Dermatology has taken a giant leap forward with the introduction of Legit.Health‘s innovative ALADIN (Automatic Lesion And Density INdex). Top researchers in the field of deep learning and neural networks have allied with expert dermatologists to develop this algorithmic tool for next-generation doctors.
It’s widely known that objective, reliable, and precise outcome measures are key to the practice of evidence-based medicine. In the case of acne, is especially hard and tedious to apply the most accepted scoring systems, as they require the doctor to count lesions manually.
That’s why Legit.Health has developed this tool that makes grading acne by counting the number and density of lesions a task that requires mere seconds.
The limited approach of traditional acne scoring systems
Since DM. Pillsbury and their team developed the first scoring system for acne in 1956, there has been a myriad of attempts to find an easy-to-use, reliable, and precise scoring system for this disease. Nowadays, more than 30 methods exist, and all of them share one of two underlying problems.
Acne scoring system
On one hand, some methods, such as GAGS, focus on lesion identification. These scoring systems try to achieve a high degree of accuracy by sacrificing speed and convenience for the physician. In the end, doctors tend to consider these methods too tedious and time-consuming.
One of the commonly used methods is lesion counting, which is time-consuming but might represent a more accurate method.Hadeel Alsulaimani,Amal Kokandi, Shahad Khawandanh and Rahf Hamad. Severity of Acne Vulgaris: Comparison of Two Assessment Methods. Clinical, Cosmetic and Investigational Dermatology, 2021
On the other hand, other methods like the IGA aim for a scoring system more usable in day-to-day practice. Sadly they achieve this result by sacrificing precision and reliability, making their use unfit for clinical trials.
Direct visual assessment and ordinary flash photography represents a normal clinical evaluation. However, both methods are compromised by viewer subjectivity.Roshaslinie Ramli, Aamir Saeed Malik, Ahmad Fadzil Mohamad Hani and Adawiyah Jamil, Acne analysis, grading and computational assessment methods: an overview. Skin Research and Technology 2012; 18: 1–14. Doi: 10.1111/j.1600-0846.2011.00542.x
It is essential to have an acceptable and easy-to-use tool for acne assessment that can be used both in day-to-day clinical practice and in clinical studies.
ALADIN: The best of both worlds
The fact that dermatologists are having to choose between speed and precision in the XXI century is depressing. Choosing is a sign of limitation, and technology should free us of those limitations. That’s where ALADIN comes in.
The revolutionary deep learning algorithm developed by Legit.Health takes the lesion-counting approach of traditional methods and elevates it to a new level, not only making it more objective, precise, and reliable but also substantially faster. The next-generation dermatologists finally have a tool that allows them to practice evidence-based medicine.
Using computer vision algorithms, ALADIN can precisely count the number of lesions shown in a picture taken with a smartphone. Additionally, it takes into account lesion density when calculating the severity, and translates it all to an easily interpretable outcome measure validated by experts on the field.
The ingredients of a brand-new scoring system
When developing a scoring system, it is vital to keep in mind some design principles to ensure that said scoring system fits its intended use. After all, a tool is only as good as its usefulness when completing the task it was designed for.
When the team of experts at Legit.Health developed the revolutionary ALADIN they considered the many criteria that are requisite to make a scoring system great at providing high-quality outcome measures. These are some of the most relevant ones:
- Ease of use: Can be easy, given constraints of time and money
- Sensitivity to change: Ability to detect clinically important changes over time
- Inter-observer reliability: Different investigators provide identical results
- Intra-observer variability: Repeated measurements by the same investigator provide identical results
- Interpretability: Assigns qualitative meaning to scores (mild, severe…)
Methods and definitions to rate the quality of outcome measures. Schmitt, J., Langan, S., Deckert, S., Svensson, A., von Kobyletzki, L., Thomas, K., & Spuls, P. (2013). Assessment of clinical signs of atopic dermatitis: A systematic review and recommendation. Journal of Allergy and Clinical Immunology, 132(6), 1337–1347. doi:10.1016/j.jaci.2013.07.008
The 7 most prominent qualities of ALADIN
The revolutionary tool developed by Legit.Health allows next-generation dermatologists to practice evidence-based medicine while speeding up the reporting process for the pathology and increasing the patient’s autonomy and control.
This clinical data and communication app uses deep learning algorithms to relieve doctors from the tedious manual calculation of scoring systems, by automatically grading lesions by analyzing smartphone images and small patient-reported outcome measures (PROMs). In other words: the tool will automatically fill in most of the dermatology scoring systems for the most common diseases such as Psoriasis, Atopic dermatitis, Hidradenitis suppurativa, and, of course, acne.
The main goal of ALADIN is to provide a tool to record data precisely, consistently, and quickly for routine evaluations and clinical studies
1. Faster than any other existing method
Most traditional lesion-counting methods might take an experienced doctor several minutes to properly perform. Not only that but is a tedious process that most physicians try to avoid, preferring to take a few seconds to take a gut estimate of the severity of the disease.
ALADIN completely breaks this paradigm by automatizing the lesion-counting process. In less than 23 seconds, the doctor can take a picture of the affected area, run it through the algorithm, and receive an estimation of the severity with non of the subjectivity implied in using the clinical eye.
The tool was developed by Legit.Health aims to end this kind of practice so deeply incompatible with the practice of evidence-based medicine and to empower doctors to use real-world scientific data to make their medical decisions.
2. Easy to use
One of the main burdens of healthcare systems all over the world is the bottleneck formed by the lack of a reliable tool for generalist doctors to decide if a patient’s case is worthy of being referred to a specialist or not.
Legit.Health allows doctors to sidestep this issue completely, as its tool is both useful for a first diagnosis and severity assessment and for a later following of a treatment. ALADIN helps both the specialist and the generalist doctor make informed decisions based on real-world data.
3. A High degree of granularity
Legit.Health‘s tool analyzes the pathologies using a validated scoring system that has both the lowest MID (Minimal important Difference) and is sensible to the lowest LDC (Lowest Detectable Change), which means the algorithm analyzes every image with more precision and attention to detail than any human observer would.
Furthermore, ALADIN adds a new and revolutionary idea to the severity assessment of acne: lesion density. In the past, scoring systems have been limited by the ability of the user to properly count and identify papules, comedones, and pustules. Legit.Health‘s algorithm takes into account the tendency of these lesions to pile up together as a key factor in determining the severity of the disease.
All of this allows ALADIN to detect very small changes in the development of the pathology with greater precision than any human observer, giving the doctor access to more precise, objective, and reliable information.
4. A smaller margin of error
Thanks to the computer vision algorithms that ALADIN is based on, each lesion is detected and counted individually, with a mean absolute margin of error of +/- 3 lesions. This feat, added to the capacity to determine and take into account the density of the lesions in a given area, allows the system to achieve a relevant and clinically validated severity assessment without needing to consider the different types of lesions.
Most of the mistakes made by physicians when assessing the severity of acne are related to misidentification of the nature of a lesion, as in many cases the distinction isn’t clear nor that well defined within the parameters of a clinical study.
A glimpse into the future
At Legit.Health we are working towards improving ALADIN’s technology even further, pushing to create even better tools for the next-generation dermatologists. This includes developing a deep learning algorithm that will be able to differentiate between different types of lesions with more precision than any human.
5. Zero intra-observer variability
Due to its algorithmic nature, ALADIN eliminates completely the intra-observer variability, as every image and calculation is stored in the database. In other words, the app has a perfect memory of every picture saved and every diagnosis made.
Estimating is guessing, counting is measuringAlfonso Medela, CAIO
Legit.Health allows the doctor to not rely on his memory when assessing the severity of the affection and focusing on the analysis of the objective data stored in the app reduces considerably the risk of misremembering, providing a more objective, accurate, and precise way of tracing the development of the disease.
Although this becomes especially important in clinical trials, where reducing this kind of variability is key to gathering the precise data required in this kind of study, is also incredibly useful in the day-to-day practice of evidence-based medicine.
6. Provides accessible and easy-to-read data
Legit.Health‘s interface has been designed to provide access to all the patient information in an easy-to-read and accessible manner.
All the data generated by ALADIN is clearly displayed on the screen, showing the severity of the affection and every factor considered by the algorithm when analyzing the image and its score.
Say goodbye to paper trails and their tendency to be lost or damaged, as all the patient’s information, from test results to relevant pictures stored in a digital database that’s constantly being backed up and accessible from both your computer, tablet, and smartphone.
7. The best way of following the progress of a treatment
Being acne a chronic disease, the follow-up after a successful diagnosis is crucial for the good development of the treatment.
Legit.Health allows the patient to become a more active part of their treatment by improving the communication between them and their doctor. The app achieves this by giving the user an easy and reliable way of sending accurate data to the doctor.
Additionally, the app displays the data in an easy-to-read graph showing the progress of the affection, allowing the doctor to answer the usually difficult question “Am I getting better, Doctor?” with scientific data to back their answer.
The revolutionary ALADIN represents the future of dermatology. Allowing doctors across the globe to practice evidence-based medicine by using the best tools during the disease diagnosis while improving the effective communication between doctor and patient.
The use of algorithms that estimate the severity of acne by counting lesions just by looking at smartphone images increases the doctors’ correct diagnosis rate by 23% and improves the following of the treatment by making the patient a more active participant in their own recovery.
Get access now
This free 23-day trial of Legit.Health gives clinics and hospitals a hands-on look at how to drive increased adherence and improve patient outcomes, as well as improving efficiency and overall quality of life.
We are here to help
What can you expect from contacting us?
- Demo of the platform: See the inside of the application first-hand
- Understand the solution: find the right features for you
- Pricing: discover the plan that suits you best
- Connect with helpful resources