Reflecting on 11th MIIT

This past Friday, I was fortunate enough to attend the 11th annual Medical Imaging Informatics and Teleradiology Conference (MIIT).

MIIT

All of the sessions were very information and, based on what I saw this year, I would highly recommend you make an effort to attend next year’s 12th annual MIIT.

For the purpose of this Blog Post, I’ve decided to comment in particular on Brad Erickson’s presentation on Deep Learning. I’m really interested in how AI will fit into our future.

Deep Learning is something most of us access multiple times a day. Anyone using Siri, Google, Facebook, Twitter, Skype and the list goes on…, is witnessing the power of Deep Learning. Here  is an article from WIRED on how AI is changing Google Searches. The article reinforces what Brad Erickson’s presentation stated on the power of systems that can ‘learn’. Here’s one quote from the article:

“Google’s search engine was always driven by algorithms that automatically generate a response to each query. But these algorithms amounted to a set of definite rules. Google engineers could readily ch ange and refine these rules. And unlike neural nets, these algorithms didn’t learn on their own. As Lau put it: “Rule-based scoring metrics, while still complex, provide a greater opportunity for engineers to directly tweak weights in specific situations.”

 

Something as common-place as searching for the best Thai restaurant in your neighborhood has been positively impacted by AI.  What will the impact be to Imaging Informatics?

It’s been 5 years since Watson won Jeopardy and since then we have watched IBM improve Watson and prepare ‘it’ for healthcare. It seems likely that in 15-20 years (or quite a bit earlier) most diagnostic imaging will been ‘seen’ by a deep learning solution. What will it take for the culture to change for us to feel comfortable with a computer performing the primary read on our diagnostic imaging?

I think there’s an analogy between self-driving cars and AI in radiology. We have Tesla’s that can drive us to work, but it’s illegal for us to sleep at the wheel. Regardless of the fact that Google’s self-driving cars had driven over 1.3 million miles before causing its first accident, many people felt like this accident emphasized why we shouldn’t have self-driving cars.

Imagine the Public’s reaction on a system’s first misdiagnosed read that caused a negative impact to patient care. Even if AI makes the odds of accidents low, it feels more natural to have humans cause accidents rather than computers.

Moore’s Law may state that computing power will approximately double every 18 months –  but can the general public’s comfort level with technology keep up with this pace?

This talk really whet my appetite for the SIIM 2016’s closing talk ‘Peering Into the Future through the Looking Glass of Artificial Intelligence’.

Hope to see you there in Portland.

 

Feel free to share your comments below on how you think AI will fit into radiology, and how the ‘court of public opinion’ will impact the technology moving forward.

 

 

 

Getting Ready for SIIM16

With SIIM 2016 being just around the corner (18 days to be exact), I thought I would take this opportunity to share the sessions and activities that have caught my eye.
Here’s a rough guide of what I plan to take in while at SIIM. I look forward to seeing everyone in Portland.

Day 1 – Wednesday

Opening Session – Leveraging Innovation to Drive Patient Care
I always enjoy watching Rasu present. He’s an engaging speaker and is mindful of the appropriate signal to noise ratio on his slides. I’m looking forward to hearing his thoughts on how to reinvent value for imaging across the current healthcare system.

9:45 am – 10:45 am: How to Develop Imaging Informatics Training Programs
To borrow a quote from Sir Ken Robinson, ‘Learning happens in the minds and souls, not in the databases of multiple-choice tests.’
How do we penetrate the minds and souls of trainees? How can we create innovative training program that can attract clinically and technically focused people to Imaging Informatics?
I’m interested to see this will involve any discussion around leveraging eLearning for remote training programs.

1:15 pm – 2:45 pm: Clinical Decision Support: How to Get Prepared for or Improve What You Are Currently Getting Out of it
Being based in Canada, we’re not affected by the passing of the Protecting Access to Medicare Act (PAMA), however it would make sense that it’s only a matter of time before some sort of guideline appropriateness for radiology will be on it’s way here.
I’ve worked with many hospitals that are able to ingest foreign exams into their local PACS and access the longitudinal DI record for a patient. Despite the seamless access to foreign exams, it’s continues to be a challenge trying to prove that this access prevented unnecessary imaging to the patient.
Try proving a negative – try proving that something didn’t happen.
CDS would potentially have a record that the decision to order an exam for a patient was prevented based on the availability of another exam.
With IHE profiles such as Guideline Appropriate Ordering (GAO) and Order Appropriate Tracking (OAT), shaping the actions of CDS I’m really interested to see how adoption for this takes off.

3:00 pm – 4:00 pm: CIIP Study Groups
Interested in learning what it takes to become a CIIP? I will be co-moderating this study group. Drop by and say hi!

4:15 pm – 5:15 pm: How Practices Can Integrate Clinical EMRs Into Their Imaging Workflow
Closing the day off with this final session.

Finally close of the day with a couple craft beers and some dinner. (I’m looking forward to checking our Portland’s own Rogue Brew Pub www.rogue.com)

Day 2: Thursday

5K Fun Run – 6:30am – I’ll try to make sure I don’t have enough craft beer to slow me down on the run.

8:00am – 9:30am: Solving Enterprise Imaging Use Cases
What’s the best way to handle other image types? Is DICOM wrapping the best answer? Should be a good discussion!
1) non-radiology DICOM-based imaging such as point of care ultrasound,
2) non-DICOM still images such as JPEGs, and
3) non-DICOM video such as endoscopy.

9:45am-10:45am: For this time slot, I can’t decide where to go. I’m at a point where I may need to do a coin toss to determine what session to attend. As it stands right now, I have my eyes on either VNA Opportunities and Issues or Enterprise Imaging: XDS and DICOMweb

12:00 pm – 1:00 pm SIIM Member Lunch
1:15pm – 2:45pm The Art of Leading Change in Healthcare IT

3:00pm – 4:00pm CIIP Study Group
Another session co-moderating this study group.

4:15-5:15pm: Analytics in Healthcare – How Do You Need to Think About Your Data?

5:30pm – 7:30pm Science & Innovation Reception
I’ll be standing by our poster submission – Measuring the Benefits of a Regional Diagnostic Imaging Environment
Feel free to drop by and check out all the posters and all the others.

Day 3 Friday:

7:00am – 8am The state of AI in Imaging

9:45-10:45 Electronic Clinical Decision Support Tools for the Referring Health Provider and the Radiologist
As mentioned above, I’m really interested in seeing the challenges and positives CDS implementation

11:00am – 1pm – last chance for Poster and Vendors

1:15 pm – 2:45 pm – Strategies for Dealing with Patient Identities in a Consolidated Enterprise
I am sitting in on the this conversation, sharing some of the practical strategies we put in place to manage patient identities across a regional environment.

3:00pm – 4:30pm: Peering Into the Future Through the Looking Glass of Artificial Intelligence.
This is going to be a great closing talk.

It’s been almost 20 years since Deep Blue beat World Chess Champion Garry Kasparov. We now live in a world where no human born will ever be a better chess player than a computer. What does this mean for other tasks that are conquered by our computer overlords? Will a time come when no human radiologist can match the skills of a computer?
I’m sure Eliot Siegal will provide a terrific closing session to what looks like another great SIIM.

See you there.

Jason N

The First Post

Welcome to the first blog post. I have decided to upgrade nagelsconsulting.com from a flat site to an interactive Word Press site.

I plan on sharing my thoughts on Healthcare IT, Imaging Informatics, IHE, DICOM, eLearning, training and development and whatever else happens to grab my attention.

Stay Tuned.

Jason N