Artificial intelligence (AI) is a significant ally in dermatology and will become an indispensable component of consultations within four or five years, believe practitioners, who say 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.
Recently, a group of dermatologists expert in new technologies gathered 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.
They believe future, potential opportunities from this technology include improving telehealth visits, immersive surgical planning, or virtual training using 3D skin models.
“The list could be endless,” said Dr Miriam Fernández-Parrado, dermatologist at Navarre Hospital in Pamplona, Spain. “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 it’s possible to perform some screenings online, which, in turn, has produced significant time and cost savings, along with greater efficacy in initial screening and early detection of serious diseases, reports Medscape.
The overall percentage of cases 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 dehumanising the doctor–patient relationship, helps to satisfy the growing need for this relationship,” she said.
Always on duty
Dr Julián Conejo-Mir, professor and head of dermatology at the Virgen del Rocío Hospital in Seville, told Medscape 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 tumours 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 tumour 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 vary significantly, depending on their anatomic location or the patient’s age.”
Maybe, he suggested, 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 might reach 70%, especially with patients who have limited mobility or who live far from a hospital.
“But that’s still 10 to 15 years away, since more powerful computers are needed – most likely quantum computers,” he said.
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 paediatric dermatology, since settings of immersive virtual reality may contribute to relaxation among children,” said Fernández-Parrado.
She also sees potential applications among patients needing surgery. The metaverse would allow them to preview a simulation of their operation beforehand, reducing their anxiety and allaying their fears.
Two lines are being pursued: automated diagnosis for telehealth consultations, which are primarily for tumours, and robotic office assistants.
“We have been using the first one in clinical practice, and 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 simultaneously (chatbot, automatic writing, image analysis, selecting the most appropriate treatment, ability to make recommendations, and even an additional one involving feelings),” said Conejo-Mir.
A wise consultant
Conejo-Mir offered examples of how this might work in the near future. “In under five 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 give 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 tumours 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 surgical decisions and to practise interventions before entering the theatre, added 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 difficult patients), 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 said she’s a techno-optimist.
With Dr Héctor Perandones, 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”.
Over the past decade, 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 personalised therapeutic protocols; and predicting medium- and long-term outcomes.
Furthermore, in onco-dermatology, AI has helped to automate the diagnosis of skin tumours by making it possible to differentiate between melanocytic and non-melanocytic lesions. This distinction promotes early diagnosis and helps produce screening systems that are capable of prioritising cases on the basis of their seriousness.
Conejo-Mir said his group has published several articles in which they explain their 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 collaborating in this area for the past four years.
Aesthetic dermatology
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 by providing a greater analytic capacity and by evaluating the procedure and technique to be used.
“It has taken great strides in aesthetic dermatology, especially regarding 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,” said Conejo-Mir.
“We have analysed 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 personalised treatment.
“It tells you the pattern of care the patient should follow; 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 programme that tells you if you’re doing well or not. Last, it gives you product recommendations.”
Intrusive technology?
AI will be a tremendous help in decision-making, to the point where "in four or five years, it will become indispensable, just like the loupe in years past, and then the dermatoscope”.
However, the machine will still have to depend on human beings.
“They won’t replace us, but they will become unavoidable assistants in our day-to-day medical practice.”
On whether these technologies would reduce the number of dermatologists or encourage intrusiveness, Conejo-Mir said: “AI will never cut back the number of specialists. When it 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. They say in 2050 is when they AI will surpass humans in intelligence and reasoning capacity.”
JEADV article – A new universe in Dermatology: From metaverse to Dermoverse (Open access)
Medscape article – The Metaverse Is the Dermatologist's Ally (Open access)
See more from MedicalBrief archives:
OECD: How artificial intelligence could change the future of health
AI outperforms clinicians in triaging post-operative patients for ICUe
AI ‘at best’ on a par with human experts when making image-based diagnoses – review