Background: Oral cancer requires early diagnosis and treatment to increase the chances of survival. This study aimed to develop an artificial neural network model that helps to predict the individuals' risk of developing oral cancer based on data on risk factors, systematic medical condition, and clinic-pathological features.Methods: A popular data mining algorithm artificial neural network was used for developing the artificial intelligence-based prediction model. A total of 29 variables that were associated with the patients were used for developing the model. The dataset was randomly split into the training dataset 54 (75%) cases and testing dataset 19 (25%) cases. All records and observations were reviewed by Board-certified oral pathologist.Results: A total of 73 patients met the eligibility criteria. Twenty-two (30.13%) were benign cases, and 51 (69.86%) were malignant cases. Thirty-seven were female, and 36 were male, with a mean age of 63.09 years. Our analysis displayed that the average sensitivity and specificity of ANN for oral cancer prediction based on the 10-fold cross-validation analysis was 85.71% (95% confidence interval [CI], 57.19-98.22) and 60.00% (95% CI, 14.66-94.73), respectively. The accuracy of ANN for oral cancer prediction was 78.95% (95% CI, 54.43-931.95). Conclusion:Our results suggest that this machine-learning technique has the potential to help in oral cancer screening and diagnosis based on the datasets. The results demonstrate that the artificial neural network could perform well in estimating the probability of malignancy and improve the positive predictive value that could help to predict the individuals' risk of developing OC based on knowledge of their risk factors, systemic medical conditions, and clinic-pathological data. K E Y W O R D Sartificial neural network, early detection, machine learning, oral cancer, prediction model | INTRODUC TI ONOral cancer (OC) is the 11th most common cancer in the world, the estimated number of new cases of OC is around 657 000, which accounts for more than 330 000 deaths each year. 1 In Saudi Arabia, OC is the third most common malignancy, with lymphoma and leukemia at the first and second positions. 2 Oral squamous cell carcinoma is the most common type of OC. 3 The prevalence of oral cancer How to cite this article: Alhazmi A, Alhazmi Y, Makrami A, et al. Application of artificial intelligence and machine learning for prediction of oral cancer risk.

Objective To provide information on the prevalence and clinical features of impacted third molar teeth in the South-Western region of Saudi Arabia. Material and methods In this cross-sectional study, 1200 panoramic radiographs (50% males and 50% females) were retrieved from the electronic clinical records of patients at the College of Dentistry, Jazan University from December 2014 to December 2016, and impacted third molars were evaluated. Data on clinical and radiographic presentation were analyzed. Results Overall, there were 291 (24.3%) patients with impacted third molars among 1200 radiographs. The distribution of impacted third molars according to the number of impacted teeth was as follows: one impaction in 121 (41.6%); two impactions in 90 (30.9%); three impactions in 42 (14.4%); and four impactions in 38 (13.1%) patients. There was a high prevalence of all impaction types among females (54.5%). Maxillary vertical angulation was most common (50%) followed by mandibular mesioangular angulation (48.3%). The depth of impaction in maxillary teeth was higher than in mandibular teeth. Pain was uncommon (4.5% of patients). Discussion Clinically, vertical impaction in the maxilla was present in 50% of patients because of limited posterior space, and mesioangular angulation in the mandible was present in 48% of patients because of inadequate space between the ramus and the second molar. These findings are similar to other reports. Vertical impaction of the maxillary wisdom tooth is mostly related to the discrepancy between the mesiodistal size of the tooth crown and the limited retromolar space. Conclusion Noiseless presentation of an impacted third molar requires raising the population’s awareness about the need for diagnosis and treatment of the problem to avoid any further complications. The study can be to guide surgical procedures. This study documented the prevalence, pattern, and clinical features of impacted third molars in South Western region of Saudi Arabia.

No abstract

No abstract