Machine learning allows robust classification of lung neoplasm tissue using an electronic biopsy through minimally-invasive electrical impedance spectroscopy


Por: Company-Se, G, Pajares, V, Rafecas-Codern, A, Riu, PJ, Rosell-Ferrer, J, Bragós, R, Nescolarde, L

Publicada: 21 mar 2025
Resumen:
New bronchoscopy techniques like radial probe endobronchial ultrasound have been developed for real-time sampling characterization, but their use is still limited. This study aims to use classification algorithms with minimally invasive electrical impedance spectroscopy to improve neoplastic lung tissue identification during biopsies. Decision Tree, Support Vector Machines (SVM), Ensemble Method, K-Nearest Neighbors, Na & iuml;ve Bayes and Discriminant Analysis were applied using mean averaged bioimpedance modulus and phase angle spectra from lung tissue across 15 frequencies (15-307 kHz). Mann-Whitney U test assessed statistical significance between neoplasm and other tissues. Grid search analysis was conducted to determine the optimal hyperparameter configuration for each model, employing a 5-fold cross-validation approach. Model performance was evaluated using Receiver Operating Characteristic curves, with the Area Under Curve (AUC), precision, recall, and F1-score calculated. All the frequencies used to train and test the algorithms obtained high significant differences between neoplasm and the other types of tissues (P < 0.001). All the algorithms implemented obtained an accuracy, AUC and F1-score above the 95% except for Na & iuml;ve Bayes. Decision Tree, Discriminant Analysis and SVM algorithms are suitable for the implementation of a new low-cost guidance method during bronchoscopy.

Filiaciones:
Company-Se, G:
 Univ Politecn Cataluna, Dept Elect Engn, Barcelona 08034, Spain

Pajares, V:
 Hosp Santa Creu i Sant Pau, Dept Resp Med, Barcelona 08041, Spain

Rafecas-Codern, A:
 Hosp Santa Creu i Sant Pau, Dept Resp Med, Barcelona 08041, Spain

Riu, PJ:
 Univ Politecn Cataluna, Dept Elect Engn, Barcelona 08034, Spain

Rosell-Ferrer, J:
 Univ Politecn Cataluna, Dept Elect Engn, Barcelona 08034, Spain

Bragós, R:
 Univ Politecn Cataluna, Dept Elect Engn, Barcelona 08034, Spain

Nescolarde, L:
 Univ Politecn Cataluna, Dept Elect Engn, Barcelona 08034, Spain
ISSN: 20452322





Scientific Reports
Editorial
NATURE RESEARCH, HEIDELBERGER PLATZ 3, BERLIN, 14197, GERMANY, Reino Unido
Tipo de documento: Article
Volumen: 15 Número: 1
Páginas:
WOS Id: 001449770200012
ID de PubMed: 40119130
imagen Green Submitted, Green Accepted, gold

MÉTRICAS