Diagnostic accuracy of artificial intelligence assisted clinical imaging in the detection of oral potentially malignant disorders and oral cancer: A systematic review and meta-analysis

JingWen Li; Wai Ying Kot; Colman Patrick McGrath; Bik Wan Amy Chan; Joshua Wing Kei Ho; Li Wu Zheng

doi:10.1097/JS9.0000000000001469

Diagnostic accuracy of artificial intelligence assisted clinical imaging in the detection of oral potentially malignant disorders and oral cancer: A systematic review and meta-analysis

Int J Surg. 2024 Apr 23. doi: 10.1097/JS9.0000000000001469. Online ahead of print.

Authors

JingWen Li¹, Wai Ying Kot², Colman Patrick McGrath³, Bik Wan Amy Chan⁴, Joshua Wing Kei Ho^{5

6}, Li Wu Zheng¹

Affiliations

¹ Division of Oral & Maxillofacial Surgery, Faculty of Dentistry, The University of Hong Kong, Hong Kong SAR, China.
² Faculty of Dentistry, The University of Hong Kong, Hong Kong SAR, China.
³ Division of Applied Oral Sciences & Community Dental Care, Faculty of Dentistry, The University of Hong Kong, Hong Kong SAR, China.
⁴ Department of Anatomical and Cellular Pathology, Prince of Wales Hospital, The Chinese University of Hong Kong, Hong Kong SAR, China.
⁵ School of Biomedical Sciences, Li Ka Shing Faculty of Medicine, The University of Hong Kong, Hong Kong SAR, China.
⁶ Laboratory of Data Discovery for Health Limited (D24H), Hong Kong Science Park, Hong Kong SAR, China.

PMID: 38652301
DOI: 10.1097/JS9.0000000000001469

Abstract

Background: The objective of this study is to examine the application of AI algorithms in detecting OPMD and oral cancerous lesions, and to evaluate the accuracy variations among different imaging tools employed in these diagnostic processes.

Materials and methods: A systematic search was conducted in four databases: Embase, Web of Science, PubMed, and Scopus. The inclusion criteria included studies using machine learning algorithms to provide diagnostic information on specific oral lesions, prospective or retrospective design, and inclusion of OPMD. Sensitivity and specificity analyses were also required. Forest plots were generated to display overall diagnostic odds ratio (DOR), sensitivity, specificity, negative predictive values, and summary receiver operating characteristic (SROC) curves. Meta-regression analysis was conducted to examine potential differences among different imaging tools.

Results: The overall DOR for AI-based screening of OPMD and oral mucosal cancerous lesions from normal mucosa was 68.438 (95%CI= [39.484, 118.623], I2 = 86%). The area under the SROC curve was 0.938, indicating excellent diagnostic performance. AI-assisted screening showed a sensitivity of 89.9% (95%CI= [0.866,0.925]; I2 = 81%), specificity of 89.2% (95%CI= [0.851,0.922], I2 = 79%), and a high negative predictive value of 89.5% (95%CI= [0.851; 0.927], I2 = 96%). Meta-regression analysis revealed no significant difference among the three image tools. After generating a GOSH plot, the DOR was calculated to be 49.30, and the area under the SROC curve was 0.877. Additionally, sensitivity, specificity, and negative predictive value were 90.5% (95%CI [0.873,0.929], I2=4%), 87.0% (95%CI [0.813,0.912], I2=49%) and 90.1% (95%CI [0.860,0.931], I2=57%), respectively. Subgroup analysis showed that clinical photography had the highest diagnostic accuracy.

Conclusions: AI-based detection using clinical photography shows a high diagnostic odds ratio and is easily accessible in the current era with billions of phone subscribers globally. This indicates that there is significant potential for AI to enhance the diagnostic capabilities of general practitioners to the level of specialists by utilizing clinical photographs, without the need for expensive specialized imaging equipment.