Evaluating Diagnostic Accuracy of Generalized Pustular Psoriasis with the Legit.Health Device

Authors

Alfonso Medela, Ignacio Hernández Montilla, Alberto Sabater, Andy Aguilar, Taig Mac Carthy, Gurpreet Singh Chowdhry, Juan Semeco, Antonio Martorell.

Introduction

Generalized Pustular Psoriasis (GPP) is a rare, severe, and potentially life-threatening form of psoriasis characterized by widespread sterile pustules on erythematous skin. Unlike plaque psoriasis, GPP can present acutely with systemic symptoms including fever, malaise, and laboratory abnormalities.

Due to its rarity (affecting fewer than 1 in 10,000 people) and the clinical overlap with other pustular conditions, GPP presents significant diagnostic challenges:

• Limited specialist access: Many dermatologists see few GPP cases in their careers
• Diagnostic delays: Patients may be misdiagnosed with other conditions
• Urgent treatment needs: GPP flares require prompt recognition and intervention
• Monitoring challenges: Assessing disease activity and treatment response

Objective

This study evaluates the diagnostic accuracy of the Legit.Health AI device for identifying and classifying GPP from clinical images. Given the rarity of the condition, AI-assisted diagnosis could help:

1. Improve early recognition of GPP in non-specialist settings
2. Support differential diagnosis from other pustular conditions
3. Enable remote monitoring of disease activity
4. Standardize severity assessment for clinical trials

Method

The study utilizes clinical images of confirmed GPP cases alongside other pustular conditions to evaluate the device’s ability to:

• Distinguish GPP from other pustular dermatoses
• Identify characteristic GPP features (lakes of pus, erythema patterns)
• Assess disease severity and extent
• Track changes over time

Preliminary Results

The preprint presents initial findings on the diagnostic performance of the AI system for this rare condition. Key metrics evaluated include:

• Sensitivity and specificity for GPP detection
• Accuracy of severity grading
• Performance across different GPP phenotypes
• Generalization to diverse patient populations

Clinical Significance

Accurate AI-assisted GPP diagnosis could significantly impact patient care by:

• Reducing diagnostic delays in emergency and primary care settings
• Supporting dermatologists in rare disease recognition
• Enabling telemedicine for patients with limited specialist access
• Facilitating clinical research through standardized case identification

This work represents an important step toward AI-assisted diagnosis of rare dermatological conditions where clinical expertise is limited.

Read full text

Preprint available at https://doi.org/10.2196/preprints.82030.

Note: This is a preprint and has not yet undergone peer review.