Effects of Tobacco Use on Oral Cancer Screening Algorithm Performance

<b>Background/Objectives:</b> Effective screening for oral cancer (OC) remains challenging. Inaccuracies contribute to delayed diagnosis and poor outcomes. Tobacco-related changes in oral mucosa may compromise the accuracy of oral screening approaches, and, in emerging "smart" screening modalities, they may overshadow the influence of other predictive variables. The objective of this study was to evaluate the screening accuracy of an imaging- and risk factor-based OC screening platform in individuals practicing different types of tobacco usage. <b>Methods:</b> 318 subjects who had previously screened positive for increased OC risk were recruited and sorted into "tobacco smoker", "tobacco vaper", "tobacco chewer", "hookah user", "multiple tobacco usage", or "tobacco non-user" groups. Next, demographic information, risk factors, outcome of clinical examination, as well as AFI and pWLI were recorded using a prototype OC screening platform. The OC risk assessment outcome from the OC screening platform was compared to that from an oral medicine specialist. <b>Results:</b> The screening platform demonstrated high sensitivity in tobacco chewers and hookah users, and it also exceeded 90% in smokers, vapers, and multi-product users. In tobacco non-users, 80% screening sensitivity was recorded. Screening specificity was considerably better in tobacco non-users than in the tobacco-user groups, and low in tobacco chewers (33.3%), vapers (55.6%), and smokers (62.5%). Across all groups, agreement between the screening platform outcome and specialist evaluation exceeded 80%. Significant differences in probe accuracy were noted between tobacco non-users and users (<i>p</i> < 0.05), except for tobacco vapers. <b>Conclusions:</b> These findings highlight the need to consider the effects of type of tobacco use on the OC screening approach, and to integrate these variables into imaging-and risk-factor-based algorithms for OC screening.