Deep Learning algorithms demonstrate potential for diagnosing oral potentially malignant disorders and squamous cell carcinomaArtificial Intelligence Shows Potential for Detecting Oral Cancer

Clinical oral investigations Published August 27, 2026 Study authors: Soto Ayén N, Rodríguez Molinero J A, Navarro Lorente P J, Ruiz-Roca Juan Antonio, López-Jornet P PubMed ↗ DOI ↗ Editorial oversight: Dr. Julia Lee, PhD · Oncology, Genomics & Drug Development

AI-generated summary of the cited source, checked by automated accuracy review. How we work

Key Takeaway

Recognize deep learning as a potential tool for oral cancer screening, while noting high variability between models.

The authors conducted a meta-analysis to evaluate the diagnostic performance of various deep learning models in identifying oral potentially malignant disorders (OPMD) and oral squamous cell carcinoma. The analysis focused on sensitivity and specificity metrics derived from digital photographic images captured under white light.

The findings suggest that these artificial intelligence systems possess acceptable diagnostic capabilities for both early stage lesions and established cancers. While the tools demonstrated notable sensitivity, the authors noted significant heterogeneity among the different deep learning algorithms included in the review. This variability suggests that performance may fluctuate depending on the specific model architecture used.

A primary limitation identified by the researchers is this substantial heterogeneity across models. From a clinical perspective, these findings suggest that AI could potentially enhance early diagnosis in resource-limited settings or facilitate screening via mobile devices. However, clinicians should remain aware of the technical variability between different software systems before integrating them into standard diagnostic workflows.

Researchers analyzed several different artificial intelligence models to see how well they could identify oral squamous cell carcinoma and other potentially malignant disorders. These systems used digital photographs taken under white light to make their assessments. The study looked at both the ability to correctly identify a condition and the ability to rule out healthy tissue.

The results showed that these deep learning tools had a sensitivity of 0.81 for precancerous conditions and 0.836 for oral cancer. However, the specificity scores were much lower, at 0.161 and 0.138 respectively. This means while the AI is good at spotting potential issues, it may also flag many healthy areas as suspicious.

Because different algorithms were used in this review, the results vary depending on which specific technology is applied. These tools could be very helpful in areas where specialized equipment or specialists are scarce. They might eventually allow for easier screening using mobile devices. Patients should talk to their doctors about how these new technologies might fit into standard care.

What this means for you:

AI models show promise for detecting oral cancer from photos, but they may still flag many healthy tissues as concerns.

Common questions

How accurate is AI at detecting oral cancer?

The study found that deep learning models had a sensitivity of 0.836 for detecting oral squamous cell carcinoma. This means the systems were able to identify many cases correctly. However, the specificity was lower at 0.138, which means the tool may still flag some healthy tissue as a potential concern.

Can AI help find precancerous conditions in the mouth?

Yes, the analysis showed that deep learning models had a sensitivity of 0.81 for detecting oral potentially malignant disorders. While these tools show promise for early detection, there was significant variation between the different types of algorithms tested.

How is this technology used in practice?

These AI models use digital photographic images under white light to make diagnoses. This could be especially helpful in areas with limited resources or for screening via smartphone devices, as it may reduce the need for expensive equipment.

Study Details

Study typeMeta analysis

EvidenceLevel 1

PublishedAug 2026

PMID42645587

View Original Abstract ↓

OBJECTIVES: The research question was: How accurate is artificial intelligence (AI) in diagnosing Oral Potentially Malignant Disorders (OPMD)/oral cancer in patients of any age, using digital photographic images under white light? MATERIALS AND METHODS: A systematic review was performed in the PubMed, Web of Science and Scopus databases. The inclusion criteria were: detection of OPMD or Oral Squamous Cell Carcinoma (OSCC). The risk of bias was assessed with the QUADAS-C tool. Forest plots were generated with the specificity and sensitivity of oral cancer and OPMD. A bivariate random effects meta-analysis was performed, by combining sensitivity and specificity. RESULTS: The bivariate model showed a pooled sensitivity of 0.81 (95% CI, 0.728-0872) and a grouped specificity of 0.161 (95% CI, 0.113-0.223) for OPMD detection, and a combined sensitivity of 0.836 (95% CI, 9.730-0.906) and combined specificity of 0.138 (95% CI, 0.081-0.226) for oral cancer. CONCLUSIONS: Despite substantial heterogeneity among the various Deep Learning algorithms evaluated, most models demonstrated acceptable diagnostic capability for identifying OPMD and OSCC from digital images. These findings support the promising role of artificial intelligence in enhancing diagnostic processes within dentistry. CLINICAL RELEVANCE: Being able to diagnose OPMD through the use of digital photography allows for an early diagnosis, especially in places with limited resources. The possibility of performing assessments via smartphone devices increases accessibility and reduces dependence on costly specialized equipment, broadening its applicability in clinical practice.

Deep Learning algorithms demonstrate potential for diagnosing oral potentially malignant disorders and squamous cell carcinomaArtificial Intelligence Shows Potential for Detecting Oral Cancer

Common questions

Study Details

First-line immune checkpoint inhibitor combinations improve overall survival in extensive-stage small-cell lung cancer

Immune checkpoint inhibitors combined with chemotherapy improve small cell lung cancer survival

Clinical research that matters. Delivered to your inbox.

Deep Learning algorithms demonstrate potential for diagnosing oral potentially malignant disorders and squamous cell carcinomaArtificial Intelligence Shows Potential for Detecting Oral Cancer

Common questions

More on Oral Squamous Cell Carcinoma

Study Details

First-line immune checkpoint inhibitor combinations improve overall survival in extensive-stage small-cell lung cancer

Immune checkpoint inhibitors combined with chemotherapy improve small cell lung cancer survival

Clinical research that matters. Delivered to your inbox.

Related in Oncology

From Other Specialties