Frontiers in Oncology (Nov 2021)

A Novel Scoring System for Response of Preoperative Chemoradiotherapy in Locally Advanced Rectal Cancer Using Early-Treatment Blood Features Derived From Machine Learning

  • Jaesik Kim,
  • Jaesik Kim,
  • Jaesik Kim,
  • Kyung-Ah Sohn,
  • Kyung-Ah Sohn,
  • Jung-Hak Kwak,
  • Min Jung Kim,
  • Min Jung Kim,
  • Seung-Bum Ryoo,
  • Seung-Yong Jeong,
  • Seung-Yong Jeong,
  • Kyu Joo Park,
  • Hyun-Cheol Kang,
  • Eui Kyu Chie,
  • Eui Kyu Chie,
  • Sang-Hyuk Jung,
  • Sang-Hyuk Jung,
  • Sang-Hyuk Jung,
  • Dokyoon Kim,
  • Dokyoon Kim,
  • Ji Won Park,
  • Ji Won Park,
  • Ji Won Park,
  • Ji Won Park

DOI
https://doi.org/10.3389/fonc.2021.790894
Journal volume & issue
Vol. 11

Abstract

Read online

BackgroundPreoperative chemoradiotherapy (CRT) is a standard treatment for locally advanced rectal cancer (LARC). However, individual responses to preoperative CRT vary from patient to patient. The aim of this study is to develop a scoring system for the response of preoperative CRT in LARC using blood features derived from machine learning.MethodsPatients who underwent total mesorectal excision after preoperative CRT were included in this study. The performance of machine learning models using blood features before CRT (pre-CRT) and from 1 to 2 weeks after CRT (early-CRT) was evaluated. Based on the best model, important features were selected. The scoring system was developed from the selected model and features. The performance of the new scoring system was compared with those of systemic inflammatory indicators: neutrophil-to-lymphocyte ratio, platelet-to-lymphocyte ratio, lymphocyte-to-monocyte ratio, and the prognostic nutritional index.ResultsThe models using early-CRT blood features had better performances than those using pre-CRT blood features. Based on the ridge regression model, which showed the best performance among the machine learning models (AUROC 0.6322 and AUPRC 0.5965), a novel scoring system for the response of preoperative CRT, named Response Prediction Score (RPS), was developed. The RPS system showed higher predictive power (AUROC 0.6747) than single blood features and systemic inflammatory indicators and stratified the tumor regression grade and overall downstaging clearly.ConclusionWe discovered that we can more accurately predict CRT response by using early-treatment blood data. With larger data, we can develop a more accurate and reliable indicator that can be used in real daily practices. In the future, we urge the collection of early-treatment blood data and pre-treatment blood data.

Keywords