Identifying prostate cancer and its clinical risk in asymptomatic men using machine learning of high dimensional peripheral blood flow cytometric natural killer cell subset phenotyping data

We demonstrate that prostate cancer can be identified by flow cytometric profiling of blood immune cell subsets. Herein, we profiled natural killer (NK) cell subsets in the blood of 72 asymptomatic men with Prostate Specific Antigen (PSA) levels < 20ng ml, of whom 31 had benign disease (no cancer...

Full description

Saved in:
Bibliographic Details
Main Authors: Simon Hood, Georgina Cosma, Gemma Foulds A., Catherine Johnson, Stephen Reeder, Stéphanie McArdle E., Masood Khan, Graham Pockley A.
Format: Default Article
Published: 2020
Subjects:
Biochemistry and Cell Biology
Online Access:https://hdl.handle.net/2134/12562178.v1
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1818167278435303424
author Simon Hood
Georgina Cosma
Gemma Foulds A.
Catherine Johnson
Stephen Reeder
Stéphanie McArdle E.
Masood Khan
Graham Pockley A.
author_facet Simon Hood
Georgina Cosma
Gemma Foulds A.
Catherine Johnson
Stephen Reeder
Stéphanie McArdle E.
Masood Khan
Graham Pockley A.
author_sort Simon Hood (5734706)
collection Figshare
description We demonstrate that prostate cancer can be identified by flow cytometric profiling of blood immune cell subsets. Herein, we profiled natural killer (NK) cell subsets in the blood of 72 asymptomatic men with Prostate Specific Antigen (PSA) levels < 20ng ml, of whom 31 had benign disease (no cancer) and 41 had prostate cancer. Statistical and computational methods identified a panel of eight phenotypic features(CD56 dimCD16high, CD56+DNAM-1-, CD56+LAIR-1+, CD56+LAIR-1-, CD56BRIGHTCD8+, CD56+NKp30+, CD56+NKp30-, CD56+NKp46+) which, when incorporated into an Ensemble machine learning prediction model, distinguished between the presence of benign prostate disease and prostate cancer. The machine learning model was then adapted to predict the D’Amico Risk Classification using data from 54 patients with prostate cancer and was shown to accurately differentiate between the presence of low/intermediate risk disease and high risk disease without the need for additional clinical data. This simple blood test has the potential to transform prostate cancer diagnostics
format Default
Article
id rr-article-12562178
institution Loughborough University
publishDate 2020
record_format Figshare
spelling rr-article-125621782020-07-28T00:00:00Z Identifying prostate cancer and its clinical risk in asymptomatic men using machine learning of high dimensional peripheral blood flow cytometric natural killer cell subset phenotyping data Simon Hood (5734706) Georgina Cosma (7050713) Gemma Foulds A. (9026177) Catherine Johnson (212246) Stephen Reeder (5734703) Stéphanie McArdle E. (9026180) Masood Khan (580947) Graham Pockley A. (9026183) Biochemistry and Cell Biology <div>We demonstrate that prostate cancer can be identified by flow cytometric profiling of blood immune cell subsets. Herein, we profiled natural killer (NK) cell subsets in the blood of 72 asymptomatic men with Prostate Specific Antigen (PSA) levels < 20ng ml, of whom 31 had benign disease (no cancer) and 41 had prostate cancer. Statistical and computational methods identified a panel of eight phenotypic features(CD56 <sup>dim</sup>CD16<sup>high</sup>, CD56<sup>+</sup>DNAM-1<sup>-</sup>, CD56<sup>+</sup>LAIR-1<sup>+</sup>, CD56<sup>+</sup>LAIR-1<sup>-</sup>, CD56<sup>BRIGHT</sup>CD8<sup>+</sup>, CD56<sup>+</sup>NKp30<sup>+</sup>, CD56<sup>+</sup>NKp30<sup>-</sup>, CD56<sup>+</sup>NKp46<sup>+</sup>) which, when incorporated into an Ensemble machine learning prediction model, distinguished between the presence of benign prostate disease and prostate cancer. The machine learning model was then adapted to predict the D’Amico Risk Classification using data from 54 patients with prostate cancer and was shown to accurately differentiate between the presence of low/intermediate risk disease and high risk disease without the need for additional clinical data. This simple blood test has the potential to transform prostate cancer diagnostics</div> 2020-07-28T00:00:00Z Text Journal contribution 2134/12562178.v1 https://figshare.com/articles/journal_contribution/Identifying_prostate_cancer_and_its_clinical_risk_in_asymptomatic_men_using_machine_learning_of_high_dimensional_peripheral_blood_flow_cytometric_natural_killer_cell_subset_phenotyping_data/12562178 CC BY 4.0
spellingShingle Biochemistry and Cell Biology
Simon Hood
Georgina Cosma
Gemma Foulds A.
Catherine Johnson
Stephen Reeder
Stéphanie McArdle E.
Masood Khan
Graham Pockley A.
Identifying prostate cancer and its clinical risk in asymptomatic men using machine learning of high dimensional peripheral blood flow cytometric natural killer cell subset phenotyping data
title Identifying prostate cancer and its clinical risk in asymptomatic men using machine learning of high dimensional peripheral blood flow cytometric natural killer cell subset phenotyping data
title_full Identifying prostate cancer and its clinical risk in asymptomatic men using machine learning of high dimensional peripheral blood flow cytometric natural killer cell subset phenotyping data
title_fullStr Identifying prostate cancer and its clinical risk in asymptomatic men using machine learning of high dimensional peripheral blood flow cytometric natural killer cell subset phenotyping data
title_full_unstemmed Identifying prostate cancer and its clinical risk in asymptomatic men using machine learning of high dimensional peripheral blood flow cytometric natural killer cell subset phenotyping data
title_short Identifying prostate cancer and its clinical risk in asymptomatic men using machine learning of high dimensional peripheral blood flow cytometric natural killer cell subset phenotyping data
title_sort identifying prostate cancer and its clinical risk in asymptomatic men using machine learning of high dimensional peripheral blood flow cytometric natural killer cell subset phenotyping data
topic Biochemistry and Cell Biology
url https://hdl.handle.net/2134/12562178.v1

Similar Items