R-009-001 US Johnson & Johnson 20251031
- Deal Id: 45489188014
- Contract sign date: 2026-01-21
- Contract effective date: 2025-11-07 (Effective Date)
- Contract end date: 2027-12-31
- Deal name: US J&J Retrospective study - AD and Psoriasis
- Master Agreement Reference: eMC R2025033170 / ICD 2272258 (effective October 10, 2025)
- J&J Address: 1125 Trenton-Harbourton Road, Titusville, NJ 08560, USA
Goals
Main Objective:
Evaluate the feasibility and value of using Legit.Health AI models with J&J’s clinical images
-
1. Applying AI models to J&J’s retrospective dataset (up to 85,000 images, focused on atopic dermatitis and psoriasis)
- 1.1. Providing automatic global and local severity scores
- Support for EASI and SCORAD (atopic dermatitis)
- Support for PASI (psoriasis)
- 1.2. Efficiently identifying and quantifying clinical signs in images
- Detect erythema, swelling, oozing/crusting, excoriations, lichenification, dryness, and other relevant signs
- 1.1. Providing automatic global and local severity scores
-
2. Comparing Legit.Health model outputs to J&J’s internal models
- To inform the decision to build vs. buy
Project definition details summary
-
Overview: J&J has an internal dataset of approximately 85,000 clinical images (~43 images per patient, ~1,977 patients) focused on Atopic Dermatitis and Psoriasis lesions. This project leverages Legit.Health AI models to provide automatic global and local severity scores and identify clinical visual signs through quantification of lesional images and lesion segmentation. Due to data sensitivity, J&J employees run the algorithm on their datasets via API; servers do not store data—only process and delete residual data. All recordkeeping is done by J&J.
-
Primary Objective: Integrate AI-driven image analysis into clinical workflows to enhance accuracy, efficiency, and scalability of disease evaluation, reduce patient burden, support decentralized clinical trials, and provide automated severity scores (PASI, EASI, SCORAD) with lesion segmentation.
-
Conditions: Atopic Dermatitis (AD), Psoriasis
-
Scoring Systems: EASI and SCORAD for Atopic Dermatitis; PASI for Psoriasis
-
Output Clinical Signs: Erythema, swelling, oozing/crusting, excoriations, lichenification, dryness
-
Integration: API (JSON Only) | Translations: No | Dashboard: No | Data Transfer: No (API calls only, no storage) | Geographical scope: US only | Timeline: 2025-11-07 to 2027-12-31
-
Data Volume:
- Total dataset: ~85,000 images (~1,977 patients)
- Phase 2: Up to 1,000 images (evaluation)
- Phase 3 (optional): ~1,000 images
- Phase 4 (optional): 1-1,000 / 1,000-5,000 / 5,001-10,000 / 10k+ images
- Maximum potential: Up to 85,000 images (subject to Phase 4 expansion)
-
Challenges: Image quality issues (poor resolution, lighting, framing); API failures (connectivity, response times, availability); incorrect patient information (wrong body area, condition codes, questionnaire answers)
-
Ethics committee approval required?: TBD
-
Technical Notes: API processes one image per call (JSON Request). J&J can implement automated batch processing. API documentation for /severity-assessment endpoint will be prepared.
Summary of dates
| Concept | Start Date | End Date | Approx. Months |
|---|---|---|---|
| Contract Period | 2025-11-07 | 2027-12-31 | ~26 |
| Study period | TBC | TBC | TBC |
| Technical Support | TBC | TBC | TBC |
Project Phases
| Phase | Description | Images to Process |
|---|---|---|
| 1 | Technical Setup: Onboarding, API Access, expert support, request/response management | - |
| 2 | First batch analysis: Algorithm suitability evaluation | Up to 1,000 images |
| Licensing | Skin-Segmentation Algorithm Monthly License (minimum 3 months, commencing upon completion of Phase 1) | - |
| 3 | Dataset Expansion (optional, subject to Phase 2 outcomes) | ~1,000 images |
| 4 | Additional Expansions (optional, case-by-case) | 1-1,000 / 1,000-5,000 / 5,001-10,000 / 10k+ images |
Project timeline and milestones
To achieve the goals, the parties agree on the following timeline.
Timeline dates are illustrative. Actual dates TBC upon contract execution.
JSON-only API Flow for J&J Backend
Data Flow for Local Severity Assessment via Legit.Health API (JSON Only)
Request details:
- EASI
- Condition: Atopic Dermatitis (ICD-11 code: EA89)
- scoringSystem: aeasi
- questionnaire:
- Question: Affected area from selected body area (%)
- Age: Patient age (years), only needed if age below 7 years or above 7 years
- PASI
- Condition: Psoriasis (ICD-11 code: EA80)
- scoringSystem: apasi
- questionnaire:
- Question: Affected area from selected body area (% or (0 to 6))
Response visual signs example
-
AEASI
- local score
- Surface area score (*)
- patient age (*)
- Redness
- Thickness
- Scratching
- Lichenification
-
APASI
- local score
- Body area (*)
- Surface area score (0 to 6)(*)
- Desquamation
- Erythema
- Induration
Quantification of intensity, count and extent of visible clinical signs
The device provides quantifiable data on the intensity, count and extent of clinical signs such as erythema, desquamation, and induration, among others; including, but not limited to:
- erythema,
- desquamation,
- induration,
- crusting,
- xerosis (dryness),
- swelling (oedema),
- oozing,
- excoriation,
- lichenification,
- exudation,
- wound depth,
- wound border,
- undermining,
- hair loss,
- necrotic tissue,
- granulation tissue,
- epithelialization,
- nodule,
- papule
- pustule,
- cyst,
- comedone,
- abscess,
- draining tunnel,
- inflammatory lesion,
- exposed wound, bone and/or adjacent tissues,
- slough or biofilm,
- maceration,
- external material over the lesion,
- hypopigmentation or depigmentation,
- hyperpigmentation,
- scar
Backend Cloud Infrastructure Flow
Default data flow diagram
Note: DPIA it is available upon request.
Note: All data flows are secured using encrypted HTTPS connections to ensure data integrity and confidentiality. Note: we employ the robust OAuth 2.0 authentication mechanisms to ensure that only authorized users can access the API. Role-based access control further restricts user privileges, enhancing data security. All data transmitted between the user and the API is encrypted using industry-standard encryption protocols.
Possible data flow diagram (upon request and contract agreement)
Note: The client may require that the data not be stored or request its immediate deletion after processing, provided this request is made explicitly and specified in the contract.
Project tasks
🧭 Definition & planning
| Task | Description | Start Date | End Date | Status | Notes |
|---|---|---|---|---|---|
| Project conception and initiation | Initial ideation and opportunity scoping with all key stakeholders. | 2025-10-30 | 2025-11-07 | ✅ Done | SOW finalized |
| Definition and planning | Define project details: scope, key deliverables, timelines, success metrics, and required resources. | 2025-10-30 | 2025-11-07 | ✅ Done | Defined in SOW |
| Implementation plan defined | Project scope, key deliverables, timelines, success metrics, and required resources are defined and clear | 2025-11-07 | 2025-11-07 | ✅ Done | SOW Exhibit 1 |
📝 Contracting
| Task | Description | Start Date | End Date | Status | Notes |
|---|---|---|---|---|---|
| Offer Sent | Formal offer/proposal shared with the customer for review. | 2025-11-20 | 2025-11-20 | ✅ Done | |
| Offer Approved | Customer reviews and approves the proposed scope, terms, and pricing. | 2025-12-11 | 2025-12-11 | ✅ Done | |
| Contract Review | Align on deliverables, timelines, legal and data terms. | 2025-12-11 | 2026-01-20 | ✅ Done | |
| Contract Signing | Finalize and sign all contractual agreements. | 2026-01-21 | 2026-01-21 | ✅ Done |
Signatories:
- J&J Innovative Medicine: Oana Cula, Sr. Director DSDH Immunology
- Legit.Health: Sheyla Andina Aguilar, CEO & Co-founder
🏁 Kickoff
| Task | Description | Date | Status |
|---|---|---|---|
| Kick-off Meeting | Initial meeting to align on project goals, timelines, and responsibilities. | February 2026 | ⏳ Pending |
🔌 Integration workflow (Phase 1 - Technical Setup)
| Task | Description | Timeline | Status | Dependencies |
|---|---|---|---|---|
| Technical onboarding | Provide comprehensive API documentation and detailed walkthroughs. | February 2026 | ⏳ Pending | Contract signed |
| API Access | Generate and deliver API keys for production environment. | February 2026 | ⏳ Pending | Contract signed |
| Professional Services | Expert support from technicians, consultants, and project managers. Review and align API input/output structures with client requirements. | February 2026 | ⏳ Pending | Technical onboarding |
| Request/Response Setup | Complete setup of request and response management, system ready for operational use of the algorithms. | February 2026 | ⏳ Pending | Professional Services |
| Algorithm Setup Support | Provide support for setting up and running the API, including troubleshooting to achieve desired solution. | February 2026 | ⏳ Pending | API Access |
📊 Phase 2 - Evaluation of Results
| Task | Description | Timeline | Status | Dependencies |
|---|---|---|---|---|
| Initial dataset analysis | J&J runs initial set of up to 1,000 images to evaluate algorithm suitability. | TBC when Phase 1 completed | ⏳ Pending | Phase 1 complete |
| Results evaluation | Assess scoring accuracy, latency, and output quality for AD and Psoriasis images. | TBC | ⏳ Pending | Initial dataset analysis |
📈 Phase 3 - Dataset Expansion (Optional)
| Task | Description | Timeline | Status | Dependencies |
|---|---|---|---|---|
| Phase 3 expansion approval | Subject to satisfactory outcomes from Phase 2, J&J may elect to proceed. | TBC when Phase 2 completed | ⏳ Pending | Phase 2 satisfactory |
| Additional dataset processing | Processing of additional ~1,000 images (psoriasis, atopic dermatitis, or combination). | TBC | ⏳ Pending | Written confirmation |
🚀 Phase 4 - Additional Expansions (Optional)
| Task | Description | Timeline | Status | Dependencies |
|---|---|---|---|---|
| Phase 4 scope agreement | Mutual written agreement on dataset size, scope of analysis, timeline, and applicable pricing. | TBC | ⏳ Pending | Phase 3 complete |
| Extended dataset processing | Potential dataset sizes: 1-1000, 1000-5000, 5001-10000, or 10k+ images. | TBC | ⏳ Pending | Scope agreement |
🚀 Project Execution
| Task | Description | Responsible | Status |
|---|---|---|---|
| User Onboarding | Train IT managers on the API and scoring system. | JD-021, JD-016 | ⏳ Pending |
| Customer Support | Setup and activate helpdesk or in-app support systems. Comprehensive assistance for complex issues | JD-021, JD-016 | ⏳ Pending |
| Ongoing Support | Legit.Health available for any ongoing support as needed | JD-016, JD-007 | ⏳ Pending |
🔁 Follow-up Meetings (Optional)
| Task | Description | Responsible | Status |
|---|---|---|---|
| Follow-up Meeting | Formal review of key findings, feedback, and performance. | JD-021, JD-016 | ⏳ Pending |
| Interim Report | Summary report of current status, insights, and recommendations mid-project. | JD-021, JD-016 | ⏳ Pending |
✅ Project Close
| Task | Description | Responsible | Status |
|---|---|---|---|
| Final Report | Analyze final outcomes, compare against objectives, and document results. | JD-021, JD-016 | ⏳ Pending |
| Define Next Steps | Outline future roadmap, improvements, or additional collaborations. | JD-021, JD-016 | ⏳ Pending |
Project leads
| Team | Code | Leader of |
|---|---|---|
| Legit.Health | JD-002, JD-008, JD-019 | Sales Manager, Business Development Manager, Sales Development Representative, Digital Health Manager |
| Legit.Health | JD-027 | Project Manager Lead |
| Legit.Health | JD-013 | Project Manager |
| Legit.Health | JD-003 | Design and Development Manager |
| Legit.Health | JD-016 | Customer Success Manager |
| Legit.Health | JD-018 | Clinical Research Manager |
| Legit.Health | JD-004 | Quality Manager & PRRC |
| Legit.Health | JD-007, JD-010 | Technology Manager, Software developer |
| Legit.Health | JD-005, JD-009 | Machine Learning Manager, Medical Data Scientist |
| Legit.Health | JD-014 | Data Analyst |
| J&J Innovative Medicine | Oana Cula | Sr. Director DSDH Immunology |
Signature meaning
The signatures for the approval process of this document can be found in the verified commits at the repository for the QMS. As a reference, the team members who are expected to participate in this document and their roles in the approval process, as defined in Annex I Responsibility Matrix of the GP-001, are:
- Author: Team members involved
- Reviewer: JD-003 Design & Development Manager, JD-004 Quality Manager & PRRC
- Approver: JD-001 General Manager