An electronic nose-based assistive diagnostic prototype for lung cancer detection with conformal prediction. / Zhan, Xianghao; Wang, Zhan; Yang, Meng; Luo, Zhiyuan; Wang, You; Li, Guang.

In: Measurement, Vol. 158, 107588, 01.07.2020, p. 1-10.

Research output: Contribution to journalArticlepeer-review

Published

Standard

An electronic nose-based assistive diagnostic prototype for lung cancer detection with conformal prediction. / Zhan, Xianghao; Wang, Zhan; Yang, Meng; Luo, Zhiyuan; Wang, You; Li, Guang.

In: Measurement, Vol. 158, 107588, 01.07.2020, p. 1-10.

Research output: Contribution to journalArticlepeer-review

Harvard

APA

Vancouver

Author

Zhan, Xianghao ; Wang, Zhan ; Yang, Meng ; Luo, Zhiyuan ; Wang, You ; Li, Guang. / An electronic nose-based assistive diagnostic prototype for lung cancer detection with conformal prediction. In: Measurement. 2020 ; Vol. 158. pp. 1-10.

BibTeX

@article{2ee6f512e6944d3fbf9897de4417a2db,
title = "An electronic nose-based assistive diagnostic prototype for lung cancer detection with conformal prediction",
abstract = "Lung cancer leads to high moralities in various countries while the reliability ofcancer diagnosis has not been paid enough attention. In this work, a novel application of conformal prediction in lung cancer diagnosis with electronic nose is introduced. The nonconformity measurement is based on k-nearest neighbors. In offline prediction, accuracies of 87.5% and 83.33% have been achieved by conformal predictors based on 1NN and 3NN respectively, outperforming those of simple k-nearest neighbor predictors. Additionally, conformal predictors provides confidence and credibility information of each prediction that could inform the patients of diagnostic risks. In online prediction, with increasing number of samples, the frequency of errors given by conformal predictions can gradually be limited by the significance level set by users. This project manifests that electronic nose promises to be an applicable cheaper analytic tool in assisting lung cancer diagnosis and conformal prediction provides a promising method to ensure reliability.",
author = "Xianghao Zhan and Zhan Wang and Meng Yang and Zhiyuan Luo and You Wang and Guang Li",
year = "2020",
month = jul,
day = "1",
doi = "10.1016/j.measurement.2020.107588",
language = "English",
volume = "158",
pages = "1--10",
journal = "Measurement",
issn = "0263-2241",
publisher = "Elsevier",

}

RIS

TY - JOUR

T1 - An electronic nose-based assistive diagnostic prototype for lung cancer detection with conformal prediction

AU - Zhan, Xianghao

AU - Wang, Zhan

AU - Yang, Meng

AU - Luo, Zhiyuan

AU - Wang, You

AU - Li, Guang

PY - 2020/7/1

Y1 - 2020/7/1

N2 - Lung cancer leads to high moralities in various countries while the reliability ofcancer diagnosis has not been paid enough attention. In this work, a novel application of conformal prediction in lung cancer diagnosis with electronic nose is introduced. The nonconformity measurement is based on k-nearest neighbors. In offline prediction, accuracies of 87.5% and 83.33% have been achieved by conformal predictors based on 1NN and 3NN respectively, outperforming those of simple k-nearest neighbor predictors. Additionally, conformal predictors provides confidence and credibility information of each prediction that could inform the patients of diagnostic risks. In online prediction, with increasing number of samples, the frequency of errors given by conformal predictions can gradually be limited by the significance level set by users. This project manifests that electronic nose promises to be an applicable cheaper analytic tool in assisting lung cancer diagnosis and conformal prediction provides a promising method to ensure reliability.

AB - Lung cancer leads to high moralities in various countries while the reliability ofcancer diagnosis has not been paid enough attention. In this work, a novel application of conformal prediction in lung cancer diagnosis with electronic nose is introduced. The nonconformity measurement is based on k-nearest neighbors. In offline prediction, accuracies of 87.5% and 83.33% have been achieved by conformal predictors based on 1NN and 3NN respectively, outperforming those of simple k-nearest neighbor predictors. Additionally, conformal predictors provides confidence and credibility information of each prediction that could inform the patients of diagnostic risks. In online prediction, with increasing number of samples, the frequency of errors given by conformal predictions can gradually be limited by the significance level set by users. This project manifests that electronic nose promises to be an applicable cheaper analytic tool in assisting lung cancer diagnosis and conformal prediction provides a promising method to ensure reliability.

U2 - 10.1016/j.measurement.2020.107588

DO - 10.1016/j.measurement.2020.107588

M3 - Article

VL - 158

SP - 1

EP - 10

JO - Measurement

JF - Measurement

SN - 0263-2241

M1 - 107588

ER -