Clinical evidence
This section compiles the peer-reviewed publications behind the automated psoriasis scoring provided by Legit.Health, the production validation results for each PASI component, and the foundational PASI references. Together they document the scientific basis of the automated PASI and how it is validated for use as a clinical trial endpoint.
Validation status and reproducibility
The automated PASI methodology was published in JEADV Clinical Practice in 2025. Each of the four PASI components is validated independently against expert assessment, so no single component is a hidden weak link in the composite score.
Severity scoring has no objective gold standard. PASI component scores are a clinical judgement, not a measurement: unlike blood pressure, where 120/80 is the same reading on every device, erythema intensity, scaling severity and plaque thickness depend on the assessor. The reference is therefore the mathematical consensus of independent expert dermatologists, the same standard the FDA and EMA accept for dermatology trials. Matching that consensus is the realistic performance ceiling for any rater, human or AI.
Two properties are decisive for endpoint use in a trial:
- Reproducibility: scoring is deterministic. The same image yields the same score at every site and every visit, with no calibration drift and no inter-reader variability, the dominant source of noise in multi-centre severity endpoints.
- Objective extent measurement: the affected area component is measured by pixel-level segmentation rather than estimated by eye. Visual area estimation is the largest single source of inter-rater variability in manual PASI, so measuring it objectively removes the most operator-dependent step of the score.
The device is CE-marked as a medical device, meaning a Notified Body has independently assessed it against the safety and performance requirements of the EU Medical Device Directive (MDD 93/42/EEC) and authorised its use on the EU market. Beyond the EU, the device is registered with the MHRA for the United Kingdom market and has obtained ANVISA approval in Brazil. Real-world performance is monitored continuously through the manufacturer's post-market surveillance and post-market clinical follow-up (PMCF) programme under MDR Annex XIV. Study-specific agreement and reproducibility metrics are available on request to support protocol design.
Legit.Health is a clinical decision support device: the automated scores provide diagnostic support and do not replace the healthcare professional's assessment.
Automated PASI
Artificial intelligence-based quantification to assess the Automatic Psoriasis Area and Severity Index. Mac Carthy T, Dagnino D, Medela A, et al. JEADV Clinical Practice. 2025;4(1):70143. DOI: 10.1002/jvc2.70143
The foundational publication for the automated PASI methodology, describing the AI-driven quantification of erythema, desquamation, induration and affected body surface area from clinical images, and the validation of each component against expert assessment.
Production model performance
Every component model is validated separately against expert assessment under the Quality Management System (IEC 62304 and ISO 14971). The acceptance criterion in each case is non-inferiority to expert inter-rater variability, so the benchmark column below is not a target we set ourselves: it is how much dermatologists disagree with each other on the same images.
| PASI component | Metric | Automated PASI | Expert dermatologists | Result |
|---|---|---|---|---|
| Erythema | RMAE | 0.13 | 0.14 | Better than expert agreement |
| Desquamation | RMAE | 0.153 | 0.17 | Better than expert agreement |
| Induration | RMAE | 0.151 | 0.17 | Better than expert agreement |
| Affected surface (BSA) | IoU | 0.61 | 0.61 | Matches expert agreement |
RMAE measures how far the AI's intensity score falls from the expert consensus, as a proportion of the scale, so a lower value is better. IoU measures how much the AI's outline of the affected skin overlaps the expert's outline of the same image, so a higher value is better.
Neither is read against zero. Dermatologists do not agree perfectly with each other either, so the benchmark is their own level of agreement, and matching it is the best any rater can do.
All four components meet their acceptance criteria, so the composite PASI score has no weak link. The affected surface row is the one that changes a trial the most, because it replaces area estimation by eye, the largest single source of variability in manual PASI, with a pixel-level measurement.
Manual PASI requires a dermatologist to grade four components across four body regions, which is 16 individual assessments per patient, and to estimate affected area by eye for each region. Automated PASI returns an objective severity read from photographs that is comparable to expert assessment, with three properties manual scoring cannot offer:
- Perfect reproducibility: the same image always produces the same component scores, with zero intra-rater variability, at every site and every visit.
- No investigator training drift: performance does not depend on how recently a site was trained or on which rater is on shift that day.
- Less noise in PASI change from baseline, which can support smaller sample sizes or greater statistical power to detect treatment response.
AI-computed PASI endpoints from Legit.Health have been accepted by regulators as secondary endpoints and for adverse event detection in clinical submissions. For primary registration endpoints, the system reports standard PASI scores on the established 0 to 72 scale.
The published study reports the models as they stood at submission. The production models are revalidated under the Quality Management System (IEC 62304 and ISO 14971) and the current per-component results are the ones reported on this page, so this page rather than the paper is the reference for present-day performance.
Image quality for psoriasis scoring (DIQA)
Dermatology Image Quality Assessment (DIQA): Artificial intelligence to ensure the clinical utility of images for remote consultations and clinical trials. Hernández Montilla I, Mac Carthy T, Aguilar A, et al. Journal of the American Academy of Dermatology. 2023;88(4):927–928. DOI: 10.1016/j.jaad.2022.11.002 | PMID: 36526082
Reliable PASI scoring depends on the quality of the input photographs. DIQA is the image quality assessment algorithm that acts as a quality gate in the psoriasis imaging workflow, checking every image against consistent quality criteria across investigator sites before it reaches the scoring algorithms. The dependency is sharpest in psoriasis, where full-body capture means that lighting consistency and framing affect both erythema assessment and area segmentation.
Image quality is the hidden failure point of decentralised and multi-site imaging. DIQA screens every photograph for clinical utility before it reaches the scoring algorithms, so unusable images are caught at capture rather than surfacing as missing data at database lock.
Conference presentations
AEDV (Spanish Academy of Dermatology and Venereology) 2025, Valencia
Oral: AI-based quantification to assess the automatic area and severity index of psoriasis
Oral presentation of the automated PASI methodology, covering PASI scoring via AI-driven quantification of erythema, desquamation, induration, and body surface area from clinical images.
EADV (European Academy of Dermatology and Venereology) 2025, Paris
Poster: APASI: Automatic Psoriasis Area and Severity Index with AI-driven quantification
Scientific poster presenting the automated PASI system, covering PASI scoring with component-level validation against expert inter-rater variability, demonstrating non-inferiority across all four PASI components.
Foundational PASI references
The platform does not introduce a new, unvalidated scale. It automates PASI, the severity index clinicians and regulators already accept, so the endpoint your protocol specifies is the endpoint the algorithm reports.
Fredriksson T, Pettersson U “Severe psoriasis: oral therapy with a new retinoid” Dermatologica 157(4):238-244. 1978. doi:10.1159/000250839
Original publication defining the PASI scoring system. Establishes the four-region, three-component methodology that remains the standard for psoriasis clinical trials.
U.S. Food and Drug Administration “Psoriasis: Developing Drug Products for Treatment. Guidance for Industry.” FDA Guidance Document. 2022. Read the document
FDA guidance establishing PASI 75/90/100 response rates and IGA as the primary endpoints for psoriasis drug development.
For the full list of clinical evidence across all indications, see the clinical validation section.
Beschleunigen Sie Ihre Studien
Schließen Sie sich Pharmaunternehmen, Biotechs und CROs an, die 4-6 Monate schneller auf den Markt kommen mit überlegener Datenqualität. Füllen Sie das Formular aus, um Ihre Studienanforderungen zu besprechen.