Interactive skin self-examination digital platforms for the prevention of skin cancer: A narrative literature review

Artificial Intelligence-Driven Skin Aging Simulation as a Novel Skin Cancer Prevention

INTRODUCTION

Skin cancer, a prevalent cancer type among fair-skinned patients globally, poses a relevant public health concern due to rising incidence rates. Ultraviolet (UV) radiation poses a major risk factor for skin cancer. However, intentional tanning associated with sunburns remains a common practice, notably among female adults. Appropriate prevention campaigns targeting children and adolescents are needed to improve sun protection behavior particularly in these age groups. The aim of our study was to investigate if an AI-based simulation of facial skin aging can enhance sun protection behavior in female adults.

METHODS

In this single-center, prospective, observational pilot study at Department of Dermatology at the University Hospital of Basel, we took photographs of healthy young females' faces with a VISIA-CR camera (Version 8.2; Canfield Scientific Inc., Parsippany, NJ, USA) between February and March 2021. Digital images were performed in three angles (straight, left 45°, and right 45°). All participants received an AI-based simulation of their facial skin with continuous aging to 80 years. A newly created anonymous questionnaire capturing participants' sociodemographic data and also tanning and sun protection behavior was completed in pre- and post-aging simulation. To observe long-term effects, a 2-year follow-up was conducted between March and April 2023.

RESULTS

The 60 participants (mean age 23.6 ± 2.5 years) evaluated the importance of sun protection significantly higher after skin aging simulation with VISIA-CR camera (p < 0.0001; 95% CI: 8.2-8.8). Post-intervention, 91.7% (55/60) of the females were motivated to reduce UV exposure and to intensify UV protection in the future since the individual UV-dependent risk was perceived significantly higher (p < 0.001; 95% CI: 5.9-6.7). At 2-year follow-up, 96% (24/25) indicated persistent effort reducing UV exposure. The preference for SPF 50+ sunscreen increased to 46.7% (28/65) directly after the skin aging simulation and continued to rise up to 60.0% (15/25) after 2 years.

CONCLUSIONS

Our data emphasize the potential of AI-assisted photoaging interventions to enhance motivation for UV protection in the short and the long term. We encourage that different age and gender groups are addressed in a personalized, generation-specific manner with the appropriate media and by considering the Hawthorne effect. Campaigns with visual AI support can improve the intent of cancer-preventative behavior.

Enhanced skin cancer diagnosis using optimized CNN architecture and checkpoints for automated dermatological lesion classification

Skin cancer stands as one of the foremost challenges in oncology, with its early detection being crucial for successful treatment outcomes. Traditional diagnostic methods depend on dermatologist expertise, creating a need for more reliable, automated tools. This study explores deep learning, particularly Convolutional Neural Networks (CNNs), to enhance the accuracy and efficiency of skin cancer diagnosis. Leveraging the HAM10000 dataset, a comprehensive collection of dermatoscopic images encompassing a diverse range of skin lesions, this study introduces a sophisticated CNN model tailored for the nuanced task of skin lesion classification. The model's architecture is intricately designed with multiple convolutional, pooling, and dense layers, aimed at capturing the complex visual features of skin lesions. To address the challenge of class imbalance within the dataset, an innovative data augmentation strategy is employed, ensuring a balanced representation of each lesion category during training. Furthermore, this study introduces a CNN model with optimized layer configuration and data augmentation, significantly boosting diagnostic precision in skin cancer detection. The model's learning process is optimized using the Adam optimizer, with parameters fine-tuned over 50 epochs and a batch size of 128 to enhance the model's ability to discern subtle patterns in the image data. A Model Checkpoint callback ensures the preservation of the best model iteration for future use. The proposed model demonstrates an accuracy of 97.78% with a notable precision of 97.9%, recall of 97.9%, and an F2 score of 97.8%, underscoring its potential as a robust tool in the early detection and classification of skin cancer, thereby supporting clinical decision-making and contributing to improved patient outcomes in dermatology.

Digital Educational Strategies to Teach Skin Self-examination to Individuals at Risk for Skin Cancer

Skin cancer is the most common cancer in the United States, and early detection of melanoma may lead to diagnosis of thinner and more treatable cancers, resulting in improved survival rates. This study examined the effects of message interactivity (high vs. low) and imagery (cartoon, real human character, or customized imagery preference) on accuracy of identifying abnormal skin lesions (ASL) and skin self-examination (SSE) intention. This study employed a 3 (cartoon character vs. real person vs. customization) x 2 (high interactivity vs. low interactivity) between-subjects online experimental design. Participants at risk for skin cancer were randomly assigned to one of the six conditions and completed a survey after reviewing the educational materials. Univariate analyses were conducted to detect group differences on the accuracy of identifying ASL and intention to conduct SSE in the next 3 months. Among 321 participants who completed the study, the mean age was 36.61 years, 56.7% were females, 76.1% had a college or higher degree, and over 60% self-identified as non-Hispanic White. Individuals in the high interactivity and customization group (compared to the low interactivity and cartoon group) were more likely to accurately identify ASL. Individuals in the high interactivity and customization or low interactivity and real person imagery groups (compared to the low interactivity and cartoon group) reported higher intention to conduct SSE in the next 3 months. These results suggest that customization and interactivity may be beneficial for educational programs or intervention design to improve both melanoma identification and SSE intention.

mySmartCheck, a Digital Intervention to Promote Skin Self-examination Among Individuals Diagnosed With or at Risk for Melanoma: A Randomized Clinical Trial

BACKGROUND

Regular skin self-examination (SSE) reduces melanoma mortality but is not often conducted.

PURPOSE

To promote SSE performance in individuals at increased risk for melanoma.

METHODS

One hundred sixteen individuals at heightened risk for development of melanoma (i.e., personal/family history of melanoma, high-risk mole phenotype) who did not conduct a thorough SSE during in the prior 3 months were randomly assigned to receive either an automated internet-based intervention (mySmartCheck) or usual care (UC). One hundred sixteen participants completed surveys before random assignment and 99 completed the follow-up survey 13-weeks afterward. The primary outcome was participant self-reported examination (SSE) of all 15 parts of the body in the last 3 months. Secondary outcomes were SSE of any part of the body in the last 3 months and number of body parts examined during the last SSE.

RESULTS

More mySmartCheck participants examined all 15 body parts (32.6% vs. 7.1%, p = .001). More individuals in mySmartCheck reported conducting SSE on any body part than those in UC (81.4% vs. 62.5%, p = .04). Effect sizes were large (d = 1.19 all 15 body parts) to moderate (d = 0.55 for any body part). mySmartCheck participants examined more body areas than UC participants (12.7 vs. 10.3, p = 0.003) during the last SSE. Participants in mySmartCheck reported higher levels of knowledge of suspicious lesions, SSE benefits, SSE self-efficacy, and planning for SSE, and lower SSE barriers, than those assigned to UC.

CONCLUSIONS

mySmartCheck had a significant positive impact on SSE performance and behaviors. Additional research with a larger sample size, a longer follow-up, and more varied clinical settings is needed.

TRIAL REGISTRATION

ClinicalTrials.gov registration # NCT03725449 (https://clinicaltrials.gov/ct2/show/NCT03725449).

Digital skin imaging applications, part I: Assessment of image acquisition technique features

BACKGROUND

The rapid adoption of digital skin imaging applications has increased the utilization of smartphone-acquired images in dermatology. While this has enormous potential for scaling the assessment of concerning skin lesions, the insufficient quality of many consumer/patient-taken images can undermine clinical accuracy and potentially harm patients due to lack of diagnostic interpretability. We aim to characterize the current state of digital skin imaging applications and comprehensively assess how image acquisition features address image quality.

MATERIALS AND METHODS

Publicly discoverable mobile, web, and desktop-based skin imaging applications, identified through keyword searches in mobile app stores, Google Search queries, previous teledermatology studies, and expert recommendations were independently assessed by three reviewers. Applications were categorized by primary audience (consumer-facing, nonhospital-based practice, or enterprise/health system), function (education, store-and-forward teledermatology, live-interactive teledermatology, electronic medical record adjunct/clinical imaging storage, or clinical triage), in-app connection to a healthcare provider (yes or no), and user type (patient, provider, or both).

RESULTS

Just over half (57%) of 191 included skin imaging applications had at least one of 14 image acquisition technique features. Those that were consumer-facing, intended for educational use, and designed for both patient and physician users had significantly greater feature richness (p < 0.05). The most common feature was the inclusion of text-based imaging tips, followed by the requirement to submit multiple images and body area matching.

CONCLUSION

Very few skin imaging applications included more than one image acquisition technique feature. Feature richness varied significantly by audience, function, and user categories. Users of digital dermatology tools should consider which applications have standardized features that improve image quality.

Prevalence and Age-Related Patterns in Health Information-Seeking Behaviors and Technology Use Among Skin Cancer Survivors: Survey Study

Background

Information is an unmet need among cancer survivors. There is a paucity of population-based data examining the health information-seeking behaviors and attitudes of skin cancer survivors.

Objective

We aimed to identify the prevalence and patterns of health information-seeking behaviors and attitudes among skin cancer survivors across age groups.

Methods

We analyzed population-based data from the 2019 Health Information National Trends Survey 5 (Cycle 3).

Results

The 5438 respondents included 346 (6.4%) skin cancer survivors (mean age 65.8 years); of the 346 skin cancer survivors, the majority were White (96.4% [weighted percentages]), and 171 (47.8%) were men. Most reported having ever looked for health- (86.1%) or cancer-related (76.5%) information; 28.2% stated their last search took a lot of effort, and 21.6% were frustrated. The internet was most often cited as being the first source that was recently used for health or medical information (45.6%). Compared to skin cancer survivors younger than 65 years old, those 65 years of age or older were more likely to see a doctor first for important health information (≥65 years: 68.3%;<65 years: 36.2%; P<.001) and less likely to have health and wellness apps (≥65 years: 26.4%; <65 years: 54.0%, P=.10), to have watched a health-related YouTube video (≥65 years: 13.3%; <65 years: 27.4%; P=.02), and to have used electronic means to look for information (≥65 years: 61.4%;<65 years: 82.3%, P<.001).

Conclusions

Searches for health information are common among skin cancer survivors, but behaviors and attitudes are associated with age, which highlights the importance of access to doctors and personalized information sources.