Evaluation of gas chromatography mass spectrometry and pattern recognition for the identification of bladder cancer from urine headspace

M. Cauchi; C. M. Weber; B. J. Bolt; P. B. Spratt; C. Bessant; D. C. Turner; C. M. Willis; L. E. Britton; C. Turner; G. Morgan

doi:10.1039/c6ay00400h

Evaluation of gas chromatography mass spectrometry and pattern recognition for the identification of bladder cancer from urine headspace

M. Cauchi, C. M. Weber, B. J. Bolt, P. B. Spratt, C. Bessant, D. C. Turner, C. M. Willis, L. E. Britton, C. Turner, G. Morgan

Technology

Research output: Contribution to Journal › Article › peer-review

Abstract

Previous studies have indicated that volatile organic compounds specific to bladder cancer may exist in urine headspace, raising the possibility that they may be of diagnostic value for this particular cancer. To further examine this hypothesis, urine samples were collected from patients diagnosed with either bladder cancer or a non-cancerous urological disease/infection, and from healthy volunteers, from which the volatile metabolomes were analysed using gas chromatography mass spectrometry. The acquired data were subjected to a specifically designed pattern recognition algorithm, involving cross-model validation. The best diagnostic performance, achieved with independent test data provided by healthy volunteers and bladder cancer patients, was 89% overall accuracy (90% sensitivity and 88% specificity). Permutation tests showed that these were statistically significant, providing further evidence of the potential for volatile biomarkers to form the basis of a non-invasive diagnostic technique.

Original language	English
Pages (from-to)	4037-4046
Journal	Analytical Methods
Volume	8
DOIs	https://doi.org/10.1039/c6ay00400h
Publication status	Published - 3 May 2016

Bibliographical note

The authors would like to thank the staff of the Urology Department, Buckinghamshire Healthcare NHS Trust for their enthusiastic support.

Keywords

Metabolomics
Bladder Cancer
Non-invasive Diagnostics
Pattern Recognition
machine learning (ML)
GC-MS

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1039/c6ay00400hLicence: CC BY

Cauchi_et_al_2016_Evaluation_of_gas_chromatography_mass_spectrometry_and_pattern_recognition_for_the_identification_of_bladder_cancer_from_urine_headspaceFinal published version, 698 KBLicence: CC BY

Cite this

@article{0a4397baed764602b35879369513e172,

title = "Evaluation of gas chromatography mass spectrometry and pattern recognition for the identification of bladder cancer from urine headspace",

abstract = "Previous studies have indicated that volatile organic compounds specific to bladder cancer may exist in urine headspace, raising the possibility that they may be of diagnostic value for this particular cancer. To further examine this hypothesis, urine samples were collected from patients diagnosed with either bladder cancer or a non-cancerous urological disease/infection, and from healthy volunteers, from which the volatile metabolomes were analysed using gas chromatography mass spectrometry. The acquired data were subjected to a specifically designed pattern recognition algorithm, involving cross-model validation. The best diagnostic performance, achieved with independent test data provided by healthy volunteers and bladder cancer patients, was 89% overall accuracy (90% sensitivity and 88% specificity). Permutation tests showed that these were statistically significant, providing further evidence of the potential for volatile biomarkers to form the basis of a non-invasive diagnostic technique.",

keywords = "Metabolomics, Bladder Cancer, Non-invasive Diagnostics, Pattern Recognition, machine learning (ML), GC-MS",

author = "M. Cauchi and Weber, {C. M.} and Bolt, {B. J.} and Spratt, {P. B.} and C. Bessant and Turner, {D. C.} and Willis, {C. M.} and Britton, {L. E.} and C. Turner and G. Morgan",

note = "The authors would like to thank the staff of the Urology Department, Buckinghamshire Healthcare NHS Trust for their enthusiastic support.",

year = "2016",

month = may,

day = "3",

doi = "10.1039/c6ay00400h",

language = "English",

volume = "8",

pages = "4037--4046",

journal = "Analytical Methods",

issn = "1759-9660",

publisher = "Royal Society of Chemistry",

}

TY - JOUR

T1 - Evaluation of gas chromatography mass spectrometry and pattern recognition for the identification of bladder cancer from urine headspace

AU - Cauchi, M.

AU - Weber, C. M.

AU - Bolt, B. J.

AU - Spratt, P. B.

AU - Bessant, C.

AU - Turner, D. C.

AU - Willis, C. M.

AU - Britton, L. E.

AU - Turner, C.

AU - Morgan, G.

N1 - The authors would like to thank the staff of the Urology Department, Buckinghamshire Healthcare NHS Trust for their enthusiastic support.

PY - 2016/5/3

Y1 - 2016/5/3

N2 - Previous studies have indicated that volatile organic compounds specific to bladder cancer may exist in urine headspace, raising the possibility that they may be of diagnostic value for this particular cancer. To further examine this hypothesis, urine samples were collected from patients diagnosed with either bladder cancer or a non-cancerous urological disease/infection, and from healthy volunteers, from which the volatile metabolomes were analysed using gas chromatography mass spectrometry. The acquired data were subjected to a specifically designed pattern recognition algorithm, involving cross-model validation. The best diagnostic performance, achieved with independent test data provided by healthy volunteers and bladder cancer patients, was 89% overall accuracy (90% sensitivity and 88% specificity). Permutation tests showed that these were statistically significant, providing further evidence of the potential for volatile biomarkers to form the basis of a non-invasive diagnostic technique.

AB - Previous studies have indicated that volatile organic compounds specific to bladder cancer may exist in urine headspace, raising the possibility that they may be of diagnostic value for this particular cancer. To further examine this hypothesis, urine samples were collected from patients diagnosed with either bladder cancer or a non-cancerous urological disease/infection, and from healthy volunteers, from which the volatile metabolomes were analysed using gas chromatography mass spectrometry. The acquired data were subjected to a specifically designed pattern recognition algorithm, involving cross-model validation. The best diagnostic performance, achieved with independent test data provided by healthy volunteers and bladder cancer patients, was 89% overall accuracy (90% sensitivity and 88% specificity). Permutation tests showed that these were statistically significant, providing further evidence of the potential for volatile biomarkers to form the basis of a non-invasive diagnostic technique.

KW - Metabolomics

KW - Bladder Cancer

KW - Non-invasive Diagnostics

KW - Pattern Recognition

KW - machine learning (ML)

KW - GC-MS

U2 - 10.1039/c6ay00400h

DO - 10.1039/c6ay00400h

M3 - Article

SN - 1759-9660

VL - 8

SP - 4037

EP - 4046

JO - Analytical Methods

JF - Analytical Methods

ER -

Evaluation of gas chromatography mass spectrometry and pattern recognition for the identification of bladder cancer from urine headspace

Abstract

Bibliographical note

Keywords

UN SDGs

Access to Document

Fingerprint

Cite this