Digital Disruption in health & medical research
summary
CSIRO software uses Spark on AWS (EMR + S3 + Jupyter) and an ML method VariancePath that claims 3.6× speedup over competitors and scales linearly to handle a trillion data points (15 hours vs an estimated 100,000 years). Genomic examples include a 50,000 case–control heart study and SARS‑CoV‑2 analysis from ~5 million sequences of which only ~5,000 have severity labels, leading to non‑spike region hits. A lightweight serverless beacon and indexed flat files replace heavy databases and cut sharing costs to about $15/month.
AI-written summary · about
chapters (10)
- 0:00Start
- 10:13Motor Neurone Disease
- 14:38Data Interoperability
- 16:10The Fast Health Interoperability Standard
- 19:22The Serverless Beacon
- 20:18Beacon Protocol
- 27:45Three Things To Remember
- 29:12Serverless Beacon
- 38:32Any Reason You Chose Aws over Other Providers
- 41:58Gdpr
related talks
42mHow Novel Compute Technology Transforms Life Science Research
46mKeynote: Life Science Research at Scale
50mCancer Genomics - a biologist and a developer
08mRevolutionizing Healthcare with Big Data and ML
50mInnovation and data analytics: Solving real-world challenges
25mScaling Up Genomics with Spark
20mMining Large Data Sets of Biomedical Omics Da...
22mReimaging Healthcare