Colorectal Cancer Detected by Machine Learning Models Using Conventional Laboratory Test Data

Background: Current diagnostic methods for colorectal cancer (CRC) are colonoscopy and sigmoidoscopy, which are invasive and complex procedures with possible complications. This study aimed to determine models for CRC identification that involve minimally invasive, affordable, portable, and accurate...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Hui Li MS, Jianmei Lin BS, Yanhong Xiao MS, Wenwen Zheng MS, Lu Zhao PhD, Xiangling Yang PhD, Minsheng Zhong MS, Huanliang Liu MD, PhD
Formato:	article
Lenguaje:	EN
Publicado:	SAGE Publishing 2021
Materias:	Neoplasms. Tumors. Oncology. Including cancer and carcinogens RC254-282
Acceso en línea:	https://doaj.org/article/ca2bfa8624df486da2556762203b5033
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:ca2bfa8624df486da2556762203b5033
record_format	dspace
spelling	oai:doaj.org-article:ca2bfa8624df486da2556762203b50332021-11-21T02:04:56ZColorectal Cancer Detected by Machine Learning Models Using Conventional Laboratory Test Data1533-033810.1177/15330338211058352https://doaj.org/article/ca2bfa8624df486da2556762203b50332021-11-01T00:00:00Zhttps://doi.org/10.1177/15330338211058352https://doaj.org/toc/1533-0338Background: Current diagnostic methods for colorectal cancer (CRC) are colonoscopy and sigmoidoscopy, which are invasive and complex procedures with possible complications. This study aimed to determine models for CRC identification that involve minimally invasive, affordable, portable, and accurate screening variables. Methods: This was a retrospective study that used data from electronic medical records of patients with CRC and healthy individuals between July 2017 and June 2018. Laboratory data, including liver enzymes, lipid profiles, complete blood counts, and tumor biomarkers, were extracted from the electronic medical records. Five machine learning models (logistic regression, random forest, k-nearest neighbors, support vector machine [SVM], and naïve Bayes) were used to identify CRC. The performances were evaluated using the areas under the curve (AUCs), sensitivity, specificity, positive predictive values (PPV), and negative predictive values (NPV). Results: A total of 1164 electronic medical records (CRC patients: 582; healthy controls: 582) were included. The logistic regression model achieved the highest performance in identifying CRC (AUC: 0.865, sensitivity: 89.5%, specificity: 83.5%, PPV: 84.4%, NPV: 88.9%). The first four weighted features in the model were carcinoembryonic antigen (CEA), hemoglobin (HGB), lipoprotein (a) (Lp(a)), and high-density lipoprotein (HDL). A diagnostic model for CRC was established based on the four indicators, with an AUC of 0.849 (0.840-0.860) for identifying all CRC patients, and it performed best in discriminating patients with late colon cancer from healthy individuals with an AUC of 0.905 (0.889-0.929). Conclusions: The logistic regression model based on CEA, HGB, Lp(a), and HDL might be a powerful, noninvasive, and cost-effective method to identify CRC.Hui Li MSJianmei Lin BSYanhong Xiao MSWenwen Zheng MSLu Zhao PhDXiangling Yang PhDMinsheng Zhong MSHuanliang Liu MD, PhDSAGE PublishingarticleNeoplasms. Tumors. Oncology. Including cancer and carcinogensRC254-282ENTechnology in Cancer Research & Treatment, Vol 20 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Neoplasms. Tumors. Oncology. Including cancer and carcinogens RC254-282
spellingShingle	Neoplasms. Tumors. Oncology. Including cancer and carcinogens RC254-282 Hui Li MS Jianmei Lin BS Yanhong Xiao MS Wenwen Zheng MS Lu Zhao PhD Xiangling Yang PhD Minsheng Zhong MS Huanliang Liu MD, PhD Colorectal Cancer Detected by Machine Learning Models Using Conventional Laboratory Test Data
description	Background: Current diagnostic methods for colorectal cancer (CRC) are colonoscopy and sigmoidoscopy, which are invasive and complex procedures with possible complications. This study aimed to determine models for CRC identification that involve minimally invasive, affordable, portable, and accurate screening variables. Methods: This was a retrospective study that used data from electronic medical records of patients with CRC and healthy individuals between July 2017 and June 2018. Laboratory data, including liver enzymes, lipid profiles, complete blood counts, and tumor biomarkers, were extracted from the electronic medical records. Five machine learning models (logistic regression, random forest, k-nearest neighbors, support vector machine [SVM], and naïve Bayes) were used to identify CRC. The performances were evaluated using the areas under the curve (AUCs), sensitivity, specificity, positive predictive values (PPV), and negative predictive values (NPV). Results: A total of 1164 electronic medical records (CRC patients: 582; healthy controls: 582) were included. The logistic regression model achieved the highest performance in identifying CRC (AUC: 0.865, sensitivity: 89.5%, specificity: 83.5%, PPV: 84.4%, NPV: 88.9%). The first four weighted features in the model were carcinoembryonic antigen (CEA), hemoglobin (HGB), lipoprotein (a) (Lp(a)), and high-density lipoprotein (HDL). A diagnostic model for CRC was established based on the four indicators, with an AUC of 0.849 (0.840-0.860) for identifying all CRC patients, and it performed best in discriminating patients with late colon cancer from healthy individuals with an AUC of 0.905 (0.889-0.929). Conclusions: The logistic regression model based on CEA, HGB, Lp(a), and HDL might be a powerful, noninvasive, and cost-effective method to identify CRC.
format	article
author	Hui Li MS Jianmei Lin BS Yanhong Xiao MS Wenwen Zheng MS Lu Zhao PhD Xiangling Yang PhD Minsheng Zhong MS Huanliang Liu MD, PhD
author_facet	Hui Li MS Jianmei Lin BS Yanhong Xiao MS Wenwen Zheng MS Lu Zhao PhD Xiangling Yang PhD Minsheng Zhong MS Huanliang Liu MD, PhD
author_sort	Hui Li MS
title	Colorectal Cancer Detected by Machine Learning Models Using Conventional Laboratory Test Data
title_short	Colorectal Cancer Detected by Machine Learning Models Using Conventional Laboratory Test Data
title_full	Colorectal Cancer Detected by Machine Learning Models Using Conventional Laboratory Test Data
title_fullStr	Colorectal Cancer Detected by Machine Learning Models Using Conventional Laboratory Test Data
title_full_unstemmed	Colorectal Cancer Detected by Machine Learning Models Using Conventional Laboratory Test Data
title_sort	colorectal cancer detected by machine learning models using conventional laboratory test data
publisher	SAGE Publishing
publishDate	2021
url	https://doaj.org/article/ca2bfa8624df486da2556762203b5033
work_keys_str_mv	AT huilims colorectalcancerdetectedbymachinelearningmodelsusingconventionallaboratorytestdata AT jianmeilinbs colorectalcancerdetectedbymachinelearningmodelsusingconventionallaboratorytestdata AT yanhongxiaoms colorectalcancerdetectedbymachinelearningmodelsusingconventionallaboratorytestdata AT wenwenzhengms colorectalcancerdetectedbymachinelearningmodelsusingconventionallaboratorytestdata AT luzhaophd colorectalcancerdetectedbymachinelearningmodelsusingconventionallaboratorytestdata AT xianglingyangphd colorectalcancerdetectedbymachinelearningmodelsusingconventionallaboratorytestdata AT minshengzhongms colorectalcancerdetectedbymachinelearningmodelsusingconventionallaboratorytestdata AT huanliangliumdphd colorectalcancerdetectedbymachinelearningmodelsusingconventionallaboratorytestdata
_version_	1718419389965926400

Colorectal Cancer Detected by Machine Learning Models Using Conventional Laboratory Test Data

Ejemplares similares