Clinical Trial Workflow and Data Integration
This page describes the end-to-end workflow for vitiligo severity assessment in a clinical trial using the Legit.Health platform, from protocol design through to EDC data delivery.
Workflow overview
The workflow has two phases: a one-time study setup, and a per-visit cycle that repeats at every assessment.
Study setup (once per study)
- Protocol design: Configure the study with Legit.Health
- Site setup: Deploy the platform to investigator sites
Per-visit cycle (each assessment)
- Patient enrolment: Register the patient in the platform
- Image capture: The standard body and face photographs, with real-time DIQA quality control
- AI scoring and review: Automated F-VASI and T-VASI, reviewed by the investigator, with change from baseline and alerts tracked across visits
- Data export: Structured delivery to the EDC system
1. Protocol design
Before the study begins, Legit.Health works with the sponsor or CRO to configure the study protocol:
| Configuration | Options |
|---|---|
| Scoring system | F-VASI, T-VASI, regional scores per VASI site, or a combination |
| Capture scope | The standard body and face views, face only for facial vitiligo studies, the face plus representative target areas, or custom views; see the imaging protocol |
| Responder definitions | F-VASI50, F-VASI75, F-VASI90, T-VASI50 or protocol-specific thresholds; see the worked example |
| Visit schedule | Assessment timepoints aligned with the study calendar |
| Alert thresholds | Configurable increase in VASI from baseline that triggers a notification to the site |
For studies with significant representation of the lightest or darkest skin types, the model's performance by Fitzpatrick group informs protocol design; see Performance across skin phototypes.
A study-specific investigator manual is generated for each trial, providing site personnel with step-by-step instructions, example images, and a knowledge test to confirm training.
The scoring model version is locked at study initiation. No mid-study model updates occur, so every patient is scored by the same validated model and endpoint integrity is preserved across the trial. Any model update requires full re-validation before deployment.
2. Site setup
The Legit.Health clinical trials platform is deployed as a web application accessible from any browser. Each investigator site receives:
- Login credentials for all study personnel
- Pre-configured protocol (capture scope, endpoints, alert thresholds)
- Investigator manual (digital, accessible from the platform)
- Training resources and knowledge test
No hardware installation is required; investigators use their existing smartphones for image capture.
3. Patient enrolment
After enrolling a patient in the study per the clinical protocol, the investigator creates the patient record in the Legit.Health platform. Each patient is identified by a study-specific pseudonymised identifier; no personal data (name, date of birth) is stored in the platform.
4. Image capture
Images are taken at the investigator site, in a room where the patient can undress the regions to be photographed. Each visit needs the same standard views of the body and the face. The distance, lighting and patient preparation are set out in the imaging protocol. The application provides:
- Perspective guidance: visual silhouettes showing the required framing for each view
- Real-time quality control: the DIQA quality gate checks each image at capture and flags substandard images for immediate recapture, so only adequate images proceed to scoring
Images are not taken by patients at home. The score depends on the framing, the light and the preparation of the skin being the same at every visit, and a patient alone at home cannot hold them: a lamp or a window can make pigmented skin look depigmented, and a patient cannot frame the back or the soles on their own. For decentralised studies, the capture is best done by trained staff, at the site or at a home visit, following the same imaging protocol.
5. AI scoring and review
Once the images are submitted, the AI processes them automatically in seconds and generates the VASI report, which the investigator reviews directly in the platform. Where the protocol also calls for a central read, the same photographs go to the central reader, who scores them by hand; the palms view shows the size of the patient's hand, the unit of that score.
The report contains:
- Depigmentation percentage per view, with the segmentation mask for each photograph
- Per-site VASI contribution, the sum of the views of each of the six VASI sites, each weighted by its share of the body surface
- F-VASI and T-VASI
- DIQA quality score per image
The investigator verifies that the AI's assessment aligns with their clinical observation. If any image is inadequate, they can recapture and resubmit the full set; only the latest submission for each visit is retained.
From the follow-up visits onward, the same report tracks how severity evolves across the study, with the absolute and percentage change in VASI from baseline.
The platform stores the baseline score and compares every follow-up visit against it. When depigmentation increases by the configured threshold, the site receives an email notification, and the investigator confirms the finding through clinical assessment. This supports both efficacy trials, where VASI tracks repigmentation, and the detection of disease progression during the study.
6. Data export and EDC integration
Where the in-platform report (step 5) is the investigator's human-readable view, the export is a structured, analysis-ready dataset built to load straight into the sponsor's EDC. Each assessment is delivered as column-level records, not a re-rendering of the report.
Exported data fields
Field names below are representative; the exact schema is agreed during study setup.
| Group | Fields |
|---|---|
| Identifiers | study_code, site_code, subject_code, visit_code, diagnostic_report_id, timestamp, condition_code |
| Source images | Anonymised image path and segmentation mask path for each view, so each score is traceable to the photograph it was computed from |
| Regional scores | Depigmentation percentage per view and VASI contribution per VASI site, plus the F-VASI and the T-VASI |
| Change from baseline | Absolute and percentage change in F-VASI and T-VASI from the baseline visit, responder status, and whether an alert was raised |
| Quality | DIQA quality score per image |
Every field is delivered per visit, so the same structure supports both single-visit analysis and longitudinal review.
Integration methods
- API-based: Automated data flow from the Legit.Health platform to the sponsor’s EDC system via RESTful API
- CSV export: Structured CSV files for manual import into EDC systems
- CRF field mapping: Data fields pre-mapped to the sponsor’s Case Report Form structure, configured during protocol design
- QuantifiCare platform integration: For studies using the combined QuantifiCare + Legit.Health solution, scoring data flows through QuantifiCare’s platform to the sponsor’s data management system
All exported data is structured for direct mapping to CRF fields in standard EDC systems.
The integration is API-based and system-agnostic; it works with any major EDC system. Export formats include RESTful API, CSV/Excel, and structured JSON.