Honor Spock's Logic - Follow the Science

Like many I was saddened to hear the loss of one of my heroes growing up - Leonard Nimoy was Spock to me as he was to many others. He epitomized the value of science and logic in the resolution of problems

As my good Friend Jane Sarasohn-Kahn highlighted in her tribute on Healthpopuli: Learning from Mr. Spock and Leonard Nimoy about living long and prospering. Her selection of this iconic moment with Spock were right on target - from one of the great movies from the franchise - Wrath of Khan

Spock: “Do not grieve, Admiral. It is logical: the needs of the many outweigh…”
Kirk: “The needs of the few…”
Spock: “Or the one.”

He spoke out on smoking - something that in the end killed him before his time in this tweet from January 2014:

I quit smoking 30 yrs ago. Not soon enough. I have COPD. Grandpa says, quit now!! LLAP

I quit smoking 30 yrs ago. Not soon enough. I have COPD. Grandpa says, quit now!! LLAP
— Leonard Nimoy (@TheRealNimoy) January 30, 2014

30% of people will suffer serious Chronic Obstructive Airways Disease (COPD) as a result of smoking - and that's just one of a slew of diseases inextricable linked to smoking. Smoking while in decline in some countries is on the rise in others and this major health risk remains one a negative impact on personal health

You can explore WHO data in this interactive chart from who here

But don't limit the application of science to health and smoking - you can put Vaccines in the same category of Science and Logic. Jimmy Kimmel captured the sentiments aptly in this segment featuring real doctors




So much of your health boils down to Lifestyle choices that was so elegantly captured by Brigitte Piniewski, MD in this chart




Where would you rather be - fun or no fun


Spock the Hero with Super Powers
We may wish for the seriously cool vulcan Nerve Pinch



But we don’t need the vulcan nerve pinch. He and his character have taught us that science while not infallible has been working for us for millennium. We have started to tap into the power of science and the opportunity offered to our health and well being.

When it comes to science and healthcare Doctors are your trusted advisor - the relationship may be changing from the paternalistic role to a collaborative role as Eric Topol so eloquently describes in his latest book - The Patient will See you Now. But as captured in this piece by this Trauma Surgeon (@DocBastard) on the Daily Beast: Why You Trust the Internet More Than Your Doctor

...for god’s sake don’t think that you know as much as a doctor because you Googled something. Medical training takes up to a decade or longer (depending on the specialty), so a 0.452 second Google search does not substitute for consulting with an actual physician whose only interest is your health.

We are only at the beginning - what comes next and in our future is unimaginable. Our innovation, inventiveness and abilities continue to expand our universe and our understanding. Science wins- every time. Be logical with that splash of human emotion and honor his legacy - open your mind, analyze the facts and apply the science. As Jesse: Yeah, Mr. White! Yeah, science!

Live Long and Prosper (LLAP)

or perhaps

Live Long, Logically and Prosper (L3AP)

On a side note - if you are interested in the history of the Spock Vulcan Salute - Live Long and Prosper you can watch his explanation of his Jewish Origins here (derived from the Hebrew letter shin  and the first letter of several hebrew words Shaddai (god), Shalom (hello/goodbye/peace) and Shekhinah (feminine word for god) - How Fascinating!

Physician Symposium #DrHIT #HIMSS14

The Physician (#DrHIT) Symposium at #HIMSS14
Opening session was eloquently covered by Robert Wah, MD (@RobertWahMD) detailing the spectrum of issues ranging from the new Healthcare System:

The challenge of SGR “fix(es)” and the evolution of the systems we are implementing and the value proposition. As he put it

Quality of care is improved with better information — saving lives and money

But Health Technology is not easy to implement:

Health tech is hard, but harder part is changing #workflow & #workforce. @RobertWahMD#HIMSS14#DrHIT Org alignment: pic.twitter.com/AQsX1a3846

— Wen Dombrowski MD (@HealthcareWen) February 23, 2014

And layered on top is the increasing challenge of securing the data with hackers seeing healthcare data as 15x more valuable than financial hacked data!

MT @CraigJoseph: #DrHIT@RobertWahMD Arms race btwn those trying to protect patient data & those trying to get it. Who'll win? #HIMSS14

— HIMSS (@HIMSS) February 23, 2014

What we need is coordinated care and Dr Wah offered this visual of the way forward

Christine Bechtel focused on the Activate Evidence Based Patient Engagement and as she reported - Patients like doctors who have an EHR

Patients think EHRs help doctors deliver better care

• Timely access to information, sharing info across care team, med history, managing health conditions
• Overall, EHRs were rated between 23%-37% points higher than paper on these elements

Interesting since doctors have been reported as saying they dislike the EHR but patients like seeing their doctors with an EHR

MT @drnic1: 80% patients say online #EHR access improves #health and a reason to stay with a practice. #DrHIT#Himss14#HITworks

— HIMSS (@HIMSS) February 23, 2014

The sad thing was this session was concurrent with @ePatientDave in another room - The Connected Patient: Learning How Patients Can Help in Healthcare only social media united these sessions

@cmaer@ePatientDave Missed opportunity - would be so much better to have those two intersecting rather than in parallel #DrHit#HIMSS14

— Susan Shaw (@drsusanshaw) February 23, 2014

As for Jonathan Teich and his session Improving Outcomes with CDS - he used his personal experience where peer pressure (as he described it 3rd time he was pressured to take on an expert triple diamond ski slope) he finally agreed and ended up in a serious ski accident fracturing multiple vertebrae. Interesting analogy relative to the Clinical Decision Support System and the pressure this applies to clinical practice sometimes inappropriately...
Interesting look at alerts and the potential for providing more than just alerts but actually providing intelligent data that distill down to 10 types of CDS interactions

1. Immediate Alerts: warnings and critiques
2. Event-driven alerts and reminders
3. Order Sets, Care Plans and Protocols
4. Parameter Guidance
5. Smart Documentation Forms Improving Outcomes with Clinical Decision Support: An Implementer’s Guide (HIMSS, Second edition, 2011)
6. Relevant Data Summaries (Single-patient)
7. Multi-patient Monitors and Dashboards
8. Predictive and Retrospective Analytics
9. Filtered Reference Information and Knowledge Resources
10. Expert Workup Advisors

And the important summary slide was the CDS Five Rights (Right information, people, formats, channels and times)

And returned to one of the core opportunities - Patient Engagement with a a session by Henry Feldman, MD FACP: Informatics Enabling Patient Transparency. He asked the same questions as another presenter - how many fo the audience considered themselves a patient (Still only a shabby 80%) and then took this further asking

• You feel that you know exactly what your provider was thinking in making his decisions
• You think the clinical systems helped your provider understand comprehensively everything about you
• You build clinical systems or are a provider
• With the inevitable decline in hands up
• You think your (or anyone else’s) software truly helps the patient or even the provider understand comprehensively or transparently what is going on

Sadly we are not near this and the reality is much further with physicians thinking patients are unsophisticated. Yes at he pointed out the airline industry gets it and even the DMV/MVA gets it offering customer engagement models:
Their experience and stats blow the unfounded resistance out of the water

• Only 2% of patients found notes more confusing than helpful
• Only 2% found the note content offensive
• 92% said they take better care of themselves
• 87% were better prepared for visits

Importantly we need to turn data into information for patients and he cited the Wired example of a Laboratory test (Blood Test Gets a Makeover Steve Leckart) and the makeover for
Basic Labs

Cardiology Result

and the PSA result

I know where I'd like to be receiving my care (and lab results) from! Great finish to the session. So as he summarized where we should be with patient engagement an data

• Open your data to your patients
• Patients understand more than we think
• Teach patients how to use data effectively – This can save you time in the long run
• Put your patients to work on their own health!
• Vendor work on how patients will view big data
• It’s a new drug, research the risks and benefits

Great start to what will be a busy HIMSS

Vaccines Don't Cause Autism - Vaccinate your Kids

It can be frustrating to be a clinician in the era of the internet and instantaneous availability of data especially when the reliability and accuracy is variable. But this is the world we live in and there is plenty of data showing that patients are accessing information in ever increasing numbers. The challenge has been helping patients filter the data for both relevance and accuracy.

Vaccination has been at the epicenter of a these challenges for some years - in fact long before the wide spread use of the internet thanks to a piece published in The Lancet in 1998  and unusually retracted. In fact the BMJ published a paper in 2011 declaring the paper fraudulent - as they noted in the discussion the lead author (now stripped of his medical degree and academic credentials) was clearly actively perpetrating the fraud

Who perpetrated this fraud? There is no doubt that it was Wakefield. Is it possible that he was wrong, but not dishonest: that he was so incompetent that he was unable to fairly describe the project, or to report even one of the 12 children’s cases accurately? No. A great deal of thought and effort must have gone into drafting the paper to achieve the results he wanted: the discrepancies all led in one direction; misreporting was gross. Moreover, although the scale of the GMC’s 217 day hearing precluded additional charges focused directly on the fraud, the panel found him guilty of dishonesty concerning the study’s admissions criteria, its funding by the Legal Aid Board, and his statements about it afterwards

Sadly despite repeated studies and investigations. Despite the retraction of the original article by the Lancet. Despite the other authors personally retracting the paper we still hear about a “link”. Sadly some high profile individuals continue to perpetrate the fraud (notably the model Jenny McCarthy and most recently the “reporter” Katie Couric).

I saw the posting by Aaron Carroll MD, MS is a Professor of Pediatrics and Assistant Dean for Research Mentoring at Indiana University School of Medicine (the Incidental Economist) last week when he posted this map of the real effects of this in Vaccine Preventable Outbreaks (click on the map button on the left if necessary)

In fact Dan Munro posted his own take on this piece: Big Data Crushes Anti-Vaccination Movement. As he sadly notes

Add a well known celebrity (or two) and the effects can be powerful, long term and hard to refute.

 And ss Dr Carroll notes the impact can be seen in the chart above:

• All of that red, which seems to dominate? It’s measles. It’s even peeking through in the United States, and it’s smothering the United Kingdom.
• If you get rid of the measles, you can start to see mumps. Again, crushing the UK and popping up in the US.
• Both measles and mumps are part of the MMR vaccine.
• Almost all the whooping cough is in the United States.

But the best part of this post is his accompanying video - included below - well worth watching the full 8 minutes

Expertly and accurately put.

Vaccinate your kids….please.

Treatment Creep in Medicine - sucking Decency out of Patients

This recent post on the Atlantic: How CPR Became So Popular reminded me of a piece I wrote some time back - Doctors Die Differently. As I said then:

Its not that doctors don't want to die, its just that they knwo they know enough about modern medicine to know its limits, importantly they have talked about this with their families as they want to be sure that no heroic measures will be used during their last moments in this reality

And the chart demonstrating the big discrepancy between what doctors want in life saving measures vs the general public pretty much said it all

So this piece in the Atlantic took it a step further - tracing the history of CPR from the 1960 at Johns Hopkins where the surgeons had

...successfully resuscitated every one of the first 20 patients they treated, 14 of whom (70 percent) survived without brain damage or other ill effects

But their source patients were not typical (young and mostly healthy) and when you extrapolate that out to an elderly population survival can fall to as low as 0% a variation in the effectiveness when performed in the real world
But it was Hollywood adn the media that pushed these procedures into the general awareness suggesting

...that two-thirds of all (fictional) cardiac arrests portrayed on ER (and other doctor shows) involved young patients who had suffered rare events like drowning or lightning strikes, rather than old people with heart disease (who account for 90 percent of cardiac arrests in real-life settings.....most of these fictional TV patients did well, unlike the vast majority of CPR recipients in real life

Dr Peter Benton was well known as all in life saving heroics



In fairness Hollywood was dramatizing some real life events - and they applied their pixie dust to this as they have to many other things.

But the problem remains and health care professionals need to help their patients understand their disease and make good choices, bearing in mind that heroics and life saving may well be a significant driver as it was for Stephen Jay Gould who was diagnosed with a rare and deadly cancer with a median survival of eight months...but as he said in his essay "The Median Isn't the Message".

this median survival means that one-half of patients die within eight months but the other half live longer. Most important, because the mesothelioma survival curve has a very long “tail,” a few lucky patients will live a lot longer

In his case his experimental treatment may have contributed to his 20 year survival past the original diagnosis...leaving a legacy of hope.

Science, Evidence and Clinical Practice

A recent article on the The Difference between Science and Technology in Birth on the AMA site demonstrates the challenges we still face in getting clicnal practice influenced by science and data. Studies and data may show the path for best clinical practice but as the authors note there are multiple instances of the clinical community - in this case the OBGYN - either knowingly or unknowingly failing to follow the best practices

For deliveries in the US evidence tells us that fetal monitoring in low risk pregnancies has a deleterious effect - yet it remains standard practice in most settings to place external scalp electrodes and intrauterine pressure catheters

Although we still see external continuous fetal monitoring employed in many low-risk pregnancies, “as a routine practice [it] does not decrease neonatal morbidity or mortality compared with intermittent auscultation…. Despite an absence of clinical trial evidence, it is standard practice in most settings to place internal scalp electrodes and intrauterine pressure catheters when there is concern for fetal well-being demonstrated on external monitoring” [3].

 

They list several other standard practices including

• routing episitomy
• Use of Doula's
• Challenges with Epidurals

Reasons for these behaviors are varied but as the authors state:

Many well-intentioned obstetricians still employ technological interventions that are scientifically unsupported or that run counter to the evidence of what is safest for mother and child. They do so not because a well-informed pregnant woman has indicated that her values contradict what is scientifically supported, a situation that might justify a failure to follow the evidence. They do so out of tradition, fear, and the (false) assumption that doing something is usually better than doing nothing

Until we fix these basic issues there seems limited opportunity to implement intelligent medicine and real evidence or science based practices.

 

Five Technologies that will Change the Practice of Medicine

Speech Technology

Speech recognition offers efficiencies today but recent innovations and new technologies will expand the horizon of opportunity with speech technologies that will change the human computer interface, simplifying the interaction and offering new and innovative tools that increase efficiency and safety of healthcare delivery and reduce the administrative burden and decrease costs.

Medical Intelligence in the Cloud

We’re facing a tsunami of patient data. The ability to process and leverage this data at the point of care is gone. Cloud based intelligence, analyzing data content and delivering contextually relevant information in real-time will become essential.


Continuous Mobile Monitoring

Our current perspective of a patient’s healthcare record is comprised of snippets of our total healthcare record (imagine a piece of string as the record – all we get is a very short piece when we visit a doctor/facility). Continuous monitoring (wireless, cloud based and automatically monitored and tracked) changes this and offers more complete view of our health record and more important data that is not just single data points but trends and changes.

Personal Health Management

This is becoming essential as we move from a system that disconnects the purchaser from the payer. It’s as if we were buying a car but someone else was paying with no personal financial consequence – we would all buy Ferrari’s, Porsche etc. As we move away from this model, personal responsibility, personal health management tools and PHR's will become essential, not just for capturing and holding the data, but for helping people interpret and manage their own care. We will all become our own care coordinators for ourselves and our extended family, but will need the tools and solutions to help – these will come in form of PHP and health management tools.

Social Media in Healthcare

If World of Warcraft can engage a generation of young adults and teens to stay online, engaged and spending enormous sums of money, the gaming industry is doing something "right". Applying this to health and getting folks engaged is the next frontier. We have already seen that just giving a patient access to their medical record and putting a definitive Diagnosis of obesity has a positive impact on their behavior and general health. Imagine what else you could do with social media and gaming engagement.


But as always - don't forget the patient. As I have noted before Doctor Please Look at Me not Your EMR

This was amplified in a recent article in JAMA: A Piece Of My Mind (JAMA. 2012;307(23):2497-2498. doi:10.1001/jama.2012.4946) that included this drawing from a 7year old girl:

Evidence Based Medicine, Medical Malpractice and Incentives

A recent Dustin Comic like all good comics hit the proverbial nail on the head



Unfortunately the healthcare reform fails to address key aspects to the incentive problem in healthcare. The system remains centered on measuring what we do for patients rather than the end result.

There are moves by employers and the insurance industry to incentives patients towards healthier behavior. This approach is not without problems as highlighted in this piece in the New England Journal of Medicine "Carrots, Sticks, and Health Care Reform — Problems with Wellness Incentives" where the authors highlight the challenges for employers, employees and insurance in creating incentive and how this can introduce inequities that do more harm than good. As they point out

If people could lose weight, stop smoking, or reduce cholesterol simply by deciding to do so, the analogy might be appropriate. But in that case, few would have had weight, smoking, or cholesterol problems in the first place

There is no doubt that patient incentives must be part of the solution but require thoughtful design and implementation to avoid the pitfalls

Incentives for healthy behavior may be part of an effective national response to risk factors for chronic disease. Wrongly implemented, however, they can introduce substantial inequity into the health insurance system. It is a problem if the people who are less likely to benefit from the programs are those who may need them more.

But incentives aligned to the practice of evidence based medicine and in particular the financial challenges facing the ever increasing ordering of tests is where there seems to be significant progress. The announcement of a statewide adoption of Radport by the Institute of Clinical Systems Improvement (ICSI), a nonprofit comprising 60 medical groups, 9,000 physicians, and six payers and health plans was covered extensively at RSNA 2010 in Chicago this year and featured in this piece in Information Week "System Helps Doctors Pick The Right Tests" demonstrating a saving of $27 Million over the preceding year

During the yearlong pilot involving more than 2,300 ICSI-member physicians, ICSI saw no growth in the number of high-tech diagnostic imaging tests ordered. In previous years, the number of tests ordered grew about 8% annually...The lack of growth translates to a savings about $28 million for the year

But any discussion on incentives needs to include the issue of malpractice - liability drives behavior in the same way as incentives do (in some respects its incentive in another from). Peter Orszag opinion in the NY Times Malpractice Methodology makes the point that

The health care legislation that Congress enacted earlier this year, contrary to much of today’s overheated rhetoric, does many things right. But it does almost nothing to reform medical malpractice laws. Lawmakers missed an important opportunity to shield from malpractice liability any doctors who followed evidence-based guidelines in treating their patients.

President Obama weighed in on this issue in June 2009 when he spoke to the American Medical Association when he highlighted the "unnecessary tests and treatments (ordered by doctors) only because they believe it will protect them from a lawsuit" and as he put it

We need to explore a range of ideas about how to put patient safety first, let doctors focus on practicing medicine and encourage broader use of evidence-based guidelines

Medicine remains "more evidence-free" than should be the case:

One estimate suggests that it takes 17 years on average to incorporate new research findings into widespread practice

Addressing the issue of liability can take the traditional approach of limiting punitive damages but as Peter Orszag said "provide safe harbor for doctors who follow evidence-based guidelines" is a much better idea and one that would sit well with patients and doctors alike (I'd be interested to hear from lawyers who agree or disagree on the merits of such an approach).

There are some initial moves in this direction and a need to implement technology to help guide the treatment (as we see with ICSI) and all this would also lead to higher quality of care for everyone and possibly a new system that reimbursed based on the quality of care delivered versus the quantity of care.

Radiology Examinations - How Much is Too Much

As is often the cases conflicting information in the media on the benefits of screen, x-rays and healthcare.
This piece in the NY Times: CT Scans Cut Lung Cancer Deaths, Study Finds suggests that annual CT Scans of current and former smokers reduces the risk of death form lung cancer:

Annual CT scans of current and former heavy smokers reduced their risk of death from lung cancer by 20 percent, a huge government-financed study has found. Even more surprising, the scans seem to reduce the risks of death from other causes as well, suggesting that the scans could be catching other illnesses.

And while there does seem to be some benefit as Dr Patz (professor of radiology at Duke who helped devise the study) put it:

he was far from convinced that a thorough analysis would show that widespread CT screening would prove beneficial in preventing most lung cancer deaths. Dr. Patz said that the biology of lung cancer has long suggested that the size of cancerous lung tumors tells little about the stage of the disease. “If we look at this study carefully, we may suggest that there is some benefit in high-risk individuals, but I’m not there yet,” Dr. Patz said.

And before you run out the door to get your CT scan its worth taking note of Dr Ben Goldacre's insightful blog Bad Science that takes a hard look at the science behind claims and does a great job debunking the myths and taking a hard look at statistics. But as we have seen over the last few months there is an increasing focus on excessive use of imaging technologies. Earlier this year the Imaging e-Ordering Coalition (Co Chaired by our very own Scott Cowsill) Successfully made a case to congress to include computer-based physician order entry (CPOE) solutions as a potential method for imaging utilization management in recently passed health care legislation:

the Coalition is making several recommendations to policy makers in Congress and CMS...One of the recommendations is that imaging CPOE tools should be based on consensus medical guidelines and literature, such as the ACR's appropriateness criteria. Another recommendation is that CPOE and decision support tools should be compatible with any CMS-approved electronic medical record (EMR) systems and be able to track results.

In recent news the Healthcare alliance aims to improve the imaging process, Changing the Game the coalition continues to push for

E-Ordering, also referred to as clinical decision support (CDS) (to) provide(s) physicians with real-time, electronic access to pre-exam, case-by-case decisions linked to evidence-based clinical guidelines and tailored to a patient’s specific circumstances

and cites a 7-year study at MGH (pub 2009) that showed a dramatic decrease in the growth rates of several imaging exams

• CT exams down from 12% growth to 1%
• MR exams down from 12% dropped to 7%
• Ultrasound down from 9% to 4%

So with that in mind the concurrent news that Minnesota’s Institute for Clinical Systems Improvement (ICSI) is spearheading the First Statewide Effort to Help Ensure Patients Receive Appropriate High-Tech Diagnostic Imaging Tests that is targeted to save Minnesota healthcare community more than $28 million annually (this was the savings estimated from the year long pilot with 2,300 physicians from five Minnesota medical groups, five health plans taking part. You can read more about it here, and here in the Star Tribune in Minneapolis St Paul and here on ZDNet

The process and challenges are outlined in this video:



Showing how you can help the busy clinician by providing them with a simple, intelligent and above all standardized appropriateness criteria to guide the clinician in ordering the most appropriate study for the patient at the time of consultation. This improved patient satisfaction, clinic efficiencies and reduced administrative costs. While there will be those who distrust technology over seeing clinical decision making the solution does not force or prevent clinicians from ordering the test they deem the most appropriate. What it does do is provide evidence based guidance on the suitability or clinical appropriateness of the test.

How do you feel as a patient or as a clinician on technology guiding care choices? Like it or not expect to see more as we continue to cope with a veritable Tsunami of clinical data, studies and discoveries that by some estimates require a doctor to read for 70 hours per week just to keep up in their one speciality.

NLP in Healthcare

Along the lines of Deep Blue IBM is breaking new ground with its latest research innovation "Watson" focused no Natural Language Processing applied in this instance to the well known television game of Jeopardy. Take a look at the video that features the Super Computer Watson pitted against contestants in a real game of Jeopardy. The only accommodation for the "silicon based" life form was providing the questions as text rather than requiring the additional step of speech recognition

Certainly impressive and looking like a real leap forward even with errors occurring. This is of course a enormous task for any computer but even to achieve success in certain instances is extremely impressive and very exciting. Here we are 13 years on from Deep Blue's famous feat of beating Gary Kasparov at chess. The New York Times featured this in the magazine over the weekend: Insert Title. As they point out this is approaching the innovation we have seen on Star Trek

The computer on Star Trek is a question-answering machine, it understands what you’re asking and provides just the right chunk of response that you needed. When is the computer going to get to a point where the computer knows how to talk to you?

Well it seems we stepped a lot closer to the Hollywood vision that's been in place since 1963. In fact I have been making this point for a number of years. We have been fooled into believing Speech Recognition achieved much more than recognizing words. In fact Spock's original interaction with the computer in 1963

Computer, compute to the last digit the value of pi" -- Spock (Wolf in the Fold)

Was asking for much more than just speech recognition but included comprehension and then actions based on that comprehension
Over time we have seen many instances but the challenge of comprehension is brought home in Star Trek IV - The Voyage Home when Scotty discovers that speaking to a computer and expecting it to understand was beyond the capabilities:
As we see (even in Hollywood) computers continue to struggle with complexity in language (Direction Unclear):
But with Watson's success in what is a good analogy of the complexity of human language we are approaching the point of genuine interaction with technology and as some of the contestants intimated:

Several made references to Skynet, the computer system in the “Terminator” movies that achieves consciousness and decides humanity should be destroyed. “My husband and I talked about what my role in this was,” Samantha Boardman, a graduate student, told me jokingly. “Was I the thing that was going to help the A.I. become aware of itself?”

I think we are still a ways away from this but with the change in approach as opposed to trying to teach computers all the variations of data and linkage allowing the system to "learn" by feeding in data and creating algorithms that link data statistically for future inference.

Much like the challenge in medicine Watson applies extensive knowledge that has been previously analyzed and stored and importantly applies multiple algorithms to come up with a stack rank of answers. In fact in the of all the predictive systems available ones that take multiple predictions form different sources and then takes the most frequent tend to be the most accurate

Watson’s speed allows it to try thousands of ways of simultaneously tackling a “Jeopardy!” clue. Most question-answering systems rely on a handful of algorithms, but Ferrucci decided this was why those systems do not work very well: no single algorithm can simulate the human ability to parse language and facts. Instead, Watson uses more than a hundred algorithms at the same time to analyze a question in different ways, generating hundreds of possible solutions. Another set of algorithms ranks these answers according to plausibility; for example, if dozens of algorithms working in different directions all arrive at the same answer, it’s more likely to be the right one. In essence, Watson thinks in probabilities. It produces not one single “right” answer, but an enormous number of possibilities, then ranks them by assessing how likely each one is to answer the question.

Thinking about this system and its application to medicine we are stepping increasingly closer to analysis of multiple inputs of signs, symptoms and subsequently examination and laboratory testing and imaging. A number of years ago I saw a similar solution in very basic form that analyzed inputs as they arrived and started to produce a short list for differential diagnosis. The limitations at the time related to computing power and inputs but and to some degree the capture of knowledge in a form that could then be used. Watson turns this process on its head providing a means to input knowledge in large quantities that can then be analyzed, cataloged and then applied. There remains the question of what is valid information that can and should be accepted but even with this problem processing the rapidly expanding knowledge base automatically provides a means to help clinicians who today do not have the time to process all the moves/adds/changes to the clinical corpus of knowledge:

The problem right now is the procedures, the new procedures, the new medicines, the new capability is being generated faster than physicians can absorb on the front lines and it can be deployed

I don't see call centers being the route of interaction but much more likely as an adjunct tool providing guidance and short lists to the clinicians at the point of care of differential diagnosis and what steps (what additional history, examination or investigation) can help rule out or confirm the various choices. This may not be a patient level tool but as an adjunct to clinical knowledge is likely to offer significant support to clinical care and help improve the diagnosis and treatment of patients.

Combine this with a speech recognition tool that accurately renders the clinical data and you have some level of real time evidence based medicine that will revolutionize healthcare. DoctorNet will become self aware....very soon.