中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 合肥物质科学研究院
  3. 中国科学院合肥物质科学研究院
Machine learning applied to near-infrared spectra for clinical pleural effusion classification

文献类型：期刊论文

作者Chen, Zhongjian1,2,3,4; Chen, Keke1,2,3,4; Lou, Yan5; Zhu, Jing2,3,4; Mao, Weimin2,3,4; Song, Zhengbo2,3,4
刊名SCIENTIFIC REPORTS
出版日期2021-05-03
卷号11
ISSN号2045-2322
DOI10.1038/s41598-021-87736-4
通讯作者Mao, Weimin(maowm1218@163.com) ; Song, Zhengbo(zbszjch@163.com)
英文摘要Lung cancer patients with malignant pleural effusions (MPE) have a particular poor prognosis. It is crucial to distinguish MPE from benign pleural effusion (BPE). The present study aims to develop a rapid, convenient and economical diagnostic method based on FTIR near-infrared spectroscopy (NIRS) combined with machine learning strategy for clinical pleural effusion classification. NIRS spectra were recorded for 47 MPE samples and 35 BPE samples. The sample data were randomly divided into train set (n=62) and test set (n=20). Partial least squares, random forest, support vector machine (SVM), and gradient boosting machine models were trained, and subsequent predictive performance were predicted on the test set. Besides the whole spectra used in modeling, selected features using SVM recursive feature elimination algorithm were also investigated in modeling. Among those models, NIRS combined with SVM showed the best predictive performance (accuracy: 1.0, kappa: 1.0, and AUC(ROC): 1.0). SVM with the top 50 feature wavenumbers also displayed a high predictive performance (accuracy: 0.95, kappa: 0.89, AUC(ROC): 0.99). Our study revealed that the combination of NIRS and machine learning is an innovative, rapid, and convenient method for clinical pleural effusion classification, and worth further evaluation.
WOS关键词CANCER ; SPECTROSCOPY ; BIOMARKERS ; DIAGNOSIS ; MARKER ; CEA
资助项目National Natural Science Foundation of China[81672315] ; National Natural Science Foundation of China[81802276] ; National Natural Science Foundation of China[81302840] ; Key R&D Program Projects in Zhejiang Province[2017C04G1360498]
WOS研究方向Science & Technology - Other Topics
语种英语
WOS记录号WOS:000657422500001
出版者NATURE RESEARCH
资助机构National Natural Science Foundation of China ; Key R&D Program Projects in Zhejiang Province
源URL[http://ir.hfcas.ac.cn:8080/handle/334002/123850]  
专题中国科学院合肥物质科学研究院
通讯作者Mao, Weimin; Song, Zhengbo
作者单位1.Zhejiang Univ, Coll Pharmaceut Sci, Yuhangtang Rd 866, Hangzhou 310000, Zhejiang, Peoples R China
2.Univ Chinese Acad Sci, Chinese Acad Sci, Canc Hosp, Banshandong Rd 1, Hangzhou 310000, Zhejiang, Peoples R China
3.Zhejiang Canc Hosp, Banshandong Rd 1, Hangzhou 310000, Zhejiang, Peoples R China
4.Chinese Acad Sci, Inst Canc & Basic Med IBMC, Hangzhou, Peoples R China
5.Hangzhou Hosp, Zhejiang Med & Hlth Grp, Intens Care Unit, Banshan Kangjian Rd 1, Hangzhou 310000, Zhejiang, Peoples R China
推荐引用方式
GB/T 7714		 Chen, Zhongjian,Chen, Keke,Lou, Yan,et al. Machine learning applied to near-infrared spectra for clinical pleural effusion classification[J]. SCIENTIFIC REPORTS,2021,11.
APA Chen, Zhongjian,Chen, Keke,Lou, Yan,Zhu, Jing,Mao, Weimin,&Song, Zhengbo.(2021).Machine learning applied to near-infrared spectra for clinical pleural effusion classification.SCIENTIFIC REPORTS,11.
MLA Chen, Zhongjian,et al."Machine learning applied to near-infrared spectra for clinical pleural effusion classification".SCIENTIFIC REPORTS 11(2021).

入库方式： OAI收割

来源：合肥物质科学研究院

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。