EPIC-X Grant Application - Data Request for Teams

Purpose: Gather specific data to complete EPIC-X grant application UPDATE placeholders

Deadline: January 2, 2026 (before final submission on January 5, 2026)

Context: We're applying for a EUR 60,000 equity-free grant from EPIC-X (European acceleration program for women-led deep-tech startups). The application is 75% complete structurally, but we need team input to fill remaining data placeholders for maximum competitive scoring (target: 80-90/100 points).

How to Respond: Please fill in the answers directly in this document under each section and return to Taig by January 2, 2026.

---

1. Medical Data Science Team (Contact: JD-005, JD-009)

1.1 Main Diagnostic Model (239 ICD-11) - Fitzpatrick Performance Breakdown

Context: We need to demonstrate unbiased AI performance across all skin tones for the "Unbiased Mission" criterion (10 points). We already have data for Acneiform and Hive Detection models, but need the main diagnostic model data.

Questions:

1. Top-5 Diagnostic Accuracy by Fitzpatrick Type:

   • Fitzpatrick I-II (Light skin): [%] with 95% CI [lower-upper]
   • Fitzpatrick III-IV (Medium skin): [%] with 95% CI [lower-upper]
   • Fitzpatrick V-VI (Dark skin): [%] with 95% CI [lower-upper] (or note if insufficient data)

2. Statistical Comparison (Chi-square test results):

   • p-value for performance differences across Fitzpatrick groups: [p-value]
   • Assessment: [PASS/FAIL] (PASS if no significant degradation p < 0.05)

3. Datasets Used:

   • Test set size total: [n images]
   • Test set breakdown by Fitzpatrick: I-II [n], III-IV [n], V-VI [n]
   • Datasets: DDI dataset ([Yes/No]), Internal test set ([Yes/No]), Other: [Name]

4. Source Document Reference:

   • This data should be in R-TF-028-005 lines 293-296 (currently marked "[TO FILL]")
   • Can you confirm the data exists and provide it? [Yes/No]
   • If not yet calculated, when can it be ready? [Date]

---

1.2 Performance vs. State-of-the-Art (SOTA) Benchmarks

Context: Demonstrate that our AI performance meets/exceeds published academic benchmarks for the "Excellence" criterion (part of 40 points).

Questions:

Diagnostic Accuracy:

Condition	Legit.Health Performance	Metric (e.g., Sensitivity, Top-5 Accuracy)	95% CI
Melanoma	[%]	[Metric name]	[lower-upper]
Psoriasis	[%]	[Metric name]	[lower-upper]
Atopic Dermatitis	[%]	[Metric name]	[lower-upper]
Acne	[%]	[Metric name]	[lower-upper]

Severity Assessment (ICC - Intraclass Correlation Coefficient):

Scale	Legit.Health ICC	95% CI	Reference Study (if available)
PASI (Psoriasis)	[ICC value]	[lower-upper]	[Study name or "Internal"]
SCORAD (Eczema)	[ICC value]	[lower-upper]	[Study name or "Internal"]
EASI (Atopic Derm)	[ICC value]	[lower-upper]	[Study name or "Internal"]

Published SOTA Benchmarks (for comparison in grant):

• Melanoma SOTA: 86-95% (Stanford HAM10000, Esteva et al., Nature 2017) ← Confirm this is accurate reference
• PASI SOTA: ICC 0.85-0.92 (Langley et al., JAAD 2015) ← Confirm accurate
• Do we have other references for psoriasis, atopic dermatitis, acne? [List]

---

1.3 Training Data Metrics

Context: Demonstrate scale and diversity of AI training for "Excellence" criterion.

Questions:

1. Total Dataset Size:

   • Total dermatological images in training dataset: [n images]
   • Breakdown: Training [n], Validation [n], Test [n]

2. CNN Architecture:

   • Main architecture used (e.g., ResNet-50, EfficientNet, custom ensemble): [Architecture name]
   • Is this shareable information (not proprietary)? [Yes/No]

3. Fitzpatrick Distribution in Training Data (if available):

   • Fitzpatrick I: [%] or [n images]
   • Fitzpatrick II: [%] or [n images]
   • Fitzpatrick III: [%] or [n images]
   • Fitzpatrick IV: [%] or [n images]
   • Fitzpatrick V: [%] or [n images]
   • Fitzpatrick VI: [%] or [n images]
   • Note: If exact % not tracked, provide estimate or note "Representative diversity across I-VI"

4. Gender Distribution in Training Data (if available):

   • Women: [%] or [n images]
   • Men: [%] or [n images]
   • Non-binary/not reported: [%] or [n images]
   • Note: If not tracked, note "Balanced representation targeted"

---

1.4 Performance by Gender (if available)

Context: Demonstrate no gender bias for "Unbiased Mission" criterion.

Question: Do we have diagnostic accuracy broken down by gender for any conditions?

Condition	Accuracy (Women)	Accuracy (Men)	Difference	Assessment
Acne	[%]	[%]	[± X pp]	[No significant bias / Data unavailable]
Psoriasis	[%]	[%]	[± X pp]	[No significant bias / Data unavailable]
Melanoma	[%]	[%]	[± X pp]	[No significant bias / Data unavailable]
Atopic Dermatitis	[%]	[%]	[± X pp]	[No significant bias / Data unavailable]

Note: If this analysis hasn't been done, simply note "Gender bias analysis not yet completed" - it's not critical for the grant.

---

2. Clinical Team (Contact: JD-018, Clinical Research Manager)

2.1 Clinical Studies Summary Table

Context: Demonstrate clinical validation rigor for "Excellence" criterion (part of 40 points). We have 7 completed studies mentioned in the application, but need details.

Questions: Please complete the table below for all clinical studies conducted:

Study Code/Name	Hospital/Institution Name	Condition(s) Studied	n Patients	Study Design	Start Date	End Date	Publication Status	DOI (if published)
APASI 2024 (Boehringer Ingelheim)	[Hospital name(s)]	Psoriasis	[n]	[RCT/Observational/Pilot]	[YYYY-MM]	[YYYY-MM or "Ongoing"]	[Published/Under Review/Not Published]	[DOI or "N/A"]
AIHS4 2025	Vall d'Hebron	Hidradenitis Suppurativa	[n]	[Design]	[Date]	[Date]	[Status]	[DOI or "N/A"]
SAN 2024	[Hospital]	[Condition]	[n]	[Design]	[Date]	[Date]	[Status]	[DOI or "N/A"]
DAO 2022 (Time savings)	[Hospital]	[Condition]	[n]	[Design]	[Date]	[Date]	[Status]	[DOI or "N/A"]
IDEI 2023 (Eczema)	[Hospital]	Eczema/Atopic Dermatitis	[n]	[Design]	[Date]	[Date]	[Status]	[DOI or "N/A"]
MC_EVCDAO_2019	[Hospital]	[Condition]	[n]	[Design]	[Date]	[Date]	[Status]	[DOI or "N/A"]
[Study 7 name if applicable]	[Hospital]	[Condition]	[n]	[Design]	[Date]	[Date]	[Status]	[DOI or "N/A"]

Total across all studies: [Sum of n patients] patients

---

2.2 Study Participant Demographics (if available)

Context: Demonstrate diversity in clinical validation for "Women Leadership" criterion (10 points) and "Unbiased Mission" (10 points).

Question: For the studies above, do we have participant demographic breakdowns available?

Study 1: [Study Name] (n = [n total])

• Gender: Women [n or %], Men [n or %], Other/Prefer not to say [n or %]
• Age: Mean [years] ± SD [years], Range [min-max years], Pediatric (<18) [n], Adult (18-65) [n], Elderly (>65) [n]
• Fitzpatrick skin types (if collected): I-II [n or %], III-IV [n or %], V-VI [n or %], or note "Not collected"

Study 2: [Study Name] (n = [n total])

• [Same format as above]

Note: If demographic data wasn't collected for some studies, note "Demographic data not available for this study" - this is common for retrospective studies.

---

2.3 Key Clinical Findings

Context: Demonstrate clinical impact for "Excellence" criterion.

Questions:

1. APASI Study (Boehringer Ingelheim, n=~1000):

   • ICC between automated PASI and dermatologist scores: [ICC value] with 95% CI [lower-upper]
   • Key finding quote: ["Quote from study report"]

2. DAO Study (Time savings):

   • Time reduction: [X%] reduction (from [X min] to [X min] per patient)
   • Key finding quote: ["Quote"]

3. Diagnostic Accuracy Study (if we have one):

   • Sensitivity for top-1 prediction: [%]
   • Sensitivity for top-5 differential diagnosis: [%]
   • Key finding quote: ["Quote"]

Note: If specific numbers aren't immediately available, provide "Study demonstrated clinical utility" or similar general statement.

---

3. Regulatory Team (Contact: JD-004, Quality Manager & PRRC)

3.1 Regulatory Certificates

Context: Demonstrate regulatory excellence for "Excellence" criterion (part of 40 points).

Questions:

1. ISO 13485:2016 Quality Management System:

   • Certification body: BSI ([Confirm] or other)
   • Certificate number: [Number]
   • Issue date: [YYYY-MM-DD]
   • Renewal/expiry date: [YYYY-MM-DD]

2. CE MDR Class IIb:

   • Notified Body: [Name and number]
   • Certificate number: [Number]
   • Issue date: [YYYY-MM-DD] (we mention 2023 in application)
   • Renewal/expiry date: [YYYY-MM-DD]

3. Spain - AEMPS:

   • Medical Device License number: [Number]
   • Issue year: [YYYY]
   • Renewal date: [YYYY-MM-DD or "N/A if no renewal required"]

4. UK - MHRA:

   • Medical Device Registration number: [Number]
   • Registration year: [YYYY]
   • Renewal date: [YYYY-MM-DD or "N/A"]

5. Brazil - ANVISA:

   • Medical Device Registration number: [Number]
   • Registration year: [YYYY]
   • Renewal date: [YYYY-MM-DD or "N/A"]

---

3.2 FDA 510(k) Strategy

Context: Demonstrate US market entry plan for "Excellence" criterion.

Questions:

1. Predicate Device Identification:

   • Have we identified an FDA-cleared predicate device for our 510(k) submission? [Yes/No]
   • If yes:
     • Predicate device name: [Device name]
     • Manufacturer: [Company name]
     • 510(k) number: [K-number, e.g., K123456]
     • Device classification: [Class and regulation number]
     • Why this is a good predicate: [Brief explanation, e.g., "Similar AI-based dermatology diagnostic support"]
   • If no:
     • Status: [Under evaluation / Will identify with coaching support]

2. FDA Timeline:

   • Pre-submission meeting planned: [Q1 2026] ← Confirm or update
   • 510(k) submission target: [Q2 2026] ← Confirm or update
   • Clearance target: [Q4 2026] ← Confirm or update

---

4. Finance Team (Contact: Finance lead)

4.1 Revenue Data

Context: Demonstrate market fit and growth trajectory for "Impact & Market" criterion (15 points).

Questions:

1. Historical Revenue:

   • 2022 Total Revenue: EUR [amount]
   • 2023 Total Revenue: EUR [amount]
   • 2024 Total Revenue (actual or projected year-end): EUR [amount]

2. Revenue Growth:

   • 2022 → 2023 Growth: [%] YoY
   • 2023 → 2024 Growth: [%] YoY

3. Revenue Projections:

   • 2025 Projected Revenue: EUR [amount] (assumptions: [Brief explanation, e.g., "Based on X new contracts signed"])
   • 2026 Projected Revenue: EUR [amount] (assumptions: [Brief explanation])
   • 2026 Growth vs. 2024: [%]

---

4.2 Hospital Contracts

Context: Demonstrate commercial traction for "Impact & Market" criterion.

Questions:

Current Hospital Contracts (as of December 2024):

Country	Hospital/Organization Name	Contract Type (Pilot/Full)	Annual Recurring Revenue (ARR)	Start Date	Status (Active/Signed/Pipeline)
Spain	[Hospital name]	[Pilot/Full]	EUR [amount]	[YYYY-MM]	[Active/Signed/Pipeline]
Spain	[Hospital name]	[Pilot/Full]	EUR [amount]	[YYYY-MM]	[Active/Signed/Pipeline]
Spain	[Hospital name]	[Pilot/Full]	EUR [amount]	[YYYY-MM]	[Active/Signed/Pipeline]
UK	[Hospital name if any]	[Pilot/Full]	EUR [amount]	[YYYY-MM]	[Active/Signed/Pipeline]

Total Spain Contracts: [Count] Total UK Contracts: [Count] Total Active ARR: EUR [sum]

---

4.3 CDTI Grant Details

Context: Demonstrate seed financing for "Impact & Market" criterion.

Questions:

1. CDTI Sello de Excelencia Grant:
   • Total grant amount: EUR 2.5M ← Confirm this is accurate
   • Award date: [YYYY-MM]
   • Project duration: [Start YYYY-MM] to [End YYYY-MM]
   • Grant scope/purpose: [Brief description, e.g., "AI development and clinical validation"]
   • Disbursement schedule: [Brief description, e.g., "EUR X upfront, EUR Y upon milestones"] or "Not needed for grant"

---

5. HR Team (Contact: HR lead)

5.1 Team Size and Diversity

Context: Demonstrate team capacity for "Implementation & Capacity" criterion (10 points) and women representation for "Women Leadership" criterion (10 points).

Questions:

1. Current Team Size (December 2024):

   • Total FTEs: [n] (we mention 31 in application - confirm or update)
   • Total headcount including part-time/contractors: [n]

2. Gender Diversity - Overall Team:

   • Women (count): [n]
   • Women (%): [%]
   • Men (count): [n]
   • Men (%): [%]
   • Non-binary/prefer not to say: [n] or "Not tracked"

3. Gender Diversity - Leadership Roles:

   • Definition of leadership: C-level (CEO, CTO, etc.) + Department Heads + Team Leads
   • Women in leadership (count): [n]
   • Women in leadership (%): [%]
   • Total leadership positions: [n]

4. Gender Diversity - Technical Roles:

   • Definition of technical: Medical Data Science + Software Engineering + QA/Testing
   • Women in technical roles (count): [n]
   • Women in technical roles (%): [%]
   • Total technical positions: [n]

5. Board Composition (for Section 6):

   • Total board members: [n]
   • Board members - Women: [n] (including Andy Aguilar as Presidenta)
   • Board members - Men: [n]
   • Board members names and roles:
     • Andy Aguilar - Presidenta del Consejo de Administración ← Confirm
     • [Name] - [Role]
     • [Name] - [Role]

---

5.2 Co-Founders Information

Context: Demonstrate women-led qualification for "Women Leadership" criterion (10 points).

Questions:

1. Co-Founders (founded September 2017):

   • Co-Founder 1: Andy Aguilar (Sheyla Andina Aguilar) - CEO, 33.33% shareholder ← Confirm
   • Co-Founder 2: [Name] - [Current role if still at company], [% shareholding]
   • Co-Founder 3: [Name] - [Current role if still at company], [% shareholding]

2. Board Appointment Date:

   • When was Andy appointed Presidenta del Consejo de Administración? [YYYY-MM or "At founding"]

---

6. Andy Aguilar Personal Information (Contact: Andy directly)

6.1 Leadership Timeline and Achievements

Context: Demonstrate women leadership track record for "Women Leadership" criterion (10 points).

Questions:

1. Forbes Recognition Details:

   • Forbes 30 Under 30: [Year], [Category, e.g., "Healthcare" or "Technology"], [Region, e.g., "Europe"]
   • Forbes 100 Most Creative Individuals in Business: [Year], [Category]

2. Conference Speaking Log (2023-2024):

   • Please list 3-5 recent conference talks where you spoke about Legit.Health, women in deep-tech, or inclusive AI:
     • Conference 1: [Conference name], [Date YYYY-MM], [Location], [Talk title]
     • Conference 2: [Conference name], [Date], [Location], [Talk title]
     • Conference 3: [Conference name], [Date], [Location], [Talk title]
     • [More if applicable]

3. Media Features (2023-2024):

   • Please list any media articles/interviews where you or Legit.Health were featured:
     • Media 1: [Publication name, e.g., "TechCrunch"], [Article title], [Date YYYY-MM], [URL if available]
     • Media 2: [Publication], [Title], [Date], [URL]
     • [More if applicable]

4. LinkedIn Metrics (for visibility assessment):

   • Current LinkedIn follower count: [n]
   • LinkedIn profile URL: [URL] (we have this from previous data collection)

5. Vision Statement (for grant narrative):

   • In 2-3 sentences, what is your vision for Legit.Health's role in democratizing dermatology and advancing inclusive AI in healthcare?
   • [Your statement here]

6. Mentorship Activities:

   • Are you currently mentoring any women entrepreneurs in healthcare/deep-tech? [Yes/No]
   • If yes, how many mentees? [n]
   • Through what program/informally? [Program name or "Informal"]

---

7. Technical/Engineering Team (Optional - Low Priority)

7.1 Interoperability

Context: Demonstrate European technical alignment for "European Added Value" criterion (5 points).

Questions (only if easily accessible):

1. EHR Integration:

   • Which specific EHR systems have we integrated with or tested? [List, e.g., "Epic, Cerner" or "Spanish hospital proprietary systems"]
   • Or note: "FHIR-compliant, tested with major EHR vendors"

2. IHE Compliance:

   • Do we implement any IHE (Integrating the Healthcare Enterprise) profiles? [Yes/No]
   • If yes, which profiles? [List]
   • If no or unsure, note: "Not applicable" (this is fine)

3. DICOM Support:

   • Do we support DICOM for dermatology imaging workflows? [Yes/No]
   • If yes, brief description: [1 sentence]
   • If no, note: "Not applicable" (this is fine - DICOM is more radiology-focused)

---

8. Environmental Impact (Optional - Very Low Priority)

Context: Demonstrate social impact for "European Added Value" criterion (5 points).

Question (only if easily calculable):

1. CO2 Emissions Avoided:
   • Estimated CO2 emissions avoided through teledermatology consultations (eliminating patient travel): [X tons] per [10,000 consultations]
   • Or note: "Not calculated" (this is fine - it's a nice-to-have, not required)

---

Response Instructions

1. Fill in all [PLACEHOLDERS] with actual data
2. If data is unavailable, note "Data not available" or "Not tracked" - this is acceptable
3. Return completed document to Taig by January 2, 2026
4. Priority ranking (focus on these if time-limited):
   • HIGHEST: MDS (1.1, 1.2), Clinical (2.1, 2.2), HR (5.1, 5.2), Andy (6.1)
   • HIGH: Regulatory (3.1, 3.2), Finance (4.1, 4.2, 4.3)
   • MEDIUM: MDS (1.3, 1.4)
   • LOW: Technical (7.1), Environmental (8.1)

---

Questions or Clarifications?

Contact: Taig Mac Carthy (taig@legit.health)

Thank you for your support in securing this EUR 60,000 grant!

The stronger our data, the more competitive our application (target score: 80-90/100 points). This grant will fund our US FDA clearance, Series A fundraising, European expansion, and Andy's visibility as a thought leader in women-led deep-tech.

---

Document Version: 1.0 Created: December 22, 2024 Deadline: January 2, 2026