Welcome back to our blog! It’s been a while since we last posted, but we’re excited to start sharing content with you again.

First and foremost, we wanted to let you know about some exciting news – we have recently launched Nagels Consulting, a company focused on providing top-tier imaging informatics training.
With the increasing reliance on electronic medical records and the growing volume of medical images being produced, there is a high demand for professionals with expertise in imaging informatics.

At Nagels Consulting, the goal is to provide comprehensive and practical training that helps professionals stay up-to-date on the latest technologies and best practices in the field. We believe that through our training, we can help professionals advance their careers and make a meaningful impact on patient care. Our training programs are designed to cater to the needs of various professionals, including radiologists, technologists, and IT professionals. We offer both in-person and online courses, allowing participants to choose the option that best fits their schedule and needs.

In addition to our training programs, we also offer consulting services to organizations looking to optimize their imaging informatics systems and processes. Our team of experts has a wealth of experience in this field and can provide valuable insights and recommendations to help organizations achieve their goals.

We hope you’ll join us on this exciting journey as we work to provide top-tier imaging informatics training and consulting services. We look forward to sharing more updates and insights with you through our regular blog posts.

Thx,
J

I recently wrote a blog post for SIIM on my experiences in Ghana.

Feel free to read the blog post at the link below:

https://siim.org/blogpost/1625199/313413/SIIM-Global-Ambassador-Assists-With-a-RIS-Implementation-in-Ghana

Thx,
J

In 2017, RAD-AID and SIIM teamed up to create the SIIM Global Ambassador program. During the first year of the program, two SIIM Global Ambassadors – Starla Longfellow and David Marichal – traveled to Laos and Nicaragua, countries in which RAD-AID had recently installed PACS. Starla and David were recently on SIIMCast, in which they sat down for an interview about their experiences participating in the program.

If you would like to listen, the interview is embedded below:

When I heard about the opportunity to support our global imaging informatics community, I was immediatley interested. I applied earlier this year and am excited and honoured to have been selected as one of the 2018 SIIM Global Abassadors.

In less than a month, on September 29th, I will be flying out to Ghana, to lend a helping hand with Imaging Informatics at Korle Bu Teaching Hospital in Accra. I will be in Accra for 2 weeks and plan on regularly tweeting, and hopefully posting to the blog while there.

Below is a terrfic video that demonstrates the positive impact that RAD-AID has had in Ghana.

Stay tuned for more updates. If anyone has tips for the trip, feel free to post a comment below.

– J

In just over 3 weeks from now, attendees of this year’s SIIM conference will arrive in Pittsburgh: The city that  brought us Heinz Ketchup and Andy Warhol, and a city that apparently has more bridges than Venice. Pittsburgh’s city planners seemed to have rubbed off on the SIIM planning committee as this year’s theme is ‘Bridging the Transformation to a New Era of Medicine’.  It’s an appropriate theme when the City of Bridges is hosting the event.

Here’s a few of the key sessions that I’m excited about for SIIM17.

Day 1:

Opening Session: Harnessing Artificial Intelligence: Medical Imaging’s Next Frontier

This is a topic that keeps growing in interest to our community – I’m interested to hear how the session touches on harnessing the power of AI rather than being fearful of AI making us irrelevant.

9:45 am – 10:45 am: Order Entry CDS: From Implementation to Positive Outcomes

IHE profiles such as Guideline Appropriate Ordering (GAO) and Order Appropriate Tracking (OAT) are helping shape the actions of CDS.  I’m interested to see how CDS can be used as a tool to report when repeat imaging is prevented due to appropriateness checks.

1:15 pm – 2:45 pm: Rad-Path Diagnostics: Rethinking Imaging Informatics

Now that the FDA has approved Phillips to Market their Intellisite Pathology Solution for Whole Slide Imaging for digital pathology, this is just the beginning. It will be interesting to see how the FDA’s approval affects consumer interest in adopting digital pathology. I’ve written in the past about the disconnect between standards development and vendor solutions for non-radiology imaging. This should be an interesting discussion.

In the evening I hope to grab a sandwich at Primanti Brothers and find a local Pittsburgh craft beer to wash it down with. (If anyone has any suggestions on local Pittsburgh craft beer, I’m all ears)

 

Day 2:

9:45am – 10:45am – Educators Toolkit for Imaging Informatics: From Basic Education to Advanced Learning

Education and effective knowledge transfer affect us all. Without effective training, our teams will be weak, adoption low and our patients and customs will suffer. 

1:15pm – 2:45pm: Carnegie Mellon Showcase: Technologies that Will Help Propel Key Aspects of Imaging Informatics

3:00 pm – 3:30 pm: Data Interoperability With, and Access For, External Referring Physicians

4:15pm – 5:15pm Radiation Dose Metrics: Current & Future Considerations

Friday evening is the only night that the Andy Warhol Museum doesn’t close at 5pm. We often talk about wanting to achieve creativity and innovation within our industry.  Andy Warhol is a good example of someone that was able to find creativity in everyday common place items.  It takes a special way to look at the world to see a soup can and figure out a way to make it art.

Day 3:

8am – 9:30am: Image Retention: Help Us Develop an Image Retention Policy that Makes Sense

9:45am – 10:45am: The Business of Imaging: Ruthlessly Quantifying Your Value Metrics

11:30am – 12:30pm: Role of Artificial Intelligence in the Future of Medical Imaging – What Do Vendors Think?

1:15pm – 2:45pm: Improvement Stories for Informatics Professionals

Closing Session: Weaving the Fabric of Trust: Security, Privacy, Resilience, and Accountability

Over the past year, there have been many reports of hospitals being victim to cyber-attacks, including ransom ware attacks. This should be a great closing session.

I look forward to seeing​ you at SIIM17.

Thanks,

J

Imagine if you will…

You’ve just wrapped up a lengthy project, in which you’ve implemented a new solution at a hospital or clinic. Now that the venture is complete, we can relax, pat ourselves on the back and watch user adoption just roll in.

Seems like a fantasy? In reality we typically see something quite different…

Regardless of how well a project is run, and despite how beneficial the implemented solution is for the end-user; any time a solution involves changing current behavior, without a well thought out change management plan, it remains a challenge to drive user adoption. It’s not uncommon to see well-designed, robust solutions fail, due to a lack of effort to implement proper change management.

USER ADOPTION TAKES TIME AND EFFORT

Successful user adoption is not accomplished in a short sprint, but rather, it occurs over time and it increases with stakeholder’s effort. As demonstrated in the graphic below, user adoption is a gradual process, with several steps to take towards full user acceptance and commitment.

image source: Erica Toelle – Create Your End User Adoption Strategy

These steps are building blocks, in which you ideally start out early in the project, making all stakeholders aware of the new solution. Once the stakeholders are aware of the general solution, further effort is required to ensure users have a thorough understanding of the solution’s functionality. Understanding the solution must develop into commitment and buy-in from the user-base, which will leads to successful adoption.

This begs the question, what efforts can we apply to achieve success across these building blocks?

ACTIONS FOR USER ADOPTION

The following are 3 key actions that should be part of the overall adoption strategy:

1.What is the baseline and what is the target?

If you are trying to improve user adoption on an existing solution that is currently available to your users, first ask yourself, where are you today and how many active users are currently using the solution?

Understanding the baseline creates realistic adoption targets. The targets should be time bound. For example, ‘over the quarter we hope to improve user adoption by 5%.’  Additionally, reviewing the existing user base may help to identify any highly active users. Active users can work as cheerleaders to ‘advertise’ the solution to their colleagues. Determining realistic targets may also require outside input from subject matter experts, or pulling data from past experiences.

The adoption rates will vary depending on the solution – for example, if the new functionality is required as part of the user’s job, the expectation would be 100% adoption. If the solution is a value add and improves the user’s work experience, but is not required functionality, it may be useful to look at adoption targets for previous comparable projects.

2. Build Awareness and Make the Solution Known

This can be as simple as trying to build a conversation related to the solution. One easy and inexpensive way to build awareness and stir up conversation is creating a poster campaign that highlights key events in the adoption process, from the launch and ongoing training, to helpful how-tos and usage success stories. A simple lunch-n-learn that provides the users with top user tips and a relaxed atmosphere for a Q&A session can be very effective.

Look at the opportunity of providing awareness to indirect stakeholders. If the primary users are physicians, is it possible to build awareness of the functionality to the patients? This might not always be possible, but if the solution is something that directly impacts the patients, they may be able to become a cheerleader for the solution.

 

3. Training, Training, Training….

Continuing from where we left on building awareness, effective training is an essential part of the adoption process. Implementing a training plan can be a bit of challenge when training isn’t your official role. Often training is just one of the hats you wear,  and your department doesn’t have access to the tools (i.e. eLearning authoring software, Learning Management Systems, etc.) that a formal training department would  have access to. Stay tuned for a follow-up post that provides some tips to help implement an effective training strategy, and what cheap or free tools are out there that can be leveraged.

The main thing I’ll mention here, as it relates to adoption, is that training is an ongoing process. Regardless of which training method you use (face-to-face, webinar, self-paced eLearning, blended style), it can not be assumed that once a user has received training, they then  have sufficient knowledge to commit to regularly using the solution. Cheat sheets and/or ‘short to the point’ eLearning modules can be beneficial to users so they can easily reference key steps if they ever feel stuck.  Again, I’ll elaborate on best practices for training in a future post.

 

These are just some of the options available for successful user adoption. I’d love to hear what successes (and pain points) you have found when trying to implement adoption strategies. Feel free to share in the comments section.

 

Thanks,

Jason

It’s been a busy 2016! Here’s a December post to cap off the year!

One of the initiatives that I’ve been involved in the past few months, is investigating the opportunity of integrating non-radiology imaging in the Diagnostic Imaging world.  Some of these non-radiology image types could include, but are not limited to:

• Wound Care
• Dermatology
• Ophthalmology
• Non-DICOM Cardiology
• and …. Pathology

Let’s spend some time on last, but by no means the least significant item on the list – Digital Pathology. As you are most likely aware, Digital Pathology is extremely large in volume and size.

If we look at this strictly from a formatting/standards perspective, it becomes an interesting exercise. There are two distinct camps on how Digital Pathology should be handled. Just like other opposing groups that we are familiar with (ie. The Montagues vs the Capulets, the Jets vs the Sharks, or Biggie Vs. Tupac, etc.) -these two imaging camps have their own moniker:

DICOM vs. Native Format

DICOM has been around for a little over 30 years and is a proven standard that’s provided interoperability between disparate imaging vendors.

 ACR/NEMA 300, version 1.0, released in 1985.

Fast forward to 2016, and this standardized interoperability makes it possible to exchange and share patient’s diagnostic imaging. Additionally this standards-based approach provides customers the possibility (and freedom) of migrating their imaging data to another PACS vendor at any point. The customer isn’t restricted to using only systems that support a ‘proprietary’ imaging format.

Considering all the pros and history of DICOM as a standard for image transfer, it would only make sense for non-Radiology imaging to follow the same approach and to adopt DICOM as an imaging format, right? Well that answer is a bit unclear.

Let’s look at Pathology for example: A lot of effort has been put into DICOM Working Group 26, which is focused on a DICOM based approach to handling Digital Pathology. Not to mention the IHE domain, PaLM (Pathology and Laboratory Medicine), which has coordinated activities and joint meetings with DICOM Working Group 26.

When we compare the work being accomplished in the standards committees to what vendors are doing in real life, we see quite a gap. I recently had a Digital Pathology vendor provide a demo of their product. They touted all the “benefits” of not relying on DICOM and using a proprietary format. According to this vendor, using a proprietary imaging format, provided ‘more flexibility and better performance’. To me that sounds a bit too much like a sales pitch. I’m curious if a customer decides to change vendors at a point in the future,  how difficult will it be to migrate/convert the proprietary imaging format so that it’s acceptable for the new vendor.

It appears that this particular vendor isn’t unique with this behavior. My very informal investigation related to this, has discovered that it’s hard to find a digital pathology vendor that isn’t using a proprietary imaging format.

This leaves us with a bit of a disconnect between the focus of Standards Committees and how vendors are building their solutions for the real world.

After all, these are ‘just’ standards. By definition the purpose of a standard is to reach a certain level of quality or attainment. Standards are not requirements, and the only thing that will drive the vendors to create change is through consumer action.

I would love to hear from others on their experience with integrating Enterprise Imaging in their environment and what you have found from a DICOM vs. Native format perspective. Feel free to comment below.

 

Thanks,

J

 

 

This past Friday, I was fortunate enough to attend the 11^th annual Medical Imaging Informatics and Teleradiology Conference (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 12^th 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.