Category Archives: technology

cool, quantified self, technology

Baby cry analytics

Unearthing powerful meaning from something as tedious and mind-numbing as a baby’s cry… nifty!

 

Source: http://www.springwise.com/early-health-diagnoses-single-baby-cry/

Early health diagnoses from a single baby cry

Brown University scientists have developed a baby crying analysis system that can help diagnose illnesses from the acoustic quality of the cry alone.alttext

United States 19th December 2013 in Health & Wellbeing.
When a baby cries, it’s usually because they need something — whether that’s breast-feeding, changing, burping or simply attention. But according to researchers at Brown University, babies cries also contain extra information that indicates the state of their health. The scientists have now developed a baby crying analysis system that can help diagnose illnesses from the acoustic quality of the cry alone.A collaboration between the university and the Women & Infants Hospital in Rhode Island, the research showed that a range of different conditions manifest themselves acoustically in the cry of babies, although the difference is imperceptible to human ears. Its digital platform takes recordings of cries, splits them into small 12.5-millisecond clips before analyzing them for any of 80 flags that may indicate anything from neurological problems or developmental disorders. The flags in each clip are then averaged out over the duration of a single cry to determine which ones are most pertinent. Harvey Silverman, professor of engineering and director of Brown’s Laboratory for Engineering Man/Machine Systems: “It’s a comprehensive tool for getting as much important stuff out of a baby cry that we can.” The idea is that the system could detect early signs of disorders such as autism, which typically aren’t apparent until the child is older.

Although the researchers don’t currently have a plan in mind to bring the system to market, it’s easy to see how an app could be developed. Could other kinds of health information be gleaned from unusual sources such as this?

Website: www.brown.edu
Contact: kevin_stacey@brown.edu

Spotted by Murtaza Patel, written by Springwise

complex adaptive systems, cool, data saving lives, healthcare, healthy habits, policy, politics, quantified self, rapid learning health systems, research methodology, technology

Hammerbacher, Sinai and Minerva…

Top piece on Sinai’s vision. Everything’s lined up there except the doctors – hmmm…. They’ll need some amazing insights to bust through the inertia, but expect they’ll glean them…

http://www.fastcoexist.com/3022050/futurist-forum/in-the-hospital-of-the-future-big-data-is-one-of-your-doctors

In The Hospital Of The Future, Big Data Is One Of Your Doctors

December 5, 2013 | 7:30 AM

From our genomes to Jawbones, the amount of data about health is exploding. Bringing on top Silicon Valley talent, one NYC hospital is preparing for a future where it can analyze and predict its patients’ health needs–and maybe change our understanding of disease.

The office of Jeff Hammerbacher at Mount Sinai’s Icahn School of Medicine sits in the middle of one of the most stark economic divides in the nation. To Hammerbacher’s south are New York City’s posh Upper East Side townhouses. To the north, the barrios of East Harlem.

What’s below is most interesting: Minerva, a humming supercomputer installed last year that’s named after the Roman goddess of wisdom and medicine.

It’s rare to find a supercomputer in a hospital, even a major research center and medical school like Mount Sinai. But it’s also rare to find people like Hammerbacher, a sort of human supercomputer who is best known for launching Facebook’s data science teamand, later, co-founding Cloudera, a top Silicon Valley “big data” software company where he is chief scientist today. After moving to New York this year to dive into a new role as a researcher at Sinai’s medical school, he is setting up a second powerful computing cluster based on Cloudera’s software (it’s called Demeter) and building tools to better store, process, mine, and build data models. “They generate a pretty good amount of data,” he says of the hospital’s existing electronic medical record system and its data warehouse that stored 300 million new “events” last year. “But I would say they are only scratching the surface.”

Could there actually be three types of Type 2 diabetes? A look at the health data of 30,000 volunteers hints that we know less than we realize. Credit: Li Li, Mount Sinai Icahn School of Medicine, and Ayasdi

Combined, the circumstances make for one of the most interesting experiments happening in hospitals right now–one that gives a peek into the future of health care in a world where the amount of data about our own health, from our genomes to ourJawbone tracking devices, is exploding.

“What we’re trying to build is a learning health care system,” says Joel Dudley, director of biomedical informatics for the medical school. “We first need to collect the data on a large population of people and connect that to outcomes.”

To imagine what the hospital of the future could look like at Mount Sinai, picture how companies like Netflix and Amazon and even Facebook work today. These companies gather data about their users, and then run that data through predictive models and recommendation systems they’ve developed–usually taking into account a person’s past history, maybe his or her history in other places on the web, and the history of “similar” users–to make a best guess about the future–to suggest what a person wants to buy or see, or what advertisement might entice them.

Through real-time data mining on a large scale–on massive computers like Minerva–hospitals could eventually operate in similar ways, both to improve health outcomes for individual patients who enter Mount Sinai’s doors as well as to make new discoveries about how to diagnose, treat, and prevent diseases at a broader, public health scale. “It’s almost like the Hadron Collider approach,” Dudley says. “Let’s throw in everything we think we know about biology and let’s just look at the raw measurements of how these things are moving within a large population. Eventually the data will tell us how biology is wired up.”

Dudley glances at his screen to show the very early inklings of this vision of what “big data” brought to the world of health care and medical research could mean.

On it (see the figure above) is a visualization of the health data of 30,000 Sinai patients who have volunteered to share their information with researchers. He points out, in color, three separate clusters of the people who have Type 2 diabetes. What we’re looking at could be an entirely new notion of a highly scrutinized disease. “Why this is interesting is we could really be looking at Type 2, Type 3, and Type 4 diabetes,” says Dudley. “Right now, we have very coarse definitions of disease which are not very data-driven.” (Patients on the map are grouped by how closely related their health data is, based on clinical readings like blood sugar and cholesterol.)

From this map and others like it, Dudley might be able to pinpoint genes that are unique to diabetes patients in the different clusters, giving new ways to understand how our genes and environments are linked to disease, symptoms, and treatments. In another configuration of the map, Dudley shows how racial and ethnic genetic differences may define different patterns of a disease like diabetes–and ultimately, require different treatments.

These are just a handful of small examples of what could be done with more data on patients in one location, combined with the power to process it. In the same way Facebook shows the social network, this data set is the clinical network. (The eventual goal is to enroll 100,000 patients in what’s called the BioMe platform to explore the possibilities in having access to massive amounts of data.) “There’s nothing like that right now–where we have a sort of predictive modeling engine that’s built into a health care system,” Dudley says. “Those methods exist. The technology exists, and why we’re not using that for health care right now is kind of crazy.”

While Sinai’s goal is to use these methods to bring about more personalized diagnoses and treatments for a wide variety of diseases, such as cancer or diabetes, and improve patient care in the hospital, there are basic challenges that need to be overcome in order to making this vision achievable.

Almost every web company was born swimming in easily harvested and mined data about users, but in health care, the struggle has for a long time been more simple: get health records digitized and keep them private, but make them available to individual doctors, insurers, billing departments, and patients when they need them. There’s not even a hospital’s version of a search engine for all its data yet, says Hammerbacher, and in the state the slow-moving world of health care is in today, making predictions that would prevent disease could be just the icing on the cake. “Simply centralizing the data and making it easily available to a broad base of researchers and clinicians will be a powerful tool for developing new models that help us understand and treat disease,” he says.

Sinai is starting to put some of these ideas into clinical practice at the hospital. For example, in a hint of more personalized medicine that could come one day, the FDA is beginning to issue labels for some medicines that dictate different doses for patients who have a specific genetic variant (or perhaps explain that they should avoid the medicine altogether). The “Clipmerge” software that the hospital is beginning to now use makes it easier for doctors to quickly search and be notified of these kinds of potential interactions on an electronic medical record form.

On the prediction side, the hospital has already implemented a predictive model called PACT into its electronic medical record system. It is used to predict the likelihood that a discharged patient will come back to the hospital within 90 days (the new health care law creates financial incentives for hospitals to reduce their 90-day readmission rate). Based on the prediction, a high-risk patient at the medical center now might actually receive different care, such as being assigned post-care coordinator.

Eventually, there will be new kinds of data that can be put in mineable formats and linked to electronic patient records, from patient satisfaction surveys and doctors’ clinical notes to imaging data from MRI scans, Dudley says.

Right now, for example, the growing volumes of data generated from people’s fitness and health trackers is interesting on the surface, but it’s hard to glean anything meaningful for individuals. But when the data from thousands of people are mined for signals and links to health outcomes, Dudley says, it’s likely to prove valuable in understanding new ways to prevent disease or detect it at the earliest signs.

A major limitation to this vision is the hospital’s access to all of these new kinds of data. There are strict federal laws that govern patient privacy, which can make doctors loathe to experiment with ways to gather it or unleash it. And there are many hoops today to transferring patient data from one hospital or doctor to another, let alone from all the fitness trackers floating around. If patients start demanding more control over their own health data and voluntarily provide it to doctors, as Dudley believes patients will start to do, privacy could become a concern in ways people don’t expect or foresee today–just as it has on the Internet.

One thing is clear: As the health care system comes under pressure to cut costs and implement more preventative care, these ideas will become more relevant. Says Dudley: “A lot of people do research on computers, but I think what we’re hoping for is that we’re going to build a health care system where complex models … are firing on an almost day-to-day basis. As patients are getting information about them put in the electronic medical record system there will be this engine in the background.”

 

JESSICA LEBER

cool, musings, technology

Service presses loved ones’ ashes as a playable vinyl record

Say no more…

http://www.springwise.com/service-presses-loved-ones-ashes-playable-vinyl-record/

Service presses loved ones’ ashes as a playable vinyl record

The UK’s And Vinyly is enabling the recently departed to have their ashes pressed as a vinyl record.

alttext

United Kingdom 6th December 2013 in Weird of the Week.
This is part of a new series of articles that looks at some of the most bizarre and niche business ideas we see here at Springwise.

Remembering loved ones is a highly personal experience, and placing ashes into an urn can be too traditional for some. The first of our Weird of the Week series focused on Holy Smokes, a service that puts ashes into bullets. Now the UK’s And Vinyly is enabling the recently departed to have their ashes pressed as a vinyl record.

Founded by Jason Leach, who also runs a number of record labels such as Subhead, Daftwerk and Death to Vinyl, the service allows anyone to have a loved one’s ashes pressed as a working record, where it can be accompanied by music, the sound of their voice or simply left blank — allowing the pops and clicks to provide an audio representation of the ashes. The ashes are placed onto the raw piece of vinyl before it gets pressed, enabling the ashes to be compressed into the material. Each record comes with personalized artwork — either a simple name and date of birth and death, or a portrait by artist James Hague, who creates his images using ashes mixed into the paint. The GBP 2,000 package gets customers 30 discs with the sounds of their choice, or they can also have a Daftwerk artist record a song about the deceased.

While some may feel uncomfortable handling the ashes of their loved ones, others may cherish the opportunity to connect with them after they die through a very personal artifact. What other unusual ways are there to commemorate the dead?

Website: www.andvinyly.com

Spotted by Denise Kuperman, written by Springwise

entrepreneurship, file note, healthcare, healthy habits, policy, rapid learning health systems, research methodology, technology

Healthy life years is the key selling proposition for funding NCD interventions…

Non-communicable disease presents an as-yet, unresolved health research challenge. But they may also lie at the heart of a similarly unresolved intergenerational, macroeconomic challenge.

To date, governments and academics around the world have sat back and carefully observed the epidemic of overweight, obesity, metabolic syndrome and diabetes overtake their communities.

The food industry has aggressively defended its turf, understandably resisting any calls for regulation in the absence of definitive evidence that these interventions will work.

Only the most courageous of politicians would ever embark on the regulation of such a powerful sector in the absence of evidence supporting efforts such as restricting advertising to children, mandating processed food composition, food labeling and taxing macronutrients know to be harmful.

So we find ourselves at an impasse that no one seems particularly able to break.

An emerging theme related to this issue is the idea that while the health system has succeeded in delivering extended life, it has not yet extended healthy life years. As such, the population still shudders at the thought of raising the retirement age past 70, even though average life expectancy now surpasses 80.

Non-communicable disease is considered a major driver of this divergence. As such, preventing non-communicable disease may represent an important challenge, not only driven by a health/moral imperative, but also for important economic reasons.

There are significant macroeconomic consequences of people not living most of their lives in a productive state of health. Most significant of these is the capacity of societies to sustain pensions when boomer-driven demographic shifts result in an increasing ratio of pensioners to tax payers.

This places life insurers, governments and superannuation funds into the medium- to long-term frame as key beneficiaries of addressing non-communicable disease.

This in turn makes them key targets for attracting investment capital to a venture addressing this concern.

Imagine a world where people lived healthy, vital, productive lives well into the 70s.

Too much?

Google have spotted this opportunity by investing $100Ms in a new start up called the California Life Company (CaLiCo). Its initial focus is on “ageing” with an early emphasis on genomics, epigenetics and a pharmaceutical fix.

I starting to think the answer is much simpler: Eat food, not too much, mainly plants. Move.

It’s about less, not more.

Establishing the evidence for this inkling, and then commercialising the insights gained is the inspiration behind Riot Health.

Stand by.

complex adaptive systems, cool, musings, nutrition, policy, politics, technology

I have no idea, I just write…

Punchy interview with Bill Gates’ favourite author. Alignment on food. Other things interesting, but unrelated.

http://www.wired.com/wiredscience/2013/11/vaclav-smil-wired/?mbid=synd_gfdn_bgtw

This Is the Man Bill Gates Thinks You Absolutely Should Be Reading

Author Vaclav Smil tackles the big problems facing America and the world.   Andreas Laszlo Konrath“There is no author whose books I look forward to more than Vaclav Smil,” Bill Gates wrote this summer. That’s quite an endorsement—and it gave a jolt of fame to Smil, a professor emeritus of environment and geography at the University of Manitoba. In a world of specialized intellectuals, Smil is an ambitious and astonishing polymath who swings for fences. His nearly three dozen books have analyzed the world’s biggest challenges—the future of energy, food production, and manufacturing—with nuance and detail. They’re among the most data-heavy books you’ll find, with a remarkable way of framing basic facts. (Sample nugget: Humans will consume 17 percent of what the biosphere produces this year.)His conclusions are often bleak. He argues, for instance, that the demise of US manufacturing dooms the country not just intellectually but creatively, because innovation is tied to the process of making things. (And, unfortunately, he has the figures to back that up.) WIRED got Smil’s take on the problems facing America and the world.

You’ve written over 30 books and published three this year alone. How do you do it?

Hemingway knew the secret. I mean, he was a lush and a bad man in many ways, but he knew the secret. You get up and, first thing in the morning, you do your 500 words. Do it every day and you’ve got a book in eight or nine months.

What draws you to such big, all-encompassing subjects?

I saw how the university life goes, both in Europe and then in the US. I was at Penn State, and I was just aghast, because everyone was what I call drillers of deeper wells. These academics sit at the bottom of a deep well and they look up and see a sliver of the sky. They know everything about that little sliver of sky and nothing else. I scan all my horizons.

Let’s talk about manufacturing. You say a country that stops doing mass manufacturing falls apart. Why?

In every society, manufacturing builds the lower middle class. If you give up manufacturing, you end up with haves and have-nots and you get social polarization. The whole lower middle class sinks.

You also say that manufacturing is crucial to innovation.

Most innovation is not done by research institutes and national laboratories. It comes from manufacturing—from companies that want to extend their product reach, improve their costs, increase their returns. What’s very important is in-house research. Innovation usually arises from somebody taking a product already in production and making it better: better glass, better aluminum, a better chip. Innovation always starts with a product.

Look at LCD screens. Most of the advances are coming from big industrial conglomerates in Korea like Samsung or LG. The only good thing in the US is Gorilla Glass, because it’s Corning, and Corning spends $700 million a year on research.

American companies do still innovate, though. They just outsource the manufacturing. What’s wrong with that?

Look at the crown jewel of Boeing now, the 787 Dreamliner. The plane had so many problems—it was like three years late. And why? Because large parts of it were subcontracted around the world. The 787 is not a plane made in the USA; it’s a plane assembled in the USA. They subcontracted composite materials to Italians and batteries to the Japanese, and the batteries started to burn in-flight. The quality control is not there.

Bill Gates’ actual bookshelf. We count six books by Smil in this section alone.   Ian Allen

Can IT jobs replace the lost manufacturing jobs?

No, of course not. These are totally fungible jobs. You could hire people in Russia or Malaysia—and that’s what companies are doing.

Restoring manufacturing would mean training Americans again to build things.

Only two countries have done this well: Germany and Switzerland. They’ve both maintained strong manufacturing sectors and they share a key thing: Kids go into apprentice programs at age 14 or 15. You spend a few years, depending on the skill, and you can make BMWs. And because you started young and learned from the older people, your products can’t be matched in quality. This is where it all starts.

You claim Apple could assemble the iPhone in the US and still make a huge profit.

It’s no secret! Apple has tremendous profit margins. They could easily do everything at home. The iPhone isn’t manufactured in China—it’s assembled in China from parts made in the US, Germany, Japan, Malaysia, South Korea, and so on. The cost there isn’t labor. But laborers must be sufficiently dedicated and skilled to sit on their ass for eight hours and solder little pieces together so they fit perfectly.

But Apple is supposed to be a giant innovator.

Apple! Boy, what a story. No taxes paid, everything made abroad—yet everyone worships them. This new iPhone, there’s nothing new in it. Just a golden color. What the hell, right? When people start playing with color, you know they’re played out.

Let’s talk about energy. You say alternative energy can’t scale. Is there no role for renewables?

I like renewables, but they move slowly. There’s an inherent inertia, a slowness in energy transitions. It would be easier if we were still consuming 66,615 kilowatt-hours per capita, as in 1950. But in 1950 few people had air-conditioning. We’re a society that demands electricity 24/7. This is very difficult with sun and wind.

Look at Germany, where they heavily subsidize renewable energy. When there’s no wind or sun, they boost up their old coal-fired power plants. The result: Germany has massively increased coal imports from the US, and German greenhouse gas emissions have been increasing, from 917 million metric tons in 2011 to 931 million in 2012, because they’re burning American coal. It’s totally zany!

What about nuclear?

The Chinese are building it, the Indians are building it, the Russians have some intention to build. But as you know, the US is not. The last big power plant was ordered in 1974. Germany is out, Italy has vowed never to build one, and even France is delaying new construction. Is it a nice thought that the future of nuclear energy is now in the hands of North Korea, Pakistan, India, and Iran? It’s a depressing thought, isn’t it?

The basic problem was that we rushed into nuclear power. We took Hyman Rickover’s reactor for submarines and pushed it so America would beat Russia. And that’s just the wrong reactor. It was done too fast with too little forethought.

You call this Moore’s curse—the idea that if we’re innovative enough, everything can have yearly efficiency gains.

It’s a categorical mistake. You just cannot increase the efficiency of power plants like that. You have your combustion machines—the best one in the lab now is about 40 percent efficient. In the field they’re about 15 or 20 percent efficient. Well, you can’t quintuple it, because that would be 100 percent efficient. Impossible, right? There are limits. It’s not a microchip.

The same thing is true in agriculture. You cannot increase the efficiency of photosynthesis. We improve the performance of farms by irrigating them and fertilizing them to provide all these nutrients. But we cannot keep on doubling the yield every two years. Moore’s law doesn’t apply to plants.

So what’s left? Making products more energy-efficient?

Innovation is making products more energy-efficient — but then we consume so many more products that there’s been no absolute dematerialization of anything. We still consume more steel, more aluminum, more glass, and so on. As long as we’re on this endless material cycle, this merry-go-round, well, technical innovation cannot keep pace.

Yikes. So all we’ve got left is reducing consumption. But who’s going to do that?

My wife and I did. We downscaled our house. It took me two years to find a subdivision where they’d let me build a custom house smaller than 2,000 square feet. And I’ll test you: What is the simplest way to make your house super-efficient?

Insulation!

Right. I have 50 percent more insulation in my walls. It adds very little to the cost. And you insulate your basement from the outside—I have about 20 inches of Styrofoam on the outside of that concrete wall. We were the first people building on our cul-de-sac, so I saw all the other houses after us—much bigger, 3,500 square feet. None of them were built properly. I pay in a year for electricity what they pay in January. You can have a super-efficient house; you can have a super-efficient car, a little Honda Civic, 40 miles per gallon.

Your other big subject is food. You’re a pretty grim thinker, but this is your most optimistic area. You actually think we can feed a planet of 10 billion people—if we eat less meat and waste less food.

We pour all this energy into growing corn and soybeans, and then we put all that into rearing animals while feeding them antibiotics. And then we throw away 40 percent of the food we produce.

Meat eaters don’t like me because I call for moderation, and vegetarians don’t like me because I say there’s nothing wrong with eating meat. It’s part of our evolutionary heritage! Meat has helped to make us what we are. Meat helps to make our big brains. The problem is with eating 200 pounds of meat per capita per year. Eating hamburgers every day. And steak.

You know, you take some chicken breast, cut it up into little cubes, and make a Chinese stew—three people can eat one chicken breast. When you cut meat into little pieces, as they do in India, China, and Malaysia, all you need to eat is maybe like 40 pounds a year.

So finally, some good news from you!

Except for antibiotic resistance, which is terrible. Some countries that grow lots of pork, like Denmark and the Netherlands, are either eliminating antibiotics or reducing them. We have to do that. Otherwise we’ll create such antibiotic resistance, it will be just terrible.

So the answers are not technological but political: better economic policies, better education, better trade policies.

Right. Today, as you know, everything is “innovation.” We have problems, and people are looking for fairy-tale solutions—innovation like manna from heaven falling on the Israelites and saving them from the desert. It’s like, “Let’s not reform the education system, the tax system. Let’s not improve our dysfunctional government. Just wait for this innovation manna from a little group of people in Silicon Valley, preferably of Indian origin.”

You people at WIRED—you’re the guilty ones! You support these people, you write about them, you elevate them onto the cover! You really messed it up. I tell you, you pushed this on the American public, right? And people believe it now.

Bill Gates reads you a lot. Who are you writing for?

I have no idea. I just write.

data saving lives, healthy habits, nutrition, quantified self, rapid learning health systems, research methodology, technology

SMS provides for an effective weight loss intervention

 

Source: http://www.fiercemobilehealthcare.com/story/study-texting-effective-intervention-tool-weight-control/2013-11-21?utm_medium=nl&utm_source=internal

Citation: http://www.jmir.org/2013/11/e244/

Study: Texting effective intervention tool for weight control

November 21, 2013 | By 

Daily text messaging may be a useful self-monitoring tool for weight control, particularly among racial/ethnic minority populations most in need of intervention, according to Duke University study results published in a Journal of Medical Internet Research article.

“Recent studies show that racial/ethnic minorities are more likely than white individuals to own mobile phones,” states the article. “The high familiarity with and penetration of mobile technologies makes text messaging an ideal intervention platform among these populations.”

The purpose of the randomized controlled pilot study was to evaluate the feasibility of a text messaging intervention for weight loss among predominantly black women, who “have alarmingly high rates of obesity as compared with other gender and racial/ethnic groups.” The secondary aim of the study was to evaluate the effects of the intervention on weight change relative to an education control arm.

Fifty obese women aged 25-50 years were randomized to either a six-month intervention using a fully automated system that included daily text messages for self-monitoring tailored behavioral goals (e.g., 10,000 steps per day, no sugary drinks) along with brief feedback and tips (26 women) or to an education control arm (24 women). The article states that weight was objectively measured at baseline and at six months, while adherence was defined as the proportion of text messages received in response to self-monitoring prompts.

At six months, the article reports that the intervention arm lost a mean of 1.27 kg, and the control arm gained a mean of 1.14 kg. The average daily text messaging adherence rate was 49 percent with 85 percent texting self-monitored behavioral goals two or more days per week. Moreover, about 70 percent strongly agreed that daily texting was easy and helpful and 76 percent felt the frequency of texting was appropriate.

“Given that the majority of evidence indicates that greater adherence leads to better outcomes, our study suggests that mHealth-based approaches to self-monitoring may enhance engagement and reduce the burdens commonly associated with other modes,” concluded the article. “Our intervention was relatively low intensity and has greater potential for dissemination compared to higher intensity interventions. As technology penetration increases in the target population, the use of this modality will become increasingly relevant and helpful as an intervention tool for weight control.”

Earlier this year, an article published in the Journal of American Medical Informatics Association revealed that mobile app self-monitoring of physical activity and dietary intake among overweight adults participating in a weight loss program are more effective than traditional methods. The study involved a post hoc analysis of a six-month randomized weight loss trial among 96 overweight men and women, which found that physical activity app users self-monitored exercise more frequently over the six-month study and reported greater intentional physical activity than non-app users.

To learn more:
– read the article in JMIR

data saving lives, facts & data points, healthcare, rapid learning health systems, technology

IBM Watson in Healthcare

What makes you sick?

Chronic health conditions impact the lives of billions of people around the world each year.

Chronic illness accounts for approximately 60% of deaths globally each year.

World population: 6.8 billion. 2 billion people worldwide struggle with chronic illnesses like cancer, heart disease and diabetes.

Early and accurate diagnosis has the potential to improve patient success rates, but it can be difficult to establish.

Medical knowledge is growing more quickly than doctors can keep up with.

In the U.S. alone, up to 15% of medical diagnoses are inaccurate or incomplete.

Digitized medicine in North America alone will grow 400% by 2015 —reaching a total of 14,000 terabytes of data, or 7,500 times the data in all U.S. libraries combined.

To give physicians better insight to help improve patient outcomes, WellPoint is pioneering the use of DeepQA technology—otherwise known as IBM Watson—in healthcare.

Imagine a patient describing her symptoms to a physician who has immediate access to Watson through his laptop.

  1. Based on the symptoms described, Watson provides probabilities for five possible diagnoses.
  2. Watson then considers explicitly absent symptoms to reassess these probabilities.
  3. Correlating the symptoms with family and patient histories, Watson is able to refine the hypotheses further.
  4. The process is repeated with a focus on the patient’s current medications.
  5. Final probabilities are determined, and the physician moves on to testing.

Every patient represents a wide spectrum of variables.

Symptoms

  • Fever
  • Dizziness
  • Abdominal pain
  • Back pain
  • Cough

Family history

  • Diabetes
  • Breast cancer
  • Colorectal cancer
  • Coagulation disorders
  • Grave’s Disease

Patient history

  • Hypertension
  • Hyperlipidemia
  • Hypothyroidism
  • Frequent urinary tract infection
  • Smoking

Clinical findings

  • Blood pressure
  • Heart rate
  • Restoration rate
  • Temperature
  • Pain score

Medications

  • Pravastatin
  • – Lasix
  • Aspirin
  • Chemotherapy
  • Antiemetics

Watson: An expert diagnostic system

This groundbreaking system can pore though the equivalent of 200 million pages of medical data and formulate a response in less than 3 seconds, enabling healthcare professionals to make more informed decisions more quickly than ever before.

Natural language processing – Breaks down the communication barrier between humans and computers.

Hypothesis generation – Offers various probabilities rather than attempting a single “right” answer.

Adaptation and learning – Builds knowledge iteratively over time, in much the same way that humans learn.

Correlated patient information

Possible conditions

  • Renal failure
  • UTI
  • Influenza
  • Esophagitis
  • Diabetes
  • Stage 1 lung cancer

WellPoint is using Watson to help physicians become better at what they do — delivering improved care more quickly and confidently than ever before. The potential of Watson doesn’t end there. The same capabilities hold enormous promise for financial services, transportation and more.

data saving lives, entrepreneurship, healthcare, healthy habits, nutrition, policy, politics, rapid learning health systems, research methodology, technology

Katz slam dunks….

  • Used the Harvard Nurses Health Study to develop an algorithm for food healthiness as determined by health outcomes from the study – a GPS for nutrition – CLEVER!
  • Offered to do this with Government in the early 2000s but was knocked back
  • Developed a proprietary algorithm called ONQI, owned by NuVal
  • Choosing higher scoring foods correlates with a lower risk of dying prematurely.
  • “The very government agencies that regulate the food supply are extensively entangled with the entities producing our food, from farm to factory. In comparison, we mere eaters of food have very little clout. The government may be just a little too conflicted on the topic of food to be in the business of putting the truth, the whole truth and nothing but the truth on at-a-glance display.
    Certainly the big food manufacturers, the makers of glow-in-the-dark snackattackables, should NOT be in the business of nutrition guidance whatever their inclination. That approach makes the fox look like a highly qualified security officer for the henhouse.
    Which leaves independent nutrition, and public health experts and private sector innovation. And here we are.
    Private-sector innovation often involves intellectual property, trade secrets and patent applications. It involves some entity making an investment and wanting a return. That is all true of NuVal, for better or worse. It wasn’t my plan – it was just the only way to get this empowering system into the hands of shoppers. Of note, the ONQI remains under the independent control of scientists, and not the business.”
  • This is a terrific strategy – worthy of emulation.

Source: http://health.usnews.com/health-news/blogs/eat-run/2013/06/11/nutrition-guidance-who-needs-to-know-what

Nutrition Guidance: Who Needs to Know What?

  June 11, 2013 

I am writing today about nutrition guidance and who needs to know what to make it useful.

Permit me to disclose right away that I am the principal inventor of the Overall Nutritional Quality Index (ONQI) algorithm, used in NuVal – a nutritional guidance system that stratifies foods from 1 to 100 on the basis of overall nutritional quality: the higher the number, the more nutritious the food. As the Chief Science Officer for NuVal, LLC, I am compensated for my continuous and considerable allocations of time and effort. But it was never supposed to be that way – and the reasons why it is are an important part of this story.

As to why this column now, there are two recent provocations. One is our ongoing work to complete the updated algorithm, ONQI 2.0, and the window that provides into a world of weirder foods than I ever even considered possible. The other is a paper published in the Journal of the Academy of Nutrition and Dietetics a few months back and a more recent exchange of letters related to that article. The article described the advantageous novelties of a nutritional profiling system, such as weighting nutrients for their health effects rather than counting them all the same. But this was less about novelty, and more about NuVal, since the innovations described have long been included in the ONQI.

[See: Debunking Common Nutrition Myths.]

Claims about alleged novelties that were already included in NuVal prompted a letter from my colleagues and me to the journal, which was published along with a response from the original authors. In that response, they acknowledged that the NuVal system included the so-called “novelties” and acknowledged that the ONQI is, to date, the only nutritional profiling system shown to correlate directly with health outcomes. So the real concern, the letter went on, is that the ONQI algorithm is proprietary and the details are not fully in the public domain.

Which brings us back to why NuVal is a private and proprietary system in the first place and whether or not it matters that certain details of the algorithm – which populate 25 pages or so of computer code written in a language called SAS – are not on a billboard. Why isn’t the ONQI public rather than private, and who really needs to know every detail of the algorithm for it to be useful? (All of the nutrients included in it, and the basic approaches used to generate scores, have been published.)

The ONQI, and NuVal, are a private sector innovation because the public sector said: no thanks. In 2003, I was privileged to be a member of a group of 15 academics invited to Washington, D.C. by then-Secretary of Health Tommy Thompson. A Food and Drug Administration task force had been formed to guide efforts related to the control of rampant obesity and diabetes, and we were a part of that effort. We gathered in a conference room with Secretary Thompson, the FDA Commissioner (Mark McClellan) and others, including the surgeon general and the heads of the National Institutes of Health and the Centers for Disease Control and Prevention.

[See: Why Aren’t Americans Healthier?]

We were each given one three-minute turn to offer up one good idea the FDA and other federal agencies might use to help combat the ominoustrends in diabetes and obesity. I used my turn to describe, in essence, the project that later became the ONQI. I suggested that the secretary might convene a totally independent group of top-notch experts in nutrition and public health, perhaps under the auspices of the Institute of Medicine.

The group should have no political or industry entanglements and should be allowed to work for as long as it took to convert the best available nutrition science and knowledge into a guidance system anyone could understand at a glance. I was thinking, in essence, of the equivalent of GPS for nutrition, so that no one trying to identify a better food in any given category would get lost, confused or misled by Madison Avenue.

[See: 10 Things the Food Industry Doesn’t Want You to Know.]

I waited two years for the feds to do something along these lines. When they didn’t, I decided to undertake the project myself, with the backing of Griffin Hospital in Derby, Conn. – a Yale-affiliated, not-for-profit community hospital, which owns the ONQI algorithm to this day. Other than this being a private rather than federal endeavor, all other aspects of the project were just as proposed to the U.S. Secretary of Health. When we completed the algorithm, I offered it again to the FDA. A scientist at the agency recommended a private-sector approach if I hoped to live long enough to see the system do its intended good.

Why didn’t the feds take on the project? We can all conjecture. I suspect it has something to do with the story Marion Nestle told us all in Food Politics, and the stories we routinely hear about the Farm Bill from the likes of Michael Pollan, Mark Bittman and others. The very government agencies that regulate the food supply are extensively entangled with the entities producing our food, from farm to factory. In comparison, we mere eaters of food have very little clout. The government may be just a little too conflicted on the topic of food to be in the business of putting the truth, the whole truth and nothing but the truth on at-a-glance display.

[See: Seeking a More Perfect Food Supply.]

Certainly the big food manufacturers, the makers of glow-in-the-dark snackattackables, should NOT be in the business of nutrition guidance whatever their inclination. That approach makes the fox look like a highly qualified security officer for the henhouse.

Which leaves independent nutrition, and public health experts and private sector innovation. And here we are.

Private-sector innovation often involves intellectual property, trade secrets and patent applications. It involves some entity making an investment and wanting a return. That is all true of NuVal, for better or worse. It wasn’t my plan – it was just the only way to get this empowering system into the hands of shoppers. Of note, the ONQI remains under the independent control of scientists, and not the business.

[See: Mastering the Art of Food Shopping.]

Which leads us back to the second question: Is it a problem for a system like this to be a private-sector innovation? Who, really, needs to know every detail of such an algorithm?

Consider that if you are shopping for a car, you do need to know if it comes with anti-lock brakes or all-wheel drive. But to decide if these are working for you, you don’t need engineering blueprints; you just need to drive in the snow. When shopping for a smartphone, you may want to know if it has GPS. But you don’t need the trigonometry equations on which the GPS is based to determine if it works; you just have to see if it helps you get where you want to go.

Nutrition guidance in general, and NuVal in particular, are just the same. What are the exact formula details? Who cares. We routinely rely on tools based on math and engineering most of us don’t understand – but we don’t need all that input to know if the tools are working for us. We just need the output. We need to be able to use them. People using NuVal have lost more than 100 pounds, and even over 200 pounds. Choosing higher scoring foods correlates with a lower risk of dying prematurely. More than 100,000 scores are on public display in 1,700 supermarkets nationwide. The ONQI is at least as transparent as any car or smartphone or computer.

[See: The No. 1 Skill for Weight Management.]

Let’s acknowledge: If you are reading this on a computer screen, neither of us truly understands the engineering involved in me writing it, using word processing software, attaching it to an email and sending it to my editor at U.S. News & World Report so she could post it in cyberspace, where you found it. But we do know it worked.

We rely on private-sector innovation for a lot of important jobs, and even many that put our safety on the line. The private sector makes our cars and planes. We seem to be comfortable using these without scrutinizing patent applications. The private sector makes our computers, and smartphones and GPS systems, and we can tell whether or not these work, even if we don’t know how.

Why, then, is nutrition guidance different? The answer, I believe, is politics, profits and the inertia of the status quo. We are accustomed to vague nutrition guidance from conflicted sources, and those same sources are apt to imply there is something wrong with private-sector innovation and the intellectual property issues that come along with it. But if those issues don’t undermine the cars, and planes and navigation systems that get us from city to city and coast to coast, it’s not at all clear why they should be a problem when navigating among choices in a supermarket aisle.

[See: The Government’s MyPlate Celebrates Second Birthday.]

As a scientist, and not a businessperson, my preference would be to put the ONQI on a billboard for all the good it would do. But on this, I must defer to the businesspeople who have made the relevant investments and are entitled to safeguard potential returns. As for the scrutiny that all advanced systems should get, the ONQI has been shared with scientists at leading universities and health agencies around the world – but for private assessment and use rather than public display. Others like them who want to review the program need only ask.

We should all care that the military-industrial establishment seems opposed to putting the blunt truth about nutritional quality, as best we know it, on at-a-glance display. We should care that federal authorities responsible for nutrition guidance are also responsible, if only indirectly, for food politics and supply-side profits. That story may lack novelty. It may be old news. But it is nonetheless something everyone who eats does need to know – engineering blueprints not required.

data saving lives, entrepreneurship, facts & data points, healthcare, quantified self, rapid learning health systems, technology

Medical Body Area Network

  • The FCC has proposed the allocation of spectrum for Medical Body Area Network (MBAN) devices.
  • Deloitte expects the wireless health device market to triple in the next few years

From: http://www.fool.com/investing/general/2013/11/17/3-technologies-that-will-change-the-face-of-medici.aspx#!

3. Wireless body monitoring
We need only to listen to the words of FCC chairman Julius Genachowski to get a feel for the potential for wireless body monitoring. Genachowski noted last year that “a monitored hospital patient has a 48% chance of surviving a cardiac arrest,” compared with only 6% for an unmonitored patient.

With the tremendous opportunity for improving health care in mind, the FCC proposed allocating spectrum for Medical Body Area Network, or MBAN, devices. Such devices will record vital signs and other important physical information through sensors attached to a person’s body, with the data transmitted to a local wireless hub. The information can then be monitored remotely by clinical professionals, with alerts sent to let these experts know when medical intervention could be needed.

GE Healthcare (NYSE: GE  ) is one company already developing MBAN devices. The giant company plans to introduce technology using sensors that monitor heart and breathing rates, temperature, and pulse oximetry within the next few years. Deloitte predicts that the wireless body monitoring market could more than triple in just the next couple of years. Within the next decade, this technology could be key in helping control overall medical costs.

data saving lives, entrepreneurship, quantified self, rapid learning health systems, technology

Extreme baby monitoring

  • baby monitoring doesn’t seem to address anything except parental free floating anxiety
  • no insights have yet been gleaned on baby (or parental) behaviour

Source: http://www.fastcompany.com/3021601/innovation-agents/tracked-since-birth-the-pros-and-cons-of-extreme-baby-monitoring

TRACKED SINCE BIRTH: THE RISE OF EXTREME BABY MONITORING

DOES TRACKING A BABY’S EVERY MOVEMENT, CRY, AND WET DIAPER MEAN HAPPIER PARENTS AND HEALTHIER INFANTS, OR ARE WE TURNING OUR KIDS INTO TAMAGOTCHIS FOR NO REASON?

 
Elle Lucero has been tracked since birth.

For the first 10 months of her life, her mother, Yasmin, kept detailed records of Elle’s sleep patterns, feedings, and diaper changes, noting the data points with a pencil and paper on a clipboard. A few months in, she digitized the logs, graphed the data, and became a more knowledgeable parent.

“It helped me feel confident,” she told Fast Company.

Elle wasn’t a very good sleeper, even for a baby. The pediatrician told Yasmin she needed to let her daughter “cry it out” until she fell asleep, but that never worked. For the sake of her sanity (and sleep), Yasmin took problem solving into her own hands. She wanted answers: Did she put Elle to bed too early? Too late? Give her too many naps? Parsing data, she thought, would help her figure it out. “That was the kind of stuff we were looking for,” she said.

Unfortunately for the Lucero family’s sleeping habits, Yasmin never found a definitive answer. Per the data, Elle was just fussy.

The results suggested Yasmin couldn’t engineer better naps, as she’d hoped. Just knowing that, however, made her feel better. “If you come to the conclusion that you have no control, then it’s okay to relax and just do whatever is convenient for you at the moment,” she explained. (Of course, many parents come to this conclusion at the moment of birth, without all that tedious data tracking.) But for Lucero, a conclusion–any conclusion at all–was all she wanted.

Many new and sleep-deprived parents crave that peace of mind and would kill for a data set that helped them determine if putting little Emma down an hour earlier would mean a restful night for the whole family. But unlike Yasmin, most people aren’t trained statisticians. Tired moms and dads with no mathematical background aren’t about to write down hundreds of data points, and might not know how to analyze that information anyway. Twenty-two months into Elle’s life, even Yasmin has semi-abandoned the project, and keeps much less rigorous records now.

In the imminent future, though, any curious parent with an iPhone will have access to helpful analytics, thanks to the rise of wearable gadgets for babies. Following the success of self-trackers for grown-ups, like Jawbone and Fitbit, companies likeSproutling, Owlet, and Mimo want to quantify your infants.

Mimo Onesie

These devices connect to a baby via boot, anklet, or onesie, and record his or her heart rate, breathing patterns, temperature, body position, as well as the ambient conditions of the room. They aim to replace baby monitors, which give an incomplete picture of a sleeping child. There’s also the nascent “smart diaper” market, led by Pixie Scientific, which scans dirty diapers for signs of infection.

In addition to alerting parents of any concerning findings, these companies encourage a big-data approach to parenting. By gathering information on your kid’s poop, sleep, and eating schedules, the idea goes, you can engineer a happier, healthier baby. The accompanying app for the Sproutling monitor, for example, looks at patterns specific to your child and its environment to offer insights–the kind that Yasmin craved–that might help the child sleep better. It might find that little Jake naps better in complete dark, for example.

The Sproutling monitor

In theory, all this data will lead to more rested, relaxed parents and healthier kids. As of now, parents do a lot of this in the dark. “There’s no owner’s manual,” Sproutling CEO Chris Bruce told Fast Company. His company hopes to change that. “It’s smart technology that helps raise the parenting IQ.”

When Bruce talks about “parenting IQ,” he doesn’t just mean his customers. Sproutling and its cohorts want to use their arsenals of data to better inform research. “The promise of big data is that we can monitor every single environmental parameter and we can find correlations and detect patterns,” added Bruce, calling big data the “holy grail” of his business. Both Owlet and Sproutling indicated that they will offer up their intel–anonymously!–to researchers so that all future parents can better understand babies.

Parents like Yasmin, who haven’t had a full night of sleep in months, are desperate to have that information. She didn’t want to know average sleep patterns–information available in baby books–she wanted bell curves. Yasmin knew her baby wasn’t normal, but she didn’t know how abnormal and her own analyses couldn’t clarify that, either. “I wasn’t finding the exact data I wanted to see,” Yasmin said, after scouring the Internet for answers.

An aggregation of Yasmins, however, can provide those insights. At least that’s the hope.

What sounds like a lot of progress for parenting also means handing a digital record of your baby over to an iPhone app. Are the benefits worth that?

While these apps could improve infant health by telling a parent the exact right nap or changing time, the app in large part benefits parents. Anxious first time moms and dads who worry about every little movement (or non-movement) can monitor their children more closely than ever. “You see your baby lying there and you don’t see them moving,” Bruce, who has two young daughters, said of his experience with old-school video monitors. “You can’t see them breathing; your first thought is: ‘Oh my God, something is wrong.'”

Unlike a basic $35 baby-monitor, the $250 Owlet bootie and accompanying app can alert parents if anything serious has gone wrong, like if a kid stops breathing, or if his heart stops beating. That means no more unnecessary freakouts for the over-protective and inexperienced dad like Bruce, which leaves more time for him to do other dad things.

But, to an extent, these apps take advantage of parent anxieties. “SIDS is the number one cause of infant death. That’s really scary to parents,” Jordan Monroe, a cofounder of Owlet, told Fast Company. Monroe has no kids, but while talking to friends and friends of friends with babies, he found that to be a common worry.

Those fears don’t come from a place of reality, though. According to the Center for Disease Control, 4,000 infants die each year from Sudden Unexpected Infant Death. Only a fraction of those deaths occur because of “accidental suffocation and strangulation in bed,” according to the CDC report. And even SIDS–which causes about 2,000 deaths a year–might stem from underlying brain issues, according to recent research. Monitoring a child’s breathing with a high-tech bootie won’t cure SIDS.

As anyone who has ever had any contact with a hypochondriac knows, those facts don’t really matter. Parents will continue to worry. And, as we saw with Yasmin, certainty has a lot of value. A certain type of parent, like TechCrunch’s Leean Rao, thinks that $250 for Owlet or $200 for Mimo’s version–Sproutling hasn’t yet announced pricing–is a reasonable price to pay to worry about one less thing. In her review of Sproutling, she writes:

As a relatively new parent myself, I would have loved to be able to use some of the data from a wearable to help determine optimal sleep patterns for my child. I’m not sure if it would have helped my daughter sleep through the night earlier in her development, but to me as a fledgling parent, knowledge is power.

Of course, the dollar amount is only a part of the price parents pay with these apps. They give up their children’s data and possibly privacy. “We’re creating the largest data set of infant health data,” Monroe said–a chilling statement in certain contexts. Trackers could turn around and sell their troves to insurers or be forced to hand them over to the government. The information is also vulnerable to hackers.

These companies say they take security issues seriously. “Security encryption has been designed in our system from the get-go,” said Bruce. Anonymous sharing with researchers is both opt-in and anonymous for Sproutling users. But, even Bruce admits that our cultural acceptance of privacy changes every day. What seems innocuous today might feel invasive tomorrow (or vice versa).

Is that risk worth the stated benefits? At this point, it’s not clear these monitors offer many health solutions. The breathing and sleeping alerts will calm (and draw) a lot of parents. But, none of these companies see that as the “holy grail.” The main sell is the tracking. And what does that do for parents and babies?

Arguably, it means finding those little tweaks that make life easier. But, as Yasmin discovered, sometimes babies fuss just because. Numbers don’t always offer solutions, as technical theorist and staunch critic of the self-quantified movement Evgeny Morozov wrote in his book To Save Everything, Click Here: The Folly of Technological Solutionism. “Self-trackers gain too much respect for the numbers and forget that other ways of telling the story–and generating action out of it–are possible.”

While pediatricians typically ask new parents to chart and report feedings and bowel movements for a few weeks after bringing babies home to make sure all systems are go, obsessive tracking beyond that could get in the way of parenting, some doctors say. “Often, when babies have regained their birthweight and are 10-14 days old, I instruct families to dial the tracking down,” Dr. Wendy Sue Swanson wrote on her blog. She adds:

I want new parents to gain confidence and appreciate the homeostasis with following a baby’s natural routine. Relying only on the numbers may cause parents to miss out on the nearly unspeakable experience of parenting a new baby and all that a baby intimately communicates from the beginning. It’s better to look up at the sky to know if it’s raining than to consult the weather report on your iPhone.

After all, do you really want to treat your child like a Tamagotchi?