Latest / Becker’s Healthcare Podcast / Advancing Clinical Decision Support and AI in Patient Care with Dr. Danny Lee

Transcript

Advancing Clinical Decision Support and AI in Patient Care with Dr. Danny Lee · Becker’s Healthcare Podcast

• 0:00
  - What we wanna do with AI is help
• 0:01
  - clinicians go from being reactive
• 0:04
  - to proactive.
• 0:05
  - At Philips, we can recognize patterns in monitoring
• 0:08
  - data across populations
• 0:10
  - and apply those insights to specific patients.
• 0:14
  - Safe and responsible AI can support sharper insights,
• 0:18
  - pave the way for faster diagnosis,
• 0:21
  - and help streamline care.
• 0:23
  - That can benefit clinicians, it can benefit health
• 0:26
  - systems. And most importantly, it can benefit patients
• 0:29
  - and their families.
• 0:33
  - Phillips.
• 0:34
  - Hello, everybody. This is Gracelyn Keller with Becker's
• 0:36
  - Healthcare. Thank you so much for tuning in
• 0:38
  - to the Becker's Healthcare podcast series. Joining me
• 0:41
  - for today's discussion is doctor Danny Lee, who
• 0:44
  - is the chief medical informatics officer at John
• 0:46
  - Hopkins Medicine Community Physicians.
• 0:49
  - So, doctor Lee, thanks for being here, and
• 0:51
  - let's jump right into our conversation. Absolutely.
• 0:54
  - So health systems are receiving a growing stream
• 0:56
  - of patient data from bedside monitoring, ambulatory devices,
• 0:59
  - and care delivered at home. Where is that
• 1:01
  - data creating actionable insights for clinicians, and where
• 1:05
  - does it still create more work than insight?
• 1:08
  - Yeah. That's that's a good question. I mean,
• 1:09
  - there is so much data coming at us
• 1:11
  - and that,
• 1:12
  - it depends on, I guess, the source of
• 1:15
  - that data. A lot of our data, we
• 1:16
  - present to providers
• 1:18
  - in dashboards that they can review. And in
• 1:20
  - other places, it is showing up inside the
• 1:22
  - patient's chart.
• 1:24
  - The thoughtful way there is trying to think
• 1:26
  - about ways of presenting that data in a
• 1:28
  - meaningful way to the provider at the time
• 1:29
  - that they were ready to receive that data.
• 1:32
  - And when clinicians are trying to reach a
• 1:34
  - diagnosis, they often must piece together information from
• 1:37
  - radiology, cardiology, pathology, urology,
• 1:40
  - and several other systems.
• 1:43
  - So where does that fragmentation create the most
• 1:45
  - friction in your organization, and how do you
• 1:47
  - bring together data sources and address this fragmentation
• 1:50
  - or close those gaps?
• 1:52
  - Yeah. That's a a big challenge.
• 1:54
  - However,
• 1:55
  - with, one of our current AI vendors,
• 1:59
  - we now have the ability to do real
• 2:00
  - time clinical decision support at the time that
• 2:03
  - we're seeing the patient
• 2:04
  - to help, one, synthesize all that data before
• 2:07
  - the patient is ready to see the patient,
• 2:10
  - and then in real time during conversations with
• 2:12
  - the patient,
• 2:13
  - giving,
• 2:14
  - patient... Giving the provider
• 2:16
  - little nudges, possible suggestions.
• 2:18
  - And then if during that conversation,
• 2:21
  - questions arise,
• 2:23
  - the CDS tool can actually pull up that
• 2:25
  - answer without ever leaving the EMR.
• 2:28
  - And patients increasingly move among the hospital, outpatient
• 2:32
  - settings, and the home.
• 2:33
  - Where does clinical context most often get lost
• 2:36
  - during these transitions, and what would it take
• 2:38
  - to give care teams a more continuous view
• 2:41
  - of the patient?
• 2:42
  - That... That's, that's always the challenge.
• 2:45
  - I think one of the biggest gaps right
• 2:46
  - now for us has been the skilled nursing
• 2:49
  - facilities.
• 2:50
  - They are
• 2:52
  - both part of the health system yet outside
• 2:54
  - the health system.
• 2:56
  - We know some of our sickest, most
• 2:58
  - severely ill patients are not ready to go
• 3:01
  - home at the time of discharge and need
• 3:02
  - to spend some time in acute care or
• 3:04
  - subacute care facilities.
• 3:06
  - And capturing them at the time that they're
• 3:08
  - released from
• 3:10
  - those institutions
• 3:11
  - is often very, very challenging.
• 3:14
  - Absolutely. And with so many AI use cases
• 3:17
  - competing for attention,
• 3:18
  - how do you distinguish a compelling pilot from
• 3:21
  - something ready to become part of everyday care,
• 3:23
  - and what must be in place to scale
• 3:25
  - that responsibly?
• 3:27
  - Yeah. So in order for us to adopt,
• 3:29
  - any AI product, especially if it's clinical facing,
• 3:33
  - what I look for are are AI technologies
• 3:35
  - that will reduce the provider burnout,
• 3:38
  - make their life easier, also making them,
• 3:41
  - making them more effective clinicians and improving patient
• 3:44
  - safety while addressing quality at the same time.
• 3:47
  - So if it addresses any of those things,
• 3:49
  - then we'll kinda... Then we'll... It will become
• 3:51
  - self evident, and we will enroll on a
• 3:52
  - pilot at that point.
• 3:54
  - And as technology
• 3:55
  - relationships move beyond onetime purchases, what should a
• 3:58
  - partner remain accountable for after go live to
• 4:01
  - make the relationship genuinely valuable over time? Yeah.
• 4:04
  - This is a a really great question and
• 4:06
  - one that we,
• 4:07
  - look for
• 4:08
  - in a vendor.
• 4:10
  - Our our relationship with our vendors don't end
• 4:12
  - with us signing a contract. It is only
• 4:14
  - the beginning, and we expect our vendors to
• 4:16
  - be fully engaged,
• 4:18
  - to interact with us, to get feedback, and
• 4:21
  - continually
• 4:22
  - improve the product. We don't expect the product
• 4:24
  - to be completed or finished when we sign
• 4:26
  - the dotted line, but we expect to see
• 4:28
  - improvement as we move along.
• 4:31
  - And finally, as care increasingly moves beyond hospital
• 4:34
  - walls, how are you using connected technologies and
• 4:36
  - AI to identify patients who need earlier follow-up,
• 4:40
  - support care coordination teams, and close gaps in
• 4:42
  - post discharge care?
• 4:44
  - Yeah. I think the pandemic helped us start
• 4:47
  - moving in that direction with the, really the
• 4:50
  - burgeoning,
• 4:51
  - telemedicine part of our practice, and that has
• 4:53
  - been... That has taken off big time. And
• 4:55
  - especially for patients who have mobility issues, who
• 4:58
  - have patients when they get out of the
• 4:59
  - hospital are not ready to come back to
• 5:01
  - one of our sites or clinic, telemedicine is
• 5:03
  - able to offer those services to the patient
• 5:06
  - and fill in those gaps when they're, when
• 5:09
  - they have a need.
• 5:10
  - Absolutely.
• 5:11
  - Well, thank you so much, doctor Li, for
• 5:13
  - your time and your insights today. And we
• 5:15
  - also wanna thank our podcast sponsor, Philips. You
• 5:18
  - can tune in to more podcasts from Becker's
• 5:20
  - Healthcare by visiting our podcast page at beckershospitalreview.com.