Background/Objectives: Artificial intelligence (AI) has emerged as a transformative tool in oral medicine, where it holds significant promise for enhancing the diagnosis, treatment, and management of oral cancer. Our team aimed to develop a new tool, capable of diagnosing oral cancer utilizing the capabilities of AI. Methods: The task we aim to solve from computer vision’s perspective is an object detection task. Under this context, a detection is essentially a bounding box drawn around an oral lesion accompanied by the disease’s description. To solve the task at hand, we collected and annotated a wide set of images which were used for training our model. Specifically, we used 205 images of Oral Squamous Cell Carcinoma (OSCC). Following common practice, 80% of the total images were allocated for training, 10% for validation, and 10% for testing. The training set was used to optimize the model’s parameters across multiple iterations. The validation set served to prevent overfitting during training and to guide hyperparameter tuning. Lastly, the test set was used for evaluation of data that had not been previously seen by the model and had not influenced any decisions regarding its architecture or hyperparameters. Moreover, during evaluation, we supplemented the test set by adding 100 images of healthy mucosa to examine whether the model generated false positives on healthy tissue. To broaden the dataset’s coverage, we generated synthetic images by applying data augmentation techniques such as random rotation, scale and noise injection. The model’s architecture was based on YOLO11, which is a widely spread neural network architecture known for its balance between efficiency and performance, used in object detection tasks. Results: The model’s detections were accompanied by a confidence measure, which was used to filter out those with low confidence, and one could choose a lower threshold for maximizing precision or a higher threshold for maximizing recall. Among images that correspond to oral cancer (oral squamous cell carcinoma), the model achieved 59% precision and 41% recall on the validation set and 56% precision and 42% recall on the test set. The limitations of this study include the single institutional design and the relatively small sample size. The number of images used for model training was relatively small (205 images of oral squamous cell carcinoma), which may limit the generalizability of the findings. The main limitation is that the model distinguishes oral squamous cell carcinoma from healthy mucosa. In routine clinical practice, however, the diagnostic challenge is to differentiate oral cancer from a variety of benign and potentially malignant disorders that may present with similar clinical features. The inclusion of other oral lesions is planned in future studies. Conclusions: The efficiency of our AI application may be considered as encouraging, taking the pilot nature of the study into consideration. More clinical photos and better training of the model may lead to better precision and recall, enabling its inclusion in standard clinical practice. Larger multicenter datasets will be required for clinical implementation. AI-driven tools can assist in risk stratification, helping clinicians determine the best treatment plans by analyzing patient data and predicting the likelihood of recurrence or metastasis. AI’s potential extends beyond diagnosis and treatment; it also contributes to monitoring patient outcomes. As research and technology evolve, AI’s role in oral cancer is likely to become increasingly indispensable.

OA Text is an independent open-access scientific publisher showcases innovative research and ideas aimed at improving health by linking research and practice to the benefit of society.

Oral squamous cell carcinoma (OSCC) prognosis remains limited by TNM staging alone. We conducted a systematic review and meta-analysis to evaluate preoperative neutrophil-to-lymphocyte (NLR), platelet-to-lymphocyte (PLR) and lymphocyte-to-monocyte (LMR) ratios as prognostic markers. We searched PubMed/MEDLINE, Scopus, Base, Google Scholar and ScienceDirect from inception to 30 May 2026. Eligible studies reported preoperative ratios and survival outcomes, namely, overall survival (OS), disease-specific survival (DSS) and disease-free survival (DFS), in surgically treated OSCC. Risk of bias was assessed with the QUIPS tool. Random-effects meta-analyses of multivariate hazard ratios (HRs) were primary; univariate data, heterogeneity, prediction intervals, sensitivity and subgroup analyses were also performed. Thirty-nine studies (12,153 patients; mostly East Asian retrospective cohorts) were included. Elevated NLR predicted worse overall survival (HR 1.51, 95% CI 1.32–1.73) and disease-specific survival (HR 2.00, 1.58–2.54). NLR also showed a significant association with DFS (HR = 1.47, 95% CI: 1.21–1.78), though the prediction interval crossed unity. PLR and LMR showed weaker, less consistent associations. Evidence was limited by predominant retrospective design, geographic concentration and variable cut-offs. Preoperative NLR is a reproducible, inexpensive prognostic biomarker that may complement TNM staging; standardized thresholds require prospective validation. The review was registered in PROSPERO; no specific funding was received.

Oral squamous cell carcinoma (OSCC), comprising ~90% of oral malignancies, remains a major global health burden with rising incidence despite declining tobacco use. While tobacco and alcohol are classic dominant risk factors, a distinct subgroup of nonsmoking, nondrinking (NSND) patients is increasingly recognized, accounting for 15–35% of OSCC cases in many cohorts, particularly in developed countries. This emerging epidemic shows striking demographic patterns: strong female predominance (often 65–77% of cases), bimodal age distribution with peaks in young adults (70 years), and overrepresentation among non-Hispanic White and certain Asian populations. Unlike traditional habit-related OSCC, which favors the floor of the mouth in older males, NSND tumors predominantly arise on the lateral tongue, gingiva, and buccal mucosa. Etiopathogenesis extends far beyond conventional carcinogens and involves multifactorial mechanisms, including chronic mechanical irritation from dental factors, oral microbiome dysbiosis enriched with periodontal pathogens (e.g., Fusobacterium nucleatum and Porphyromonas gingivalis), limited roles for viruses (minimal HPV contribution, possible EBV or “hit-and-run” HSV effects), genetic susceptibilities (e.g., Fanconi anemia and CDKN2A mutations), epigenetic changes, hormonal influences contributing to female bias, metabolic conditions (diabetes and hyperlipidemia), poor oral hygiene, and chronic inflammation. NSND OSCC frequently exhibits a distinct immunological profile with higher tumor-infiltrating lymphocytes and PD-L1 expression, potentially favoring immunotherapy, though prognosis remains heterogeneous—better in some cohorts due to fewer comorbidities, yet worse in young patients with higher recurrence and second primary tumor risks. Delayed diagnosis is common due to low suspicion in “low-risk” individuals. This review underscores NSND OSCC as a unique entity requiring expanded risk assessment, heightened clinical vigilance for persistent oral lesions regardless of habit history, and targeted research into novel prevention and therapeutic strategies.