Customer Story - Audere
Raw data is just noise without strategy. Different data sources require tailored approaches and without the right structure, building AI tools that deliver real-world impact is impossible. IndiVillage partnered with Audere to tackle a life-saving challenge - ensuring that HIV self-test results were interpreted with absolute accuracy.
Overview
Data That Drives Life-Saving Decisions
IndiVillage’s AI model didn’t just support the process, it outperformed expectations, achieving 100% accuracy in identifying both positive and negative cases. With over 619K interpretations and 185K annotations until March 2025, we turned raw data into actionable insights, ensuring safer, more reliable HIV testing for all.
The Challenge
The Risk of Misinterpreted HIV Tests
HIV self-testing (HIVST) empowers individuals, but a single misread result can change a life-delaying treatment, spreading infection, or leading to unnecessary medication. With varying data sources and human interpretation inconsistencies, a reliable AI solution was critical.
The Solution
Smarter Testing, Safer Outcomes
IndiVillage collaborated with researchers in Kenya to test an AI-driven approach. Pharmacy staff assisted clients with testing and securely uploaded test images.
These were analyzed by four groups: test-takers, pharmacy providers, a panel of 20 HIVST experts, and IndiVillage’s AI model, trained to detect results with unmatched precision.
Project Focus
- AI Model Training
- Image Annotation
- Data Interpretation
- Quality Assurance
IndiVillage Tech Solutions has been a great partner in our mission to advance health equity through AI-enabled solutions. By providing accurately labeled images of the most widely used diagnostic tool globally, rapid diagnostic tests (RDTs), they have provided an invaluable input into our computer vision algorithms, allowing us to build highly accurate AI that assesses the quality of administration and interpretation of RDTs. IndiVillage's meticulous image annotation and interpretation services are instrumental in the ongoing development and monitoring of our AI solutions.
