Registration for a live webinar on 'Innovative Vaccines and Viral Pathogenesis: Insights from Recent Monkeypox Research' is now open.
See webinar detailsWe noted you are experiencing viewing problems
-
Check with your IT department that JWPlatform, JWPlayer and Amazon AWS & CloudFront are not being blocked by your network. The relevant domains are *.jwplatform.com, *.jwpsrv.com, *.jwpcdn.com, jwpltx.com, jwpsrv.a.ssl.fastly.net, *.amazonaws.com and *.cloudfront.net. The relevant ports are 80 and 443.
-
Check the following talk links to see which ones work correctly:
Auto Mode
HTTP Progressive Download Send us your results from the above test links at access@hstalks.com and we will contact you with further advice on troubleshooting your viewing problems. -
No luck yet? More tips for troubleshooting viewing issues
-
Contact HST Support access@hstalks.com
-
Please review our troubleshooting guide for tips and advice on resolving your viewing problems.
-
For additional help, please don't hesitate to contact HST support access@hstalks.com
We hope you have enjoyed this limited-length demo
This is a limited length demo talk; you may
login or
review methods of
obtaining more access.
Printable Handouts
Navigable Slide Index
- Introduction
- Educational goals
- Two emerging AI opportunities
- It’s the data
- Real-world data networks
- Generating high-quality data
- Expanding data points available for AI
- The rich potential of unstructured data
- Deeper and denser data is better for AI
- But where the data comes from matters
- Ensuring representativeness and diversity
- Introduction to AI for personalization
- How AI really works
- Applications
- Use cases relevant to medical devices
- Example-OM1 Patient FinderTM: how it works
- Use case 1: finding patients
- Patient FinderTM for at risk or undiagnosed
- Identifying patients most likely to benefit
- BMI outcome
- Performance: ranking by predicted benefit
- BMI outcome: enrichment
- Underdiagnosis in AAA
- Using Patient FinderTM for AAA
- Applying Patient FinderTM in AAA
- Focusing on highest-risk patients
- Value-based care
- An example: spine surgery
- Comorbidities and risk
- An example: spine surgery
- Bundle breaking: full at-risk scenario
- Implementation: the last mile
- Using OMBI Spine to achieve savings
- Spine site of care selection: ambulatory or not?
- ROI even earlier with shared decision making
- Shared decision making
- Joint Insights™ clinical trial
- Takeaways
- Questions
Topics Covered
- Artificial intelligence
- AI in healthcare
- Shared decision-making
- Value-based care
- Patient identification
- Personalized healthcare
- Patient Finder
- OM1 Medical Burden Index (OMBI)
- OMBI Score
Links
Categories:
Therapeutic Areas:
Talk Citation
Gliklich, R.E. (2022, October 31). AI for medical devices [Video file]. In The Biomedical & Life Sciences Collection, Henry Stewart Talks. Retrieved November 2, 2024, from https://doi.org/10.69645/RWJY4178.Export Citation (RIS)
Publication History
Financial Disclosures
- Prof. Richard E. Gliklich is an employee of and stockholder in OM1, Inc.
A selection of talks on Cardiovascular & Metabolic
Transcript
Please wait while the transcript is being prepared...
0:00
Hello, my name is Rich Gliklich,
I'm CEO of OM1,
a healthcare data and
artificial intelligence company
that's focused on
personalizing healthcare.
Today I'm going to
be speaking about
using artificial intelligence
with medical devices.
0:17
The goals I'm going
to try to cover
really boil down to these
three bullet points.
The secret to AI and
healthcare, to me,
is high-quality,
clinically rich,
and representative data.
I'll explain why.
We'll talk about using AI to
find patients and
select treatments.
I'll post some examples
from patient identification
for the use of AI for
value-based care,
as well as shared
decision-making.
0:41
There are two emerging areas
of artificial
intelligence that we
think about with the
greatest applicability
to the medical device space.
The first, we refer to as
patient identification
and segmentation.
What this really means is
finding and targeting
patients who are most
likely to have a
particular diagnosis,
and to benefit from therapy.
The second, that we'll
spend less time on today,
is really about the area of
clinical decision-making
and its application
to value-based care.
This centers around both being
able to identify the
riskiest patients,
so that they can
be accelerated in
the path to medical
device-related treatments,
as well as being
able to predict,
and describe to them,
what their potential
outcomes might be.
1:24
One point I'm going
to come back to
over and over again, is while
artificial intelligence is
an incredibly powerful tool
to be able to develop models
that can be used in these ways,
really, it's the data underlying
the tool, that powers it.