utility for Raman spectroscopy as an adjunct to (or to replace) faecal tests for colorectal cancer screening. However, current AUC results do not support its use at present. A much higher sample number will be required to allow a fuller understanding of machine model classification ability and a more informed discussion regarding its use in the screening pathway. Declaration and Statements This work has not previously been accepted in substance for any degree and is not being concurrently submitted in candidature for any degree. Signed Date 26/08/2025 Statement 1 This thesis is the result of my own investigations, except where otherwise stated and any other sources are acknowledged by footnotes, giving explicit references. A bibliography is appended. Signed Date 26/08/2025 Statement 2 I hereby give consent that any metadata and abstract are

FAQs

What is the main objective of combining Raman spectroscopy with machine learning in this thesis?

To evaluate whether Raman spectroscopy paired with machine learning can non-invasively detect colorectal cancer and colorectal adenomas among a FIT-positive bowel screening population.

How were the Raman spectral data analyzed before training diagnostic models?

Pre-processed Raman spectra from human serum samples were analyzed using principal component analysis, random forest feature importance ranking, and Mann-Whitney U testing to identify spectral patterns and statistically significant differences.

Why do the current machine learning results not support clinical use yet?

The thesis attributes the limited diagnostic classification performance to low spectral variance between groups, high training dimensionality, inadequate sample size, biologically complex samples, lack of significantly advanced cancers, and dilution effects from a large adenoma population.

Aug 6, 2026

Upload by Hazel