Title: Redefining oral cancer detection: The role of AI-based biotechnological methods beyond conventional technologies—a systematic review
Abstract:
Background: Oral cancer, particularly oral squamous cell carcinoma (OSCC), remains a major global health concern, with delayed diagnosis contributing substantially to morbidity and mortality. Conventional clinical examination, imaging and histopathological assessment remain the cornerstone of diagnosis but may have limitations related to accessibility, sampling, subjectivity and recognition of early molecular changes. Recent advances in biotechnology have enabled the identification of molecular, biochemical, metabolic and spectral signatures associated with oral carcinogenesis. Integration of these technologies with artificial intelligence (AI) may facilitate automated and non-invasive detection of oral cancer.
Objective: This systematic review evaluated the diagnostic performance of AI-based biotechnological methods for oral cancer detection beyond conventional diagnostic technologies and examined differences in performance according to the underlying biotechnology and AI methodology.
Materials and Methods: A Systematic literature search was performed in PubMed/MEDLINE, Scopus, Web of Science, Embase, Google Scholar and IEEE Xplore from 2010 to 2026 (until June 2026). These terms used for the search were: oral cancer, oral squamous cell carcinoma, OPMDs, artificial intelligence, machine learning, biotechnology, molecular biomarkers, saliva, metabolomics, genomics, epigenomics, transcriptomics, microbiome, spectroscopy, biosensors. Overall 1,304 records were found. There were 884 records after duplicates were removed that were screened for title and abstract. Eighty-four full-text articles were evaluated for eligibility, 46 of which were excluded because of prespecified reasons. There were 38 manuscripts eligible. After reconciling duplicate publications and overlapping and secondary cohorts, 34 independent studies were included in the final narrative synthesis. Studies with only traditional photographs, radiographs or histopathological images were not included. Due to significant sample heterogeneity in biological samples, biotechnology platforms, AI algorithms, reference standards, and validation strategies, a meta-analysis was not performed.
Results: Studies included were molecular, epigenomic profiling, salivary transcriptomics and microbiome analysis, metabolomics, Raman and Fourier-transform infrared (FTIR) spectroscopy, surface-enhanced Raman spectroscopy (SERS), electronic biosensors and multimodal approaches. Generally, molecular assays had the best reported diagnostic performance. In one study, the AUC for salivary DNA methylation and ML was 1.00, and the AUC for salivary metabolomic models was near 0.99. The area under the curve (AUC) for salivary metatranscriptomic models ranged up to 0.90 with a specificity reported up to 97.9%. Raman-based deep-learning techniques showed classification accuracy of >90% in selected datasets and FTIR-based techniques showed classification accuracy of ~95% in selected precancerous tissue datasets. More recent SERS-based liquid-biopsy methods were shown to exhibit promising performance, such as AI-assisted salivary exosome profiling and breath/saliva biosensing.
Conclusion: Oral cancer detection is set to be transformed by an emerging paradigm of AI-based biotechnological approaches to detection, which goes beyond the traditional technology that is based on morphology. A wide range of approaches are available that might allow the detection of biological signatures relevant to oral carcinogenesis with minimal invasiveness, such as salivary molecular profiling, epigenomics, metabolomics, microbial transcriptomics, Raman/FTIR spectroscopy and SERS. But there is currently mostly exploratory evidence. In future studies, prospective multicentre validation, data partitioning at the patient level, independent external validation should be considered before widespread clinical use.
Keywords: Artificial Intelligence, Oral Cancer, Oral Squamous Cell Carcinoma, Biotechnology, Molecular Biomarker, Saliva, Metabolomics, Spectroscopy, Biosensors.
