Discovery of prostate specific antigen pattern to predict castration resistant prostate cancer of androgen deprivation therapy

Yejin Kim; Yong Hyun Park; Ji Youl Lee; In Young Choi; Hwanjo Yu

doi:10.1186/s12911-016-0297-0

Discovery of prostate specific antigen pattern to predict castration resistant prostate cancer of androgen deprivation therapy

Yejin Kim, Yong Hyun Park, Ji Youl Lee, In Young Choi, Hwanjo Yu

Pohang University of Science and Technology

Research output: Contribution to journal › Review article › peer-review

9 Scopus citations

Abstract

Background: Prostate specific antigen (PSA) is an important biomarker to monitor the response to the treatment, but has not been fully utilized as a whole sequence. We used a longitudinal biomarker PSA to discover a new prognostic pattern that predicts castration-resistant prostate cancer (CRPC) after androgen deprivation therapy. Methods: We transformed the longitudinal PSA into a discrete sequence, used frequent sequential pattern mining to find candidate patterns from the sequences, and selected the most predictive and informative pattern among the candidates. Results: Patients were less likely to be CRPC if, after PSA values reach nadir, the PSA decreases more than 0.048 ng/ml during a month, and the decrease occurs again. This pattern significantly increased the accuracy of predicting CRPC by supplementing information provided by existing PSA patterns such as pretreatment PSA. Conclusions: This result can help clinicians to stratify men by the risk of CRPC and to determine the patient that needs intensive follow-up.

Original language	English
Article number	63
Journal	BMC Medical Informatics and Decision Making
Volume	16
DOIs	https://doi.org/10.1186/s12911-016-0297-0
State	Published - 18 Jul 2016

Bibliographical note

Funding Information:
Publication charges for this work was partly supported by the Ministry of Science, ICT and Future Planning NIPA-2014-H0201-14-1001 ”IT Consilience Creative Program”, the ICT R&D program of MSIP/IITP B0101-15-0307 "Basic Software Research in Human-level Lifelong Machine Learning", and the Ministry of Education, Science and Technology No. 2012M3C4A7033344 "Next-Generation Information Computing Development Program through the National Research Foundation of Korea". This article has been published as part of BMC Medical Informatics and Decision Making Volume 16 Supplement 1, 2016: Proceedings of the ACM Ninth International Workshop on Data and Text Mining in Biomedical Informatics. The full contents of the supplement are available online at https://bmcmedinformdecismak.biomedcentral.com/ articles/supplements/volume-16-supplement-1.

Publisher Copyright:
© 2016 Kim et al.

Keywords

Frequent sequential pattern mining
Longitudinal biomarker
Prediction
Prostate specific antigen

UN SDGs

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

Access to Document

10.1186/s12911-016-0297-0

Cite this

@article{dc910a26e1a34dd196acdcc658c117be,

title = "Discovery of prostate specific antigen pattern to predict castration resistant prostate cancer of androgen deprivation therapy",

abstract = "Background: Prostate specific antigen (PSA) is an important biomarker to monitor the response to the treatment, but has not been fully utilized as a whole sequence. We used a longitudinal biomarker PSA to discover a new prognostic pattern that predicts castration-resistant prostate cancer (CRPC) after androgen deprivation therapy. Methods: We transformed the longitudinal PSA into a discrete sequence, used frequent sequential pattern mining to find candidate patterns from the sequences, and selected the most predictive and informative pattern among the candidates. Results: Patients were less likely to be CRPC if, after PSA values reach nadir, the PSA decreases more than 0.048 ng/ml during a month, and the decrease occurs again. This pattern significantly increased the accuracy of predicting CRPC by supplementing information provided by existing PSA patterns such as pretreatment PSA. Conclusions: This result can help clinicians to stratify men by the risk of CRPC and to determine the patient that needs intensive follow-up.",

keywords = "Frequent sequential pattern mining, Longitudinal biomarker, Prediction, Prostate specific antigen",

author = "Yejin Kim and Park, {Yong Hyun} and Lee, {Ji Youl} and Choi, {In Young} and Hwanjo Yu",

note = "Funding Information: Publication charges for this work was partly supported by the Ministry of Science, ICT and Future Planning NIPA-2014-H0201-14-1001 ”IT Consilience Creative Program”, the ICT R&D program of MSIP/IITP B0101-15-0307 {"}Basic Software Research in Human-level Lifelong Machine Learning{"}, and the Ministry of Education, Science and Technology No. 2012M3C4A7033344 {"}Next-Generation Information Computing Development Program through the National Research Foundation of Korea{"}. This article has been published as part of BMC Medical Informatics and Decision Making Volume 16 Supplement 1, 2016: Proceedings of the ACM Ninth International Workshop on Data and Text Mining in Biomedical Informatics. The full contents of the supplement are available online at https://bmcmedinformdecismak.biomedcentral.com/ articles/supplements/volume-16-supplement-1. Publisher Copyright: {\textcopyright} 2016 Kim et al.",

year = "2016",

month = jul,

day = "18",

doi = "10.1186/s12911-016-0297-0",

language = "English",

volume = "16",

journal = "BMC Medical Informatics and Decision Making",

issn = "1472-6947",

publisher = "BioMed Central Ltd.",

}

TY - JOUR

T1 - Discovery of prostate specific antigen pattern to predict castration resistant prostate cancer of androgen deprivation therapy

AU - Kim, Yejin

AU - Park, Yong Hyun

AU - Lee, Ji Youl

AU - Choi, In Young

AU - Yu, Hwanjo

N1 - Funding Information: Publication charges for this work was partly supported by the Ministry of Science, ICT and Future Planning NIPA-2014-H0201-14-1001 ”IT Consilience Creative Program”, the ICT R&D program of MSIP/IITP B0101-15-0307 "Basic Software Research in Human-level Lifelong Machine Learning", and the Ministry of Education, Science and Technology No. 2012M3C4A7033344 "Next-Generation Information Computing Development Program through the National Research Foundation of Korea". This article has been published as part of BMC Medical Informatics and Decision Making Volume 16 Supplement 1, 2016: Proceedings of the ACM Ninth International Workshop on Data and Text Mining in Biomedical Informatics. The full contents of the supplement are available online at https://bmcmedinformdecismak.biomedcentral.com/ articles/supplements/volume-16-supplement-1. Publisher Copyright: © 2016 Kim et al.

PY - 2016/7/18

Y1 - 2016/7/18

N2 - Background: Prostate specific antigen (PSA) is an important biomarker to monitor the response to the treatment, but has not been fully utilized as a whole sequence. We used a longitudinal biomarker PSA to discover a new prognostic pattern that predicts castration-resistant prostate cancer (CRPC) after androgen deprivation therapy. Methods: We transformed the longitudinal PSA into a discrete sequence, used frequent sequential pattern mining to find candidate patterns from the sequences, and selected the most predictive and informative pattern among the candidates. Results: Patients were less likely to be CRPC if, after PSA values reach nadir, the PSA decreases more than 0.048 ng/ml during a month, and the decrease occurs again. This pattern significantly increased the accuracy of predicting CRPC by supplementing information provided by existing PSA patterns such as pretreatment PSA. Conclusions: This result can help clinicians to stratify men by the risk of CRPC and to determine the patient that needs intensive follow-up.

AB - Background: Prostate specific antigen (PSA) is an important biomarker to monitor the response to the treatment, but has not been fully utilized as a whole sequence. We used a longitudinal biomarker PSA to discover a new prognostic pattern that predicts castration-resistant prostate cancer (CRPC) after androgen deprivation therapy. Methods: We transformed the longitudinal PSA into a discrete sequence, used frequent sequential pattern mining to find candidate patterns from the sequences, and selected the most predictive and informative pattern among the candidates. Results: Patients were less likely to be CRPC if, after PSA values reach nadir, the PSA decreases more than 0.048 ng/ml during a month, and the decrease occurs again. This pattern significantly increased the accuracy of predicting CRPC by supplementing information provided by existing PSA patterns such as pretreatment PSA. Conclusions: This result can help clinicians to stratify men by the risk of CRPC and to determine the patient that needs intensive follow-up.

KW - Frequent sequential pattern mining

KW - Longitudinal biomarker

KW - Prediction

KW - Prostate specific antigen

UR - http://www.scopus.com/inward/record.url?scp=84978380790&partnerID=8YFLogxK

U2 - 10.1186/s12911-016-0297-0

DO - 10.1186/s12911-016-0297-0

M3 - Review article

C2 - 27453983

AN - SCOPUS:84978380790

SN - 1472-6947

VL - 16

JO - BMC Medical Informatics and Decision Making

JF - BMC Medical Informatics and Decision Making

M1 - 63

ER -

Discovery of prostate specific antigen pattern to predict castration resistant prostate cancer of androgen deprivation therapy

Abstract

Bibliographical note

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this