Psoriasis Severity Endpoints for Clinical Trials
The AI scoring provided by Legit.Health delivers automated, clinically validated psoriasis severity scoring for clinical trials, quantifying erythema, desquamation, induration, and affected body surface area across four body regions to compute the Psoriasis Area and Severity Index (PASI).
The device supports interventional and observational studies across all clinical trial phases, from Phase I to Phase IV, as well as real-world evidence (RWE) and post-marketing studies. Its diagnostic support capability also assists patient pre-screening during recruitment.
Psoriasis Area and Severity Index
Global PASI 7.3
0 to 72 scale, four regions scored on erythema, desquamation and induration
Images analysed
8 (4 perspectives + 4 close-ups)
Analysis performed in
2.1 seconds
Extent: body surface area
Whole-body extent measured from 4 full-body perspectives
Affected surface 4.33%
Head & trunk, front
Head & trunk, back
Legs, front
Legs, back
Body region
Head
Image quality
94%
Area affected
0.0% (area score 0)
Local PASI
0.0
Body region
Upper extremities
Image quality
93%
Area affected
9.9% (area score 1)
Local PASI
1.6
Body region
Trunk
Image quality
91%
Area affected
4.0% (area score 1)
Local PASI
2.1
Body region
Lower extremities
Image quality
88%
Area affected
4.1% (area score 1)
Local PASI
3.6
These automated scores are backed by peer-reviewed validation; see Clinical evidence.
The example images on this page are synthetic dermatology imagery used for illustration; they are not patient records.
Why automated PASI scoring for clinical trials?
Manual PASI asks a dermatologist to estimate the affected area in each of four body regions and to grade three intensity signs in each of them, sixteen separate judgements per patient per visit. Estimating area by eye is the most operator-dependent step of the score and the largest single source of inter-rater variability in psoriasis endpoints.
The AI automates every component of the score:
- Affected area measurement: pixel-level segmentation of psoriatic skin in each of the four PASI regions, replacing visual estimation
- Intensity scoring: erythema, desquamation and induration, each graded 0 to 4 per region
- DIQA (Dermatology Image Quality Assessment): image quality assessed before scoring, so substandard images are flagged for recapture at the visit rather than surfacing as missing data at database lock
The same capture set works in the clinic and at home, so a protocol can place PASI assessments between site visits without adding travel; see Imaging protocol.
Endpoint capabilities
The AI reports two measures from a single capture set, each configurable per study protocol:
Psoriasis Area and Severity Index
Erythema, desquamation, induration
Area-weighted across head, trunk, upper and lower extremities
Measured at pixel level, not estimated
Regional percentages feed the PASI and stand as an endpoint in their own right
PASI is the registration endpoint in almost every psoriasis programme, and PASI response milestones (PASI 75, PASI 90, PASI 100) are the usual primary efficacy measures. BSA is reported alongside it because treatment guidelines use extent in its own right, and because it is the component that manual scoring estimates least reliably.
How the AI works
The scoring pipeline processes each set of body photographs in two stages.
Stage 1: Affected area segmentation
A deep learning model locates the body, divides it into the four PASI regions using anatomical landmarks, and classifies every pixel as affected skin, unaffected skin or background. Counting those pixels gives the percentage of affected skin in each region, and those four percentages are what the index weights.
Input: body area photograph
Body detection: body isolated from the background
Output: affected area at pixel level
Combined: segmentation overlaid on photograph
Stage 2: Intensity sign scoring
For each region, a dedicated AI model scores three clinical signs independently on a 0 to 4 scale, giving an intensity total from 0 to 12:
Automated analysis of a plaque: pixel-level segmentation and sign-level scoring
Longitudinal severity tracking
From the follow-up visits onward, the same report shows how severity evolves across the study:
- PASI trajectory: absolute and percentage change from baseline at each visit, from screening to end of study
- PASI response milestones: whether the patient has reached PASI 75, PASI 90 or PASI 100 against their own baseline
- Per-sign trends: which of the three intensity signs is driving improvement or worsening
- Affected area change: how the extent of psoriatic skin evolves over time
- Protocol adherence: whether assessments are captured at the correct intervals
For follow-up visits, the platform charts this severity evolution across all assessments for the patient:
The platform provides automated severity scoring as decision support. Scores are interpreted by qualified healthcare professionals within the patient's overall clinical context; the platform does not replace clinical judgement or make autonomous diagnostic decisions.