Bridging health inequalities through machine learning
summary
Describes Feebris’ ML-powered health platform that pairs digital stethoscope + pulse oximeter with a mobile app, tested in a 1300‑child 2017 India trial and scaled to 10,000, reporting 97% triage and 85% pneumonia accuracy versus x‑ray/blood tests. Explains handling noisy community recordings, poor annotator agreement, cloud inference and the push to on‑device models for patchy connectivity, plus regulatory and ethical hurdles and concrete deployment tradeoffs.
AI-written summary · about
chapters (8)
- 0:00Introduction
- 3:14Universal healthcare access challenge
- 7:10Bridging community care with machine learning
- 13:57AI and noisy medical signals
- 20:44Pneumonia diagnosis with ML
- 26:23AI in low-resource healthcare
- 29:13Elderly care expansion
- 30:17Q&A
related talks
25mAI for healthcare: Scaling Access and Quality of Care for Everyone
01h 03mUsing Machine Learning and AI to serve people and communities
22mReimaging Healthcare
06mUser-Based Collaborative Filtering Mobile Health System
47mLeveraging AI for Global Health
23mEngineering AI-Powered Predictive Healthcare Systems
01h 14mChallenges for Leveraging the Potential of Digital Technology in Medi
20mDiagnostic Medical application of ML