Data analysis of electronic nose technology in lung cancer: Generating prediction models by means of Aethena

Sharina Kort, Marjolein Brusse-Keizer, Jan-Willem Gerritsen, Job van der Palen

Research output: Contribution to journalArticleAcademicpeer-review

15 Citations (Scopus)

Abstract

INTRODUCTION: Only 15% of lung cancer cases present with potentially curable disease. Therefore, there is much interest in a fast, non-invasive tool to detect lung cancer earlier. Exhaled breath analysis using electronic nose technology measures volatile organic compounds (VOCs) in exhaled breath that are associated with lung cancer.

METHODS: The diagnostic accuracy of the Aeonose™ is currently being studied in a multi-centre, prospective study in 210 subjects suspected for lung cancer, where approximately half will have a confirmed diagnosis and the other half will have a rejected diagnosis of lung cancer. We will also include 100-150 healthy control subjects. The eNose Company (provider of the Aeonose™) uses a software program, called Aethena, comprising pre-processing, data compression and neural networks to handle big data analyses. Each individual exhaled breath measurement comprises a data matrix with thousands of conductivity values. This is followed by data compression using a Tucker3-like algorithm, resulting in a vector. Subsequently, model selection takes place after entering vectors with different presets in an artificial neural network to train and evaluate the results. Next, a 'judge model' is formed, which is a combination of models for optimizing performance. Finally, two types of cross-validation, being 'leave-10%-out' cross-validation and 'bagging', are used when recalculating the judge models. These judge models are subsequently used to classify new, blind measurements.

DISCUSSION: Data analysis in eNose technology is principally based on generating prediction models that need to be validated internally and externally for eventual use in clinical practice. This paper describes the analysis of big data, captured by eNose technology in lung cancer. This is done by means of generating prediction models with Aethena, a data analysis program specifically developed for analysing VOC data.
Original languageEnglish
Pages (from-to)1752-7163
Number of pages12
JournalJournal of breath research
Volume11
Issue number2
DOIs
Publication statusPublished - 1 Jun 2017

Fingerprint

Electronic Nose
Lung Neoplasms
Technology
Data Compression
Volatile Organic Compounds
Nose
Healthy Volunteers
Software
Prospective Studies

Cite this

@article{7d8953aaf83b43f7bc29d85440841798,
title = "Data analysis of electronic nose technology in lung cancer: Generating prediction models by means of Aethena",
abstract = "INTRODUCTION: Only 15{\%} of lung cancer cases present with potentially curable disease. Therefore, there is much interest in a fast, non-invasive tool to detect lung cancer earlier. Exhaled breath analysis using electronic nose technology measures volatile organic compounds (VOCs) in exhaled breath that are associated with lung cancer. METHODS: The diagnostic accuracy of the Aeonose™ is currently being studied in a multi-centre, prospective study in 210 subjects suspected for lung cancer, where approximately half will have a confirmed diagnosis and the other half will have a rejected diagnosis of lung cancer. We will also include 100-150 healthy control subjects. The eNose Company (provider of the Aeonose™) uses a software program, called Aethena, comprising pre-processing, data compression and neural networks to handle big data analyses. Each individual exhaled breath measurement comprises a data matrix with thousands of conductivity values. This is followed by data compression using a Tucker3-like algorithm, resulting in a vector. Subsequently, model selection takes place after entering vectors with different presets in an artificial neural network to train and evaluate the results. Next, a 'judge model' is formed, which is a combination of models for optimizing performance. Finally, two types of cross-validation, being 'leave-10{\%}-out' cross-validation and 'bagging', are used when recalculating the judge models. These judge models are subsequently used to classify new, blind measurements.DISCUSSION: Data analysis in eNose technology is principally based on generating prediction models that need to be validated internally and externally for eventual use in clinical practice. This paper describes the analysis of big data, captured by eNose technology in lung cancer. This is done by means of generating prediction models with Aethena, a data analysis program specifically developed for analysing VOC data.",
author = "Sharina Kort and Marjolein Brusse-Keizer and Jan-Willem Gerritsen and {van der Palen}, Job",
year = "2017",
month = "6",
day = "1",
doi = "10.1088/1752-7163/aa6b08",
language = "English",
volume = "11",
pages = "1752--7163",
journal = "Journal of breath research",
issn = "1752-7155",
publisher = "IOP Publishing Ltd.",
number = "2",

}

Data analysis of electronic nose technology in lung cancer : Generating prediction models by means of Aethena. / Kort, Sharina; Brusse-Keizer, Marjolein; Gerritsen, Jan-Willem; van der Palen, Job.

In: Journal of breath research, Vol. 11, No. 2, 01.06.2017, p. 1752-7163.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Data analysis of electronic nose technology in lung cancer

T2 - Generating prediction models by means of Aethena

AU - Kort, Sharina

AU - Brusse-Keizer, Marjolein

AU - Gerritsen, Jan-Willem

AU - van der Palen, Job

PY - 2017/6/1

Y1 - 2017/6/1

N2 - INTRODUCTION: Only 15% of lung cancer cases present with potentially curable disease. Therefore, there is much interest in a fast, non-invasive tool to detect lung cancer earlier. Exhaled breath analysis using electronic nose technology measures volatile organic compounds (VOCs) in exhaled breath that are associated with lung cancer. METHODS: The diagnostic accuracy of the Aeonose™ is currently being studied in a multi-centre, prospective study in 210 subjects suspected for lung cancer, where approximately half will have a confirmed diagnosis and the other half will have a rejected diagnosis of lung cancer. We will also include 100-150 healthy control subjects. The eNose Company (provider of the Aeonose™) uses a software program, called Aethena, comprising pre-processing, data compression and neural networks to handle big data analyses. Each individual exhaled breath measurement comprises a data matrix with thousands of conductivity values. This is followed by data compression using a Tucker3-like algorithm, resulting in a vector. Subsequently, model selection takes place after entering vectors with different presets in an artificial neural network to train and evaluate the results. Next, a 'judge model' is formed, which is a combination of models for optimizing performance. Finally, two types of cross-validation, being 'leave-10%-out' cross-validation and 'bagging', are used when recalculating the judge models. These judge models are subsequently used to classify new, blind measurements.DISCUSSION: Data analysis in eNose technology is principally based on generating prediction models that need to be validated internally and externally for eventual use in clinical practice. This paper describes the analysis of big data, captured by eNose technology in lung cancer. This is done by means of generating prediction models with Aethena, a data analysis program specifically developed for analysing VOC data.

AB - INTRODUCTION: Only 15% of lung cancer cases present with potentially curable disease. Therefore, there is much interest in a fast, non-invasive tool to detect lung cancer earlier. Exhaled breath analysis using electronic nose technology measures volatile organic compounds (VOCs) in exhaled breath that are associated with lung cancer. METHODS: The diagnostic accuracy of the Aeonose™ is currently being studied in a multi-centre, prospective study in 210 subjects suspected for lung cancer, where approximately half will have a confirmed diagnosis and the other half will have a rejected diagnosis of lung cancer. We will also include 100-150 healthy control subjects. The eNose Company (provider of the Aeonose™) uses a software program, called Aethena, comprising pre-processing, data compression and neural networks to handle big data analyses. Each individual exhaled breath measurement comprises a data matrix with thousands of conductivity values. This is followed by data compression using a Tucker3-like algorithm, resulting in a vector. Subsequently, model selection takes place after entering vectors with different presets in an artificial neural network to train and evaluate the results. Next, a 'judge model' is formed, which is a combination of models for optimizing performance. Finally, two types of cross-validation, being 'leave-10%-out' cross-validation and 'bagging', are used when recalculating the judge models. These judge models are subsequently used to classify new, blind measurements.DISCUSSION: Data analysis in eNose technology is principally based on generating prediction models that need to be validated internally and externally for eventual use in clinical practice. This paper describes the analysis of big data, captured by eNose technology in lung cancer. This is done by means of generating prediction models with Aethena, a data analysis program specifically developed for analysing VOC data.

U2 - 10.1088/1752-7163/aa6b08

DO - 10.1088/1752-7163/aa6b08

M3 - Article

VL - 11

SP - 1752

EP - 7163

JO - Journal of breath research

JF - Journal of breath research

SN - 1752-7155

IS - 2

ER -