Establishment of prediction of lymph node metastasis by constructing a genetic algorithm in oral squamous cell carcinoma.

2021 Fiscal Year Final Research Report

• Project/Area Number: 19K10312
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Review Section: Basic Section 57060:Surgical dentistry-related
• Research Institution: Ehime University
• Principal Investigator: Goda Hiroyuki 愛媛大学, 医学部附属病院, 講師 (00464371)
• Project Period (FY): 2019-04-01 – 2022-03-31
• Keywords: 口腔癌 / 頸部リンパ節転移 / 遺伝子診断

Outline of Final Research Achievements

The most important prognostic factor in oral squamous cell carcinoma is the presence of lymph node metastasis. In this study, we investigated the possibility of predicting lymph node metastasis by machine learning based on gene expression profiles of primary tissues. Total RNA was extracted from primary tumors of primary cases of oral squamous cell carcinoma, and after comprehensive gene expression analysis using microarrays, a lymph node metastasis prediction model was constructed using a support vector machine (SVM). The accuracy of the model was evaluated as follows: sensitivity 60%, specificity 100%, and accuracy 80%. The results suggest that machine learning using gene expression profiles of primary tumors may be useful for predicting cervical lymph node metastasis in oral squamous cell carcinoma.

Free Research Field

外科系歯学

Academic Significance and Societal Importance of the Research Achievements

本研究の目的は、原発組織（生検組織）または血清の網羅的遺伝子解析から頸部郭清術の真の適応症例のみ抽出する遺伝子アルゴリズムを構築することである。厳正な適格症例の選択基準が遺伝子解析によって行われ、センチネルリンパ節生検の手法による適切な郭清領域に対する治療が行われれば、治療成績の向上、過剰医療や不足医療による医療費の削減が見込まれ、標準治療の確立という EBM に基づいた cN0 症例の治療方針へのパラダイムシフトにつなげることができると考えられる。また、他領域への適応等による医療界全体への波及効果をも期待できる研究と考えられる。