MADRID — Artificial intelligence (AI) is a significant ally in dermatology and will become an indispensable component of consultations within 4 or 5 years. There are endless possibilities within the dermoverse (a term coined by joining “dermatology” and “metaverse”), from a robot office assistant to the brand new world it offers for virtual training and simulation.
A group of dermatologists expert in new technologies came together at the 50th National Congress of the Spanish Academy for Dermatology and Venereology to discuss the metaverse: that sum of all virtual spaces that bridges physical and digital reality, where users interact through their avatars and where these experts are discovering new opportunities for treating their patients. The metaverse and AI offer a massive opportunity for improving telehealth visits, immersive surgical planning, or virtual training using 3D skin models. These are just a few examples of what this technology may eventually provide.
“The possibilities offered by the metaverse in the field of dermatology could be endless,” explained Miriam Fernández-Parrado, MD, dermatologist at Navarre Hospital. To her, “the metaverse could mean a step forward in teledermatology, which has come of age as a result of the pandemic.” These past few years have shown that it’s possible to perform some screenings online. This, in turn, has produced significant time and cost savings, along with greater efficacy in initial screening and early detection of serious diseases.
The overall percentage of cases that are potentially treatable in absentia is estimated to exceed 70%. “This isn’t a matter of replacing in-person visits but of finding a quality alternative that, far from dehumanizing the doctor–patient relationship, helps to satisfy the growing need for this relationship,” said Fernández-Parrado.
Always on Duty
Julián Conejo-Mir, MD, PhD, professor and head of dermatology at the Virgen del Rocío Hospital in Seville, told Medscape Spanish Edition that AI will help with day-to-day interactions with patients. It’s already a reality. “But to say that with a simple photo, we can address 70% of dermatology cases without being physically present with our patients — I don’t think that will become a reality in the next 20 years.”
Currently, algorithms can identify tumors with high success rates (80% to 90%) using photographs and dermoscopic images; rates increase significantly when both kinds of images are available. These high success rates are possible because tumor morphology is stationary. “However, for inflammatory conditions, accurate diagnosis generally doesn’t exceed 60%, since these are conditions in which morphology can change a lot from one day to the next and can vary significantly, depending on their anatomic location or the patient’s age.”
Maybe once metaclinics, with 3D virtual reality, have been established and clinicians can see the patient in real time from their offices, the rate of accurate diagnosis will reach 70%, especially with patients who have limited mobility or who live at a distance from the hospital. “But that’s still 10 to 15 years away, since more powerful computers are needed, most likely quantum computers,” cautioned Conejo-Mir.
The Patient’s Ally
In clinical practice, facilitating access to the dermoverse may help reduce pain and divert the patient’s attention, especially during in-person visits that require bothersome or uncomfortable interventions. “This is especially effective in pediatric dermatology, since settings of immersive virtual reality may contribute to relaxation among children,” explained Fernández-Parrado. She also sees potential applications among patients who need surgery. The metaverse would allow them to preview a simulation of their operation before undergoing it, thus reducing their anxiety and allaying their fears about these procedures.
Two lines are being pursued: automated diagnosis for telehealth consultations, which are primarily for tumors, and robotic office assistants.
“We have been using the first one in clinical practice, and we can achieve a success rate of 85% to 90%.” The second one is much more complex, “and we’re having a hard time moving it forward within our research team, since it doesn’t involve only one algorithm. Instead, it requires five algorithms working together simultaneously (chatbot, automatic writing, image analysis, selecting the most appropriate treatment, ability to make recommendations, and even an additional one involving feelings),” explained Conejo-Mir.
A Wise Consultant
Conejo-Mir offered examples of how this might work in the near future. “In under 5 years, you’ll be able to sit in front of a computer or your smartphone, talk to an avatar that we’re able to select (sex, appearance, age, kind/serious), show the avatar your lesions, and it will tell us a basic diagnostic impression and even the treatment.”
With virtual learning, physicians can also gather knowledge or take refresher courses, using skin models in augmented reality with tumors and other skin lesions, or using immersive simulation courses that aid learning. Digital models that replicate the anatomy and elasticity of the skin or other characteristics unique to the patient can be used to reach decisions regarding surgeries and to practice interventions before entering the operating room, explained Fernández-Parrado.
Optimal Virtual Training
Virtual reality and simulation will doubtless play a major role in this promising field of using these devices for training purposes. “There will be virtual dermatology clinics or metaclinics, where you can do everything with virtual simulated patients, from gaining experience in interviews or health histories (even with patients who are difficult to deal with), to taking biopsies and performing interventions,” said Conejo-Mir.
A recent study titled “How the World Sees the Metaverse and Extended Reality” gathered data from 29 countries regarding the next 10 years. One of the greatest benefits of this technology is expected in health resources (59%), even more than in the trading of digital assets. While it is difficult to predict when the dermoverse will be in operation, Fernández-Parrado says she’s a techno-optimist. Together with Héctor Perandones, MD, a dermatologist at the University Healthcare Complex in León and co-author with Fernández-Parrado of the article, “A New Universe in Dermatology: From Metaverse to Dermoverse,” she’s convinced that “if we can imagine it, we can create it.”
A Differential Diagnostician
Over the past 10 years, AI has become a major ally of dermatology, providing new techniques that simplify the diagnosis and treatment of patients. There are many applications for which it adds tremendous value in dermatology: establishing precise differential diagnoses for common diseases, such as psoriasis, atopic dermatitis, or acne; developing personalized therapeutic protocols; and predicting medium- and long-term outcomes.
Furthermore, in onco-dermatology, AI has helped to automate the diagnosis of skin tumors by making it possible to differentiate between melanocytic and nonmelanocytic lesions. This distinction promotes early diagnosis and helps produce screening systems that are capable of prioritizing cases on the basis of their seriousness.
When asked whether any group has published any promising tools with good preliminary results, Conejo-Mir stated that his group has produced three articles that have been published in top-ranking journals. In these articles, “we explain our experience with artificial intelligence in Mohs surgery, in automated diagnosis, and for calculating the thickness of melanomas.” The eight-person research team, which comprises dermatologists and software engineers, has been working together in this area for the past 4 years.
Unlike other specialists, dermatologists have 4D vision when it comes to aesthetics, since they are also skin experts. AI plays a major role in aesthetic dermatology. It supports this specialty by providing a greater analytic capacity and by evaluating the procedure and technique to be used. “It’s going to help us think and make decisions. It has taken great strides in aesthetic dermatology, especially when it comes to techniques and products. There have been products like collagen, hyaluronic acid, then thread lifts…. Also, different techniques have been developed, like Botox, for example. Before, Botox was given following one method. Now, there are other methods,” explained Conejo-Mir.
He explained, “We have analyzed the facial image to detect wrinkles, spots, enlarged pores, et cetera, to see whether there are any lesions, and, depending on what the machine says you have, it provides you with a personalized treatment. It tells you the pattern of care that the patient should follow. It also tells you what you’re going to do, whether or not there is any problem, depending on the location and on what the person is like, et cetera. Then, for follow-up, you’re given an AI program that tells you if you’re doing well or not. Lastly, it gives you product recommendations.
“We are among the specialties that are going through the most change,” said Conejo-Mir.
An Intrusive Technology?
AI will be a tremendous help in decision-making, to the point where “in 4 or 5 years, it will become indispensable, just like the loupe in years past, and then the dermatoscope.” However, the machine will have to depend on human beings. “They won’t replace us, but they will become unavoidable assistants in our day-to-day medical practice.”
Questions have arisen regarding the potential dangers of these new technologies, like that of reducing the number of dermatologists within the population, and whether they might encourage intrusiveness. Conejo-Mir made no bones about it. “AI will never cut back the number of specialists. That is false. When AI supports us in teledermatology, even currently on our team, it spits out information, but the one making the decision is the practitioner, not the machine.”
AI is a tool but is not in itself something that treats patients. It is akin to the dermatoscope. Dermatologists use these tools every day, and they help arrive at diagnoses in difficult cases, but they are not a replacement for humans. “At least for the next 50 years, then we’ll see. In 2050 is when they say AI will surpass humans in its intelligence and reasoning capacity,” said Conejo-Mir.
Julián Conejo-Mir has disclosed no relevant financial relationships.
This article was translated from the Medscape Spanish Edition.