Plasma lipid-based machine learning models provides a potential diagnostic tool for colorectal cancer patients

doi:10.1016/j.cca.2022.09.002

	Plasma lipid-based machine learning models provides a potential diagnostic tool for colorectal cancer patients
	Yang, Chenxi 3,4; Zhou, Sicheng 3,4; Zhu, Jing 3,4; Sheng, Huaying 3,4; Mao, Weimin 2,3,4; Fu, Zhixuan 1,3,4; Chen, Zhongjian 1,2,3,4
刊名	CLINICA CHIMICA ACTA
	2022-11-01
卷号	536
关键词	Lipidomics Diagnosis Prognosis ROC Machine learning
ISSN号	0009-8981
DOI	10.1016/j.cca.2022.09.002
通讯作者	Fu, Zhixuan(fuzx@zjcc.org.cn) ; Chen, Zhongjian(chenzj@zjcc.org.cn)
英文摘要	Colorectal cancer is the second leading cause of cancer-related death across the world. So far, screening method for colorectal cancer are limited to blood test, imaging test, and digital rectal examination, that are either invasive or ineffective. So, this study aims to explore novel, more convenient and effective diagnostic method for colorectal cancer. First, the experiment cohort was randomly split to train set and test set, and LC-MS-based plasma lipidomics was applied to identify lipid features in colorectal cancer. Second, univariate and multivar-iate analyses were performed to screen for significantly differentially expressed lipids. Third, single-lipid-based ROC analysis and multiple-lipid-based machine learning modeling were conducted to assess differential lipids' diagnostic performance. Lastly, survival analyses were used to evaluate lipids' prognostic values. In total, 41 differential lipids were screened out, 10 were upregulated and 31 were downregulated in CRC. Only CerP (d15:0_22:0 + O) showed fine predictive accuracy in single-lipid-based ROC analysis. Among the four machine learning models, SVM showed best predictive performance with accuracy (in predicting test set) of 1.0000 (95 % CI: 0.8806, 1.0000), that can be reached by modeling with only 14 lipids. Four lipids had significant prognostic values, that were TG(11:0_18:0_18:0) (HR: 0.34), TG(18:0_18:0_18:1) (HR: 0.34), PC(22:1_12:3) (HR: 2.22), LPC (17:0) (HR: 3.16). In conclusion, this study discovered novel lipid features that have potential diagnostic and prognostic values, and showed combination of plasma lipidomics and machine learning modeling could have outstanding diagnostic performance and may serve as a convenient and more accessible way to aid in clinical diagnosis of colorectal cancer.
资助项目	Projects of Zhejiang Province Medical and Health Science and Technology Plan[2022KY622] ; Projects of Zhejiang Province Medical and Health Science and Technology Plan[2018KY300] ; Projects of Zhejiang Province Medical and Health Science and Technology Plan[2018KY316] ; Key R&D Program Projects in Zhejiang Province[2018C04009] ; National Natural Science Foundation of China[83172210]
WOS关键词	BIOMARKERS ; METABOLISM ; STRATEGY ; RISK
WOS研究方向	Medical Laboratory Technology
语种	英语
出版者	ELSEVIER
WOS记录号	WOS:000875703900001
资助机构	Projects of Zhejiang Province Medical and Health Science and Technology Plan ; Key R&D Program Projects in Zhejiang Province ; National Natural Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.hfcas.ac.cn:8080/handle/334002/129805]
专题	中国科学院合肥物质科学研究院
通讯作者	Fu, Zhixuan; Chen, Zhongjian
作者单位	1.Univ Chinese Acad Sci, Zhejiang Canc Hosp, Canc Hosp, Hangzhou 310022, Zhejiang, Peoples R China 2.Zhejiang Key Lab Diag & Treatment Technol Thorac O, Hangzhou, Zhejiang, Peoples R China 3.Chinese Acad Sci, Inst Basic Med & Canc IBMC, Hangzhou, Zhejiang, Peoples R China 4.Univ Chinese Acad Sci, Zhejiang Canc Hosp, Canc Hosp, Hangzhou, Zhejiang, Peoples R China
推荐引用方式 GB/T 7714	Yang, Chenxi,Zhou, Sicheng,Zhu, Jing,et al. Plasma lipid-based machine learning models provides a potential diagnostic tool for colorectal cancer patients[J]. CLINICA CHIMICA ACTA,2022,536.
APA	Yang, Chenxi.,Zhou, Sicheng.,Zhu, Jing.,Sheng, Huaying.,Mao, Weimin.,...&Chen, Zhongjian.(2022).Plasma lipid-based machine learning models provides a potential diagnostic tool for colorectal cancer patients.CLINICA CHIMICA ACTA,536.
MLA	Yang, Chenxi,et al."Plasma lipid-based machine learning models provides a potential diagnostic tool for colorectal cancer patients".CLINICA CHIMICA ACTA 536(2022).