Development of an artificial intelligence algorithm for the diagnosis of infantile hemangiomas

Perspectives and Challenges of Telemedicine and Artificial Intelligence in Pediatric Dermatology

BACKGROUND

Pediatric dermatology represents one of the most underserved subspecialties in pediatrics. Artificial intelligence (AI) and telemedicine have become considerable in dermatology, reaching diagnostic accuracy comparable to or exceeding that of in-person visits. This work aims to review the current state of telemedicine and AI in pediatric dermatology, suggesting potential ways to address existing issues and challenges.

METHODS

We conducted a literature review including only articles published in the last 15 years. A total of 458 studies were identified, of which only 76 were included.

RESULTS

Most of the studies on telemedicine evaluate accuracy focused on concordance, which ranges from 70% to 89% for the most common pediatric skin diseases. Telemedicine showed the potential to manage chronic dermatological conditions in children, as well as decrease waiting times, and represents the chance for unprivileged populations to overcome barriers limiting access to medical care. The main limitations of telemedicine consist of the language barrier and the need for adequate technologies and acceptable image-quality video, which can be overcome by AI. AI-driven apps and platforms can facilitate remote consultations between pediatric dermatologists and patients or their caregivers. However, the integration of AI into clinical practice faces some challenges ranging from technical to ethical and regulatory. It is crucial to ensure that the development, deployment, and utilization of AI systems conform to the seven fundamental requirements for trustworthy AI.

CONCLUSION

This study supplies a detailed discussion of open challenges with a particular focus on equity and ethical considerations and defining possible concrete directions.

Digital Imaging and Artificial Intelligence in Infantile Hemangioma: A Systematic Literature Review

Infantile hemangioma (IH) is a vascular anomaly observed in newborns, with potential severe complications if left undetected. Consequently, researchers have turned to artificial intelligence (AI) and digital imaging (DI) methods for detection, segmentation, and assessing the treatment response in IH cases. This paper conducts a systematic literature review (SLR) following the Kitchenham framework to scrutinize the utilization of AI and digital imaging techniques in IH applications. A total of 21 research articles spanning from 2014 to April 2024 were carefully selected and analyzed to address four key research questions: the issues solved in IH using AI and DI, the most-used AI and DI techniques, the best-performing technique in detecting IH, and the limitations and future directions in the various fields of IH. After an extensive review of the selected articles, it was found that 10 of the 21 articles focused on detecting IH, and 15 articles utilized AI. However, the best-performing technique in detecting IH employed DI. Additionally, the SLR offers insights and recommendations into future directions for IH applications.

Past, present, and future of global research on artificial intelligence applications in dermatology: A bibliometric analysis

In recent decades, artificial intelligence (AI) has played an increasingly important role in medicine, including dermatology. Worldwide, numerous studies have reported on AI applications in dermatology, rapidly increasing interest in this field. However, no bibliometric studies have been conducted to evaluate the past, present, or future of this topic. This study aimed to illustrate past and present research and outline future directions for global research on AI applications in dermatology using bibliometric analysis. We conducted an online search of the Web of Science Core Collection database to identify scientific papers on AI applications in dermatology. The bibliometric metadata of each selected paper were extracted, analyzed, and visualized using VOS viewer and Cite Space. A total of 406 papers, comprising 8 randomized controlled trials and 20 prospective studies, were deemed eligible for inclusion. The United States had the highest number of papers (n = 166). The University of California System (n = 24) and Allan C. Halpern (n = 11) were the institution and author with the highest number of papers, respectively. Based on keyword co-occurrence analysis, the studies were categorized into 9 distinct clusters, with clusters 2, 3, and 7 containing keywords with the latest average publication year. Wound progression prediction using machine learning, the integration of AI into teledermatology, and applications of the algorithms in skin diseases, are the current research priorities and will remain future research aims in this field.

Artificial intelligence applications in pediatric oncology diagnosis

Artificial intelligence (AI) algorithms have been applied in abundant medical tasks with high accuracy and efficiency. Physicians can improve their diagnostic efficiency with the assistance of AI techniques for improving the subsequent personalized treatment and surveillance. AI algorithms fundamentally capture data, identify underlying patterns, achieve preset endpoints, and provide decisions and predictions about real-world events with working principles of machine learning and deep learning. AI algorithms with sufficient graphic processing unit power have been demonstrated to provide timely diagnostic references based on preliminary training of large amounts of clinical and imaging data. The sample size issue is an inevitable challenge for pediatric oncology considering its low morbidity and individual heterogeneity. However, this problem may be solved in the near future considering the exponential advancements of AI algorithms technically to decrease the dependence of AI operation on the amount of data sets and the efficiency of computing power. For instance, it could be a feasible solution by shifting convolutional neural networks (CNNs) from adults and sharing CNN algorithms across multiple institutions besides original data. The present review provides important insights into emerging AI applications for the diagnosis of pediatric oncology by systematically overviewing of up-to-date literature.