What Healthcare Can Learn from Netflix
summary
Omada Health builds personalization with analytics, machine learning and built‑in experimentation across 60,000 participants, mailing physical scales and collecting longitudinal weight, steps and meal logs. A/B experiments produce actionable wins: coach food feedback yields an ~8% relative weight‑loss lift and more meal tracking, adaptive step goals (age/BMI +20%) show subgroup gains, and a random‑forest uplift model boosts targeted tracking from ~5% to ~7%. The platform-backed, outcomes‑based program averages 5% weight loss at 12 months versus ~2.5% for traditional in‑person programs.
AI-written summary · about
chapters (7)
- 0:00Introduction
- 1:57Chronic disease prevention gap
- 4:45Data science as conductor
- 7:12Building data science culture
- 11:55Experimentation in health
- 14:44Personalization through modeling
- 18:39Summary and takeaways
related talks
07mHow AI is Enabling Healthcare's Biggest Blindspot
24mBuilding Cloud-based Solutions in Healthcare
06mUser-Based Collaborative Filtering Mobile Health System
14mDoes fitness data make the average person healthier?
33mData Science in Healthcare: Beyond the Hype
37mNew Era of Data Insights with Samsung Health
03mMachine Learning for Personalization
26mMachine Learning for Personalised Health