Wednesday, March 21, 2018

I Bless The Rains Down In Africa...Again

Some of you might have noticed that I haven't posted for a while. Did you call? Did you write? Did you check to see if i was still alive?

Sorry...just the Jewish mother in me coming out. I'm sure you all knew that the hiatus was justified, and you simply decided that my next missive would be well worth the wait. And I certainly hope to rise to your expectations.

Many things have indeed been happening. Doctor Dolly is getting married in a few months, and you can imagine the turmoil joy that has brought to the Dalai household. In the midst of plans for that amazing(ly expensive) event (JUST KIDDING, DOLLY!!) I received a promotion to the Management team of RAD-AID, which has taken up a great deal of time. Fortunately, this came with a tripling of my salary from my favorite NGO...I went from $0 to $0, but the satisfaction derived from being a part of this is priceless.

And yes, I've been back in Ghana for the past week on another RAD-AID trip to Korle Bu Teaching Hospital in Accra. As I noted upon last year's expedition to Dar es Salaam, Tanzania, you just can't be in Africa without thinking of Toto's song by the same name, and I must again present both the original and a very moving chorale version:

OK, time for business.

I'm here with a a team of incredible people (and then, of course, there's me...)

Erin, with whom I traveled to Ghana last time, is head of a Radiography school in the Northeast, and plans to help out with the program here as she did two years ago.

Alice is a breast-imaging specialist from a rather well-known hospital also in the Northeast, who will work with the radiologists and surgeons (and maybe even the pathologists!) to enhance imaging and treatment of breast cancer.

Kwasi (on the right, with 4th year resident Paul) is a neuroradiologist with Ghanaian roots who will work with the IR and imaging folks here at Korle Bu.

We have been delivering lectures to staff, residents, and anyone else we can gather. I managed to hit the ground running in that regard with an introductory talk about Nuclear Medicine to the Internal Medicine Department. Which occurred at 8AM sharp the day after I arrived in Accra (at 8PM but who's counting...) Despite some computer glitches (when connected to the projector, my borrowed laptop tried to go into Picture in Picture mode or something like that), the talk seemed to be well-received and there were many good questions asked.

We were able to meet with some of the radiologists and with Dr. Awo, the Nuclear Medicine physician:

My main duty here at Korle Bu, beyond boring the staff with Nuclear Medicine lectures, is to help pave the way for a RIS to mate with the PACS. There will be many discussions in that regard as we progress, but the principals here are pleased with the way we are approaching this project.

I have been able to travel a bit, seeing Accra last Saturday and going back to Cape Coast Castle and the Kakum Canopy walk on Sunday. I'm not going to post all 300+ pics, but here are a few highlights. I have to note that wherever we went, little children tagged after me, and usually not the ladies. I'm thinking they saw the old white guy with the white beard and figured I was Santa Claus. Ho, Ho Ho! Christmas in March in Ghana! Except it turns out that there is no Santa tradition here. Oh, well....

I've got another week to go, with a trip to Kumasi and a surprise!

I should note that I don't speak even the slightest bit of Twi, the more common of over 70 dialects in this region...I tried last time, and after getting laughed at, I decided to stick to English. It IS the official language of Ghana, after all!

But for now, I bid you Maadwo, a very good evening!

Sunday, February 25, 2018

Life REALLY Imitates Art!
More on Apple's EMR

To welcome myself back after a two-month absence, I'll brag a bit about my prescience. You'll recall my April Fool's Day mock-up of an Apple EMR:

No, it wasn't real, for those who didn't realize this.

But as with "The Simpsons" predicting an unlikely candidate (some say this isn't true, but go with it),

Apple has finally come around. I alluded to this in a recent post, but it seems to be coming to pass quickly. Here's the latest, from Wired of all places...

IN LATE JANUARY, Apple previewed an iOS feature that would allow consumers to access their electronic health records on their phones. Skeptics said the move was a decade too late given a similar (and failed) effort from Google. Optimists argued that Apple was capable of translating health data into something meaningful for consumers.

But the announcement portends great things for consumers and the app developers seeking to serve them, from our perspectives as the former US chief technology officer under President Obama, and as an early adopter of the Apple service as Rush University Medical Center’s chief information officer. That’s because Apple has committed to an open API for health care records—specifically, the Argonaut Project specification of the HL7 Fast Health Interoperability Resources—so your doctor or hospital can participate with little extra effort.

This move is a game-changer for three reasons: It affirms there is one common path to open up electronic health records data for developers so they can focus on delighting consumers rather than chasing records. It encourages other platform companies to build on that path, rather than pursue proprietary systems. And it ensures that the pace of progress will accelerate as healthcare delivery systems respond to the aggregate demand of potentially millions of iPhone users around the world.

Understanding the promise of this announcement requires a bit of historical context. In the wake of the 2008 economic crisis, President Obama signed into law the Recovery and Reinvestment Act, which included more than $37 billion for investing in the adoption and use of electronic health records by doctors and hospitals. Tucked away in that program was a comparably modest $15 million investment in research and development to bring to life a vision of applications inspired by Apple’s App Store. That R&D funding contributed to the development of the open API standard that Apple now requires of providers wishing to make the feature available to their patients.

Spurred by financial incentives in the Recovery Act, the Affordable Care Act and in 2015, the bipartisan Medicare Access and CHIP Reauthorization Act, providers are implementing health IT systems that are certified to meet certain government requirements.

One such mandate is to allow patients the ability to connect any application of their choice, like Apple Health, to a portion of their records via an API. However, the government left room for the private sector to build consensus on how to achieve this requirement, which resulted in the Argonaut Project specification. Apple's decision to require that open API standard decreases the likelihood that health IT developers will adopt a proprietary system.

Better still, once a provider’s electronic health records system delivers health data in accordance with the standard, that same connection will be available to any app developer offering consumer applications, including those built for the Android ecosystem, or competing to serve the highly anticipated Amazon, JPMorgan Chase, and Berkshire Hathaway employee health joint venture. Imagine if Apple had instead introduced a proprietary system that didn't allow competitors to access data in the same manner from the participating providers.

Naysayers point out the fact that Apple is currently displaying only a sliver of a consumer’s entire electronic health record. That is true, but it's largely on account of the limited information available via the open API standard. As with all standards efforts, the FHIR API will add more content, like scheduling slots and clinical notes, over time. Some of that work will be motivated by proposed federal government voluntary framework to expand the types of data that must be shared over time by certified systems, as noted in this draft approach out for public comment.

Imagine if Apple further opens up Apple Health so it no longer serves as the destination, but a conduit for a patient's longitudinal health record to a growing marketplace of applications that can help guide consumers through decisions to better manage their health.

Thankfully, the consumer data-sharing movement—placing the longitudinal health record in the hands of the patient and the applications they trust—is taking hold, albeit quietly. In just the past few weeks, a number of health systems that were initially slow to turn on the required APIs suddenly found the motivation to meet Apple's requirement.

When we look back a decade from now to render judgment, it will be the impact Apple Health has had in changing the default setting in health information sharing—from closed to open.

Two points. First, I knew there had to be something about Obama Care that wasn't all bad. This is it. Second, don't count Google out.

Still, Apple is the master of usable GUI's, and IF they continue down this path, they will be come a major player in this space.

Told you so.

Tuesday, December 26, 2017

Dalai's XIIth Law

Some years ago, I created Dalai's Laws of PACS, a distillation of my observations of PACS over time. I managed to insult most everyone involved in imaging, including vendors, IT, radiologists, hospital administrators, and probably His Holiness, the Dalai Lama Himself. Ah, those were the days.

Perhaps my favorite among the Laws was number XII:

Which is graphically illustrated by this photo meant to remind us of some radiologists we know:

This Law was inspired by interactions with one of my former partners, now bosses, who happens to be a superb interventional rad. However, not long before I codified the Laws, he called me from a plane about to take off to ask how to adjust the volume on his laptop so his kids could watch a movie. 

The Law was also prompted by another partner, the one who is no longer with us, having gone to a far, far better place (no, he's not dead, he's in Florida!) This fellow inflicted upon us a very early advanced visualization program (it could do real-time MPR, and that's about it) that had a horrid interface. My friend didn't care about the latter, and insisted that we all use this piece of garbage.

And so the XIIth Law was born. You might say it is designed to appeal to the least common (technical) denominator, and you would be correct. But that isn't necessarily a bad thing. Usually. PACS and associated products are used for life-saving evaluations and they have to work for everyone. Simple, yes?

The late, great George Carlin once said, "Behind every silver lining, there's a black cloud." I now find myself boxed in by XII and the associated philosophy, and I'm stuck. 

As negotiations are ongoing, I cannot reveal the companies or even the product involved, so forgive me for the following, rather obtuse description of the problem. In brief, one of our sites is getting a new piece of equipment, and it comes with the option for new reading software. Another site has a similar device with older software. I am quite comfortable with the latter as I selected this package myself several years ago. But when we went on the obligatory site-visit to see the new machine, it was being used with a different package, actually not from the hardware vendor, that was highly recommended by all involved. 

In anticipation of the blessed event (the delivery of the new device) in a few months, we've had a demonstration version new software installed to get everyone used to it. And there begins the grief. 

To be fair, there has been some degree of miscommunication with the vendor, which was apparently not aware of the XIIth Law, and had the impression that they needed only to create a profile to my liking, and not worry about the rest of the boys. And they got my profile pretty close to what I wanted, ignoring a few things such as number of clicks to get from A to B that I figured would be ironed out in the final production install. 

But then I made the mistake of listening to myself. I polled the peanut gallery audience to be sure everyone was on board with the new program. And lo and behold, they were most emphatically not. The other rads far preferred the older, less-powerful program they are used to using over the newer, much more powerful, but more complex newcomer. Of course, in discussing the situation, it becomes clear that the rest of the gang really wasn't all that familiar with the older program, and really didn't realize that the smooth functionality they craved was in large part due to hundreds of hours of work by one of my technologists, who created maps by which the program knew which images to place where in the great scheme of things. But that's all under the hood, and no one really is concerned with how it works, just so long as it does work. 

So the big question is this: Do I insist on the program I think is best, or do I practice what I preach, and go with what works best for the crowd? Actually, that misstates the situation somewhat, as I have asked the vendor in question to create a pablumized pared-down profile that should make everyone happy. It remains to be seen if they can do so. 

I am a Bioengineer by training, which is a branch of Electrical Engineering. I have managed to make the two persona live in internal harmony, but for most physicians, Star Trek's Dr. McCoy said it best:

"I know engineers, they LOVE to change things."  And so they do. And sometimes for the better. I've whined for years and years that engineers don't design usable PACS interfaces, but that isn't always the problem. Sometimes, PBKAC.

Hoist by my own petard. We'll see what happens. 

Sunday, December 17, 2017

RSNA 2017: 2016 Redux...
Centaurs Will Make Radiology Great Ag-AI-n!

In reading last year's RSNA report, I was struck with just how little has changed.

Here I am this year, 2017, and here's how I looked at RSNA 2016:

A little grayer, perhaps a pound or two more. But otherwise same ol' Dalai. And same ol' RSNA. I even manned the RAD-AID booth again:

Yes, I tied the bow-tie all by myself.

This is a model housed at the Bayer booth of the airship RAD-AID hopes to use to bring imaging to underserved areas; I think the official rendering is much more impressive, and maybe even a little, well, buxom:

I'm still lobbying for a seat on the first flight. Did I say buxom? I meant handsome!

I did attend the requisite PET/CT and SPECT/CT lectures. Once again, I was impressed by the fact that I have a better SPECT/CT scanner (Siemens Symbia Intevo) than some of the BIG NAMES in Nuclear Medicine who are out there giving the lectures. Of course, with their knowledge and expertise, they can probably get as much information out of their Hawkeye SPECT/pseudoCT scanner than I can from my advanced instrument, but they aren't available down in the boonies where I practice...

Yes, yes. I know. Get to the point, Dalai! What about AI!?

You probably know by now that AI dominated RSNA, even more so than last year. Here is a photo of the average attendee trying to get into one of the packed AI lectures:

If you count residency, I've been in this business since 1985, over 32 years. I've seen the rise of MRI, multi-slice CT, PET/CT, PET/MRI, SPECT/CT, PACS, EMR, Digital Everything, endoscopy, DRA(eck) 2005, "value-based" imaging, Imaging 3.x (a.k.a. "We're Doctors Too!!"), Image Gentlemanly, Meaningless Use, and other revolutions. I've seen the fall of film and the decline of barium. It's been quite a ride. But I've never, ever, EVER seen the level of interest, well, more accurately, fear, trepidation, anxiety, paranoia, and sheer terror that AI has inspired. The draw for AI lectures seemed not unlike the morbid compulsion to stop to look at a really bad car wreck. I don't think a live mud-wrestling match between Trump and Hillary would draw even half the audience. 

I found the whole thing quite amusing, really. There were crowds at any talk with a title or description or anything at all that suggested AI; if this talk had been at RSNA, I'm sure it would have attracted hundreds. I did find a rough dichotomy in the AI talks. There were those which talked about the mechanics of AI and Machine Learning, covering all sorts of things like Convoluted Neural Networks; you could literally hear crystalline tinkling of the eyes of the crowd glazing over as the talks progressed further and further into the very complex weeds. And then there were the sessions more applicable to the riff-raff such as myself, who just want to know where we are with AI relative to radiology. Of course, the picture wouldn't be complete without a chat with a couple of the vendors who are, ummmm, deeply embedded in this space. 

If you are the type to skip to the last page of the book, I'll save you the trouble. Here are the punch-lines of this entire article: AI is still not taking over. AI will be a tool to assist radiologists, not replace them. Radiologists who embrace and use AI will excel over those who don't. And finally...radiologists should help develop (and thereby control) AI's for our use. You can now go back to sleep.

I'm not going to try to recapitulate the technical talks about Artificial Intelligence (some are suggesting we call it Augmented Intelligence instead, but that evokes thoughts of another kind of silicon/silicone) and Machine Learning. There are about a zillion resources out there that will do a far better job than I ever could on these pages. Try THIS article from Radiographics as a starting-point. The more practical talks (for us out here in the boonies) were a little more reassuring. There were certain trends noted. First, when it comes to AI and surrounding hype, we appear to be at the "Peak of Inflated Expectations" as per the graph below, which you've probably seen before:

And of course you've all see these by now...

There are those, virtually ALL non-radiologists, and most from the world of AI, who are preaching the imminent demise of Radiology (if not Humanity), which is to me the most blatant example of "Inflated Expectations". This list of meanies is topped by Geoffrey Hinton from Google:

(I far prefer the views of Dr. Eliot Siegel, pictured to the right, who NOT a meanie, and is much more optimistic about our future, and considerably more believable as he has spent quite a few years researching AI in radiology.) 

Other nay-sayers include Andrew Ng, currently out of Stanford, recently of Baidu AI and also with Google connections. He has stated that AI would take over Radiology:

...but his Stanford group only recently published a rather flawed paper on a non-peer-reviewed site, claiming that their AI could outdo humans in diagnosing pneumonia on chest radiographs. And let us not forget Ezekiel Emanuel, M.D., non-radiologist physician brother of Hizzoner Rahm, who pushes Single Payor and seems to hate radiology in particular, stating in the New England Journal of (Esoteric) Medicine that radiologists will be replaced by computers within 5 years. Bah Humbug!

Typical of doomsaying articles is this recent piece in The Economist, which wildly extrapolates from very limited data, suggesting that an AI that can operate at the level of a human radiologist absolutely, positively will bring about amazing things which will displace radiologists, and naturally stipulates that all this is imminent. Of course, the author neglects the minor problem that no such machine exists. 

Notice a trend? Those who are pushing this meme are not radiologists, and I submit they do not grasp what we do beyond "lookin' at the purty pitchurs". 

But back to RSNA. The radiologist-centric take-home message was best voiced by Dr. Keith Dreyer in a very well-crafted talk:

  • Radiologists and AI will be far better together then either one alone
  • Our biggest challenge has been the lack of an AI-ecosystem
  • Limiting AI - creation, validation, approval, integration, surveillance, adoption
  • We see an AI future that is very bright for radiology and radiologists
  • ACR is working with radiologists, industry, and government to create the future

Dr. Dreyer did state rather explicitly that the ACR would be our prime resource in this realm, guiding AI standards that will maintain its functionality as a tool to help us improve patient care, and I'm quite willing to accept their guidance. Dreyer notes that while machines are growing intelligent more quickly than we humans can manage, we are still better off working together (my comments on that later) and suggests this as our combined "evolution":

Here are the potential feedback loops for the human-AI hybrid:

Keith ended the talk with what is perhaps the most profound slide to have ever been shown at RSNA:

Absolutely indisputable.

A few vendors were more into the hype than the speakers:

The only even mildly threatening booth was from Deep Radiology, which consisted of a few benches and a monitor showing a continuous loop of a Deep Radiology stooge scientist droning on about how their system, which no one has ever seen, outdoes human rads. I took a huge chance in shooting this image, as they had a "No Photographs" policy. Like there was something to photograph.

But let's turn now to some of the vendors that at least appear to be delivering, rather than hyping.

I'll start of course with my friends at WatsonHealthIBMergeAMICAS. I guess my venerable AMICAS PACS is now Watson PACS, and when I need it, I don't even have to ask it to come here. (OOPS, wrong Watson!) I was able to visit with our new salesperson, and one of the apps people I've known from the beginning of my relationship with AMICAS. My time was very limited, as I had a roundtable to attend shortly after my appointment (more on that below) and I didn't get to see everything I would have liked, such as the plans for Version 8.x, nor did I see all the Watson AI programs. I did get to preview some of the more imminent (don't ask me when) add-ons to PACS. These include more robust analytics that should replace the old AMICAS Watch, utilizing IBM COGNOS business software. Marktation is coming, which will speed the process of measuring a finding and documenting it in the report.

"Patient Synopsis," another work-in-progress, is rather like a news-aggregator for radiology. It will glean context-sensitive information from the EMR and present it as a separate pane for you interpretive pleasure. I have to add here that a colleague was with me during this demonstration, and instantly noted that this could conceivably get us in trouble; what happens if Patient Synopsis doesn't pull something pertinent? My response was simple-minded as usual, but I think accurate: Without this, most of us simply don't have the time to mine though the EMR for important little tidbits. At least Patient Synopsis gives us a lot more information than we could obtain practically before.

"IBM Watson Imaging Clinical Review" is apparently available for use already. It, too, snoops into the EMR, and

Watson Imaging Clinical Review improves the path from diagnosis to documentation, eliminating data leaks caused by incomplete or incorrect documentation. This innovative cognitive data review tool supports accurate and timely clinical and administrative decision-making by:

  • Reading structured and unstructured data
  • Understanding data to extract meaningful information
  • Comparing clinical reports with the EMR problem list and recorded diagnosis
  • Empowering users to input the correct information back into the EMR reports

Watson Imaging Clinical Review enables reconciliation of inconsistencies between clinical diagnoses and administrative records. Those inconsistencies that can impact billing accuracy, quality metrics, and an organization’s bottom line.
The original release was exclusively geared toward aortic stenosis. Version 2.0 was shown on the floor which evaluates 24 disease states including cardiomegaly, stroke, and cancer, per IBM.

Finally, there was the "Breast Care Advisor," a system that works in the background of one's mammography PACS, which pre-reads old reports, and then "looks" at the mammographic images themselves, assigning an "intricacy score". The Advisor then prioritizes and triages those studies which need attention, so the patient can undergo any necessary additional testing during the same visit.

But perhaps the most important development at IBMergeWatsonHealth is the chance to get involved in Watson's evolution. I spoke with one of the IBM VP's on this topic, noting that as a PACS customer, we had never been contacted to allow Watson to peek at our patients' anonymized data. I was promised that this would be remedied, and in fact there will be opportunities to participate in training Watson's various personae. I'll keep everyone posted on this.

I might have missed one of the more promising offerings on the exhibit floor had I not been spotted by my old friend Fred, Master Salesman for TeraRecon. Fred could quite successfully sell ice cubes to Eskimos, and was instrumental in keeping TR on my horizon whilst waiting for my hospital to understand the need for Advanced Imaging. Fred knows absolutely Everyone who is Anyone in the imaging business (although I'm not sure how I managed to become Anyone). He insisted that I look at EnvoyAI, which had embarked upon a distributing relationship with TeraRecon, and introduced me to EnvoyAI's CEO, Misha Herscu, and the other two members of the core team, Jake Taylor, and Dr. Steven Rothenberg. There will be many more folks working with them when all is said and done, but I can now say I met them when it all started. Almost, anyway. Fred also fetched Jeff Sorenson, TeraRecon's CEO, with whom I spent a great deal of time, actually closing out the exhibit floor. More on that in a moment. And Fred managed to drop a name you've just heard me mention, Dr. Eliot Siegel, noting that he was on the EnvoyAI Advisory Board, as well as Drs. Paul Chang and Khan Siddiqui. This is an incredible pedigree, making EnvoyAI pretty much instantly worthy of attention.

Misha, who was running on Red Bull and fumes by the time I spoke with him, describes his company as the "Amazon of AI" and that is quite accurate, although I might personally have used "iTunes Store of AI" instead. (When I suggested that AI today is where PACS was 20 years ago, he responded, "I was 6 years old back then." Nurse? Could I have the green Jello, today, please?) EnvoyAI's vision statement foreshadows the rest of the story: "Our number one goal is to empower physicians by giving them access to the best algorithms available." And that's what they do. At its essence, Envoy is an aggregator. It arbitrates and vets (along with partner TeraRecon) AI algorithms and presents them to the radiologist-user. The folks pushing these AI components were literally lining up at the EnvoyAI booth to get on the roster. Right now there are about 38 algorithms in the system with many more to come. (Signify Research says there are 14 signed distribution deals with partner companies, with three of the algorithms having FDA clearance. Some of the companies signed-up to the EnvoyAI platform are 4Quant, Aidoc, icometrix, Imbio, Infervision, Lunit, Quibim, and VUNO.)

Here are a few of the algorithms available to date:
  • Imbio offers lung density reporting for COPD analysis with chest CT scans. The Imbio CT Lung Density Analysis™ software provides reproducible CT values for pulmonary tissue, which is essential for providing quantitative support for diagnosis and follow up examinations.
  • icometrix offers icobrain, an FDA-cleared brain MRI tool that is intended for automatic labeling, visualization and volumetric quantification of segmentable brain structures from a set of MR images. The software is intended to automate the current manual process of identifying, labeling and quantifying the volumes of segmentable brain structures identified on MR images.
  • TeraRecon offers iNtuition Time Density Analysis for CT, which supports stroke triage workflow by producing colorized parametric maps of the brain from time-resolved, thin-slice CT scans of the head with contrast, including CBF, CBV, MTT, TTP, TOT, RT map types.
EnvoyAI utilizes these components:
A medical imaging algorithm in a software container with well-defined inputs and outputs for easy distribution

Developer Portal
Website for building, testing, and sharing machines

EnvoyAI Exchange
Where an end user can buy or test a machine

EnvoyAI Liaison
On site software that communicates with hospitals' scanners, viewers, and either the EnvoyAI Inference Cloud or Inference Appliance

EnvoyAI Inference Cloud
Runs machines in the cloud using de-identified data sent by the EnvoyAI Liaison

EnvoyAI Inference Appliance
Runs machines on site in your data center

EnvoyAI Machine API
A simple way for AI developers to implement their innovations in the EnvoyAI Inference Cloud

EnvoyAI Liaison API
A developer interface that provides an easy way to connect the AI machines you want to the workflow tools you use

iNtuition EnvoyAI Adapter
Allows machine results to be viewed inside of TeraRecon's iNtuition

Interestingly, the system does not use DICOM, but rather moves data around via a JSON (JavaScript Object Notation) contract for data transmission. Data can be sent to a cloud or to an in-house Inference Appliance if you don't want anything escaping your (fire)walls.

This is where TeraRecon comes in. They have created NorthStar*, the "last mile" of the solution to the AI problem. In Mr. Sorenson's own words:
It’s time for a fresh approach to artificial intelligence in medicine. By presenting findings and conclusions in a format where the suggestions of many intelligence engines can be considered and accepted or rejected by the physician in real-time, it provides a reward system to the intelligence machine to improve its performance overall. Similarly, the interactions with the image data and intelligence machine findings during routine diagnostic interpretation can be captured for future training of these machines. This requires technology to ensure that the applicable source data is processed prior to interpretation, proper suggestion of applicable intelligence engines has occurred during interpretation, and the physician remains in control of what findings are propagated into their interpretation within the PACS environment.

The technologies required to achieve this future-state machine intelligence workflow are: 1) one or more app stores with intelligence machine content, 2) data transport and machine instantiation technologies to solve the last mile integration into routine clinical interpretations, 3) a viewer or embeddable viewing component allowing interaction with a plurality of machines, findings and observed user behaviors.
TR's website completes the story:
Built from the ground up on a state-of-the-art technology stack, TeraRecon's NorthStar™ viewer is the culmination of more than 20 man-years of effort. It is an AI content-enabled medical image viewer which stands to revolutionize the way physicians incorporate the galaxy of third party AI machines and embed them into their PACS workflow.

NorthStar* allows you to benefit from the assistance of artificial intelligence, but remain in control of which results become a part of the permanent image records and your diagnostic report. Stay in control while you experiment with the future of artificial intelligence.
I had the chance to see NorthStar* in operation, demonstrated by Mr. Sorenson himself, and like any first-pass at something revolutionary, the interface is not yet quite as smooth as I would like. But the potential is very clear.: NorthStar*/EnvoyAI provides a platform that lets radiologists test out various AI algorithms, utilize the results or not as they see fit, and even retrain the algorithm (for their own site or individual use, not for all users). Or, as Dr. Siegel put it, "What we’ve lacked is the communication mechanism that delivers their algorithms to a broad audience allowing clinicians to try out algorithms, while maintaining control over the patient interaction and report.” And now we have it.

In the interest of thoroughness, I should add that Nuance has a somewhat similar platform for their PowerShare network, and Blackford Analysis and Visage have their own takes as well.

I mentioned above my participation in a round-table on the topic, the specifics of which I cannot really discuss. Suffice it to say that an interested party gathers a group together every RSNA to discuss the controversial topic of the year, and of course AI in Radiology was the clear choice for 2017. I was somehow included in a list of luminaries, and I quickly felt like an 8th-grader who wandered into a Quantum Physics class at MIT. But I held my own in this rarefied crowd of radiologists, executives, and even an attorney; at least there was relatively little eye-rolling and snickering when I offered my humble opinions. I can tell you that the general feeling was positive for our future. Since I don't have permission to quote the other members, I'll simply tell you what I said. My profound comments were synthesized after a long phone chat with Dr. Siegel, and long (and occasionally adversarial) discussions with friends on Aunt Minnie. Several things are clear to me. First and foremost, AI is a tool, a very powerful tool, but still a tool. It will not take our jobs away. Why? Here, I can only hand-wave, but I think I've hit the answer: Computers do not think. We do. Moreover, we have insight, we dream, we have intuition. Our AI's might someday become very good at identifying stuff, but not at doing whatever it is we do to be radiologists, physicians. Computers don't have empathy, or feeling of any sort (although they can simulate it) and for that reason alone, they will never replace us. I can tell you that no one on the panel was particularly worried about AI taking over.

HOWEVER, there is no denying the tremendous power AI potentially yields, and again, we should embrace it AS A TOOL.  I thought I was quite clever when suggesting that the relationship must be symbiotic, the human and the cybernetic working together as one organism. The old term Cyborg comes to mind. As it turns out, Dr. Dreyer mentioned something similar but a bit more organic in a recent article: "Centaur radiologists, by understanding how to work with computers, AI, and ML, combined with their sophisticated clinical knowledge base gained from medical training and experience, can provide more and better information in their interpretations."  Emphasis mine.

Integral to the symbiotic/cyborg/centaur approach is the need for interactivity with the process itself. We have to be a huge part of the feedback loop for AI's deployment and training. We MUST keep control of this process, or we'll end up with the same situation we had with PACS: the vendors will create products that sell to the IT and C-Suite folks, but are not optimal for us. I fear that scenario far more than any fantasy of HAL taking over the radiological ship.

The lesson for us radiologists is simple. GET INVOLVED. I've discovered two approaches that allow us to do so, and I'm sure there are more. I promise everyone has something to contribute to this process. But if you sit back and watch, you might end up being superseded by those who understand and value this technology.

So, together, we can all...                                                                                              !

Saturday, November 11, 2017

Traveling At The Edge Of Life Expectancy

Allow me to deviate a bit from the worlds of Imaging and PACS...I'm straying way out of my wheelhouse on this one.

This starts off with a happy occasion, a Mediterranean cruise. Mrs. Dalai and I recently joined some friends for a two-week trip through various European cities and towns. We had a great time and enjoyed some beautiful sights and wonderful food. I won't bore you with every little detail, but suffice it to say the ship was very comfortable, and the destinations were spectacular.

Mrs. Dalai and I have travelled extensively over the years, often by sea. Until recently, we were generally the youngest people on the ship, and even when we went to Antarctica, we were in the lowest quartile or quintile age-wise. On this last trip, we were perhaps in the lower third. Still respectable.

Modern medicine is a wonderful thing. We cure diseases that were once fatal, and we perpetuate life way beyond the limits our grandparents, or even our parents, thought possible. And that is certainly a good thing. But it can be somewhat of a mixed blessing. With the reasonable expectation of living well into our 70's, 80's, and not uncommonly, our 90's, we may feel less pressure to accomplish the things we should be doing at a younger age. I'm surrounded by this mentality. Many colleagues and acquaintances are working themselves to death, hoping that they really aren't, trying to make hay while the sun shines. If you believe you will be alive and kicking after retirement, and assume you will be as healthy as the day you turned 40, that makes some sense. But my observations on this particular journey demonstrate some fallacy in that approach.

True, modern medicine has delivered us many spry individuals in the 70's and 80's, although I can't honestly say if they represent the majority of their age-group. Some of our fellow travelers certainly fit that category. Sadly, many, at least a significant plurality, did not. There were any number of folks who could not walk up a flight of stairs (but tried anyway), who could not walk more than a few hundred feet on a tour clearly labeled "NOT FOR THOSE WITH PHYSICAL LIMITATIONS" (but tried anyway), and who really weren't quite sure what time-zone, what port, what country, or even what planet they were visiting (but didn't care anyway). These pour souls rather clearly didn't enjoy the experience, and presented an impediment and even some danger to the rest of the gang. I'm speculating a bit, of course, but I think it likely that these folks delayed their gratification to the point of no return. They saved and saved and saved for the trip of a lifetime, working hard, sacrificing, scrimping, and generally putting things off until just short of too late.

Please don't think I'm a callous jerk. I love old people. I hope to be one someday. According to AARP, I'm one already. So stop throwing dentures at me. I don't blame the old folks for trying to enjoy life, even if their insistence on doing so impacts me. That isn't really what this is about.

The message I want to deliver is directed at those my age and younger. It is simple but profound: Life is to be enjoyed, treasured, and cherished. It is not meant to be a rat-race wherein we try to accumulate the most cash and the most stuff before we croak.

He who dies with the most toys is still dead.

While it's rude to tell people how to spend their money, and how much to work or not to work, I'm hoping I can inspire some of you to strike a balance. Find what you love, and indulge yourself while you can still enjoy it. Obviously, don't break the bank, but don't deprive yourself until you have no self to deprive. Find a way to enjoy yourself without killing yourself, losing sight of who you are and what incredible things you already have. Like a spouse, kids, dogs, cats, etc.

I wish I had the complete answer, but I don't. You can't take a round-the-world cruise in the Owner's Suite of the Queen Mary II, or drive a $300,000 Bentley SUV at age 35 unless you were born rich, hit the lottery, or came up with that Killer App. But perhaps you can do a shorter trip on a slightly less luxurious vessel, and drive a very nice Toyota. Or a trip to the beach. Or even camping in the backyard. Enjoy what you have while you have it. There is always something desirable just out of reach, no matter what level you've achieved. If you let the pursuit of such define you, you'll never, ever be content.

For most of us, it's all about compromise, and the realization that very, very few can have it all right bloody now. But putting everything off until you're 95% deceased because you had to collect just one more paycheck is a shame, a tragedy. Compound that with the sad truth, which I see daily, that sometimes life does not go on. All the more reason to celebrate and enjoy.

In the Talmud, the collective work of Jewish wisdom, is found this passage:
Rabbi Eliezer said: “Repent one day before your death.” So his disciples asked him: “Does a person know which day he will die?” Rabbi Eliezer responded: “Certainly, then, a person should repent today, for perhaps tomorrow he will die—so that all his days he is repenting.” (Talmud, Shabbat 153a)
I'm more into reflecting than repenting, although I do my share of that, too. I might alter the Rabbi's response to read, "Certainly, then, a person should live today..." I'm not suggesting indulging in a daily bacchanalia, but rather to simply enjoy life and all the gifts thereof. Live within your means, invest for the future, but LIVE today. It really is that simple.

You may now resume throwing your dentures.

Wednesday, November 08, 2017

Interventional SPAM

I've been out of the country for several weeks, which is the usual explanation for by lack of posting. I was on a pleasure trip, or I would have posted from off. There will be an article about that later.

Blogs are easy targets for spammers, if you didn't know. That "Comment" field is a magnet to the unscrupulous who somehow think that bloggers will gleefully allow advertisements to appear on their site. Wrong, buffalo-breath. All but the least experienced bloggers maintain control over their comments and never, ever, EVER allow this trash to reach their readers. 

Most of this seems to come from a concept called "affiliate marketing" wherein someone gets paid for pushing someone else's product or website. Great idea? Not to me. When coupled with the power and reach of the Internet, it prompts the greedy to bombard the rest of us with garbage emails, blog-comments, and other bogus instruments designed to make us click into some site for which the spammer gets a penny or two. Or some fraction thereof. When you send out millions of these things, those fractions add up. These are mostly generated by 'bots, as an aside, a complete misuse of limited AI technology. But some might be human-borne...

Normally, I delete each and every SPAM comment, after reporting the sender and the advertised company to the appropriate places. Once in a great while, I shut one of them down. Today, however, I'm going to make an exception, and publish the SPAM comment as its very own blog-post. And the advertiser is NOT going to like it. 

Early this morning, I received this comment from "Ruben Fogg" on my RAD-AID article:

Ruben Fogg has left a new comment on your post "Giving Back: RAD-AID":

RAD-AID has literally hundreds of opportunities for everyone in imaging from physicians to medical students and residents, as well as interventional radiology chicago technologists, sonographers, nurses, physicians assistants, health physicists, as well as specialists in health information technologies and public health. If you have a radiologic skill, there’s a place where you are needed. Trust me on that. 

This miscreant inserted his advertising link into a paragraph quoted from the article itself. I find it rather sad that he chose this particular post, but spammers tend not to have much of a conscience. 

Against the usual standing advice, I clicked the "interventional radiology chicago" link...and it leads me to the advertiser, VIR Chicago:

Find an Interventional Radiologist at VIR Chicago

VIR is comprised of eight IR specialists whose experience in interventional radiology in the Chicago area extends over 25 years. We are clinic-based, but practice at and cover the Adventist Midwest Health hospitals in the western suburbs of Chicago:

Adventist Bolingbrook Hospital
Adventist GlenOaks Hospital
Adventist Hinsdale Hospital
Adventist La Grange Hospital
Advocate Sherman Hospital

Please contact us to schedule a consultation with one of our Chicago-based interventional radiologist team members.

Each interventional radiologist at VIR has been a leader in bringing this modern specialty to Illinois. All of our physicians have the highest level of certification from the American Board of Medical Specialties: the Certificate of Added Qualifications in Vascular and Interventional Radiology. At VIR, our interventional radiologist team participates in ongoing research and clinical trials and has authored many scientific papers and presentations in the field of interventional radiology. We have had several “firsts” including the first uterine fibroid embolization (UFE) in Illinois, the first placement of a flexible metal stent in a human in Illinois, and recently, the first fibroid embolization ever performed in a gorilla (see photo).

The VIR interventional radiologist team has three other condition-specific websites that we invite you to visit:

Uterine Fibroids
Aortic Stents

Seems like an upstanding practice; at least they came up with a good website. But someone thought it necessary to hire affiliate marketer to SPAM on behalf of their site. And that is a very, very bad idea.

I'm old enough to remember when doctors (and drug companies) didn't advertise. At all. It was consider gauche, low-class, greedy, nasty, whatever. That has changed, obviously. Our local news broadcasts are all sponsored by various hospitals, orthopedic groups, and chiropractors. The national network shows feature ads for various biologicals and chemo drugs that can only be delivered by prescription.

Clearly, the implication is that Health Care is just another product like cars or floor wax, to be sold with Madison Avenue aplomb. How do you feel about that? I'll tell you how I feel...I feel sickened. This is not how the profession should function. Clearly, the pursuit of revenue has taken precedence over everything else. Some will argue that patients need to be empowered and educated, and that's true to an extent. However, as with the issue of patients reading their own reports, their ability to assimilate the information thrown at them is variable at best. I personally see all of this, advertising and all, as attempts to decrease the influence and importance of physicians. And to boost revenue by directly targeting patients as customers. Is this why I went to medical school?

I guess I'm getting old and crotchety.

I'm not going to apologize for "outing" VIRChicago. They hired the spammer, I mean marketing affiliate. They wanted publicity. I'm happy to oblige.

If you’re interested, here is some information about the spammer...note nation of origin...