Copyright
©The Author(s) 2020. Published by Baishideng Publishing Group Inc. All rights reserved.
Highly accurate colorectal cancer prediction model based on Raman spectroscopy using patient serum
Hiroaki Ito, Naoyuki Uragami, Tomokazu Miyazaki, William Yang, Kenji Issha, Kai Matsuo, Satoshi Kimura, Yuji Arai, Hiromasa Tokunaga, Saiko Okada, Machiko Kawamura, Noboru Yokoyama, Miki Kushima, Haruhiro Inoue, Takashi Fukagai, Yumi Kamijo
Hiroaki Ito, Naoyuki Uragami, Kai Matsuo, Noboru Yokoyama, Haruhiro Inoue, Digestive Disease Center, Showa University Koto Toyosu Hospital, Tokyo 135-8577, Japan
Tomokazu Miyazaki, Research Division, JSR Corporation, Tokyo 105-0021, Japan
William Yang, BaySpec Inc., San Jose, CA 95131, United States
Kenji Issha, Fuji Technical Research Inc., Yokohama 220-6215, Japan
Satoshi Kimura, Department of Laboratory Medicine and Central Clinical Laboratory, Showa University Northern Yokohama Hospital, Yokohama 224-8503, Japan
Yuji Arai, Saiko Okada, Department of Clinical Laboratory, Showa University Koto Toyosu Hospital, Tokyo 135-8577, Japan
Hiromasa Tokunaga, Department of Clinical Laboratory, Showa University Hospital, Tokyo 142-8555, Japan, BML Inc., Tokyo 151-0051, Japan
Machiko Kawamura, Department of Hematology, Saitama Cancer Center, Inamachi, Saitama 362-0806, Japan
Miki Kushima, Department of Pathology, Showa University Koto Toyosu Hospital, Tokyo 135-8577, Japan
Takashi Fukagai, Department of Urology, Showa University Koto Toyosu Hospital, Tokyo 135-8577, Japan
Yumi Kamijo, Showa University Koto Toyosu Hospital, Tokyo 135-8577, Japan
Author contributions: Ito H conceived the study; Ito H, Miyazaki T, Kimura S, Kawamura M, Inoue H, Fukagai T, and Kamijo Y contributed to the study design; Ito H, Uragami N, Matsuo K, Arai Y, Tokunaga H, and Okada S collected the blood samples; Arai Y, Tokunaga H, and Okada S centrifuged the blood to prepare the serum samples; Ito H, Uragami N, Matsuo K, and Yokoyama N performed the experiments and delivered patients’ clinical data; Miyazaki T, Yang W and Issha K participated in the measurements; Ito H, Uragami N, Matsuo K, Miyazaki T, Kimura S, and Kawamura M contributed to the data interpretation; Ito H and Miyazaki T performed the statistical analysis; Inoue H, Fukagai T, and Kamijo Y contributed to developing an environment for promoting research; Yang W created the customized Raman spectrometer and measurement software used in this study; Issha K coordinated Raman spectroscopy and software production, and transported and maintained the completed Raman spectroscopy and software; Kushima M performed the histopathological diagnoses of the participants; All authors contributed to manuscript writing, revision, and final approval.
Supported by the Japanese Society for the Promotion of Science (JSPS), based on the JSPS KAKENHI Grants-in-Aid for Scientific Research (C), No. JP17K09022.
Institutional review board statement: The study protocol was reviewed and approved (No. 18T5005) by the Institutional Review Board of Showa University Koto Toyosu Hospital.
Informed consent statement: All participants provided written consent for their participation in this study.
Conflict-of-interest statement: The authors declare no conflicts of interest.
Data sharing statement: The original dataset analyzed in this study was uploaded to “figshare” (
https://figshare.com/s/538980237eea527631a3). All other data in this study are available upon reasonable request to the corresponding author.
Open-Access: This article is an open-access article that was selected by an in-house editor and fully peer-reviewed by external reviewers. It is distributed in accordance with the Creative Commons Attribution NonCommercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited and the use is non-commercial. See:
http://creativecommons.org/Licenses/by-nc/4.0/ Corresponding author: Hiroaki Ito, MD, PhD, Associate Professor, Department of Surgery, Digestive Disease Center, Showa University Koto Toyosu Hospital, 5-1-38 Toyosu, Koto-ku, Tokyo 135-8577, Japan.
h.ito@med.showa-u.ac.jp
Received: July 31, 2020
Peer-review started: July 31, 2020
First decision: September 17, 2020
Revised: September 28, 2020
Accepted: October 19, 2020
Article in press: October 19, 2020
Published online: November 15, 2020
Processing time: 103 Days and 20.7 Hours
BACKGROUND
Colorectal cancer (CRC) is an important disease worldwide, accounting for the second highest number of cancer-related deaths and the third highest number of new cancer cases. The blood test is a simple and minimally invasive diagnostic test. However, there is currently no blood test that can accurately diagnose CRC.
AIM
To develop a comprehensive, spontaneous, minimally invasive, label-free, blood-based CRC screening technique based on Raman spectroscopy.
METHODS
We used Raman spectra recorded using 184 serum samples obtained from patients undergoing colonoscopies. Patients with malignant tumor histories as well as those with cancers in organs other than the large intestine were excluded. Consequently, the specific diseases of 184 patients were CRC (12), rectal neuroendocrine tumor (2), colorectal adenoma (68), colorectal hyperplastic polyp (18), and others (84). We used the 1064-nm wavelength laser for excitation. The power of the laser was set to 200 mW.
RESULTS
Use of the recorded Raman spectra as training data allowed the construction of a boosted tree CRC prediction model based on machine learning. Therefore, the generalized R2 values for CRC, adenomas, hyperplastic polyps, and neuroendocrine tumors were 0.9982, 0.9630, 0.9962, and 0.9986, respectively.
CONCLUSION
For machine learning using Raman spectral data, a highly accurate CRC prediction model with a high R2 value was constructed. We are currently planning studies to demonstrate the accuracy of this model with a large amount of additional data.
Core Tip: We developed a comprehensive, spontaneous, minimally invasive, label-free, blood-based colorectal cancer (CRC) screening technique based on Raman spectroscopy. We used Raman spectra recorded using 184 serum samples obtained from patients undergoing colonoscopies. Use of the recorded Raman spectra as training data allowed the construction of a boosted tree CRC prediction model based on machine learning. The generalized R2 values for CRC was 0.9982. For machine learning using Raman spectral data, we are currently working on the construction of a more accurate CRC prediction model with a large amount of additional data.
