Accelerating COVID-19 insights for clinical use with intelligent search
summary
PanSurg builds REDASA, a living systematic-review pipeline that crawls targeted sources with MirrorWeb into S3, labels in SageMaker, and indexes with Amazon Kendra to enable natural‑language search using reading‑comprehension, FAQ matching and document‑ranking models. A human‑in‑the‑loop curation interface scores relevance, MeSH, tone, quality and data type, and the team curates 1500 documents in two weeks across ~15 COVID queries, demonstrating rapid, reproducible evidence synthesis and veracity checking.
AI-written summary · about
chapters (6)
- 0:00Introduction to intelligent search
- 3:33How Amazon Kendra works
- 12:14COVID-19 infodemic challenge
- 16:19REDASA project overview
- 21:01Results and future plans
- 23:29Q&A and resources
related talks
26mAccelerating COVID-19 insights for clinical use with intelligent search
28mGive users relevant answers quickly with intelligent search
57mHow Machine Learning and AI Can Support the Fight Against COVID-19
26mAccelerating innovation in the healthcare and life sciences industry
45mDigital Disruption in health & medical research
37mUsing the power of Azure and AI to help fight the COVID pandemic
50mInnovation and data analytics: Solving real-world challenges
59mArtificial intelligence in Healthcare