Case Studies

Explore real-world examples of assurance cases across different domains. These case studies demonstrate how the TEA methodology can be applied to various AI and data-driven systems.

Available Case Studies

Healthcare

• Diabetic Retinopathy Screening - An AI system for detecting diabetic retinopathy in retinal images
• Transparent Clinical GenAI System with Legacy Data - A GenAI clinical decision support system trained on patient data collected under historical consent frameworks

Pharmaceutical

• Equitable Personalised Pharmaceutical Formulation System - AI-powered personalised drug formulations with fairness considerations for demographically biased training data

Agriculture

• Crop Damage Assessment - Using satellite imagery and ML for agricultural damage assessment

Environmental

• Flood Risk Assessment - AI-powered flood risk prediction and management

Education

• Student Learning Assessment - AI systems for educational assessment and feedback

How to Use These Case Studies

Each case study includes:

1. Overview - Background on the domain and system being assessed
2. System Description - Technical details of the AI system
3. Stakeholders - Key parties with interests in the system’s assurance
4. Regulatory Context - Relevant regulations and standards
5. Assurance Considerations - Specific concerns for the assurance goal (e.g., fairness, explainability, transparency)
6. Deliberative Prompts - Questions for reflection and discussion
7. Suggested Strategies - Approaches for developing the assurance case
8. Recommended Techniques - Links to relevant TEA Techniques for gathering evidence

These case studies can be used for:

• Self-study - Work through examples at your own pace
• Workshops - Group activities and discussions
• Templates - Starting points for your own assurance cases