#AI in Healthcare at Brain Tumor Summit at Stephenson Cancer Center on May 6 http://stephensoncancercenter.org/Calendar/Event/TabId/8494/ArtMID/23681/ArticleID/2081/Brain-Tumor-Summit.aspx
7. Imaging and advances in
computer vision
• Dramatically improve ability of
health professionals to establish a
prognosis and improve diagnostic
accuracy
• Will drive rapid improvements in
performance and machine accuracy
will soon exceed that of humans.
Help Catch Alzheimer's Early
http://www.livescience.com/55313-artificial-intelligence-alzheimers-early-
detection.html#sthash.ilbHTCKm.uxfs&st_refDomain=&st_refQuery=
• People with Alzheimer's typically display
decreased perfusion in brain tissue, which results
in insufficient supply of oxygen and nutrients to
the brain.
• MRI technique called arterial spin labeling (ASL),
which measures perfusion — the process of
blood being absorbed into a tissue — across the
brain. Still experimental
12. Search for pathways linked to gene LYPLA1
Reasoning on gene-pathway links
A key step is the definition of an ontology,
which facilitates the modeling of complex
datasets and guarantees information
consistency.
Inference rules allow the extraction of implicit
information from explicit data, to achieve logical
reasoning over the represented knowledge.
• if genes codify proteins
• if proteins belong to pathways
• Thus, it is possible to infer the following fact:
• then genes can be linked to pathways
• Therefore, we can write an inference rule that
infers genes-pathways links:
BioGrakn been built on top of GRAKN.AI
https://blog.grakn.ai/a-knowledge-graph-based-semantic-database-for-biomedical-sciences-167154319a0a
Distributed knowledge graph database
which allows complex data modeling,
verification, scaling, querying and analysis.
13. @Allen_Institute scientists are using #GPUs + #AI to predict the look of stem cells to
better understand cancer http://nvda.ws/2nTonjJ
Allen Cell Explorer: A portal to the human cell
https://youtu.be/E7PYBUyp4k0
14. Deep Genomics to develop drugs using #deeplearning to find
patterns in genomic & medical data
https://www.technologyreview.com/s/604305/an-ai-driven-genomics-company-is-turning-to-drugs/
Models fundamental aspects of molecular biology so can be used for any variant and any disease.
• Target bio-marker discovery
• Interpretation of genetic variation
• Genome-based therapeutic development
• Molecular diagnostics and carrier screening
• Risk assessment for complex disorders