Diagnostic delay is a moderate risk factor of mortality from head and neck cancer. However, part of the effect observed may be due to residual confounding (confounding from unknown variables that are not eliminated by adjustment).

A longer time interval from first symptom to referral for diagnosis is a risk factor for advanced stage and mortality of oral cancer. © 2015 Wiley Periodicals, Inc. Head Neck 38: E2182-E2189, 2016.

Background: In the last decade, several observational studies have suggested that there exists an association between periodontal disease (PD) and Alzheimer's disease (AD). The aim of this systematic review was to investigate whether or not this link exists. Summary: The Preferred Reporting Items for Systematic Reviews and Meta-Analysis guideline for systematic review was used and registered at PROSPERO (CRD42016035377). The search strategy included using electronic databases and by hand searching articles published up to January 2016. MEDLINE via PubMed, EMBASE and Web of Science were searched by 2 independent reviewers. Observational studies including patients meeting criteria for both AD and PD were eligible to be included in the analysis. Quality assessment of selected studies was performed by the Newcastle-Ottawa Scale. From a total of 550 titles and abstracts, 5 studies were included (2 cross-sectional, 2 case-control and one cohort study) in the review. A fixed effects meta-analysis showed that the presence of PD is associated with the presence of AD (OR 1.69, 95% CI 1.21-2.35). When only severe forms of PD were evaluated, a significant association was also observed (OR 2.98, 95% CI 1.58-5.62). Key Messages: In the present review, a significant association was observed between PD and AD. Further studies should be carried out in order to investigate the direction of the association and factors that may confound it.

Aims: To identify factors related to advanced-stage diagnosis of oral cancer to disclose high-risk groups and facilitate early detection strategies. Study design: An ambispective cohort study on 88 consecutive patients treated from January 1998 to December 2003. Inclusion criteria: pathological diagnosis of OSCC (primary tumour) at any oral site and suffering from a tumour at any TNM stage. Variables considered: age, gender, smoking history, alcohol usage, tumour site, macroscopic pattern of the lesion, co-existing precancerous lesion, degree of differentiation, diagnostic delay and TNM stage. Results: A total of 88 patients (mean age 60±11.3; 65.9% males) entered the study. Most patients (54.5%) suffered no delayed diagnosis and 45.5% of the carcinomas were diagnosed at early stages (I-II). The most frequent clinical lesions were ulcers (70.5%). Most cases were well- and moderately-differentiated (91%). Univariate analyses revealed strong associations between advanced stages and moderate-poor differentiation (OR=4.2; 95%CI=1.6-10.9) or tumour site (floor of the mouth (OR=3.6; 95%CI=1.2-11.1); gingivae (OR=8.8; 95%CI=2.0-38.2); and retromolar trigone (OR=8.8; 95%CI=1.5-49.1)). Regression analysis recognised the site of the tumour and the degree of differentiation as significantly associated to high risk of late-stage diagnosis. Conclusions: Screening programmes designed to detect asymptomatic oral cancers should be prioritized. Educational interventions on the population and on the professionals should include a sound knowledge of the disease presentation, specifically on sites like floor of the mouth, gingivae and retromolar trigone. More studies are needed in order to analyse the part of tumour biology on the extension of the disease at the time of diagnosis. Key words: Oral cancer, advanced-stage, diagnosis, cohort study.

The early diagnosis of cancer can facilitate subsequent clinical patient management. Artificial intelligence (AI) has been found to be promising for improving the diagnostic process. The aim of the present study is to increase the evidence on the application of AI to the early diagnosis of oral cancer through a scoping review. A search was performed in the PubMed, Web of Science, Embase and Google Scholar databases during the period from January 2000 to December 2020, referring to the early non-invasive diagnosis of oral cancer based on AI applied to screening. Only accessible full-text articles were considered. Thirty-six studies were included on the early detection of oral cancer based on images (photographs (optical imaging and enhancement technology) and cytology) with the application of AI models. These studies were characterized by their heterogeneous nature. Each publication involved a different algorithm with potential training data bias and few comparative data for AI interpretation. Artificial intelligence may play an important role in precisely predicting the development of oral cancer, though several methodological issues need to be addressed in parallel to the advances in AI techniques, in order to allow large-scale transfer of the latter to population-based detection protocols.