University of Hertfordshire

From the same journal

By the same authors

Standard

Development of PancRISK, a urine biomarker-based risk score for stratified screening of pancreatic cancer patients. / Blyuss, Oleg; Zaikin, Alexey; Cherepanova, Valeriia; Munblit, Daniel; Kiseleva, Elena M; Prytomanova, Olga M; Duffy, Stephen W; Crnogorac-Jurcevic, Tatjana.

In: British Journal of Cancer, 20.12.2019, p. 1-5.

Research output: Contribution to journalArticle

Harvard

Blyuss, O, Zaikin, A, Cherepanova, V, Munblit, D, Kiseleva, EM, Prytomanova, OM, Duffy, SW & Crnogorac-Jurcevic, T 2019, 'Development of PancRISK, a urine biomarker-based risk score for stratified screening of pancreatic cancer patients', British Journal of Cancer, pp. 1-5. https://doi.org/10.1038/s41416-019-0694-0

APA

Blyuss, O., Zaikin, A., Cherepanova, V., Munblit, D., Kiseleva, E. M., Prytomanova, O. M., Duffy, S. W., & Crnogorac-Jurcevic, T. (2019). Development of PancRISK, a urine biomarker-based risk score for stratified screening of pancreatic cancer patients. British Journal of Cancer, 1-5. https://doi.org/10.1038/s41416-019-0694-0

Vancouver

Author

Blyuss, Oleg ; Zaikin, Alexey ; Cherepanova, Valeriia ; Munblit, Daniel ; Kiseleva, Elena M ; Prytomanova, Olga M ; Duffy, Stephen W ; Crnogorac-Jurcevic, Tatjana. / Development of PancRISK, a urine biomarker-based risk score for stratified screening of pancreatic cancer patients. In: British Journal of Cancer. 2019 ; pp. 1-5.

Bibtex

@article{376fbc55124a459c8e3da0336e12b706,
title = "Development of PancRISK, a urine biomarker-based risk score for stratified screening of pancreatic cancer patients",
abstract = "BACKGROUND: An accurate and simple risk prediction model that would facilitate earlier detection of pancreatic adenocarcinoma (PDAC) is not available at present. In this study, we compare different algorithms of risk prediction in order to select the best one for constructing a biomarker-based risk score, PancRISK.METHODS: Three hundred and seventy-nine patients with available measurements of three urine biomarkers, (LYVE1, REG1B and TFF1) using retrospectively collected samples, as well as creatinine and age, were randomly split into training and validation sets, following stratification into cases (PDAC) and controls (healthy patients). Several machine learning algorithms were used, and their performance characteristics were compared. The latter included AUC (area under ROC curve) and sensitivity at clinically relevant specificity.RESULTS: None of the algorithms significantly outperformed all others. A logistic regression model, the easiest to interpret, was incorporated into a PancRISK score and subsequently evaluated on the whole data set. The PancRISK performance could be even further improved when CA19-9, commonly used PDAC biomarker, is added to the model.CONCLUSION: PancRISK score enables easy interpretation of the biomarker panel data and is currently being tested to confirm that it can be used for stratification of patients at risk of developing pancreatic cancer completely non-invasively, using urine samples.",
author = "Oleg Blyuss and Alexey Zaikin and Valeriia Cherepanova and Daniel Munblit and Kiseleva, {Elena M} and Prytomanova, {Olga M} and Duffy, {Stephen W} and Tatjana Crnogorac-Jurcevic",
note = "{\textcopyright} The Author(s) 2019. Published by Springer Nature on behalf of Cancer Research UK.",
year = "2019",
month = dec,
day = "20",
doi = "10.1038/s41416-019-0694-0",
language = "English",
pages = "1--5",
journal = "British Journal of Cancer",
issn = "0007-0920",
publisher = "Nature Publishing Group",

}

RIS

TY - JOUR

T1 - Development of PancRISK, a urine biomarker-based risk score for stratified screening of pancreatic cancer patients

AU - Blyuss, Oleg

AU - Zaikin, Alexey

AU - Cherepanova, Valeriia

AU - Munblit, Daniel

AU - Kiseleva, Elena M

AU - Prytomanova, Olga M

AU - Duffy, Stephen W

AU - Crnogorac-Jurcevic, Tatjana

N1 - © The Author(s) 2019. Published by Springer Nature on behalf of Cancer Research UK.

PY - 2019/12/20

Y1 - 2019/12/20

N2 - BACKGROUND: An accurate and simple risk prediction model that would facilitate earlier detection of pancreatic adenocarcinoma (PDAC) is not available at present. In this study, we compare different algorithms of risk prediction in order to select the best one for constructing a biomarker-based risk score, PancRISK.METHODS: Three hundred and seventy-nine patients with available measurements of three urine biomarkers, (LYVE1, REG1B and TFF1) using retrospectively collected samples, as well as creatinine and age, were randomly split into training and validation sets, following stratification into cases (PDAC) and controls (healthy patients). Several machine learning algorithms were used, and their performance characteristics were compared. The latter included AUC (area under ROC curve) and sensitivity at clinically relevant specificity.RESULTS: None of the algorithms significantly outperformed all others. A logistic regression model, the easiest to interpret, was incorporated into a PancRISK score and subsequently evaluated on the whole data set. The PancRISK performance could be even further improved when CA19-9, commonly used PDAC biomarker, is added to the model.CONCLUSION: PancRISK score enables easy interpretation of the biomarker panel data and is currently being tested to confirm that it can be used for stratification of patients at risk of developing pancreatic cancer completely non-invasively, using urine samples.

AB - BACKGROUND: An accurate and simple risk prediction model that would facilitate earlier detection of pancreatic adenocarcinoma (PDAC) is not available at present. In this study, we compare different algorithms of risk prediction in order to select the best one for constructing a biomarker-based risk score, PancRISK.METHODS: Three hundred and seventy-nine patients with available measurements of three urine biomarkers, (LYVE1, REG1B and TFF1) using retrospectively collected samples, as well as creatinine and age, were randomly split into training and validation sets, following stratification into cases (PDAC) and controls (healthy patients). Several machine learning algorithms were used, and their performance characteristics were compared. The latter included AUC (area under ROC curve) and sensitivity at clinically relevant specificity.RESULTS: None of the algorithms significantly outperformed all others. A logistic regression model, the easiest to interpret, was incorporated into a PancRISK score and subsequently evaluated on the whole data set. The PancRISK performance could be even further improved when CA19-9, commonly used PDAC biomarker, is added to the model.CONCLUSION: PancRISK score enables easy interpretation of the biomarker panel data and is currently being tested to confirm that it can be used for stratification of patients at risk of developing pancreatic cancer completely non-invasively, using urine samples.

UR - http://www.scopus.com/inward/record.url?scp=85077067503&partnerID=8YFLogxK

U2 - 10.1038/s41416-019-0694-0

DO - 10.1038/s41416-019-0694-0

M3 - Article

C2 - 31857725

SP - 1

EP - 5

JO - British Journal of Cancer

JF - British Journal of Cancer

SN - 0007-0920

ER -