A text-based data mining and toxicity prediction modeling system for a clinical decision support in radiation oncology: A preliminary study

Kwang Hyeon Kim, Suk Lee, Jang Bo Shim, Kyung Hwan Chang, Dae-Sik Yang, Won Sup Yoon, Young Je Park, Chul Yong Kim, Yuan Jie Cao

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

The aim of this study is an integrated research for text-based data mining and toxicity prediction modeling system for clinical decision support system based on big data in radiation oncology as a preliminary research. The structured and unstructured data were prepared by treatment plans and the unstructured data were extracted by dose-volume data image pattern recognition of prostate cancer for research articles crawling through the internet. We modeled an artificial neural network to build a predictor model system for toxicity prediction of organs at risk. We used a text-based data mining approach to build the artificial neural network model for bladder and rectum complication predictions. The pattern recognition method was used to mine the unstructured toxicity data for dose-volume at the detection accuracy of 97.9%. The confusion matrix and training model of the neural network were achieved with 50 modeled plans (n = 50) for validation. The toxicity level was analyzed and the risk factors for 25% bladder, 50% bladder, 20% rectum, and 50% rectum were calculated by the artificial neural network algorithm. As a result, 32 plans could cause complication but 18 plans were designed as non-complication among 50 modeled plans. We integrated data mining and a toxicity modeling method for toxicity prediction using prostate cancer cases. It is shown that a preprocessing analysis using text-based data mining and prediction modeling can be expanded to personalized patient treatment decision support based on big data.

Original languageEnglish
Pages (from-to)231-237
Number of pages7
JournalJournal of the Korean Physical Society
Volume71
Issue number4
DOIs
Publication statusPublished - 2017 Aug 1

Fingerprint

data mining
toxicity
rectum
bladder
radiation
predictions
pattern recognition
cancer
decision support systems
dosage
confusion
preprocessing
organs
education
causes
matrices

Keywords

  • Big data
  • Clinical decision support system
  • Data mining
  • Radiotherapy
  • Toxicity prediction

ASJC Scopus subject areas

  • Physics and Astronomy(all)

Cite this

A text-based data mining and toxicity prediction modeling system for a clinical decision support in radiation oncology : A preliminary study. / Kim, Kwang Hyeon; Lee, Suk; Shim, Jang Bo; Chang, Kyung Hwan; Yang, Dae-Sik; Yoon, Won Sup; Park, Young Je; Kim, Chul Yong; Cao, Yuan Jie.

In: Journal of the Korean Physical Society, Vol. 71, No. 4, 01.08.2017, p. 231-237.

Research output: Contribution to journalArticle

@article{e23d632543ec44e99e107f199579d05e,
title = "A text-based data mining and toxicity prediction modeling system for a clinical decision support in radiation oncology: A preliminary study",
abstract = "The aim of this study is an integrated research for text-based data mining and toxicity prediction modeling system for clinical decision support system based on big data in radiation oncology as a preliminary research. The structured and unstructured data were prepared by treatment plans and the unstructured data were extracted by dose-volume data image pattern recognition of prostate cancer for research articles crawling through the internet. We modeled an artificial neural network to build a predictor model system for toxicity prediction of organs at risk. We used a text-based data mining approach to build the artificial neural network model for bladder and rectum complication predictions. The pattern recognition method was used to mine the unstructured toxicity data for dose-volume at the detection accuracy of 97.9{\%}. The confusion matrix and training model of the neural network were achieved with 50 modeled plans (n = 50) for validation. The toxicity level was analyzed and the risk factors for 25{\%} bladder, 50{\%} bladder, 20{\%} rectum, and 50{\%} rectum were calculated by the artificial neural network algorithm. As a result, 32 plans could cause complication but 18 plans were designed as non-complication among 50 modeled plans. We integrated data mining and a toxicity modeling method for toxicity prediction using prostate cancer cases. It is shown that a preprocessing analysis using text-based data mining and prediction modeling can be expanded to personalized patient treatment decision support based on big data.",
keywords = "Big data, Clinical decision support system, Data mining, Radiotherapy, Toxicity prediction",
author = "Kim, {Kwang Hyeon} and Suk Lee and Shim, {Jang Bo} and Chang, {Kyung Hwan} and Dae-Sik Yang and Yoon, {Won Sup} and Park, {Young Je} and Kim, {Chul Yong} and Cao, {Yuan Jie}",
year = "2017",
month = "8",
day = "1",
doi = "10.3938/jkps.71.231",
language = "English",
volume = "71",
pages = "231--237",
journal = "Journal of the Korean Physical Society",
issn = "0374-4884",
publisher = "Korean Physical Society",
number = "4",

}

TY - JOUR

T1 - A text-based data mining and toxicity prediction modeling system for a clinical decision support in radiation oncology

T2 - A preliminary study

AU - Kim, Kwang Hyeon

AU - Lee, Suk

AU - Shim, Jang Bo

AU - Chang, Kyung Hwan

AU - Yang, Dae-Sik

AU - Yoon, Won Sup

AU - Park, Young Je

AU - Kim, Chul Yong

AU - Cao, Yuan Jie

PY - 2017/8/1

Y1 - 2017/8/1

N2 - The aim of this study is an integrated research for text-based data mining and toxicity prediction modeling system for clinical decision support system based on big data in radiation oncology as a preliminary research. The structured and unstructured data were prepared by treatment plans and the unstructured data were extracted by dose-volume data image pattern recognition of prostate cancer for research articles crawling through the internet. We modeled an artificial neural network to build a predictor model system for toxicity prediction of organs at risk. We used a text-based data mining approach to build the artificial neural network model for bladder and rectum complication predictions. The pattern recognition method was used to mine the unstructured toxicity data for dose-volume at the detection accuracy of 97.9%. The confusion matrix and training model of the neural network were achieved with 50 modeled plans (n = 50) for validation. The toxicity level was analyzed and the risk factors for 25% bladder, 50% bladder, 20% rectum, and 50% rectum were calculated by the artificial neural network algorithm. As a result, 32 plans could cause complication but 18 plans were designed as non-complication among 50 modeled plans. We integrated data mining and a toxicity modeling method for toxicity prediction using prostate cancer cases. It is shown that a preprocessing analysis using text-based data mining and prediction modeling can be expanded to personalized patient treatment decision support based on big data.

AB - The aim of this study is an integrated research for text-based data mining and toxicity prediction modeling system for clinical decision support system based on big data in radiation oncology as a preliminary research. The structured and unstructured data were prepared by treatment plans and the unstructured data were extracted by dose-volume data image pattern recognition of prostate cancer for research articles crawling through the internet. We modeled an artificial neural network to build a predictor model system for toxicity prediction of organs at risk. We used a text-based data mining approach to build the artificial neural network model for bladder and rectum complication predictions. The pattern recognition method was used to mine the unstructured toxicity data for dose-volume at the detection accuracy of 97.9%. The confusion matrix and training model of the neural network were achieved with 50 modeled plans (n = 50) for validation. The toxicity level was analyzed and the risk factors for 25% bladder, 50% bladder, 20% rectum, and 50% rectum were calculated by the artificial neural network algorithm. As a result, 32 plans could cause complication but 18 plans were designed as non-complication among 50 modeled plans. We integrated data mining and a toxicity modeling method for toxicity prediction using prostate cancer cases. It is shown that a preprocessing analysis using text-based data mining and prediction modeling can be expanded to personalized patient treatment decision support based on big data.

KW - Big data

KW - Clinical decision support system

KW - Data mining

KW - Radiotherapy

KW - Toxicity prediction

UR - http://www.scopus.com/inward/record.url?scp=85027891926&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85027891926&partnerID=8YFLogxK

U2 - 10.3938/jkps.71.231

DO - 10.3938/jkps.71.231

M3 - Article

AN - SCOPUS:85027891926

VL - 71

SP - 231

EP - 237

JO - Journal of the Korean Physical Society

JF - Journal of the Korean Physical Society

SN - 0374-4884

IS - 4

ER -