Oral Cancer Early Detection: What Do Patients Need To Know?

How good is ChatGPT at answering patients' questions related to early detection of oral (mouth) cancer?

OBJECTIVES

To examine the quality, reliability, readability, and usefulness of ChatGPT in promoting oral cancer early detection.

STUDY DESIGN

About 108 patient-oriented questions about oral cancer early detection were compiled from expert panels, professional societies, and web-based tools. Questions were categorized into 4 topic domains and ChatGPT 3.5 was asked each question independently. ChatGPT answers were evaluated regarding quality, readability, actionability, and usefulness using. Two experienced reviewers independently assessed each response.

RESULTS

Questions related to clinical appearance constituted 36.1% (n = 39) of the total questions. ChatGPT provided "very useful" responses to the majority of questions (75%; n = 81). The mean Global Quality Score was 4.24 ± 1.3 of 5. The mean reliability score was 23.17 ± 9.87 of 25. The mean understandability score was 76.6% ± 25.9% of 100, while the mean actionability score was 47.3% ± 18.9% of 100. The mean FKS reading ease score was 38.4% ± 29.9%, while the mean SMOG index readability score was 11.65 ± 8.4. No misleading information was identified among ChatGPT responses.

CONCLUSION

ChatGPT is an attractive and potentially useful resource for informing patients about early detection of oral cancer. Nevertheless, concerns do exist about readability and actionability of the offered information.

Oral cancer risk behaviours of Indian immigrants in Australia: a qualitative study

OBJECTIVE

Oral cancer is widespread in South Asia, particularly India. In Australia, Indians are one of the fastest-growing communities. This study aimed to explore the oral cancer-related knowledge, attitudes and practices of Indian immigrants in Australia.

METHODS

Fourteen semi-structured interviews were conducted with Indian immigrants residing across New South Wales and Victoria. Purposive and snowball sampling were used for recruitment. Data were analysed through a directed content analysis approach.

RESULTS

All participants were knowledgeable of oral cancer risks associated with tobacco and alcohol, but few were familiar with the harmful effects of areca nut preparations. Varied attitudes were evident with most participants acknowledging the importance of oral cancer check-ups, yet very few followed this practice. All participants admitted engaging in oral cancer risk practices including areca nut use at least once or more in their lifetime.

CONCLUSION

Oral cancer risk practices are common among Indian immigrants in Australia who possess limited knowledge with varying attitudes in this area. Implications for public health: Preventative strategies are needed to limit the use of oral cancer risk products among Indian immigrants. General practitioners and community organisations can play a key role in raising awareness in this area.

Relationship between oral cancer stage and elapsed time from the onset of signs and symptoms to diagnosis and treatment

BACKGROUND

Oral cancer includes a variety of diagnoses of malignancies that manifest in the oral tissues. Prognosis and treatment depend on the site of involvement, the time of diagnosis, and the stage of the tumor. Early diagnosis of oral mucosal lesions facilitates the early detection of cancer, which is a key step for treatment. The purpose of this study was to investigate the relationship between delayed referral of patients with oral cancer and disease progression at the time of diagnosis.

MATERIALS AND METHODS

In this cross-sectional study, data were collected from 108 patients with a definitive diagnosis of oral cancer by a standardized questionnaire. Data were analyzed by descriptive statistics, including mean, standard deviation, frequency, frequency percentage, and inferential statistics, including logistic regression analysis. P<0.05 was considered to be statistically significant.

RESULTS

The mean time of referral to a therapist was 17.73 ± 22.80 weeks, with 53 (49.1%) patients having a delay of more than 10 weeks. Age, education level, smoking, disease stage, N class, M class, and type of cancer were not significantly associated with the incidence of delay (P>0.05). Patients whose first signs were significant bleeding and/or unrecovered ulceration showed a significant reduction in the delay time (OR = 0.024 and P = 0.038).

CONCLUSION

There was no significant relationship between the disease progression in oral cancer and the time elapsed from the onset of symptoms to diagnosis and treatment. Hence, it seems necessary to take appropriate measures to enhance public awareness of oral cancer and its symptoms.

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.

A Snapshot of Knowledge about Oral Cancer in Italy: A 505 Person Survey

Objectives: Patients' knowledge about oral squamous cell carcinoma (OSCC) plays an important role in primary prevention, early diagnosis, and prognosis and survival rate. The aim of this study was to assess OSCC awareness attitudes among general population in order to provide information for educational interventions. Methods: A survey delivered as a web-based questionnaire was submitted to 505 subjects (aged from 18 to 76 years) in Italy, and the answers collected were statistically analyzed. Information was collected about existence, incidence, features of lesions, risk factors of oral cancer, and self-inspection habits, together with details about professional reference figures and preventive behaviors. Results: Chi-square tests of independence with adjusted standardized residuals highlighted correlations between population features (age, gender, educational attainment, provenance, medical relationship, or previous diagnoses of oral cancer in family) and knowledge about oral cancer. Conclusions: Knowledge about OSCC among the Italian population is limited, and it might be advisable to implement nudging and sensitive customized campaigns in order to promote awareness and therefore improve the prognosis of this disease.

Screening and early detection of oral cancer: current controversies

Some evidence suggests that the early detection of oral cancer (OC) during surveillance might improve survival rates. In addition to this, interventions aimed at enhancing public awareness and knowledge of signs, symptoms and risk factors of OC are thought to decrease the burden of disease. Nevertheless, there is much controversy with regard to the cost-effectiveness of population-based strategies for OC screening. Here, we present and briefly discuss timely findings that have put under scrutiny the applicability of approaches targeted at the early identification of patients with OC.