Extracellular vesicles (EVs) are secreted from most cell types and utilized in a complex network of near and distant cell-to-cell communication. Insight into this complex nanoscopic interaction in the development, progression and treatment of oral squamous cell carcinoma (OSCC) and precancerous oral mucosal disorders, termed oral potentially malignant disorders (OPMDs), remains of interest. In this review, we comprehensively present the current state of knowledge of EVs in OSCC and OPMDs. A systematic literature search strategy was developed and updated to December 17, 2019. Fifty-five articles were identified addressing EVs in OSCC and OPMDs with all but two articles published from 2015, highlighting the novelty of this research area. Themes included the impact of OSCC-derived EVs on phenotypic changes, lymph-angiogenesis, stromal immune response, mechanisms of therapeutic resistance as well as utility of EVs for drug delivery in OSCC and OPMD. Interest and progress of knowledge of EVs in OSCC and OPMD has been expanding on several fronts. The oral cavity presents a unique and accessible microenvironment for nanoparticle study that could present important models for other solid tumours.

Machine learning analyses within the realm of oral cancer outcomes are relatively underexplored compared to other cancer types. This study aimed to assess the performance of machine learning algorithms in identifying oral cancer patients, utilizing microRNA expression data. In this study, we implemented this approach using a panel of oral cancer-associated microRNAs sourced from standard incisional biopsy specimens to identify cases of oral squamous cell carcinomas (OSCC). For the model development process, we used a dataset comprising 30 OSCC and 30 histologically normal epithelium (HNE) cases. We initially trained a logistic regression prediction model using 70 percent of the dataset, while reserving the remaining 30 percent for testing. Subsequently, the model underwent hyperparameter tuning resulting in enhanced performance metrics. The hyperparameter-tuned model exhibited high accuracy (0.894) and ROC AUC (0.898) in predicting OSCC. Testing the model on cases of potentially malignant disorders (OPMDs) revealed that leukoplakia with mild dysplasia was predicted as having a high risk of progressing to OSCC, emphasizing machine learning’s advantage over histopathology in detecting early molecular changes. These findings underscore the necessity for further refinement, incorporating a broader set of variables to enhance the model’s predictive capabilities in assessing the risk of oral potentially malignant disorders.