Oral squamous cell carcinoma diagnosed from saliva metabolic profiling
Menée sur 124 personnes en bonne santé et 249 patients présentant un carcinome épidermoïde de la cavité buccale ou des lésions précancéreuses, cette étude met en évidence l'intérêt d'une méthode, combinant spectrométrie de masse à ionisation par pulvérisation de polymères conducteurs et algorithme d'apprentissage automatique, pour diagnostiquer de manière automatisée un carcinome épidermoïde de la cavité buccale à partir d'échantillons salivaires
We show that the combination of conductive polymer spray mass spectrometry (CPSI-MS) and machine learning provides a simple, fast, and affordable method for oral squamous cell carcinoma diagnosis with 86.7% accuracy. By using CPSI-MS, the direct, high-throughput metabolic profiling of saliva can be readily realized in a noninvasive manner. The self-conductive materials used in CPSI-MS for sample loading and ionization are clean, cheap, and consumable for cohort analysis. Wide coverage of chemical species provides not only the pools of possible metabolite signatures for molecular diagnosis but also the possibility of exploring metabolite function and oncological mechanism. The analysis of saliva samples from 373 individuals was completed within 4.5 h, satisfying the technical demand for point-of-care testing.Saliva is a noninvasive biofluid that can contain metabolite signatures of oral squamous cell carcinoma (OSCC). Conductive polymer spray ionization mass spectrometry (CPSI-MS) is employed to record a wide range of metabolite species within a few seconds, making this technique appealing as a point-of-care method for the early detection of OSCC. Saliva samples from 373 volunteers, 124 who are healthy, 124 who have premalignant lesions, and 125 who are OSCC patients, were collected for discovering and validating dysregulated metabolites and determining altered metabolic pathways. Metabolite markers were reconfirmed at the primary tissue level by desorption electrospray ionization MS imaging (DESI-MSI), demonstrating the reliability of diagnoses based on saliva metabolomics. With the aid of machine learning (ML), OSCC and premalignant lesions can be distinguished from the normal physical condition in real time with an accuracy of 86.7%, on a person by person basis. These results suggest that the combination of CPSI-MS and ML is a feasible tool for accurate, automated diagnosis of OSCC in clinical practice.
Proceedings of the National Academy of Sciences , article en libre accès, 2019