Content analysis of oral (mouth) cancer-related posts on Instagram.

OBJECTIVE: To examine the content of Instagram posts about oral cancer and assess its usefulness in promoting oral cancer awareness and early detection practices. METHODS: A systematic search of Instagram for posts about oral (mouth) cancer was conducted using the hashtags #oral cancer and #mouth cancer. Posts usefulness in promoting awareness and early detection was assessed using the early detection usefulness score, and caption readability was assessed using the Flesch Kincaid readability score. RESULTS: A total of 81,000 posts were identified, and 200 posts were thoroughly evaluated. Included posts gathered a total of 48,118 (mean = 420.59 likes) and 27,898 views. Most posts (81.5%) were educational to the lay person, and India and the UK were the major contributors. The most discussed topics were prevention and early detection (55%). Representative clinical images were present in 35.5% of posts. Only 9.5% of posts mentioned the source of information, and the mean usefulness score was only 2.1 out of 10. The mean reading ease score was 56.7 ± 43.8 (range from 1 to 98 out of 100). CONCLUSION: Instagram shows potential for promoting oral cancer awareness, particularly in prevention and early detection. However, concerns regarding content quality, scientific validity, and clarity persist.

A novel lightweight deep convolutional neural network for early detection of oral cancer.

OBJECTIVES: To develop a lightweight deep convolutional neural network (CNN) for binary classification of oral lesions into benign and malignant or potentially malignant using standard real-time clinical images. METHODS: A small deep CNN, that uses a pretrained EfficientNet-B0 as a lightweight transfer learning model, was proposed. A data set of 716 clinical images was used to train and test the proposed model. Accuracy, specificity, sensitivity, receiver operating characteristics (ROC) and area under curve (AUC) were used to evaluate performance. Bootstrapping with 120 repetitions was used to calculate arithmetic means and 95% confidence intervals (CIs). RESULTS: The proposed CNN model achieved an accuracy of 85.0% (95% CI: 81.0%-90.0%), a specificity of 84.5% (95% CI: 78.9%-91.5%), a sensitivity of 86.7% (95% CI: 80.4%-93.3%) and an AUC of 0.928 (95% CI: 0.88-0.96). CONCLUSIONS: Deep CNNs can be an effective method to build low-budget embedded vision devices with limited computation power and memory capacity for diagnosis of oral cancer. Artificial intelligence (AI) can improve the quality and reach of oral cancer screening and early detection.

Prevalence and clinical features of pigmented oral lesions.

BACKGROUND: To examine the relative prevalence, types, and clinical features of pigmented lesions of the oral mucosa in 1275 patients attending a university hospital for dental care. METHODS: Patients attending dental clinics at The University of Jordan Hospital over a 1-year period were examined for the presence of oral pigmentations. Histopathological examination was performed on focally pigmented lesions with a suspicious or uncertain clinical diagnosis. RESULTS: A total of 386 (30.2%) patients were found to have oral pigmentations. Of these, racial pigmentation (39.9%) and smokers' melanosis (32.9%) were the most common causes of oral pigmentations. Other causes included amalgam tattoo (18.9%), focal melanotic macules (5.7%), postinflammatory pigmentation (1.6%), pigmentation due to medications or systemic disease (0.52%), heavy metal deposits (0.26%), and oral nevus (0.26%). Gingivae and buccal mucosae were the most common sites for oral pigmentations. CONCLUSION: Pigmentations of the oral mucosa are common. Gingivae and buccal mucosae are the most common sites for oral pigmentations. Proper history and recognition of clinical features are important for effective management.

Antibiotic prophylaxis and early dental implant failure: a quasi-random controlled clinical trial.

PURPOSE: To compare the efficacy of three different antibiotic regimens in reducing early dental implant failure. MATERIALS AND METHODS: In a controlled clinical trial, 270 consecutively treated patients were allocated to three antibiotic groups, alternatively, according to order of participation in the trial: Group A (2 g amoxicillin single preoperative dose), Group B (single preoperative 2 g amoxicillin followed by 500 mg three times daily for 5 days) and Group C (postoperative amoxicillin with clavulanic acid 625 mg three times daily for 5 days). Outcomes were pain, wound infection, dehiscence, adverse events possibly related to antibiotics and early implant failure. The patients were followed postoperatively at 1 week, 1 month and at the beginning of the prosthetic stage. Chi-square test and ANOVA test were used to examine differences. RESULTS: In total, 240 patients were adherent to the trial protocol: Group A, 73 patients (210 implants); Group B, 79 patients (266 implants); and Group C, 88 patients (290 implants). Patients experiencing early implant failure: 12 in Group A (16.4%), 11 in Group B (13.9%) and 13 in Group C (14.8%). No statistically significant differences were observed for any of the outcome measures between the three groups. CONCLUSIONS: It may not be necessary to provide postoperative antibiotics in patients undergoing dental implant placement, however, these preliminary findings need to be confirmed by large multicentre clinical trials.