Clinical Application of Expert Software Based on Six Tumour Biomarkers to Stratify the Risk of Lung Cancer in a Pulmonary Rapid Diagnosis Unit

• Rafael Molina ^[1] ; Jaume Trapé ^[6] ; Adolfo Garrido ^[7] ; Ernesto Salas ^[2] ; Rosa María Domínguez Gutiérrez de Ceballos ^[8] ; Simón Gundín ^[3] ; Antonio León Justel ^[9] ; Marta García de Burgos ^[10] ; Juana Piedad Rivas ^[11] ; María Ángel Julián Ansón ^[12] ; Manuel Matos Garrido ^[13] ; Sofía Lorenzo García ^[14] ; Ramón Marrades ^[1] ; Nekane Múgica Atorrasagasti ^[15] ; Estefanía Luque Crespo ^[4] ; Cecilia López-Ramírez ^[16] ; Fernando Gustavo Gutiérrez Herrero ^[17] ; Carolina González-Fernández ^[6] ; Victoria Villalta Robles ^[10] ; María Cruz González Cocaño ^[18] ; Mónica Ramos Álvarez ^[12] ; José Carvalho Marta ^[13] ; Clara Jiménez García ^[14] ; Raquel Cabezón Vicente ^[7] ; María Pavón Masa ^[4] ; Ruth Sáez de la Maleta Úbeda ^[3] ; Oscar Bernadich ^[19] ; Graciliano Estrada Trigueros ^[20] ; Aurora Orejas ^[18] ; Juan Carlos Santana Astudillo ^[15] ; Jordi Trapé-Úbeda ^[5] ; Antonio Barco-Sánchez ^[9]
  1. [1] Universitat de Barcelona

     Universitat de Barcelona

     Barcelona, España

     
  2. [2] Hospital San Juan de Dios

     Hospital San Juan de Dios

     Santiago, Chile

     
  3. [3] Complejo Asistencial Universitario de Burgos

     Complejo Asistencial Universitario de Burgos

     Burgos, España

     
  4. [4] Hospital Universitario Virgen Macarena

     Hospital Universitario Virgen Macarena

     Sevilla, España

     
  5. [5] Generalitat de Catalunya

     Generalitat de Catalunya

     Barcelona, España

     
  6. [6] Laboratory Medicine, Althaia Xarxa Assistencial Universitària de Manresa, Spain
  7. [7] Clinical Biochemistry Department, Hospital Donostia, San Sebastian, Spain
  8. [8] Clinical Analysis Department, University Hospital Virgen del Rocío, Seville, Spain
  9. [9] Clinical Biochemistry Department, University Hospital Virgen Macarena, Seville, Spain
  10. [10] Clinical Analysis Department, General Hospital of Segovia, Segovia, Spain
  11. [11] Pneumology Department, Leon University Healthcare Complex, Leon, Spain
  12. [12] Clinical Biochemistry Department, Clinical University Hospital Lozano Blesa, Zaragoza, Spain
  13. [13] Clinical Pathology Department, Centro Hospitalar Universitario Lisboa Central, Lisbon, Portugal
  14. [14] Clinical Analysis Department, University General Hospital of Alicante, Alicante, Spain
  15. [15] Pneumology Department, Hospital Donostia, San Sebastian. Spain
  16. [16] Pneumology Department, University Hospital Virgen del Rocío, Seville, Spain
  17. [17] Pneumology Department, Burgos University Hospital, Burgos, Spain
  18. [18] Clinical Analysis Department, Leon University Healthcare Complex, Leon, Spain
  19. [19] Pneumology Department, Althaia Xarxa Assistencial Universitària de Manresa, Spain
  20. [20] Pneumology Department, General Hospital of Segovia, Segovia, Spain

  Mostrar afiliaciones +
• Localización: Archivos de bronconeumología: Organo oficial de la Sociedad Española de Neumología y Cirugía Torácica SEPAR y la Asociación Latinoamericana de Tórax ( ALAT ), ISSN 0300-2896, Vol. 62, Nº. 4 (April 2026), 2026, págs. 226-235
• Idioma: inglés
• Enlaces
  • Texto completo
• Resumen

  • Objectives Diagnostic tools that stratify lung cancer (LC) risk can help prioritize care for patients at the highest risk and optimize time and procedures to achieve the final diagnosis. We have previously demonstrated that six tumour biomarkers (TBs) – CEA, CYFRA 21.1, CA 15-3, SCC Ag, ProGRP, and NSE – can help assess LC risk. We developed expert software that combines these TBs with clinical and imaging data to estimate LC risk.

    Methods The diagnostic accuracy of this expert software was evaluated in a multicentre study. We prospectively recruited 2005 individuals referred to 12 reference hospitals in Spain and Portugal for suspicion of LC. The six TBs were determined and the expert software was applied to all patients and correlated with the final diagnosis.

    Results A final diagnosis of LC was made in 1392 patients. The expert software yielded 87.7% sensitivity, 75.5% specificity, 89.0% positive predictive value and 73.0% negative predictive value. Sensitivity increased with tumour size and extension. The software also provides histological information, correctly predicting cancer in 98.4% of small-cell LC and 93.2% of non-small-cell LC, which correlates with the histological diagnosis of 90% and 91.2%, respectively.

    Conclusions The expert software developed provides excellent diagnostic accuracy for diagnosing LC. Accordingly, this software can help stratify the risk of LC and prioritize the evaluation of patients at higher risk, optimizing procedures based on risk and knowledge of the most likely histological type, and providing a valuable tool for risk stratification and clinical decision support, particularly in Rapid Diagnostic Units.