Journal of Pharmaceutical Research & Reports

Background: Oral Squamous Cell Carcinoma (OSCC) accounts for a significant proportion of oral cancers, often diagnosed at late stages with poor survival outcomes. Artificial Intelligence (AI) has demonstrated promising capabilities in oncology, particularly in survival prediction. This systematic review and meta-analysis evaluates the role of AI in predicting survival outcomes, recurrence, and treatment responses in OSCC patients.

Objective: To assess the diagnostic accuracy, sensitivity, specificity, and clinical impact of AI algorithms in predicting survival outcomes in OSCC.

Methods: A systematic search of PubMed, Scopus, Web of Science, and Cochrane Library databases was conducted to identify studies published between 2000 and 2024. Studies were included if they evaluated AI models for survival prediction in OSCC patients. Pooled diagnostic metrics were calculated, and heterogeneity was assessed using the I² statistic. Subgroup analyses were performed based on data type, AI model, and patient population.

Results: A total of 45 studies involving 8,200 patients were included. The pooled sensitivity and specificity of AI models in predicting 5-year survival were 87% and 82%, respectively. AI models incorporating clinical, imaging, and genetic data outperformed those using single data modalities (AUC: 0.91 vs. 0.79; p < 0.01). Machine learning models, particularly ensemble methods, demonstrated higher accuracy than traditional statistical approaches.

Conclusion: AI provides high accuracy in predicting survival outcomes in OSCC patients, especially when integrating multimodal data. These findings highlight the potential of AI to support personalized treatment planning and improve patient outcomes. Future research should focus on external validation and implementation in clinical workflows.