Please wait while the transcript is being prepared...
0:00
Hello everyone.
My name is Khanh,
and it is my pleasure
to share with you today
an overview of artificial
intelligence in biomedicine.
Over the next few minutes,
I will introduce
the core concepts,
highly likely application areas,
some examples from research,
and then discuss
some challenges,
opportunities, and
the future outlook.
0:26
Here's the roadmap
of today's talk.
First, I will define
what AI in biomedicine
really means.
Then I will move into some of
the key application areas where
AI is already having an impact.
I will share a few case studies
from my research
and others' work.
After that, we will look at
some challenges and
open questions,
and finally, I will wrap up with
future directions and
a take-home message.
0:58
So why has AI become so important
in biomedicine right now?
One major reason is
the explosion of biomedical
data like genomics,
medical images, and
electronic health records.
Traditional analysis
methods struggle to
handle the scale and
complexity of this data.
AI now provides
a powerful toolkit for
pattern recognition,
prediction, and also
personalization.
We have already seen
some success in
areas like diagnostics and
also drug development tasks.
1:38
Core concepts in AI
for biomedicine.
Before diving into applications,
let's quickly review
some core concepts.
AI is probably about simulating
human intelligence by machine,
and within AI, machine
learning is about
algorithms that learn from data,
either labeled or unlabeled.
We mentioned supervised
and unsupervised learning.
Deep learning is a
different model.
So it takes this further
with neural networks that handle
very complex data,
complex tasks,
and more recently, large
language models and
NLP approaches have been
adopted to biological data,
enabling us to read and write
biological sequences much
like natural language.
