EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Explainable AI-based breath metabolite profiling for early lung cancer detection

Varsha Ghatage, Shwetha V, Chiranjit Ghosh, Ruchita R Patil

Biosensors and Bioelectronics · 2027

DOI: 10.1016/j.bios.2026.119214 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biosensors and Bioelectronics, 2027. Verfasst von Varsha Ghatage und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Bioinformatics, Manipal School of Life Sciences, Manipal Academy of Higher Education, Manipal, India. Hauptthemen laut MEDLINE: Lung Neoplasms, Electronic Nose, Early Detection of Cancer, Biosensing Techniques. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Manipal Academy of Higher Education.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Lung cancer (LC) is a major cause of cancer-related mortality and current screening methods are invasive, costly or radiation-intensive. This study aims to develop a machine-learning-framework using electronic nose (E-nose) sensor data and demographic variables to classify LC in a cohort of 118 participants (65 LC, 53 healthy controls). Breath samples were analyzed using a six-sensor metal-oxide semiconductor array, with each sensor operated at three different temperatures, resulting in 18 sensor-response features. Regularized logistic regression, random forest and XGBoost classifiers were trained and evaluated using nested five-fold cross-validation with three-fold inner hyperparameter tuning, on sensor-only, demographic-only and combined feature sets with and without SMOTE class balancing. Sensor-only models achieved the highest performance across all three classifiers (ROC-AUC up to 0.9611 ± 0.0357), while demographic-only models performed substantially lower (ROC-AUC 0.7566 ± 0.0468- 0.7815 ± 0.0833). The addition of demographic features did not provide a performance improvement over the sensor-only model. Out-of-fold SHAP analysis identified sensor S4, across all three temperature regimes as the most influential predictor, consistent with univariate statistical testing. A nested feature-ablation analysis showed that a stable subset of ten SHAP-ranked features retained performance comparable to the full feature set (ROC-AUC of 0.9575 ± 0.0462 vs 0.9529 ± 0.0522). Age and smoking status were significantly associated with disease status but contributed limited additional predictive value beyond sensor measurements. These findings support sensor-derived breath VOC patterns as a promising interpretable, non-invasive signal for LC screening, supporting further evaluation of E-nose based screening in large, multi-centre cohorts.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Lung NeoplasmsElectronic NoseEarly Detection of CancerBiosensing TechniquesHumansBreath TestsFemaleMiddle AgedMachine LearningMaleAgedVolatile Organic CompoundsClassification Algorithms

Stichwörter der Autor:innen

Breath analysisElectronic noseFeature importanceMachine learningNested cross-validationVolatile organic compounds

Substanzen

Volatile Organic Compounds

Autor:innen und Institutionen

  • Department of Bioinformatics, Manipal School of Life Sciences, Manipal Academy of Higher Education, Manipal, India.
  • Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, India. Electronic address: shwetha.v@manipal.edu.
  • Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, India.

Förderung

  • Manipal Academy of Higher Education

Zitieren

APA

Ghatage, V., V, S., Ghosh, C., & Patil, R. R. (2027). Explainable AI-based breath metabolite profiling for early lung cancer detection. Biosensors and Bioelectronics. https://doi.org/10.1016/j.bios.2026.119214

Vancouver

Ghatage V, V S, Ghosh C, Patil RR. Explainable AI-based breath metabolite profiling for early lung cancer detection. Biosensors and Bioelectronics. 2027. doi:10.1016/j.bios.2026.119214

BibTeX
@article{Ghatage2027,
  author = {Ghatage, Varsha and V, Shwetha and Ghosh, Chiranjit and Patil, Ruchita R},
  title = {Explainable AI-based breath metabolite profiling for early lung cancer detection},
  journal = {Biosensors and Bioelectronics},
  year = {2027},
  doi = {10.1016/j.bios.2026.119214}
}
Kostenlos starten →