Intraoperative Diagnosis Support Tool for Serous Ovarian Tumors Based on Microarray Data Using Multicategory Machine Learning

Jee Soo Park, Soo Beom Choi, Hee Jung Kim, Nam Hoon Cho, Sang Wun Kim, Young Tae Kim, Eun Ji Nam, Jai Won Chung, Deok Won Kim

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Objectives Serous borderline ovarian tumors (SBOTs) are a subtype of serous ovarian carcinoma with atypical proliferation. Frozen-section diagnosis has been used as an intraoperative diagnosis tool in supporting the fertility-sparing surgery by diagnosing SBOTs with accuracy of 48% to 79%. Using DNA microarray technology, we designed multicategory classification models to support frozen-section diagnosis within 30 minutes. Materials and Methods We systematically evaluated 6 machine learning algorithms and 3 feature selection methods using 5-fold cross-validation and a grid search on microarray data obtained from the National Center for Biotechnology Information. To validate the models and selected biomarkers, expression profiles were analyzed in tissue samples obtained from the Yonsei University College of Medicine. Results The best accuracy of the optimal machine learning model was 97.3%. In addition, 5 features, including the expression of the putative biomarkers SNTN and AOX1, were selected to differentiate between normal, SBOT, and serous ovarian carcinoma groups. Different expression levels of SNTN and AOX1 were validated by real-time quantitative reverse-transcription polymerase chain reaction, Western blotting, and immunohistochemistry. A multinomial logistic regression model using SNTN and AOX1 alone was used to construct a simple-to-use equation that gave a diagnostic test accuracy of 91.9%. Conclusions We identified 2 biomarkers, SNTN and AOX1, that are likely involved in the pathogenesis and progression of ovarian tumors. An accurate diagnosis of ovarian tumor subclasses by application of the equation in conjunction with expression analysis of SNTN and AOX1 would offer a new accurate diagnosis tool in conjunction with frozen-section diagnosis within 30 minutes.

Original languageEnglish
Pages (from-to)104-113
Number of pages10
JournalInternational Journal of Gynecological Cancer
Volume26
Issue number1
DOIs
Publication statusPublished - 2016 Jan 1

Fingerprint

Frozen Sections
Neoplasms
Biomarkers
Logistic Models
Carcinoma
Information Centers
Biotechnology
Oligonucleotide Array Sequence Analysis
Routine Diagnostic Tests
Reverse Transcription
Fertility
Machine Learning
Western Blotting
Immunohistochemistry
Medicine
Technology
Polymerase Chain Reaction

All Science Journal Classification (ASJC) codes

  • Oncology
  • Obstetrics and Gynaecology

Cite this

Park, Jee Soo ; Choi, Soo Beom ; Kim, Hee Jung ; Cho, Nam Hoon ; Kim, Sang Wun ; Kim, Young Tae ; Nam, Eun Ji ; Chung, Jai Won ; Kim, Deok Won. / Intraoperative Diagnosis Support Tool for Serous Ovarian Tumors Based on Microarray Data Using Multicategory Machine Learning. In: International Journal of Gynecological Cancer. 2016 ; Vol. 26, No. 1. pp. 104-113.
@article{590f8bc0599344a2a052935490b45b74,
title = "Intraoperative Diagnosis Support Tool for Serous Ovarian Tumors Based on Microarray Data Using Multicategory Machine Learning",
abstract = "Objectives Serous borderline ovarian tumors (SBOTs) are a subtype of serous ovarian carcinoma with atypical proliferation. Frozen-section diagnosis has been used as an intraoperative diagnosis tool in supporting the fertility-sparing surgery by diagnosing SBOTs with accuracy of 48{\%} to 79{\%}. Using DNA microarray technology, we designed multicategory classification models to support frozen-section diagnosis within 30 minutes. Materials and Methods We systematically evaluated 6 machine learning algorithms and 3 feature selection methods using 5-fold cross-validation and a grid search on microarray data obtained from the National Center for Biotechnology Information. To validate the models and selected biomarkers, expression profiles were analyzed in tissue samples obtained from the Yonsei University College of Medicine. Results The best accuracy of the optimal machine learning model was 97.3{\%}. In addition, 5 features, including the expression of the putative biomarkers SNTN and AOX1, were selected to differentiate between normal, SBOT, and serous ovarian carcinoma groups. Different expression levels of SNTN and AOX1 were validated by real-time quantitative reverse-transcription polymerase chain reaction, Western blotting, and immunohistochemistry. A multinomial logistic regression model using SNTN and AOX1 alone was used to construct a simple-to-use equation that gave a diagnostic test accuracy of 91.9{\%}. Conclusions We identified 2 biomarkers, SNTN and AOX1, that are likely involved in the pathogenesis and progression of ovarian tumors. An accurate diagnosis of ovarian tumor subclasses by application of the equation in conjunction with expression analysis of SNTN and AOX1 would offer a new accurate diagnosis tool in conjunction with frozen-section diagnosis within 30 minutes.",
author = "Park, {Jee Soo} and Choi, {Soo Beom} and Kim, {Hee Jung} and Cho, {Nam Hoon} and Kim, {Sang Wun} and Kim, {Young Tae} and Nam, {Eun Ji} and Chung, {Jai Won} and Kim, {Deok Won}",
year = "2016",
month = "1",
day = "1",
doi = "10.1097/IGC.0000000000000566",
language = "English",
volume = "26",
pages = "104--113",
journal = "International Journal of Gynecological Cancer",
issn = "1048-891X",
publisher = "Lippincott Williams and Wilkins",
number = "1",

}

Intraoperative Diagnosis Support Tool for Serous Ovarian Tumors Based on Microarray Data Using Multicategory Machine Learning. / Park, Jee Soo; Choi, Soo Beom; Kim, Hee Jung; Cho, Nam Hoon; Kim, Sang Wun; Kim, Young Tae; Nam, Eun Ji; Chung, Jai Won; Kim, Deok Won.

In: International Journal of Gynecological Cancer, Vol. 26, No. 1, 01.01.2016, p. 104-113.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Intraoperative Diagnosis Support Tool for Serous Ovarian Tumors Based on Microarray Data Using Multicategory Machine Learning

AU - Park, Jee Soo

AU - Choi, Soo Beom

AU - Kim, Hee Jung

AU - Cho, Nam Hoon

AU - Kim, Sang Wun

AU - Kim, Young Tae

AU - Nam, Eun Ji

AU - Chung, Jai Won

AU - Kim, Deok Won

PY - 2016/1/1

Y1 - 2016/1/1

N2 - Objectives Serous borderline ovarian tumors (SBOTs) are a subtype of serous ovarian carcinoma with atypical proliferation. Frozen-section diagnosis has been used as an intraoperative diagnosis tool in supporting the fertility-sparing surgery by diagnosing SBOTs with accuracy of 48% to 79%. Using DNA microarray technology, we designed multicategory classification models to support frozen-section diagnosis within 30 minutes. Materials and Methods We systematically evaluated 6 machine learning algorithms and 3 feature selection methods using 5-fold cross-validation and a grid search on microarray data obtained from the National Center for Biotechnology Information. To validate the models and selected biomarkers, expression profiles were analyzed in tissue samples obtained from the Yonsei University College of Medicine. Results The best accuracy of the optimal machine learning model was 97.3%. In addition, 5 features, including the expression of the putative biomarkers SNTN and AOX1, were selected to differentiate between normal, SBOT, and serous ovarian carcinoma groups. Different expression levels of SNTN and AOX1 were validated by real-time quantitative reverse-transcription polymerase chain reaction, Western blotting, and immunohistochemistry. A multinomial logistic regression model using SNTN and AOX1 alone was used to construct a simple-to-use equation that gave a diagnostic test accuracy of 91.9%. Conclusions We identified 2 biomarkers, SNTN and AOX1, that are likely involved in the pathogenesis and progression of ovarian tumors. An accurate diagnosis of ovarian tumor subclasses by application of the equation in conjunction with expression analysis of SNTN and AOX1 would offer a new accurate diagnosis tool in conjunction with frozen-section diagnosis within 30 minutes.

AB - Objectives Serous borderline ovarian tumors (SBOTs) are a subtype of serous ovarian carcinoma with atypical proliferation. Frozen-section diagnosis has been used as an intraoperative diagnosis tool in supporting the fertility-sparing surgery by diagnosing SBOTs with accuracy of 48% to 79%. Using DNA microarray technology, we designed multicategory classification models to support frozen-section diagnosis within 30 minutes. Materials and Methods We systematically evaluated 6 machine learning algorithms and 3 feature selection methods using 5-fold cross-validation and a grid search on microarray data obtained from the National Center for Biotechnology Information. To validate the models and selected biomarkers, expression profiles were analyzed in tissue samples obtained from the Yonsei University College of Medicine. Results The best accuracy of the optimal machine learning model was 97.3%. In addition, 5 features, including the expression of the putative biomarkers SNTN and AOX1, were selected to differentiate between normal, SBOT, and serous ovarian carcinoma groups. Different expression levels of SNTN and AOX1 were validated by real-time quantitative reverse-transcription polymerase chain reaction, Western blotting, and immunohistochemistry. A multinomial logistic regression model using SNTN and AOX1 alone was used to construct a simple-to-use equation that gave a diagnostic test accuracy of 91.9%. Conclusions We identified 2 biomarkers, SNTN and AOX1, that are likely involved in the pathogenesis and progression of ovarian tumors. An accurate diagnosis of ovarian tumor subclasses by application of the equation in conjunction with expression analysis of SNTN and AOX1 would offer a new accurate diagnosis tool in conjunction with frozen-section diagnosis within 30 minutes.

UR - http://www.scopus.com/inward/record.url?scp=84953337505&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84953337505&partnerID=8YFLogxK

U2 - 10.1097/IGC.0000000000000566

DO - 10.1097/IGC.0000000000000566

M3 - Article

C2 - 26512784

AN - SCOPUS:84953337505

VL - 26

SP - 104

EP - 113

JO - International Journal of Gynecological Cancer

JF - International Journal of Gynecological Cancer

SN - 1048-891X

IS - 1

ER -