Multi-omic diagnostics of prostate cancer in the presence of benign prostatic hyperplasia

Matt Spick, Ammara Muazzam, Hardev Pandha, Agnieszka Michael, Lee A Gethings, Christopher J Hughes, Nyasha Munjoma, Robert S Plumb, Ian D Wilson, Anthony D Whetton, Paul A Townsend, Nophar Geifman

Research output: Contribution to journalArticlepeer-review

Abstract

There is an unmet need for improved diagnostic testing and risk prediction for cases of prostate cancer (PCa) to improve care and reduce overtreatment of indolent disease. Here we have analysed the serum proteome and lipidome of 262 study participants by liquid chromatography-mass spectrometry, including participants diagnosed with PCa, benign prostatic hyperplasia (BPH), or otherwise healthy volunteers, with the aim of improving biomarker specificity. Although a two-class machine learning model separated PCa from controls with sensitivity of 0.82 and specificity of 0.95, adding BPH resulted in a statistically significant decline in specificity for prostate cancer to 0.76, with half of BPH cases being misclassified by the model as PCa. A small number of biomarkers differentiating between BPH and prostate cancer were identified, including proteins in MAP Kinase pathways, as well as in lipids containing oleic acid; these may offer a route to greater specificity. These results highlight, however, that whilst there are opportunities for machine learning, these will only be achieved by use of appropriate training sets that include confounding comorbidities, especially when calculating the specificity of a test.

Original languageEnglish
Article numbere22604
JournalHeliyon
Volume9
Issue number12
Early online date19 Nov 2023
DOIs
Publication statusPublished - 1 Dec 2023

Keywords

  • Biomarkers
  • Complement
  • LC-MS
  • Lipidomics
  • MAPK
  • Prostate cancer
  • Proteomics
  • Tumor progression

Fingerprint

Dive into the research topics of 'Multi-omic diagnostics of prostate cancer in the presence of benign prostatic hyperplasia'. Together they form a unique fingerprint.

Cite this