Hear about: Anticipatory Guidance, Cancer Diagnoses revealed online, Risk of marginalization, the Ethics of Ethics notes, and more…
Here’s a link to our University of Colorado, Anschutz Medical Campus, Ethics Grand Rounds with our topic: Ethical Issues with Open Notes and Open Results.
Thanks to all who participated; a robust conversation about the value of information transparency, leavened with concerns about worsening disparity for the digital divide, language and cultural barriers, the unintended disclosure of bad medical news, other unintended consequences of immediate transparency to progress notes and results.
For example: A medicine service is treating a patient. There are suspicions that there may be domestic violence at home. Team calls “Ethics consult: shall we call Adult Protective Services before the patient returns home from hospital?” Should this note be shown to the patient / family? Could a family member gain access to this note which then CREATES a problem when none existed before?
Use this to explain to your colleagues that some requests are easy and others might just be impossible.
Have you ever been asked by a colleague: “Hey, wouldn’t it be great if Epic could just do ___ ?”
Some recent examples from my life:
Show me my last progress note so I don’t have to hunt for it (Yes, it does that, right here in the Story Board, I can show you in 2 minutes).
Find all the open appointments to put a patient into a provider’s schedule, quickly at a glance (Yes, Epic top tool bar: Provider Calendar does that)
Remind me of the pre-op scrub protocol (Yes, we can build that into an order set but you have to develop consensus, that will take YOU weeks of discussion)
Fund a Sprint EHR optimization team to teach everyone efficient work tools (sure, took me 2 years of convincing leadership to invest in a Sprint team)
I want to bill insurance for responding to online messages WITHOUT a co-pay (Welllll, you’ll need to change Federal and Medicare rules, so that will be YEARS TO NEVER).
Yes, we know our colleagues have great ideas and they’re well intentioned, but only IT and informatics people have a sense of what it will REALLY TAKE. So, I made this pyramid to show people, examples of how an tiny, itty-bitty, innocent request can turn out to be nearly nothing or an ENORMOUS MONSTER.
What does TikTok have to do with Classroom Training? And what is “so last year” with EHR onboarding? And which uke song is up next?
We discuss: uPerform (self-paced EHR online training), Amplifire (adult learning theory and what we call “pot-hole” training for difficult EHR workflows), no-more-classroom, and 1:1 coaching sessions based on “cognitive struggle” and EHR Signal data. And of course, TikTok.
How to tackle the hyperobject that is the EHR inbasket?
Does your legal/compliance team worry that deleting messages is bad idea?
Do you have users with tens of thousands of unread inbasket messages?
Are you having trouble getting starting on this ambiguous, massive effort?
Would you like to know some of the specific settings and decisions we made?
Are you concerned that it is difficult to measure improvement with inbasket?
Are you eager to see CT Lin and team fail at yet another ambitious but ill-fated project?
If so, you =might= find some answers in our recorded discussion above.
We touch on: leadership, governance, organizational change, legal concerns, specific Epic EHR inbasket settings and decisions, clinician burnout, high-performing teamwork, and human connection. Really.
Note: Hosted by Epic. Login to Epic Userweb required. Go watch it, then come back and tell me what you REALLY think.
Find out: What is a centaur and what does it have to do with healthcare? What are the criteria for a good machine learning project? What is the role of a virtual health center with predictive models? And most importantly: What ukulele song goes with machine learning?
Here are the slides for my talk given at SMILE (Symposium for Machine learning, ImpLementation and Evaluation). The slides are mostly self-explanatory. You can also watch my talk at YouTube. Here is a PDF of the entire deck.
This data dilettante (see previous posts: dilettante #1, dilettante #2) has enjoyed armchair theorizing with all of you, my best (online) friends. Today we explore how our super-smart team scrambled our way to improving sepsis care with a predictive algorithm we built.
The old saying goes: the success of any major project in a large organization follows the 80:20 rule. 20% of the work is getting the technology right, and 80% is the socio-political skill of the people doing the work.
We all underappreciate this fact.
It turns out that we spent months building a sepsis alert predictive tool, based on various deterioration metrics, and a deep analysis of years of our EHR data across multiple hospitals. We designed it to alert providers and nurses up to 12 hours BEFORE clinicians would spot deterioration.
We patted ourselves on the back, deployed the predictive score in a flowsheet row, and in the patient lists and monitoring boards, with color coding and filters, and stepped back to revel in our glory.
Turns out that our doctors and nurses were ALREADY FULLY BUSY (even before the pandemic) taking are of critically ill patients. Adding YET ANOTHER alert, even with fancy colors, did NOT result in a major behavior shift to ordering IV fluids, blood cultures, or life-saving antibiotics any quicker.
See the fancy patient-wearable tech on the left (Visi from Sotera, in this case), and one of our hardworking nurses, with ALL of our current technology hanging off her jacket and stethoscope. She should be the visual encyclopedia entry for “alert fatigue.” 🙁
Back to the drawing board
As result of our failure, we huddled to think about transforming the way we provided care. It was time to disrupt ourselves. We decided to implement a Virtual Health Center, mimicking what we had seen in a couple places around the country: we deployed 2 critical care physicians and about a half-dozen critical care nurses on rotation, off-site at an innovative, award-winning Virtual Health Center.
This second time around, we created a cockpit of EHR data and predictive alerts to the VHC clinicians, who were dedicated to watching for deterioration across ALL our hospitals, and responding quickly. This does several things:
Takes the load off busy front line clinicians
Creates a calm environment for focused, rapid response
Dramatically improves the signal-to-noise ratio coming from predictive alerts
This way, the VHC nurses view all the alerts, investigate the chart, and contact the bedside nurse when the suspicion is high for sepsis, and start the sepsis bundle immediately.
Soon, by tweaking the ways our teams worked together, we were able to reduce the burden on bedside nurses and physicians and simplify handoffs.
See chart above: Before the VHC, bedside nurses were responsible for detecting sepsis (infrequent, subtle signals during a busy shift with lots of loud alarms for other things), with many ‘grey box’ tasks, as well as ‘magenta box’ delays.
After implementing the VHC, the VHC nurses took over the majority of ‘green box’ tasks, reducing the bedside ‘grey box’ work and completely eliminating ‘magenta box’ delays.
As a result, we have dropped our “time to fluids” by over an hour, and “time to antibiotics” by 20 minutes, which we estimate has saved 77 more lives from sepsis each year.
CMIO’s take? Predictive analytics, data science, machine learning, call it what you like. This is a paradigm shift in thinking that requires disrupting “business as usual” and is hard, but rewarding work. I can’t wait to see what we all can achieve with these new tools.
Thanks to my collaborators on the Patient Radiology Image Viewing team at UCHealth: Evan Norris MD, Ciarra Halaska, Justin Honce MD, Peter Sachs MD, and Kate Sanfilippo. Come see our talk at Epic XGM 2021 (eXpert Group Meeting) next month! Session Rad 1.4
What’s the TL;DR? Allowing patients to view their radiology images in their patient portal, alongside their radiology reports, is technically feasible, and does NOT cause increased anxiety for patients or increased workload for providers (in fact, ZERO phone calls, and yet our patients view 39,000 images per month!). Eighty percent of patients liked it. Many showed their images to their providers, some saved copies, some posted on social media! Some had technical difficulties, some had trouble understanding the images.
It is a good start, but there is more work to be done!
Thanks to Dr. Bryan Vartabedian for a fun wide-ranging conversation about INFO BLOCKING and our information transparency efforts at UCHealth over the past 2 decades. A trip down memory lane, and the potholes I’ve stepped in, and the battle scars from pushing the edge of what providers are ready for…
In case you are willing to come reminisce with me for 50 minutes…