Detection of COPD and Lung Cancer with electronic nose using ensemble learning methods

Binson, V A; Subramoniam, M.; Mathew, Luke

doi:10.1016/j.cca.2021.10.005

Cited by 52 publications

(7 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In earlier studies, the differentiation between lung cancer and non-lung cancer patients was performed without validation [4]. Some studies split one single cohort into training and validation part [5,21,22]. In one study, for instance, 199 participants were randomly split into an 80% training cohort and 20% validation cohort.…”

Section: Discussionmentioning

confidence: 99%

“…In one study, for instance, 199 participants were randomly split into an 80% training cohort and 20% validation cohort. A classification accuracy of 79% was subsequently attained by using XGBoost method [22]. In another study, by including 60 patients with lung cancer and 107 controls and assigning participants either to training or blinded validation cohort, the blinded validation cohort yielded diagnostic accuracy of 86%, sensitivity of 88% and specificity of 86%.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Cross-site validation of lung cancer diagnosis by electronic nose with deep learning: a multicenter prospective study

Lee,

Kao,

Hsieh

et al. 2024

Respir Res

View full text Add to dashboard Cite

Background Although electronic nose (eNose) has been intensively investigated for diagnosing lung cancer, cross-site validation remains a major obstacle to be overcome and no studies have yet been performed. Methods Patients with lung cancer, as well as healthy control and diseased control groups, were prospectively recruited from two referral centers between 2019 and 2022. Deep learning models for detecting lung cancer with eNose breathprint were developed using training cohort from one site and then tested on cohort from the other site. Semi-Supervised Domain-Generalized (Semi-DG) Augmentation (SDA) and Noise-Shift Augmentation (NSA) methods with or without fine-tuning was applied to improve performance. Results In this study, 231 participants were enrolled, comprising a training/validation cohort of 168 individuals (90 with lung cancer, 16 healthy controls, and 62 diseased controls) and a test cohort of 63 individuals (28 with lung cancer, 10 healthy controls, and 25 diseased controls). The model has satisfactory results in the validation cohort from the same hospital while directly applying the trained model to the test cohort yielded suboptimal results (AUC, 0.61, 95% CI: 0.47─0.76). The performance improved after applying data augmentation methods in the training cohort (SDA, AUC: 0.89 [0.81─0.97]; NSA, AUC:0.90 [0.89─1.00]). Additionally, after applying fine-tuning methods, the performance further improved (SDA plus fine-tuning, AUC:0.95 [0.89─1.00]; NSA plus fine-tuning, AUC:0.95 [0.90─1.00]). Conclusion Our study revealed that deep learning models developed for eNose breathprint can achieve cross-site validation with data augmentation and fine-tuning. Accordingly, eNose breathprints emerge as a convenient, non-invasive, and potentially generalizable solution for lung cancer detection. Clinical trial registration This study is not a clinical trial and was therefore not registered.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Cross-site validation of lung cancer diagnosis by electronic nose with deep learning: a multicenter prospective study

Lee,

Kao,

Hsieh

et al. 2024

Respir Res

View full text Add to dashboard Cite

show abstract

“…In the case of the MOS, for example, these sensors change the conductivity of their sensing element in response to being exposed to the gases [ 54 ]. The response of the sensors is, then, registered and converted to a spectrum or to numerical data by the computer to be posteriorly processed [ 55 ]. The described procedure was used by Binson et al.…”

Section: Volatile Organic Compounds: Detection and Analysismentioning

confidence: 99%

Breath volatile organic compounds (VOCs) as biomarkers for the diagnosis of pathological conditions: A review

2023

View full text Add to dashboard Cite

“…Electronic nose uses an assemblage of metal oxide semiconductor (MOS) sensors to detect diverse gases, and then converts the signals into digital data that can be processed by computer algorithms to attain quantitative prediction along with qualitative identification. Over time, the electronic nose has found extensive application in diverse fields, including food corruption detection [1], air quality monitoring [2], and biomedical diagnosis [3].…”

Section: Introductionmentioning

confidence: 99%

Concentration Prediction of Multi-component Gases Based on Improved Sparrow Search Algorithm

Zhu,

Tian,

Fan

et al. 2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

The electronic nose consists of a sensor array and software algorithms, which can be used for gas identification and concentration prediction. The least-squares support vector machine (LSSVM) is often used for gas concentration prediction. However, the effectiveness of its performance is largely influenced by the chosen parameters. Hence, it is essential to integrate efficient optimization algorithms to enhance the predictive capabilities of LSSVM. This work introduces an improved sparrow search algorithm (ISSA) to enhance the precision of gas concentration prediction by LSSVM. The ISSA approach is evaluated against the particle swarm optimization algorithm (PSO) and the sparrow search algorithm (SSA). Response data of different concentrations of CH4, CO, H2 and their binary gases mixture have been measured using an electronic nose composed of six gas sensors. After processing feature extraction and principal component analysis (PCA) on the original data, it is used as a training and test dataset for prediction models. The results demonstrate that ISSA can significantly enhance the precision of the LSSVM model for gas concentration prediction.

show abstract

Detection of COPD and Lung Cancer with electronic nose using ensemble learning methods

Cited by 52 publications

References 22 publications

Cross-site validation of lung cancer diagnosis by electronic nose with deep learning: a multicenter prospective study

Cross-site validation of lung cancer diagnosis by electronic nose with deep learning: a multicenter prospective study

Breath volatile organic compounds (VOCs) as biomarkers for the diagnosis of pathological conditions: A review

Concentration Prediction of Multi-component Gases Based on Improved Sparrow Search Algorithm

Contact Info

Product

Resources

About