EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Breath Insights: Advancing Lung Cancer Early-Stage Detection Through AI Algorithms in Non-Invasive VOC Profiling Trials

Bernardo S Raimundo iD, Pedro M Leitão iD, Manuel Vinhas iD, Maria V Pires iD, Laura B Quintas iD, Catarina Carvalheiro, Rita Barata, Joana Ip iD, Ricardo Coelho, Sofia Granadeiro, Tânia S Simões, João Gonçalves iD und 17 weitere

Cancers · 16.05.2025 · 17 (10) · 1685

DOI: 10.3390/cancers17101685 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Cancers, online erschienen am 16.05.2025. Verfasst von Bernardo S Raimundo und 28 weiteren Autor:innen. Beteiligte Einrichtung: Unidade de Pulmão, Centro Clínico Champalimaud, Fundação Champalimaud, 1400-038 Lisboa, Portugal. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Champalimaud Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Lung cancer (LC) is the leading cause of cancer-related deaths worldwide. Effective screening strategies for early diagnosis that could improve disease prognosis are lacking. Non-invasive breath analysis of volatile organic compounds (VOC) is a potential method for earlier LC detection. This study explores the association of VOC profiles with artificial intelligence (AI) to achieve a sensitive, specific, and fast method for LC detection. Patients and methods: Exhaled breath air samples were collected from 123 healthy individuals and 73 LC patients at two clinical sites. The enrolled patients had LC diagnosed with different stages. Breath samples were collected before undergoing any treatment, including surgery, and analyzed using gas chromatography coupled to ion-mobility spectrometry (GC-IMS). AI methods classified the overall chromatographic profiles.

Results

GC-IMS is highly sensitive, yielding detailed chromatographic profiles. AI methods ranked the sets of exhaled breath profiles across both groups through training and validation steps, while qualitative information was deliberately not taking part nor influencing the results. The K-nearest neighbor (KNN) algorithm classified the groups with an accuracy of 90% (sensitivity = 87%, specificity = 92%). Narrowing the LC group to those only in early-stage IA, the accuracy was 90% (sensitivity = 90%, specificity = 93%).

Conclusions

Evaluation of the global exhaled breath profiles using AI algorithms enabled LC detection and demonstrated that qualitative information may not be required, thus easing the frustration that many studies have experienced so far. The results show that this approach coupled with screening protocols may improve earlier detection of LC and hence its prognosis.

Schlagwörter

Stichwörter der Autor:innen

artificial intelligencebreath analysisearly detectionlung cancernon-small cell lung cancervolatile organic compounds

Autor:innen und Institutionen

  • Unidade de Pulmão, Centro Clínico Champalimaud, Fundação Champalimaud, 1400-038 Lisboa, Portugal.
  • Departamento de Engenharia Electrotécnica e de Computadores, Faculdade de Ciências e Tecnologia, Universidade Nova de Lisboa, Quinta da Torre, 2829-516 Caparica, Portugal.
  • Serviço de Radiologia, Centro Clínico Champalimaud, Fundação Champalimaud, 1400-038 Lisboa, Portugal.
  • Unidade de Ensaios Clínicos, Centro Clínico Champalimaud, Fundação Champalimaud, 1400-038 Lisboa, Portugal.
  • Unidade de Risco e Diagnóstico Precoce, Centro Clínico Champalimaud, Fundação Champalimaud, 1400-038 Lisboa, Portugal.
  • Serviço de Pneumologia, Centro Hospitalar e Universitário Lisboa Norte, 1649-035 Lisboa, Portugal.

ORCID-Profile: Bernardo S Raimundo, Pedro M Leitão, Manuel Vinhas, Maria V Pires, Laura B Quintas, Joana Ip, João Gonçalves, Paulo Fidalgo, Alípio Araújo, Marcos Pantarotto, Cristina Bárbara, Nuno Gil, Fernando Luis-Ferreira, Pedro D Vaz

Förderung

  • Champalimaud Foundation

Zitieren

APA

Raimundo, B. S., Leitão, P. M., Vinhas, M., Pires, M. V., Quintas, L. B., Carvalheiro, C., Barata, R., Ip, J., Coelho, R., Granadeiro, S., Simões, T. S., Gonçalves, J., Baião, R., Rocha, C., Alves, S., Fidalgo, P., Araújo, A., Matos, C., Simões, S., …, & Vaz, P. D. (2025). Breath Insights: Advancing Lung Cancer Early-Stage Detection Through AI Algorithms in Non-Invasive VOC Profiling Trials. Cancers, 17(10), 1685. https://doi.org/10.3390/cancers17101685

Vancouver

Raimundo BS, Leitão PM, Vinhas M, Pires MV, Quintas LB, Carvalheiro C, et al. Breath Insights: Advancing Lung Cancer Early-Stage Detection Through AI Algorithms in Non-Invasive VOC Profiling Trials. Cancers. 2025;17(10):1685. doi:10.3390/cancers17101685

BibTeX
@article{Raimundo2025,
  author = {Raimundo, Bernardo S and Leitão, Pedro M and Vinhas, Manuel and Pires, Maria V and Quintas, Laura B and Carvalheiro, Catarina and Barata, Rita and Ip, Joana and Coelho, Ricardo and Granadeiro, Sofia and Simões, Tânia S and Gonçalves, João and Baião, Renato and Rocha, Carla and Alves, Sandra and Fidalgo, Paulo and Araújo, Alípio and Matos, Cláudia and Simões, Susana and Alves, Paula and Garrido, Patrícia and Pantarotto, Marcos and Carreiro, Luís and Matos, Rogério and Bárbara, Cristina and Cruz, Jorge and Gil, Nuno and Luis-Ferreira, Fernando and Vaz, Pedro D},
  title = {Breath Insights: Advancing Lung Cancer Early-Stage Detection Through AI Algorithms in Non-Invasive VOC Profiling Trials},
  journal = {Cancers},
  year = {2025},
  volume = {17},
  number = {10},
  pages = {1685},
  doi = {10.3390/cancers17101685}
}
Kostenlos starten →