Practical AI NLP to help pregnant mothers in Kenya
Aug 17, 2021
Jay Patel and Sathy Rajasekharan from Jacaranda Health share their mission to revolutionize maternal care in Kenya using AI-powered NLP solutions. They discuss the alarming maternal mortality rates and how SMS technology helps prioritize urgent messages from pregnant mothers. The duo explores the challenges of data labeling and collaboration in developing effective communication platforms. They also highlight the importance of navigating Kenya's linguistic diversity to enhance health responses, ultimately aiming to ensure safe childbirth and newborn care.
AI Snips
Chapters
Transcript
Episode notes
Data Labeling Challenges
- Labeling 13,000 questions was labor-intensive, requiring manual labeling by multiple team members over several weeks.
- Training on label definitions was crucial due to subjectivity, emphasizing the need for clear guidelines and consensus among labelers.
Gaining Team Buy-in for AI
- To build team buy-in for AI solutions, focus on demonstrating how the technology directly improves their work.
- Show how AI reduces workloads and increases efficiency, rather than focusing on technical details or abstract benefits.
From Initial Excitement to Practical Results
- Initial excitement about AI's potential waned when the help desk found the first model ineffective, highlighting the importance of practical results.
- Addressing practical issues like filtering unnecessary responses led to increased team buy-in and further model refinement.