Detection of lung cancer with electronic nose and logistic regression analysis

Tirzīte, Madara; Bukovskis, Maris; Strazda, Gunta; Jurka, Normunds; Taivāns, Immanuels

doi:10.1088/1752-7163/aae1b8

Cited by 54 publications

(62 citation statements)

References 20 publications

(26 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Suppose the first sensor responds with r 11 at t 1 second and ( 1 + 1) with 12 . The response of the second sensor at 1 second is 21 , ( 1 + 1) is 22 , and the response of the -th sensor at 1 second…”

Section: B Non-uniform Sampling Algorithmmentioning

confidence: 99%

POP-CNN: Predicting Odor Pleasantness With Convolutional Neural Network

Luo

Wong

et al. 2019

IEEE Sensors J.

View full text Add to dashboard Cite

Predicting odor's pleasantness simplifies the evaluation of odors and has the potential to be applied in perfumes and environmental monitoring industry. Classical algorithms for predicting odor's pleasantness generally use a manual feature extractor and an independent classifier. Manual designing a good feature extractor depend on expert knowledge and experience is the key to the accuracy of the algorithms. In order to circumvent this difficulty, we proposed a model for predicting odor's pleasantness by using convolutional neural network. In our model, the convolutional neural layers replace manual feature extractor and show better performance. The experiments show that the correlation between our model and human is over 90% on pleasantness rating. And our model has 99.9% accuracy in distinguishing between absolutely pleasant or unpleasant odors. Index Terms-predicting pleasantness, convolutional neural network, electronic nose.

show abstract

Section: B Non-uniform Sampling Algorithmmentioning

confidence: 99%

POP-CNN: Predicting Odor Pleasantness With Convolutional Neural Network

Luo

Wong

et al. 2019

IEEE Sensors J.

View full text Add to dashboard Cite

show abstract

“…However, logistic regression analysis including clinical parameters in studies using pattern recognition techniques has not been shown often yet. TIRZÏTE et al [19] used logistic regression analysis to predict the presence of lung cancer with the Cyranose 320 electronic nose mainly using segments of exhaled breath as input variables for the logistic regression analysis, but also including a few clinical parameters, such as age, smoking status, smoking history and ambient temperature. They were able to distinguish subjects with lung cancer from controls with a sensitivity of 96% in both smokers and nonsmokers, and a specificity >90% in both groups.…”

Section: Discussionmentioning

confidence: 99%

“…VOCs are of interest since they might be directly related to the presence of diseases, they can be tested noninvasively and pattern recognition techniques can serve as classifiers for diseases. Several studies on exhaled-breath analysis have supported the hypothesis that VOC patterns alter when lung cancer is present [13][14][15][16][17][18][19][20].…”

Section: Introductionmentioning

confidence: 96%

Improving lung cancer diagnosis by combining exhaled-breath data and clinical parameters

et al. 2020

View full text Add to dashboard Cite

IntroductionExhaled-breath analysis of volatile organic compounds could detect lung cancer earlier, possibly leading to improved outcomes. Combining exhaled-breath data with clinical parameters may improve lung cancer diagnosis.MethodsBased on data from a previous multi-centre study, this article reports additional analyses. 138 subjects with non-small cell lung cancer (NSCLC) and 143 controls without NSCLC breathed into the Aeonose. The diagnostic accuracy, presented as area under the receiver operating characteristic curve (AUC-ROC), of the Aeonose itself was compared with 1) performing a multivariate logistic regression analysis of the distinct clinical parameters obtained, and 2) using this clinical information beforehand in the training process of the artificial neural network (ANN) for the breath analysis.ResultsNSCLC patients (mean±sd age 67.1±9.1 years, 58% male) were compared with controls (62.1±7.0 years, 40.6% male). The AUC-ROC of the classification value of the Aeonose itself was 0.75 (95% CI 0.69–0.81). Adding age, number of pack-years and presence of COPD to this value in a multivariate regression analysis resulted in an improved performance with an AUC-ROC of 0.86 (95% CI 0.81–0.90). Adding these clinical variables beforehand to the ANN for classifying the breath print also led to an improved performance with an AUC-ROC of 0.84 (95% CI 0.79–0.89).ConclusionsAdding readily available clinical information to the classification value of exhaled-breath analysis with the Aeonose, either post hoc in a multivariate regression analysis or a priori to the ANN, significantly improves the diagnostic accuracy to detect the presence or absence of lung cancer.

show abstract

“…109 In 2018, several studies were presented or published on this topic and are also summarized in Table 2. 101,105,[110][111][112][113][114][115][116][117] With the exception of one study (de Vries et al 110 ), they all included patients with a suspicion of or proven lung cancer. The percentage of patients with early-stage disease varied between 12% and 79%.…”

Section: Breath-based Screeningmentioning

confidence: 99%

Prevention and Early Detection for NSCLC: Advances in Thoracic Oncology 2018

Balata

Fong

Hendriks

et al. 2019

Journal of Thoracic Oncology

View full text Add to dashboard Cite

Lung cancer remains the leading cause of cancer-related mortality worldwide. Tobacco consumption remains the most important risk factor. Although the prevalence of smoking has decreased overall, it continues to be a significant burden for global health. It is estimated that there are still nearly 1 billion cigarette smokers worldwide. Prevention strategies have largely focused on tobacco control and prevention. However, we have witnessed a dramatic increase in the use of e-cigarettes and other vaping products. Primary chemoprevention has historically not been a successful strategy for lung cancer; however, focused approaches in specific groups of patients at high risk for development of lung cancer are underway. The majority of cases with NSCLC are diagnosed with locally advanced or metastatic disease, where the overall prognosis remains very poor. Early-stage NSCLC on the other hand has a much better prognosis and can usually be treated radically with either surgical resection or radical radiotherapy, with relatively favorable long-term outcomes. In addition to image-based screening, other methods such as breath-based and biofluidbased approaches are now being investigated for early detection of NSCLC. This review will focus on recent advancements in the field of prevention, screening, and early detection of NSCLC.

show abstract

Detection of lung cancer with electronic nose and logistic regression analysis

Cited by 54 publications

References 20 publications

POP-CNN: Predicting Odor Pleasantness With Convolutional Neural Network

POP-CNN: Predicting Odor Pleasantness With Convolutional Neural Network

Improving lung cancer diagnosis by combining exhaled-breath data and clinical parameters

Prevention and Early Detection for NSCLC: Advances in Thoracic Oncology 2018

Contact Info

Product

Resources

About