KAI-VORAL-VAL-001 — Validation Plan
Template ID: TPL-07-07 | Stage: 07-Test-and-Validate | Version: 0.3
Status: Project record created from the controlled template.
Purpose: Prespecify how the product will be shown to meet user needs and intended use in its real setting, with acceptance criteria fixed before results are seen.
Required inputs: PRD; intended use; quality and validation plan; risk register.
Document control
| Field |
Required entry |
| Document ID |
KAI-VORAL-VAL-001 |
| Template used |
TPL-07-07 Validation Plan v0.3 |
| Product / project / software version or commit SHA |
VORAL (Visionary Oral) / PRJ-001 / a6b4429e3165 (branch app_dev of AI-Dental-Project/Visionary_Oral) |
| Record status and version |
Draft v0.1 |
| Author / technical reviewer / quality reviewer |
Claude Code (drafted with Claude Code for KrinosAI) / Tech Lead (name to be assigned) / Qualified regulatory reviewer (name to be assigned) |
| Created / updated / approved dates |
2026-10-28 / 2026-10-28 / Pending |
| Applicable SOP and revision |
SOP-LC-07 v0.3 |
| Related issue, commit, requirement and evidence links |
KAI-VORAL-MDC-001; KAI-VORAL-QVP-001; KAI-VORAL-DPIA-001 |
| Approver and decision record |
Pending |
Applicability and evidence baseline
Product / system boundary: Web app and API (dentalapp/), doctor/admin mobile app (mobile/), on-device models (mobile/assets/models/), PDF Lambda (dentalapp/pdf-lambda/) at a6b4429e3165, and the external services they call.
Related approved requirements, risks and change records: None approved. Related drafts are listed in document control.
Retrospective record? Yes — follows the Retrospective Documentation Protocol (KrinosAI lifecycle pack, 05-References/). Items are labelled Observed (code or Git at a6b4429), Measured (dated run), Stated (named person, dated) or Not recorded. Test records describe the tests that exist at a6b4429 and the one run made on 2026-10-28. No earlier test runs, test plans or sign-offs were recorded; tests for untested requirements are planned, not run. This plan is a proposal; no validation study has been run.
Acceptable evidence: an implementation reference (file:line at a commit SHA), a dated test record, a signed decision, a vendor agreement, or another independently verifiable artifact. Never invent approvals, clinical results, measurements or performance data.
1. Users intended use and clinical workflow
| Item |
Entry |
| Users |
Dentists at partner clinics |
| Intended use |
Proposed (Claude Code, for confirmation): flag possible cavity, calculus, gum recession and swollen gums on three phone photos for the dentist to confirm |
| Workflow |
Journey J1 in KAI-VORAL-PRD-001 §3 |
2. Population and representative samples
| Sample |
Size |
Why representative |
| Proposed (Claude Code, for confirmation): prospective photo sets |
≥ 300 patients (900 photos) from ≥ 3 clinics |
Mix of ages, genders, phones and lighting; at least 62 positive cases per finding |
3. Primary endpoints and prespecified metrics
| Endpoint |
Threshold |
| Sensitivity per finding |
Proposed (Claude Code, for confirmation): ≥ 0.80, lower 95 % CI ≥ 0.70 |
| Specificity per finding |
Proposed (Claude Code, for confirmation): ≥ 0.80 |
| Phone vs server agreement |
Proposed (Claude Code, for confirmation): ≥ 90 % of findings |
4. Study methodology and reference standard
| Item |
Entry |
| Design |
Proposed (Claude Code, for confirmation): prospective, blinded |
| Reference standard |
Two dentists label each photo independently; a third resolves disagreements |
| Comparison |
Per photo and per finding, at the shipped thresholds |
5. Bias subgroup and failure analysis
| Subgroup |
Minimum n |
| Age band (< 18, 18–40, 41–60, > 60) |
Proposed (Claude Code, for confirmation): 30 each |
| Phone model / camera |
Proposed (Claude Code, for confirmation): 30 each |
| Clinic |
Proposed (Claude Code, for confirmation): 30 each |
6. Ethics consent and data permissions as applicable
| Item |
Entry |
| Ethics |
Ethics committee approval before data collection |
| Consent |
Written patient consent for photos and research use (OPEN-031) |
| Data permissions |
Under the approved DPIA (OPEN-009) |
7. Statistical approach and acceptance decision
| Item |
Entry |
| Statistics |
Wilson 95 % confidence intervals; pre-specified thresholds above |
| Decision |
Clinical advisor and qualified regulatory reviewer, Pending |
| Status |
Not started — OPEN-011 |
Open issues and decisions
| ID |
Specific gap or decision |
Responsible owner |
Due date |
Blocks gate? |
Evidence required |
Status |
| OPEN-001 |
Tracker project ID, named requester and sponsor, and named reviewers are not recorded |
Product Owner |
2026-11-10 (proposed) |
Yes |
Tracker entry; names with roles |
Open |
| OPEN-009 |
No DPIA |
Security & Privacy Officer |
2026-11-30 (proposed) |
Yes |
DPIA |
Open |
| OPEN-011 |
No clinical validation |
Clinical advisor with ML Lead |
2026-12-15 (proposed) |
Yes |
Validation study |
Open |
| OPEN-031 |
No recorded patient consent or privacy notice for photo capture, AI processing and QR self-registration |
Security & Privacy Officer |
2026-11-30 (proposed) |
Yes |
Consent text, where it is shown, and stored consent records |
Open |
Review and approval
| Review role |
Named individual |
Decision |
Date |
Signed / controlled record |
| Author |
Claude Code (drafted with Claude Code) |
Draft |
2026-10-28 |
This file at the commit that adds it |
| Technical reviewer |
Tech Lead (name to be assigned) |
Pending |
Pending |
Pending |
| Quality / regulatory reviewer (if applicable) |
Qualified regulatory reviewer (name to be assigned) |
Pending |
Pending |
Pending |
| Authorized approver |
Clinical advisor (name to be assigned) |
Pending |
Pending |
Pending |