Modern healthcare is sick, but Dr. Daniel Kraft knows a little something about the cure. At the 2011 TEDMED conference in San Diego, the stem cell researcher gave a great overview on the emerging trends which are poised to play a big role in how medicine develops in the decades ahead. Mobile platforms, 24 hour at home monitoring, artificial intelligence, social networking, massive data collection, crowd-sourcing – Kraft expounds upon them all with his characteristic charm and humor. He even explains how lessons learned from aviation (checklists, simulations, heads-up displays) could help transform healthcare. With $2.4 trillion spent on medicine in the United States alone, there’s a huge incentive to make the industry faster, smarter, and more efficient. Kraft’s TEDMED presentation is a great guide to how humanity can make that happen. Don’t miss it below:

If you find yourself wanting to learn even more check out Dr. Kraft’s recent Q&A with Singularity Hub. Or think about attending the exciting FutureMed Executive Program at Singularity University in February, headed by Kraft and featuring some amazing innovators in the field of medicine.

[screen capture and video credit: TEDMED]

Hi, I'm Watson. Let's talk about your latest medical claim, shall we?

Ever feel like the people reviewing your claims at the insurance company are a bunch of faceless, mindless drones? Well it turns out your paranoid cynicism is coming true – congratulations! In a historic step towards modernizing healthcare, insurance giant WellPoint is teaming up with IBM so that the Watson AI can help their staff make informed decisions. The amount of medical literature is staggering – doubling in size about every five years. No human can possibly hope to keep up. Watson, however, is able to process 200 million pages of content in just three seconds. In early 2012, some WellPoint nurses will be able to access Watson to assist them in reviewing patient cases and treatment requests. Later, WellPoint expects to roll out the service to a few oncology practices and eventually this technology could be helping medical professionals all over the world. Taste a bit of this AI-fueled medical utopia in the video from IBM below. While many will undoubtedly lament the “dehumanizing” nature of AI in healthcare, Watson represents one of the great hopes in this field. With unparalleled abilities to understand human writing in huge amounts at high speeds, Watson can place the entire global history of medical literature in the hands of your doctor. Faceless and cold? Perhaps. But better and smarter as well.

As we discussed when Watson was poised to take on Jeopardy! champions earlier this year, the IBM system is a wonder when it comes to understanding natural human language. That’s not an easy skill for a computer, yet Watson is able to process billions of documents to find correlations between key words and concepts. This allowed the AI to win at Jeopardy! and it also allows it to recommend the best solutions to medical problems by searching through records and finding the most likely causes for ailments. Early tests with Watson have shown it to process complex symptoms, recognize possible causes with uncanny range and accuracy, and suggest treatments that impress the doctors working with the AI. The big goal of Watson in medicine is to give every medical professional access to the system, not to replace human decision making but to improve upon it by keeping humans informed. Here’s a brief video from IBM that highlights that vision:

WellPoint is one of the largest insurance groups in the US (the largest by some counts) with one in nine Americans participating. They have 34 million+ members and 70+ million when counting subsidiaries. Their agreement with IBM is historic not because it’s the first time AI is being applied to medical databases (it’s not, this has been done before) but because of the scale of the company and Watson’s superior understanding of human language. Early next year when Watson is made available to WellPoint personnel it will be used to sort through patient charts, medical records, WellPoint’s history of treatments, and IBM’s library of medical textbooks and journals so that the computer can synthesize treatment recommendations using all of these sources. We’re talking about millions upon millions of documents reviewed in just seconds. Nurses will take Watson’s recommendations as guidance, but conflicts in claims (your doctor wants to give you Drug X but Watson recommends Drug Y) will still be settled by human reviewers.

From there, WellPoint expects to roll out the medical version of Watson to oncology practices to assist in complex treatment plans. No word yet on the time it will take for that application to come online, nor how long WellPoint and IBM will stay at that level before moving on towards more general uses of the technology.

Eventually, however, I think we’ll see Watson, or its successor, commonly used in all areas of the medical industry from patient interviews to ER visits to insurance claim lawsuits. WellPoint expects the nurses in the opening trial will be able to access Watson from desktop computers or even mobile devices, and I foresee a future where tablet computers (or smart phones) serve as easy to use portals to Watson medical solutions calculated in the cloud. That means that not only will Watson-like technology be available to all levels of medical professionals but it will be available almost anywhere.

Consider that possibility for a moment. Every doctor (or nurse, or claim adjuster, etc) would have access to the world’s collection of medical expertise at their fingertips. And, because Watson not only makes recommendations but also cites the sources it used to make its decisions, your medical provider could quickly perform their own research to verify or expand upon Watson’s suggestions. This technology may turn every doctor into a super doctor. If we could make it freely accessible via smart phones it could also turn even untrained humans into passable medical assistants. These are world-changing possibilities.

And they come with world-sized risks. While I’m not a pessimist, there are clear avenues for abuse or failure. What if insurance companies (or governments, or whoever) got to decide that some treatments were too costly, and kept Watson from suggesting them? What if medical professionals became so trusting of Watson that an error in the AI would be accepted as medical fact and cause misdiagnoses of patients? What if Watson (or its successor) had no real competition, making an entire industry reliant upon a single system, and again allowing an error to be propagated to millions across the world?

WellPoint (and IBM) have assured the public (1,2) that they only intend Watson to be an objective assistant, and that it won’t take financial cost-benefit into account. Likewise, they have openly stated that Watson is here to augment human judgement, not replace it. Yet the fact that these companies must come out and assuage our fears about these risks reinforces the fact that such possibilities do exist.

That doesn’t mean we should let our fears keep us from adopting Watson on a large scale in the medical industry, but we should go into this with open eyes. AI could be one of the most powerful and transformative tools in world healthcare.  It is overwhelming a positive trend, and we need to support it and grow it as much possible. But, while this technology is still young, we should be very vocal about how we, as patients and human medical professionals, want it to be developed. One way or another medical AIs are going to revolutionize the industry. If WellPoint, IBM, and the public work together we can ensure that the revolution leaves us with a much healthier world.

[image and video credit: IBM]
[sources: WellPoint press release, IBM]

Warn your stylist: robots are ready to take over the hair salon.

I remember back in the 1980s, water was like a scifi robot’s kryptonite. Now, if you splash a bot it’ll probably just assume you want it to give you a shampoo. At the recent International Home Care and Rehabilitation Exhibition 2010 (HCR 2010), Panasonic unveiled two new technologies to help healthcare workers tending the sick and elderly. The first was a robot washstand that will automatically clean a patient’s hair from start to finish. The device uses sixteen ‘fingers’ to gently massage the scalp. It has a 3D scanner so that it can use the correct pressure and comes with memory so that it can recall the preferences of each individual. Panasonic also demonstrated their new Roboticbed, which is actually both a bed and wheelchair. The device transforms from one shape to the other, minimizing the risk that a patient will fall or be dropped moving from bed to chair. Both devices are aimed at giving healthcare workers more free time to focus on health rather than mundane tasks. Watch the Panasonic presentations at HCR 2010 in the videos below. The shampooing robot looks pretty amazing – I wonder if it’s taking appointments?

Another video showing a close up of the shampooing process:

We’ve already seen various robotic lifting devices from Panasonic aimed at medical applications, including a wheelchair-bed transformer. This new version’s pneumatic manual controls are a good addition, giving healthcare workers more flexibility in how the platform can be used. It’s hard to hear in the following video, but the bed also makes an audible announcement (using a simulated voice) as well as flashing LED lights when the wheelchair is fully docked back into the bed station.

The world population is getting older, and an increasing share of our economy will need to be focused on tending to elderly populations in the decades ahead. Japan is particularly concerned with this trend, and unsurprisingly has focused on robotics as the solution. I’m curious, however, as to how well these systems will be accepted by the elder population at large. Will they simply be yet another series of mechanisms, like motorized wheelchairs and automatic doors, that are adopted easily? Or will the increased capabilities of robots require patient’s to make a leap of faith? Beds that transform into wheelchairs are actually fairly mundane, even if they are motorized. Putting your head in a sink and having your hair washed by a machine – that’s different enough to give someone pause. And it’s probably only a matter of time before a more elaborate system could be built to provide a full shower. Robotic Elder Care Washers …try not to remind Grandma that you use a similar machine to clean the family car.

[image credit: Panasonic]
[video credits: K. Moriyama]
[source: Panasonic Press Release]

A new gripper could be a key ingredient in iRobot's entry into elderly care.

Colin Angle’s presentation at TEDMED this past year has me wondering about the future of home healthcare. According to the CEO of iRobot, makers of the Roomba vacuuum, robots are the solution to extending the time in which the elderly can live independently in their own homes. Robots could allow caregivers to monitor patients from afar, they could remind people to take their medications on time, lift simple objects, or even transport heavy items. I totally agree with Angle’s assessment, but I’m not sure he does a good job of pitching iRobot as the company to make these solutions happen. Check out Angle’s TEDMED presentation in the video below and judge for yourself. Does it seem like iRobot is close to putting medical bots in our homes?

iRobot created a whole new unit of their company to deal with medical applications. When I first heard about Angle’s aspirations for home care robots I was picturing something more advanced. Certainly the compliant manipulator Angle demos around 14:22 in the video is cool but we’ve already seen the ‘jammable material’ in action before with their BlobBot prototype. Most of the rest of Angle’s talk seems just that – talk. We hear a lot about the necessity of robots in the home, and he shows how iRobot platforms like the SugV (at 10:50) and Warrior (16:35) could be remodeled for caregiver applications, but he doesn’t show a finished product, or even a truly innovative prototype. Compare this with the healthcare robots we’ve seen from Panasonic. Sure, those are still in the early phases of development, but they already seem more polished and applicable than what Angle demonstrates.

I have a lot respect for iRobot. They created and conquered the robot vacuum market. They’ve used that success to fuel some great research and create a host of other robots that most consumers probably don’t know about. Angle and his team have taken huge steps towards making robots a beneficial part of our daily lives.

However, they’ve fallen behind in the vacuum market (see our review on next generation of vacuum-bot, the XV-11 from Neato). And now when I watch Angle’s presentation on medical bots I feel very disappointed. This is what you bring to TEDMED? A few seconds of robot demos that we could have already seen years ago, and a brief look at an interesting new gripper? That’s totally lame. Admittedly Angle’s approach to the topic is emotional and moving, and this presentation is a year old, but I still expect better. I think the crowd at TEDMED did too.

Elder care is going to be huge in upcoming decades. It seems undeniable that we will spend larger portions of our economic and social might tackling that problem. Robots are a way of mediating the effect of the boom in the number of elderly, and could provide meaningful improvements in quality of life to our aging loved ones. But it’s going to take a lot of innovation to make robotics ready for that task. iRobot is a good robotics company, but I think they’re progress is trailing their vision. We need better robots, and soon.

[screen capture and video credit: TEDMED]
[source: TEDMED, iRobot Press Release]

Venter, Collins grace the Time cover, July 3, 2000

“It is fair to say that the Human Genome Project has not yet directly affected the health care of most individuals.” – Francis Collins, April 2010, Nature.

What’s in a genome?  Ten years ago, the completion of the Human Genome Project promised to usher in a whole new era of heath care.  Revolutionary gene therapies would soon conquer everything from cancer and heart disease to diabetes and autoimmunity.  A roll-call of our genes would unlock the causes (and the solutions) to death and disease.  But a decade on, most of these hopes have failed to materialize, and most of our lives haven’t changed.  So where’s the revolution?

A recent retrospective in Nature includes some sobering reviews by such genetic gurus as Craig Venter and Francis Collins.  Sure, there have been some significant gains.  In vitro genetic screening has greatly reduced the risk of many common genetic diseases at the pre-birth stage.  Risk factors for a range of adult diseases (including cancer) are coming into focus, and a host of new drugs have been developed.  But as scientists expected to find common genetic determinants underlying common diseases, they quickly discovered that the genome was anything but straightforward.  Instead, the genes behind disease have been shown to be highly complex and individually variable, even for widespread disorders.  There isn’t a SNP for cancer.

The problem is that currently, the field of genomics is data-rich and application-poor.  Thanks to companies like Complete Genomics, there is a flood of new genetic data and even more on the way – but we still don’t know how it works.  So far, the primary focus of interest (and funding) has been the most easily quantifiable advances, such as sequencing speed and costs.  Accomplishments in this arena have been impressive, but a complementary push for clinical applications is needed to sort through all of this genomic data that we still don’t understand.

The fate of commercial genetics hangs in the balance.  Companies like deCODE and 23andMe were born on the hope that laypeople might be willing to pay for a glimpse at their own DNA.  The bankruptcy of deCODE and troubling rumors about 23andMe raise the question of whether personal genomics is an industry born premature.  So far, their products feed a curiosity niche, not a utilitarian one.  When a genome points to little more than SNP-based correlations, few people can justify spending their recession-hit income on what remains a biotech novelty.

As Collins, Venter and others have suggested, a health care revolution requires bridging the gap between genomic data and its clinical utility.  Any disappointments of the past decade point to the directions of the next.  We’re learning that so-called “junk DNA” isn’t really junk, but can regulate the expression of other, coding sequences of the genome.  Untangling the various networks of gene regulation will illuminate the pathways which result in a given phenotype, pathological or not.  The roles of epigenetic processes are also undoubtedly complicating factors which will need to be better understood.

Most approaches over the past decade have used SNP chip analysis to identify mutations associated with particular phenotypes.  This type of analysis only looks at small parts of the genome, and has largely failed to identify the genetic determinants of most diseases.  The SNP chip approach will be phased out as whole-genome scans become faster and more affordable (costs should drop below $1000 within the next three years).  Complete Genomics aims to sequence 1 million human genomes within the next five years, and that’s a lot of data to crunch. Venter is calling for two ways of making better sense of this flood of whole-genome scans: more detailed phenotype analyses, and the development of computational tools that can link them to their genetic counterparts.

It’s interesting to note the parallel between difficulties encountered in genomics and neuroscience. Recent years have seen an increasing shift in brain science from localization (areas of the brain that “do” things) towards neural-network approaches.  Just as we’ll unlikely find a single gene that causes cancer, we’re not going to find the “irony zone” of the brain anytime soon.  Reconceptualizing both genomics and the brain as complex, interactive networks remains a necessary step to significant advances in either field (e.g. a health care revolution or AI, respectively). And despite these setbacks, we can expect big things on the way.

Genetics has already revolutionized our health care in certain respects. Preimplantation genetic diagnosis (PGD) has already made huge progress towards eradicating genetic disease before birth, a significant but often overlooked accomplishment. But more lies ahead. Coming decades will see the creation of genetic therapies based around the specific molecular details of a given disorder. Diseases such as pediatric cancer are already the target of multi-year genomic research, and more diseases will benefit from genomic research as costs come down. And as the genetic underpinnings of disease come into focus, personal genetics will also undoubtedly enjoy a second life – regardless of whether today’s companies survive to see it.

We’ve scanned the genome; what remains to be seen is what we can do with it.

Here is a short summary video from Reuters that may be of interest:

Can we trust computer programs with making our medical decisions?

Say hello to the healthcare revolution. Of the technology kind. Most of us don’t realize it, but artificial intelligence has invaded medicine. Smart software is now poised to assist doctors with diagnosing conditions and selecting treatments. And despite economic concerns and misguided assumptions about computer error, the medical field has much to gain by allowing this friendly technological takeover. For a better part of the last century, misdiagnosis has plagued the industry with no improvement. But now, thanks to AI, the future of medicine’s prognosis is a good one.

On the frontline of this new virtual healthcare campaign is the “artificial neural network” (ANN)—a new type of software that uses the combined knowledge of its network connections to help lower patient risk and decrease costs. Fashioned after the biological brain, the software boasts the ability to learn from observed data, upping the ante for making logical decisions and avoiding mistakes. But can we trust computer programs with making our medical decisions? Truth is, we’re doing it already.

In 2009, the Mayo Clinic—a national integrated group practice—used an ANN program to help physicians rule out the need for invasive procedures by accurately diagnosing patients previously thought to have endocarditis—a deadly heart infection. By decreasing expenses and lowering risk (at a confidence level of 99 percent), the clinic’s program clearly demonstrated its worth to patients and doctors alike. The same year, General Electric developed a software program that could suggest treatment options for patients in real time by recognizing patterns of information in data. Software engineering firms like Artificial Intelligence In Medicine, Inc. continue to develop informatics products for the healthcare industry. And in 2007, the Healthways Center for Health Research in Nashville, Tennessee—a company that helps manage the health of millions—was recognized for implementing AI-based computer models that help target members for the center’s healthcare programs. Healthways’ long-term value has since been attributed to reducing healthcare costs.

It was only a matter of time before AI would evolve into high-skilled fields like medicine. In fact, medical AI has been on the drawing board for decades, but usability issues and incompatible terminology and language prevented early software programs from gaining the traction needed to significantly affect the industry. What makes AI and medicine such a good fit is the highly structured reasoning methods they share. But some professionals still don’t trust the idea of computers making health decisions for people, and the prospect of swapping out consciences for motherboards may not sit well ethically. But there’s really nothing to fear. With AI counterparts at their side, doctors may actually serve their patients better.

The problem of misdiagnosis persists. Yet we rarely take action unless it escalates to malpractice. Because doctors lack sufficient incentive to second-guess their instincts, an alarming number of patients are treated for the wrong disease each year; in 2004, misdiagnoses of fatal illnesses were reported to be at 20 percent [nytimes.com]. What’s worse is that the number hasn’t improved in nearly one hundred years. Artificial intelligence is ready to change all of that—a main directive being to successfully assist doctors with diagnosing conditions. Drawing on millions of points of data, smart software can think of things doctors forget. And while human doctors become fatigued, their AI counterparts remain alert 24 hours a day, 7 days a week, even as patient waiting rooms ebb and flow. It’s a logical partnership—one that will allow doctors to concentrate on solving medical problems while their artificial assistants crunch data. X-Prize Foundation’s Chairman and CEO Peter Diamondis is so invested in the idea that he is considering a life sciences prize—one defined with futurist Ray Kurzweil—that would reward the design on an AI physician capable of making decisions better than a board of 10 certified doctors. And as the software’s capabilities increase, so will the potential benefits.

Once programs are taught to recognize symptoms of more common conditions—like pneumonia for instance—their value will become more quantifiable to physicians. The University of Colorado Health Services Center and Denver’s Children’s Hospital used an artificial neural network’s system of classification to screen heart murmurs in children, allowing professionals to identify pathological cases. And The University of Chicago has trained its own artificial neural network to read thoracic computed tomography (CT) images. Assistant Professor of Radiology Dr. Kenji Suzuki developed the massive training artificial neural network (MTANN) in 2001 when he first joined the University. The MTANN employs a new pixel-based approach to ANN technology that has since been used to detect lung nodules in chest radiographs and polyps in CT colonography. Interfacing directly with image data expands the capabilities of artificial neural networks beyond synapse design to mimicking our visual functions as well. “I designed it to act like the human visual system,” Suzuki says. “The pixel-based approach is unique because it looks at images directly, compared to standard neural networks that use image features instead.”

Developing artificial intelligence in medicine may be advantageous, but the rapid spread of medical knowledge does have its potential setbacks. While AI promises to bring even remote healthcare facilities into the fold of progressive medical practice, bad data could be disseminated faster, damaging the integrity of new information as it surfaces in real time. The quality of standardized information could suffer amidst local and global transitions. And there is—understandably—some skepticism surrounding the economic effects of automation that will come with this new wave of technology.

Still, by bringing healthcare facilities together and keeping track of patients and their needs, AI invading medicine is a good thing. In an industry where automation is fast becoming the standard, it’s prudent to remain open to the possibilities. The key here is that these intelligent technologies won’t supplant human expertise. Artificial intelligence will work in league with humans as experienced professionals continue to “train” these programs—at least for the time being.

[image credit: medGadget]
[source: Scientific American, The New York Times]

iRobot is making a healthcare bot, but what will it be?

TEDMED 2009 just passed and with it came some news about the future of robotics and healthcare. iRobot (Nasdaq: IRBT), the company that brought you the Roomba, is set to enter the healthcare business. As discussed in a press release, Colin Angle (iRobot CEO) announced the creation of a robot (or robots) that will help care for the elderly and ill. The details of the robot haven’t been widely announced, and speculation is still running amok. Will the robot be a medication dispenser, an assistant for household chores, or a floating balloon that helps you lift hard to reach objects?

Tod Loofburrow has been hired to head iRobot’s new Healthcare Business Unit. According to press, that division of the company aims to “add a million years of independent living to its customers.” That goal would seem to sync well with Angle’s TEDMED talk which was titled “Will A Robot Care for My Mom?” All would seem to point to robots that help patients with difficult or important tasks in place of more costly human assistants. So, while we could have seen iRobot try to mimic some of the recently discussed healthcare bots from Panasonic, BotJunkie reported that the robot demonstrated at TEDMED was an airborne vacuum that could help you pick up objects or hold them in place. Until iRobot or TEDMED releases the video of Angle’s presentation, we’ll just have to wait and see. Needless to say, as soon as we know something, you will too.