Machine Learning Based Risk Prediction Models for Oral Squamous Cell Carcinoma Using Salivary Biomarkers

Yi Cheng Wang; Pei Chun Hsueh; Chih Ching Wu; Yi Ju Tseng

doi:10.3233/SHTI210213

Machine Learning Based Risk Prediction Models for Oral Squamous Cell Carcinoma Using Salivary Biomarkers

Yi Cheng Wang, Pei Chun Hsueh, Chih Ching Wu, Yi Ju Tseng

Department of Information Management

Research output: Contribution to journal › Article › peer-review

2 Scopus citations

Abstract

Tumor-associated autoantibodies can be used as biomarkers for detecting different types of cancers. Our objective was to use machine learning techniques to predict high-risk cases of oral squamous cell carcinoma (OSCC) with salivary autoantibodies. The optimal model was using eXtreme Gradient Boosting (XGBoost) with the area under the receiver operating characteristic curve (AUC) of 0.765 (p < 0.01). Thus, applying machine learning model to early detect high-risk cases of OSCC could assist the clinic treatment and prognosis.

Original language	English
Pages (from-to)	498-499
Number of pages	2
Journal	Studies in Health Technology and Informatics
Volume	281
DOIs	https://doi.org/10.3233/SHTI210213
State	Published - 27 May 2021

Keywords

autoantibody
machine learning
oral squamous cell carcinoma

UN SDGs

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

Access to Document

10.3233/SHTI210213

Cite this

@article{57cbfd90fdfd4c2eb24f0a55d3c9278c,

title = "Machine Learning Based Risk Prediction Models for Oral Squamous Cell Carcinoma Using Salivary Biomarkers",

abstract = "Tumor-associated autoantibodies can be used as biomarkers for detecting different types of cancers. Our objective was to use machine learning techniques to predict high-risk cases of oral squamous cell carcinoma (OSCC) with salivary autoantibodies. The optimal model was using eXtreme Gradient Boosting (XGBoost) with the area under the receiver operating characteristic curve (AUC) of 0.765 (p < 0.01). Thus, applying machine learning model to early detect high-risk cases of OSCC could assist the clinic treatment and prognosis.",

keywords = "autoantibody, machine learning, oral squamous cell carcinoma",

author = "Wang, {Yi Cheng} and Hsueh, {Pei Chun} and Wu, {Chih Ching} and Tseng, {Yi Ju}",

year = "2021",

month = may,

day = "27",

doi = "10.3233/SHTI210213",

language = "???core.languages.en_GB???",

volume = "281",

pages = "498--499",

journal = "Studies in Health Technology and Informatics",

issn = "0926-9630",

}

TY - JOUR

T1 - Machine Learning Based Risk Prediction Models for Oral Squamous Cell Carcinoma Using Salivary Biomarkers

AU - Wang, Yi Cheng

AU - Hsueh, Pei Chun

AU - Wu, Chih Ching

AU - Tseng, Yi Ju

PY - 2021/5/27

Y1 - 2021/5/27

N2 - Tumor-associated autoantibodies can be used as biomarkers for detecting different types of cancers. Our objective was to use machine learning techniques to predict high-risk cases of oral squamous cell carcinoma (OSCC) with salivary autoantibodies. The optimal model was using eXtreme Gradient Boosting (XGBoost) with the area under the receiver operating characteristic curve (AUC) of 0.765 (p < 0.01). Thus, applying machine learning model to early detect high-risk cases of OSCC could assist the clinic treatment and prognosis.

AB - Tumor-associated autoantibodies can be used as biomarkers for detecting different types of cancers. Our objective was to use machine learning techniques to predict high-risk cases of oral squamous cell carcinoma (OSCC) with salivary autoantibodies. The optimal model was using eXtreme Gradient Boosting (XGBoost) with the area under the receiver operating characteristic curve (AUC) of 0.765 (p < 0.01). Thus, applying machine learning model to early detect high-risk cases of OSCC could assist the clinic treatment and prognosis.

KW - autoantibody

KW - machine learning

KW - oral squamous cell carcinoma

UR - http://www.scopus.com/inward/record.url?scp=85107238073&partnerID=8YFLogxK

U2 - 10.3233/SHTI210213

DO - 10.3233/SHTI210213

M3 - 期刊論文

C2 - 34042619

AN - SCOPUS:85107238073

SN - 0926-9630

VL - 281

SP - 498

EP - 499

JO - Studies in Health Technology and Informatics

JF - Studies in Health Technology and Informatics

ER -

Machine Learning Based Risk Prediction Models for Oral Squamous Cell Carcinoma Using Salivary Biomarkers

Abstract

Keywords

UN SDGs

Access to Document

Fingerprint

Cite this