Skip to main content
QMSQMS
QMS
  • Welcome to your QMS
  • Quality Manual
  • Procedures
    • GP-001 Control of documents
    • GP-002 Quality planning
    • GP-003 Audits
    • GP-004 Vigilance system
    • GP-005 Human Resources and Training
    • GP-006 Non-conformity, Corrective and Preventive actions
    • GP-007 Post-market surveillance
    • GP-008 Product requirements
    • GP-009 Sales
    • GP-010 Purchases and suppliers evaluation
    • GP-011 Provision of service
    • GP-012 Design, redesign and development
    • GP-013 Risk management
    • GP-014 Feedback and complaints
    • GP-015 Clinical evaluation
    • GP-016 Traceability and identification
    • GP-017 Technical assistance service
    • GP-018 Infrastructure and facilities
    • GP-019 Software validation plan
    • GP-020 QMS Data analysis
    • GP-021 Communications
    • GP-022 Document translation
    • GP-023 Change control management
    • GP-024 Predetermined Change Control Plan
    • GP-025 Usability and Human Factors Engineering
    • GP-027 Corporate Governance
    • GP-028 AI Development
      • Specific procedures
        • T-TF-028-001 AI Description
        • T-TF-028-002 AI Development Plan
        • T-TF-028-003 Data Collection Instructions
        • T-TF-028-004 Data Annotation Instructions
        • T-TF-028-005 AI Development Report
        • T-TF-028-006 AI Release Report
        • T-TF-028-007 AI Retraining Report
        • T-TF-028-008 AI Reevaluation Report
        • T-TF-028-009 AI Design Checks
        • T-TF-028-010 AI V&V Checks
        • T-TF-028-011 AI Risk Assessment
    • GP-029 Software Delivery and Commissioning
    • GP-030 Cyber Security Management
    • GP-050 Data Protection
    • GP-051 Security violations
    • GP-052 Data Privacy Impact Assessment (DPIA)
    • GP-100 Business Continuity (BCP) and Disaster Recovery plans (DRP)
    • GP-101 Information security
    • GP-200 Remote Data Acquisition in Clinical Investigations
    • GP-026 Market-specific product requirements
    • GP-110 Esquema Nacional de Seguridad
  • Records
  • Legit.Health Plus Version 1.1.0.0
  • Legit.Health Plus Version 1.1.0.1
  • Legit.Health Utilities
  • Licenses and accreditations
  • Applicable Standards and Regulations
  • Pricing
  • Public tenders
  • Procedures
  • GP-028 AI Development
  • Specific procedures
  • T-TF-028-005 AI Development Report

T-TF-028-005 AI Development Report

Table of contents
  • Introduction
    • Context
    • Algorithms Description
    • AI Standalone Evaluation Objectives
  • Data Management
    • Overview
    • Data Collection
    • Foundational Annotation
    • Data Partitioning
  • Model Development and Validation
    • [Model Name]
      • Model Overview
      • Data Requirements and Annotation
      • Training Methodology
      • Performance Results
      • Verification and Validation Protocol
      • Bias Analysis and Fairness Evaluation
  • Overall Conclusions
  • Risk Assessment Integration
  • Related Documents

Introduction​

Context​

Describe the context for this development report. Reference the governing procedure (GP-028) and the AI Development Plan (R-TF-028-002).

Algorithms Description​

Provide a summary of all algorithms covered in this report.

Algorithm Summary:

AlgorithmTypeDescription

AI Standalone Evaluation Objectives​

Describe the objectives for standalone AI evaluation.

Data Management​

Overview​

Provide an overview of the data management approach.

Data Collection​

Describe the data sources and collection process. Reference the Data Collection Instructions (R-TF-028-003).

Dataset Summary:

ItemValue
Total images
Total categories

Foundational Annotation​

Describe the foundational annotation process. Reference the Data Annotation Instructions (R-TF-028-004).

Data Partitioning​

Describe how data was partitioned into training, validation, and test sets.

PartitionSizePercentage
Training
Validation
Test

Model Development and Validation​

For each model, provide the following sections:

[Model Name]​

Model Overview​

Reference: Reference to R-TF-028-001 section

Provide a brief overview of the model.

Data Requirements and Annotation​

Describe model-specific data and annotation requirements.

Dataset Statistics:

ItemValue

Training Methodology​

Pre-processing:

Describe pre-processing steps.

Architecture:

Describe the model architecture and selection rationale.

Training:

  • Optimizer: Optimizer details
  • Loss function: Loss function details
  • Learning rate: Learning rate strategy
  • Training duration: Number of epochs

Post-processing:

Describe post-processing steps.

Performance Results​

MetricResultSuccess CriterionOutcome

Verification and Validation Protocol​

Test Design:

Describe the test design.

Complete Test Protocol:

Describe the test protocol.

Data Analysis Methods:

Describe the data analysis methods.

Test Conclusions:

State the conclusions from testing.

Bias Analysis and Fairness Evaluation​

Objective:

Describe the objective of bias analysis.

Subpopulation Analysis Protocol:

Describe the subpopulations analyzed.

Results Summary:

Summarize the bias analysis results.

MetricOverallSubgroup 1Subgroup 2

Bias Analysis Conclusion:

State conclusions from bias analysis.

Overall Conclusions​

Provide overall conclusions from the development report.

Risk Assessment Integration​

Describe how findings relate to the AI Risk Assessment (R-TF-028-011).

Related Documents​

Document IDTitle
R-TF-028-001
R-TF-028-002
R-TF-028-003
R-TF-028-004
R-TF-028-006
R-TF-028-011

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: JD-009
  • Reviewer: JD-009
  • Approver: JD-005
Previous
T-TF-028-004 Data Annotation Instructions
Next
T-TF-028-006 AI Release Report
  • Introduction
    • Context
    • Algorithms Description
    • AI Standalone Evaluation Objectives
  • Data Management
    • Overview
    • Data Collection
    • Foundational Annotation
    • Data Partitioning
  • Model Development and Validation
    • [Model Name]
      • Model Overview
      • Data Requirements and Annotation
      • Training Methodology
      • Performance Results
      • Verification and Validation Protocol
      • Bias Analysis and Fairness Evaluation
  • Overall Conclusions
  • Risk Assessment Integration
  • Related Documents
All the information contained in this QMS is confidential. The recipient agrees not to transmit or reproduce the information, neither by himself nor by third parties, through whichever means, without obtaining the prior written permission of Legit.Health (AI Labs Group S.L.)