ABSTRACT
Data mining has proven to be a reliable method to analyze and discover useful knowledge about various diseases, including cancer research. In particular, data mining and machine learning algorithms to study oral squamous cell carcinoma (OSCC), the most common form of oral cancer, is a new area of research. This malignant neoplasm can be studied using saliva samples. Saliva is an important biofluid that must be used to verify potential biomarkers associated with oral cancer. In this study, first, we provide an overview of OSSC diagnoses based on machine learning and salivary metabolites. To our knowledge, this is the first study to apply advanced data mining techniques to diagnose OSCC. Then, we give new results of classification and feature selection algorithms used to identify potential salivary biomarkers of OSCC. To accomplish this task, we used the filter feature selection random forest importance algorithm and a wrapper methodology to evaluate the importance of metabolites obtained from gas chromatography mass-spectrometry (GC-MS) in the context of differentiation of OSCC and the control group. Salivary samples (n = 68) were collected for the control group, and the OSCC group were from patients matched for gender, age, and smoking habit. The classification process occurred based on Random Forest (RF) classification algorithm along with 10-cross validation. The results showed that glucuronic acid, maleic acid, and batyl alcohol can classify the samples with an area under the curve (AUC) of 0.91 versus an AUC of 0.76 using all 51 metabolites analyzed. The methodology used in this study can assist healthcare professionals and be adopted to discover diagnostic biomarkers for other diseases.
ABSTRACT
Oral squamous cell carcinoma (OSCC) represents 90% of oral malignant neoplasms. The search for specific biomarkers for OSCC is a very active field of research contributing to establishing early diagnostic methods and unraveling underlying pathogenic mechanisms. In this work we investigated the salivary metabolites and the metabolic pathways of OSCC aiming find possible biomarkers. Salivary metabolites samples from 27 OSCC patients and 41 control individuals were compared through a gas chromatography coupled to a mass spectrometer (GC-MS) technique. Our results allowed identification of pathways of the malate-aspartate shuttle, the beta-alanine metabolism, and the Warburg effect. The possible salivary biomarkers were identified using the area under receiver-operating curve (AUC) criterion. Twenty-four metabolites were identified with AUC > 0.8. Using the threshold of AUC = 0.9 we find malic acid, maltose, protocatechuic acid, lactose, 2-ketoadipic, and catechol metabolites expressed. We notice that this is the first report of salivary metabolome in South American oral cancer patients, to the best of our knowledge. Our findings regarding these metabolic changes are important in discovering salivary biomarkers of OSCC patients. However, additional work needs to be performed considering larger populations to validate our results.
