Advancing frontline early pancreatic cancer detection using within-class feature extraction in FTIR spectroscopy

Abstract This study introduces a novel approach for the early detection of pancreatic cancer through biofluid spectroscopy, leveraging a unique machine learning pipeline comprising class-specific principal component analysis (PCA), linear discriminant analysis (LDA), and support vector machine (SVM)...

Full description

Saved in:
Bibliographic Details
Main Authors: Zheng Tang, Edward Duckworth, Benjamin Mora, Bilal Al - Sarireh, Matthew Mortimer, Debdulal Roy
Format: Article
Language:English
Published: Nature Portfolio 2024-11-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-024-79153-0
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850127928393728000
author Zheng Tang
Edward Duckworth
Benjamin Mora
Bilal Al - Sarireh
Matthew Mortimer
Debdulal Roy
author_facet Zheng Tang
Edward Duckworth
Benjamin Mora
Bilal Al - Sarireh
Matthew Mortimer
Debdulal Roy
author_sort Zheng Tang
collection DOAJ
description Abstract This study introduces a novel approach for the early detection of pancreatic cancer through biofluid spectroscopy, leveraging a unique machine learning pipeline comprising class-specific principal component analysis (PCA), linear discriminant analysis (LDA), and support vector machine (SVM) in both real patient and synthetic data. By conducting separate PCA on cancerous and non-cancerous samples and integrating the projections prior to LDA and SVM classification, we demonstrate significantly improved diagnostic accuracy compared to traditional methods. This methodology not only enhances predictive performance but also offers deeper insights into the influence of molecular spectra on model efficacy. Our findings, validated on real patient data, suggest a promising avenue for developing non-invasive, accurate diagnostic tools for early-stage pancreatic cancer detection.
format Article
id doaj-art-e5924e719594478ba9a154ce7eb97b92
institution OA Journals
issn 2045-2322
language English
publishDate 2024-11-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-e5924e719594478ba9a154ce7eb97b922025-08-20T02:33:31ZengNature PortfolioScientific Reports2045-23222024-11-011411910.1038/s41598-024-79153-0Advancing frontline early pancreatic cancer detection using within-class feature extraction in FTIR spectroscopyZheng Tang0Edward Duckworth1Benjamin Mora2Bilal Al - Sarireh3Matthew Mortimer4Debdulal Roy5Department of Computer Science and Mathematics, Swansea UniversityConnectomX LtdDepartment of Computer Science and Mathematics, Swansea UniversityMorriston Hospital, Heol Maes EglwysMorriston Hospital, Heol Maes EglwysDepartment of Chemistry, Swansea UniversityAbstract This study introduces a novel approach for the early detection of pancreatic cancer through biofluid spectroscopy, leveraging a unique machine learning pipeline comprising class-specific principal component analysis (PCA), linear discriminant analysis (LDA), and support vector machine (SVM) in both real patient and synthetic data. By conducting separate PCA on cancerous and non-cancerous samples and integrating the projections prior to LDA and SVM classification, we demonstrate significantly improved diagnostic accuracy compared to traditional methods. This methodology not only enhances predictive performance but also offers deeper insights into the influence of molecular spectra on model efficacy. Our findings, validated on real patient data, suggest a promising avenue for developing non-invasive, accurate diagnostic tools for early-stage pancreatic cancer detection.https://doi.org/10.1038/s41598-024-79153-0
spellingShingle Zheng Tang
Edward Duckworth
Benjamin Mora
Bilal Al - Sarireh
Matthew Mortimer
Debdulal Roy
Advancing frontline early pancreatic cancer detection using within-class feature extraction in FTIR spectroscopy
Scientific Reports
title Advancing frontline early pancreatic cancer detection using within-class feature extraction in FTIR spectroscopy
title_full Advancing frontline early pancreatic cancer detection using within-class feature extraction in FTIR spectroscopy
title_fullStr Advancing frontline early pancreatic cancer detection using within-class feature extraction in FTIR spectroscopy
title_full_unstemmed Advancing frontline early pancreatic cancer detection using within-class feature extraction in FTIR spectroscopy
title_short Advancing frontline early pancreatic cancer detection using within-class feature extraction in FTIR spectroscopy
title_sort advancing frontline early pancreatic cancer detection using within class feature extraction in ftir spectroscopy
url https://doi.org/10.1038/s41598-024-79153-0
work_keys_str_mv AT zhengtang advancingfrontlineearlypancreaticcancerdetectionusingwithinclassfeatureextractioninftirspectroscopy
AT edwardduckworth advancingfrontlineearlypancreaticcancerdetectionusingwithinclassfeatureextractioninftirspectroscopy
AT benjaminmora advancingfrontlineearlypancreaticcancerdetectionusingwithinclassfeatureextractioninftirspectroscopy
AT bilalalsarireh advancingfrontlineearlypancreaticcancerdetectionusingwithinclassfeatureextractioninftirspectroscopy
AT matthewmortimer advancingfrontlineearlypancreaticcancerdetectionusingwithinclassfeatureextractioninftirspectroscopy
AT debdulalroy advancingfrontlineearlypancreaticcancerdetectionusingwithinclassfeatureextractioninftirspectroscopy