Category Archives: data saving lives

data saving lives, healthcare, healthy habits, policy, quantified self

Health Miranda: You have the right to keep your health information private, anything you disclose about your health can and will be used against you.

  • The Affordable Care Act now lets employers charge employees different health insurance rates, based on whether they exercise, eat healthful foods and other “wellness” choices they make outside of work.
  • As different phases of the law have taken effect and companies have better understood how to implement it, there basically have been three levels of wellness engagement:
  • Level 1 encourages employees to join a wellness program with exercise and nutrition activities and undergo biometric screenings that check weight, body mass, cholesterol and other health indicators.

    Level 2 trades the carrot for the stick. Employees (and insured family members) who don’t submit to the screening and participate in wellness programs face steep penalties; they may have to pay up to 30 per cent more for their share of health insurance costs.

  • Level 3 in the march towards wellness adopts “outcomes” based programs that can require employees to meet specific fitness goals or pay higher insurance costs.
  • WELLOGRAPH.com looks like an interesting prospect at AUD354

http://www.afr.com/p/technology/wearable_tech_privacy_headed_on_1uDsKFvA5cacLwe6vTKIBN

Wearable tech, privacy on collision course

PUBLISHED: 8 HOURS 48 MINUTES AGO | UPDATE: 4 HOURS 28 MINUTES AGO

Wearable tech, privacy on collision courseThe Zepp Labs wearable sensor on a golf glove … this year’s Consumer Electronics Show was dominated by the next generation of fitness devices. With more advanced sensors and improved hardware.

BRIER DUDLEY

Outrage over NSA spying is nothing compared to how people may react to the upcoming collision with wearable computing, medical privacy and new insurance rules.

You don’t need leaked documents to see it coming, though it took me a while to connect the dots after seeing the bewildering array of new health and fitness-tracking gadgets shown at January’s Consumer Electronics Show.

The show was seen as a turning point for “wearables”, including watches, wristbands, headsets and other gadgets. The most popular wearables monitor physical activity and connect wirelessly to phones, which may then upload the data to online services.

Research firms expect the fitness-wearables category to soar over the next few years, outpacing the growth of smartphones and tablets.

Not everyone wants to have a little computer on the wrist or head keeping track of what a wearer does around the clock. But I wonder if they won’t have much choice in the future, under new insurance laws in the US that invite companies to scrutinise and monitor their employees’ health and fitness.

In the past, medical information was generally none of your employer’s business. It’s still technically private. But the health-care overhaul known as Obamacare is chipping away at this wall.

The Affordable Care Act now lets employers charge employees different health insurance rates, based on whether they exercise, eat healthful foods and other “wellness” choices they make outside of work.

A 2013 survey by Aon Hewitt consulting found that motivating employees to change health behaviours is a “significant focus” over the next three to five years at 69 per cent of employers.

It doesn’t seem like a bad thing because it’s wrapped up in warm and fuzzy doublespeak. This isn’t about saving companies money; it’s about your health. Companies aren’t forcing you to participate, they’re offering rewards. We all want to be healthy, right?

As different phases of the law have taken effect and companies have better understood how to implement it, there basically have been three levels of wellness engagement.

TRACKING HEALTH

 

The first encourages employees to join a wellness program with exercise and nutrition activities and undergo biometric screenings that check weight, body mass, cholesterol and other health indicators.

Level 2 trades the carrot for the stick. Employees (and insured family members) who don’t submit to the screening and participate in wellness programs face steep penalties; they may have to pay up to 30 per cent more for their share of health insurance costs.

The law calls this a “reward” for participation. Flip it around and it’s a penalty for not authorising your employer to manage and monitor how you live outside of work.

Better health overall is in everyone’s best interest. But you can’t help but be cynical when it becomes tied to benefit levels, especially in an era of vanishing pensions, flat pay cheques and longer work days.

It’s too early to say whether wellness programs will make a big difference. In the meantime, they can change the workplace dynamic.

By insinuating that individual choices are the driver of health-care costs, they erode the social contract of group plans in which everyone contributes to coverage that takes care of each other and their families in case something happens.

I’m digressing.

Level 3 in the march towards wellness adopts “outcomes” based programs that can require employees to meet specific fitness goals or pay higher insurance costs.

At this point, when body tracking and measurements are used to adjust benefits, it gets harder to maintain the pretence of privacy. Even if individual records are masked, the data will provide enough insight to assess employees’ potential health costs as well as job performance, enabling a new form of discrimination.

Aon Hewitt’s survey said 64 per cent of employers that offer health-care coverage are using data to find cost savings and as they shift towards health-improvement strategies, they’re relying “more on integrated, dynamic data aggregation tools to laser in on the best opportunities for reduction of unnecessary costs”.

TECHNOLOGY ADVANCEMENTS HELP MONITORING

 

Tech companies are ahead of the game. One is Limeade, a hot start-up in Bellevue that last year doubled sales of its software platform, which employers and insurance companies use to encourage and monitor wellness activities. The platform can sync with dozens of fitness-tracking devices and apps.

Last month’s Consumer Electronics Show was dominated by the next generation of fitness devices. With more advanced sensors and improved hardware, they’re building on the success of activity trackers such as the Fitbit and Nike FuelBand that millions of people — including me — already use. Show organisers gave an “innovation award” to the $US320 ($354) Wellograph Watch, which includes a continuous heart-rate monitor, wellness tracker and running watch in a sleek case.

Fitness tracking may become hard to avoid. Intel unveiled sensors at CES that can be embedded into common devices such as earbuds, which then track physical activity. The data can be relayed to a wellness app on a phone and online wellness programs.

Apple also is chasing this opportunity. With the iPhone 5S, it began using a processor with built-in sensors that can be used by fitness apps.

On January 31, word surfaced that Apple had a big meeting with the Food and Drug Administration, apparently to discuss medical apps and perhaps its own version of a health-monitoring watch. This isn’t too surprising. After years of back and forth with tech companies and others, the FDA in September issued guidelines for health-related apps and gadgets, to clarify which will be considered medical devices and require regulatory approval.

I suggest regulators go a step further and issue privacy guidelines for wellness programs, health apps and wearable devices that may share data with insurers and employers. They could be modelled on the Miranda warnings that police use, informing people of their right to avoid self-incrimination under the Fifth Amendment:

“You have the right to keep your health information private, anything you disclose about your health can and will be used against you.”

data saving lives, healthy habits, nutrition, quantified self

Reporter app – self-discovery through data

At least it won’t harm you, physically…

Reporter app, for self-discovery through data

Reporter app, for self-discovery through data

FEBRUARY 13, 2014  |  SELF-SURVEILLANCE

Reporter app

Nicholas Felton, Drew Breunig, and Friends of the Web released Reporter for iPhone. The app—$3.99 on the app store—prompts you with quizzes, such as who you’re with or what you’re doing, sparsely throughout the day to help you collect data about yourself and surroundings. You can also create your own survey questions to collect data on what interests you and use your phone’s existing capabilities to record location, sound levels, weather, and photo counts automatically.

Those who are familiar with Felton’s annual reports will recognize the design of the app, as it has a familiar look and feel, and it works almost how you’d expect an interactive version of his printed reports would. The charts are straightforward. They provide a quick summary of the data you collect.

Photo_Working

But back to the survey collection process. This is the part that interests me most, because as those who have collected data about themselves know, the collection is the hard part and the most important.

When collection is all automatic, it’s easy to forget about and oftentimes we lose context, whereas when collection is all manual, you have to remember to log things and collection grows to be a chore. Reporter is a hybrid between automatic and manual. The automatic part serves as metadata, and the manual portion tries to be as quick and painless as possible (and it is for the most part).

I’ve been using the app for the past week, and it’s actually kind of fun to collect. It takes about as much time as a check-in on Foursquare or a status update on Twitter or Facebook, and all the data stays on your phone or saves to Dropbox, if you like. Export your data as CSV or JSON.

From there, do what you want, because it’s your data. Most people will probably stay inside the app, but the best part is what can be done outside.

Of course, this is still the honeymoon phase of personal data collection, where I want to log everything in the whole wide world. I’ll let you know what it’s like in a month. For now though, the Reporter app is nice.

data saving lives, healthy habits, quantified self

Wrist tracker and diary

Clumsy and cumbersome, but on the right track. Shrink it and make it predictive and then you’ve got something… Apple?

http://www.medgadget.com/2014/02/camntech-receives-fda-clearance-for-wrist-worn-motion-tracker-and-diary.html

CamNtech Receives FDA Clearance for Wrist-Worn Motion Tracker and Diary

by WOUTER STOMP on Feb 12, 2014 • 5:54 pm

MotionWatch 8 CamNtech Receives FDA Clearance for Wrist Worn Motion Tracker and Diary
CamNtech has received FDA approval for two wrist-worn products to monitor patient activity for clinical purposes and in research trials. First is the MotionWatch 8, a small and light-weight waterproof wrist-worn device that uses a digital tri-axial accelerometer to monitor patient activity, similarly to many consumer fitness trackers. Furthermore, it contains a light sensor and activity marker. Data can be transferred to a PC using a USB connection. Accompanying software converts the data into activity plots to quantify the intensity and duration of daily physical activity. Example use cases indicated by CamNtech include as an indicator of a particular lifestyle, to monitor the effects on mobility of a medical condition or efficacy of its treatment, or to identify irregular activity patterns for assessment of sleep quality.

PRO Diary CamNtech Receives FDA Clearance for Wrist Worn Motion Tracker and Diary

The second cleared device is the PRO-Diary, a compact wrist–worn electronic diary which also integrates the same activity monitor as the MotionWatch. The PRO–Diary features an OLED screen along with a touch sensitive slider and two buttons, which enables patients to answer questions at any moment of the day. Questionnaires are uploaded to the device via USB and questions can be asked at given times, random times or can be user initiated. The PRO-Diary has a battery life of two weeks. By being on the patient’s wrist at all times, the PRO–Diary should result in higher levels of compliance than paper based or other electronic alternatives.

Press release: MotionWatch and PRO-Diary gain FDA clearance…

Product pages: MotionWatch 8…; PRO-Diary…

data saving lives, file note, healthcare, policy, politics

Senior Doctors rorting Queensland Health

  • double-billing
  • charging but not present
  • overtime while on holidays

Queensland auditor-general refers some public hospital doctors to CMC over possible fraud

By Melinda Howells

Updated Tue 11 Feb 2014, 7:15pm AEDT

The Crime and Misconduct Commission (CMC) has been asked to investigate whether some senior doctors have defrauded Queensland Health by claiming excess overtime and double-billing.

The auditor-general investigated 88 of the state’s 2,500 Senior Medical Officers.

He found that seven of them did not attend work during their rostered hours for more than 30 days, and that doctors who were on leave were paid $500,000 in overtime.

Health Minister Lawrence Springborg says the evidence gathered warrants further investigation.

Mr Springborg says the report shows systemic failings and ‘double-dipping’ by some doctors in the state’s public hospitals.

“The report highlights gaps in both rostering and attendance processes and treatment and billing practices, which have been open to exploitation,” he said.

He says some doctors were paid overtime while on holidays, turned up late but claimed overtime, or billed patients privately when they had no right of private practice.

“Inadequate oversight and administration, and we’ve had double dipping and we’ve had people that have taken advantage,” he said.

Mr Springborg admits better checks are needed.

“I’m talking here today about a small number of doctors – the majority of people are doing the right thing,” he said.

“Matters are going to be referred to the Crime and Misconduct Commission in Queensland.

“Also there are a number of recommendations which have been made to improve scrutiny and oversight in the system, which will all be implemented and adopted by the Government.”

Report a ‘smokescreen’ amid contract push

Alex Scott from the Together Union says the report comes as the State Government pushes for individual contracts with doctors.

“This Government is trying to use a smokescreen of this auditor-general’s report to completely misrepresent the true state of affairs in relation to the hours of work for doctors, the private practice arrangement for doctors,” he said.

Dr Shaun Rudd from the Australian Medical Association says it is an attack on the profession.

He says only a small percentage of Senior Medical Officers appear to be involved.

“If that’s correct that’s very worrying,” he said.

“However again it’s usually a system problem in the fact they’re probably working somewhere else in the public system, or it’s not been recorded what they’re actually doing.

“The problem with the Queensland Health system has been that it is a system which has been very difficult.

“It’s had its problems as well with the payroll system etcetera.

“The vast majority of doctors in the public system work long and hard.”

The report comes amid a dispute between the State Government and unions about putting senior doctors onto individual work contracts.

data saving lives, healthcare, policy, startup

Rock Health: Treating patients like consumers

White House’s “Consumer Privacy Bill of Rights”

keep your product dialed on:

  • Focused Collection
  • Transparency
  • Access, and
  • Control

http://www.gocovered.com/

http://rockhealth.com/2014/01/why-patients-need-to-be-treated-like-consumers-qa-noah-lang/

Why patients need to be treated like consumers

Sonia Havele 

January 28, 2014

Noahlang

We sat down for a little Q&A with Rock Health entrepreneur and Covered CEO and privacy expert Noah Lang.  You can catch Lang at Rock Health’s CEO Summit next week, where he’ll be diving into privacy issues on his panel, Privacy by Design.

What was your inspiration for Covered?

A year ago, I needed to select a health plan from my wife’s employer options.  There were only 4 choices, and we’re pretty healthy people, so it couldn’t be that hard, right? I searched for our favorite doctors, but had to do it in four different places. I tried to search for some preferred drugs to figure out what they would cost and found it nearly impossible to compare.  In search of an apples-to-apples comparison, I built an excel model to figure out what might happen if I tear my knee up skiing again or one of us needed emergency care, but very quickly realized it takes more data than a single person can wrangle with to find the answer to those questions. And that data is very hard to get.

Everybody told me there were already tools out there to help consumers with their coverage decisions. I tried all of them. None of the tools gave me confidence in my decision or helped me understand the product I was purchasing. In fact, none treated health insurance like a consumer product at all. The average consumer is willing to spend 9 minutes choosing a plan so often ends up taking an “educated guess.” It was clear to me that it was time for a new vocabulary: insurance in the context of the individual.  I set out to ensure consumers can make a logic-driven decision in that amount of time, or less—without picking up the phone, without confusion, and without resorting to educated guesses.

 Why must health transactions become more accessible to consumers?

 Nobody uses the word consumer in healthcare.  It’s a patient, an employee, an insured.  Healthcare companies are focused on the traditional “payers,” not the consumer.  Well, guess who pays the bills at the end of the day?  Us.  We are customers and deserve to be treated like we’re buying expensive, complex products.

Not only does health coverage come in just behind housing and transportation as one of the largest personal investments of the year, it’s the hub-of-the-wheel that impacts every downstream health transaction that a family makes. This is the reality in a world where only 14% of the employed population are able explain the four key concepts of insurance (deductibles, co-pays, co-insurance, and out-of-pocket maximums). When consumers don’t understand their own coverage, they’re not equipped to understand each subsequent transaction in their doctor’s office, the pharmacy, or the hospital.  As a result, we as Americans often under-use, overpay, and remain in a general state of confusion.

255M Americans see a doctor every year. Most have no idea how much they’ll pay.  150M Americans take a drug every month, but only 19% mail-order those drugs to save 30% of costs. Why? Because the matrix of plan “benefits” from our carriers and employers is pure cognitive overload for most of us. I believe in speaking the language of the consumer—not the insurance carriers—so I set out to simplify the experience, ensure product comprehension, and save consumers money.  At Covered, we translate coverage into a language everybody can understand.

 

How has your background in data collection and tracking influenced your approach to Covered?

Prior to founding Covered, I built and sold privacy products at Reputation.com for 5 years.  In the midst of the social media revolution, I witnessed both the underbelly of the personal data trade and the beautiful experiences that can be built when that data is used effectively.

Personalization is not a commonly used word in healthcare. The “payer” focus is traditionally on the population, rather than the individual. I think it can be done a different way, particularly if we want to liberate individuals and families to direct their own health spending. Covered borrows from streamlined consumer experiences in recommendation engines like Netflix and Amazon, and delivers them to health insurance transactions. Users can enjoy personalized experiences by sharing data with us, but we can only succeed so long as we’re honest about what we know about you as a consumer and how we use that information. The value at Covered for the user is explicit: you’re not wasting time starting from scratch filling out an overwhelming form. Covered uses your shared data to make the process easier and provide high-confidence recommendations. Then, we earn your trust for the long run by responding with value every time you share information, never asking for more information than we need at that point in time (“Focused Collection”), and never sharing it with 3rd parties unless you ask us to.

What role does privacy protection play in the digital health space?

 We have to start thinking of it in terms of the consumer perspective on privacy rather than just falling back on HIPAA as our only guide. Consumers stand to benefit from health data collection and analysis with tangible improvements to their health shopping experiences, but each individual must decide if they are comfortable with the trade-off. At Covered, there’s a lot of good we can do with personal health information.  The more a family shares with us the more refined a plan recommendation we can deliver.  But the only way to trump very real privacy fears and execute on our responsibility to protect your data is to design a privacy-centric experiences from the ground up (“Privacy by Design”).

In digital health today there’s an attitude we’ve seen before: collect as much information as you can about this person and there will be some way to monetize it later. The last go-round, many multi-billion dollar brands like Facebook and Experian were tarnished by personal data privacy fiascos in the social revolution.  Let’s make sure this doesn’t happen in the health tech revolution, I’d highly recommend reading the White House’s “Consumer Privacy Bill of Rights” to any consumer health entrepreneurs out there—keep your product dialed on Focused Collection, Transparency, Access, and Control.

—-

Noah Lang is the Founder and CEO of  Covered, Inc., aiming to translate health coverage transactions into simple language. He is a recognized expert in online behavioral tracking, consumer data collection, and digital PII publication, and he sits on the DMA’s Data Governance Advisory Board. Before Covered, Lang was a founding VP of Business Development at Reputation.com and in 2011, he was selected as a “Privacy by Design Amabassador.”

data saving lives, healthcare, healthy habits, quantified self, rapid learning health systems

Apple stalking wearable opportunities

 

http://rockhealth.com/2014/02/five-signs-apple-creating-health-product/

Five signs that Apple is creating a health product

Malay Gandhi
February 03, 2014

Last week, Apple announced record quarterly revenue and earnings and was subsequently rewarded with almost 10% of its stock value being wiped out. Analysts cited anemic growth for the tech giant, and apparent saturation in the high-end smartphone market. Not surprisingly, many investors are wondering whether the category invented by the iPhone was a once in a lifetime opportunity. In fact, smartphones represent an era of computing that has far exceeded the previous era of personal computers in both install base and usage. Apple seems less concerned, perhaps because their eyes are set on the next era of computing—wearables.

Over the past year, Apple has been quietly building up the resources necessary to release a health product of their own. If the past continues to repeat itself, the digital health landscape could see a huge shift as the standard setter works to create a product that consumers love and use. Culminating in a meeting late last year between senior Apple execs and the FDA, here are five signs that a potentially game-changing digital health product is on the horizon.

1. “The whole sensor field is going to explode.” -Apple CEO Tim Cook

Tim Cook has indicated that wearables are an area of intense interest for Apple, labeling it as a “key branch of the tree” for the post-PC world at D11 last year.

2. The M7 coprocessor.

Apple has already released dedicated hardware for tracking health. The M7 coprocessor is included in every iPhone 5s and has been designed specifically to monitor physical activity, using motion data from the phone’s embedded sensors. The chip has been engineered from the ground up to sip power, extending battery life while allowing for high resolution capture of activity data. Leading fitness apps including Moves, Nike+ Move and Fitbit’s MobileTrack feature take advantage of the new hardware.

Shipping this component in the high volume iPhone product category has allowed Apple to bring the M7 to scale much faster than if they had initially released it within a new product category. The company’s relentless focus on integrated hardware and software experience has allowed them to achieve unmatched performance, and battery life is likely to be one of the keys to winning in wearables.

Bonus: With its “secure enclave” in the A7 processor designed for managing fingerprint data, Apple has also proven it can manage biometric data that is intended to be kept highly secure.

3. They’re hiring medical device experts.

  • Ravi Narasimhan, a Stanford PhD with expertise in “biomedical algorithms, data analysis and wireless technologies” and former VP of R&D in Biosensor Technologies at Vital Connect joined Apple in December 2013 (LinkedIn).

  • Nancy Dougherty, who previously worked at digital health sensor startups Proteus and Sano Intelligence, was hired in December (LinkedIn).

  • Michael O’Reilly, the former CMO of Masimo, developers of a pulse oximeter for the iPhone, joined Apple in July (LinkedIn).

  • Dr. Todd Whitehurst, a self-proclaimed “medical device R&D professional” and former VP of Product Development of Senseonics, a developer of glucose sensors, joined Apple 8 months ago as a Director of Hardware Development (LinkedIn).

  • Ueyn Block who was formerly with C8 MediSensors developing “non-invasive measurement of substances in the human body” joined 10 months ago as a Technical Lead for Optical Sensing (LinkedIn).

  • Yuming Liu, who previously worked at O2MedTech and Accuvein, was hired as an Analog Engineer (LinkedIn).

  • Bob Mansfield, Apple’s longtime lead for hardware engineering, was lured out of retirement to develop unspecified “future products.” The New York Times reports that Mansfield has been exploring sensor technologies for health and is directly involved with the future smartwatch project.

4. Intellectual property.

In 2009, Apple filed a patent for a “seamlessly embedded heart rate monitor” and was ultimatelyawarded the patent by the United States Patent and Trademark Office (USPTO) in late 2013. The patent covers the use of embedded sensors to measure a user’s heartbeat, heart rate, or other cardiac signals. The patent further covers locating the leads in accessories, such as headphones (or perhaps a wearable device).Embedded Heart Sensor

Source: USPTO, annotations by Rock Health

Apple has also explored using personal area networks that would cover items such as the “event monitor device” (EMD) that would include an adhesive strip, a processor, a detector, and a communications port. The patent provides an example of monitoring an individual’s heart rate for events over a threshold (e.g., 180 beats per minute). While such a device sounds familiar to iRhytm’s Zio patch, the patent suggests Apple is looking more broadly into the development of an ecosystem of products that would be anchored by a single wearable platform device (likely wrist-worn), and augmented through various hardware sensors that could live in, on, or around the body and communicate with the primary device.

EMD Heart Rate Monitor Patch

Source: USPTO, annotations by Rock Health

Most recently, Patently Apple has uncovered a patent application for a medical app that can monitor physiological data (e.g., arrhythmias), and either store it on a device like an iPhone and/or transmit the data to health facilities via a communication network. The patent was filed by Naeem Ansari, who was also behind a recent financial system patent that was ultimately assigned to Apple.

5.  Check-in with the Food and Drug Administration (FDA).

Senior Apple executives met with FDA leadership, including the Director of the Agency’s Center for Devices and Radiological Health, which has oversight of medical devices, and Bakul Patel, the author of the FDA’s guidance on mobile medical applications. Patel’s guidance indicates that any mobile technologies which are intended for use in the diagnosis of a medical condition, or in the cure, mitigation or treatment of one will be regulated as medical devices.

cool, data saving lives, healthy habits, quantified self, rapid learning health systems

Twitter can tell when you’re depressed

  • Eric Horwitz leading the way on mining twitter feeds for signs of depression
  • He muses on looking at the impact of news on mood at a population level
  • Conway’s team is looking at some of the tough ethical questions involved, by “investigating public attitudes towards the ethics of using social media for public health monitoring,” he says. “This ethical component of the work is particularly important given the evolving role of social media in society and concerns regarding the activities of the NSA.”

http://business.time.com/2014/01/27/how-twitter-knows-when-youre-depressed/

How Twitter Knows When You’re Depressed

Scientists can now accurately predict if you have the blues—just by looking at your Twitter feed

FRANCE-TECHNOLOGY-BLOGGING-TWITTER-FEATURE
AFP/Getty Images / AFP/Getty Images

With its 230 million regular users, Twitter has become such a broad stream of personal expression that researchers are beginning to use it as a tool to dig into public health problems. Believe it or not, a scientist out there might actually care about the sandwich you ate for lunch—even if most of your followers don’t.

“Our attitude is that Twitter is the largest observational study of human behavior we’ve ever known, and we’re working very hard to take advantage of it,” explains Tyler McCormick of the Center for Statistics and the Social Sciences at the University of Washington.

What if, for example, an artificial intelligence model could scan your Twitter feed and tell you if you’re at risk for depression? And what if you could receive notices from third parties, for instance, that warned you that you may want to seek help, just based on an automated scan of your tweets? Eric Horvitz, co-director of Microsoft Research Redmond has helped pioneer research on Twitter and depression. He says that could one day be a possibility.

“We wondered if we could actually build measures that might be able to detect if someone is severely depressed, just in publicly posted media. What are people telling the world in public spaces?” asks Horvitz. “You might imagine tools that could make people aware of a swing in mood, even before they can feel it themselves.”

Horvitz and a team of researchers helped develop a model that can scan tweets and predict depression in Twitter users, with an accuracy they claim to be 70%. Researchers say the system is still far from perfect. When the model scans your tweets, it misses some signals and doesn’t diagnose many people—about 30%—who really will get depression. And the system has a “false positive” issue, Horvitz said, causing it to incorrectly predict that healthy Twitter users will get depression in about 10% of cases.

The Microsoft team found 476 Twitter users, 171 of whom were seriously depressed. They went back into users’ Twitter histories as far as a year in advance of their depression diagnosis, examining their tweets for language, level of engagement, mentions of certain medications, and other factors, using computer models to sift through a total of 2.2 million tweets. By comparing depressed Twitter users’ feeds with the non-depressed user sample class, they came up with a method for predicting depression diagnoses before they happened. When they tested the model on a different set of Twitter users, it showed 70% accuracy in predicting depression before its onset.

Some tweets the scientists looked at in the depressed group pretty obviously indicate some level of emotional distress. For example, the study cited tweets like these from their depressed user group:

“Having a job again makes me happy. Less time to be depressed and eat all day while watching sad movies.”

“I want someone to hold me and be there for me when I’m sad.”

“‘Are you okay?’ Yes… I understand that I am upset and hopeless and nothing can help me… I’m okay… but I am not all right.”

Not all users’ feeds are so clear. Microsoft’s researchers looked at factors like the number of tweets users made per day, what time of day users tweeted, how often users interacted with each other, and what kind of language tweeters were using. For example, seemingly depressed tweeters were more likely to post messages late at night (between 9pm and 6am) compared with healthy tweeters, who were most active during the day and after work hours.

The team also noticed that certain isolated words in Twitter posts also were characteristic of depression. Words like anxiety, severe, appetite, suicidal, nausea, drowsiness, fatigue, nervousness, addictive, attacks, episodes, andsleep were used by depressed users, but more surprisingly, words like she, him, girl, game, men, home, fun, house, favorite, wants, tolerance, cope, amazing, love, care, songs, and movie could be indications of depression as well.

The volume of tweets mattered too, as did the percentage of exchanges—users who are depressed begin to tweet less, and tweet less at other people, indicating a possible loss of social connectedness, said Horvitz. Of course, just because a Twitter user makes a post that includes the word fatigue and house at 4am, that doesn’t mean they’re depressed. The Microsoft team’s classifier looked at users’ feeds over long periods of time and incorporated many factors. A second Microsoft study that focused more on broader populations using slightly different methods achieved similar results, determining depression in tweets with around 70% accuracy.

One area of public health where this kind of research could come in handy is in measuring public reactions to events. Tracking public Twitter feeds after profound or traumatic events could help scientists understand how we’re affected by the news. “We really didn’t used to have many tools available traditionally for that kind of fine-grained analysis,” says said Horvitz. “Now there’s a new direction for doing the science.”

McCormick, of the University of Washington, said part of the research he and his team is now doing will involve improving earlier Twitter depression models, by weeding out false or misleading data and figuring out areas where depression-related data is being underreported. His team has also identified a group of first-year students at a number of colleges across the country based on their Twitter feeds—hashtags, posts relating to orientation—and is following them for “red flags” that could indicate emotional issues.

A study by University of California San Diego will also build on that research. Funded by the federal government’s National Institute of Health, UCSD’s Michael Conway is creating models that will eventually track depression in communities and figure out how to apply mental health resources better assess public health. “The ultimate goal of this work is to provide a cost-effective, real-time means of monitoring the prevalence of depression in the general population,” Conway said in an email.

In a post-Snowden era, privacy is a major concern facing any kind of mass-data collection. The Twitter users in the Microsoft study permitted Horvitz and his team to examine their tweets, but a possible future in which computer programs  automatically sift through your tweets to make judgments on your health could understandably set off alarms with big data skeptics.

Conway’s team is looking at some of the tough ethical questions involved, by “investigating public attitudes towards the ethics of using social media for public health monitoring,” he says. “This ethical component of the work is particularly important given the evolving role of social media in society and concerns regarding the activities of the NSA.”

It may be some time before the research is developed enough for Twitter to warn individuals at risk for depression to seek help. Horvitz says part of what’s driven his research is the staggering number of suicides in the United States every year due to depression: 30,000. “If we can even save through interventions a few of those 30,000 people each year, it will make this research well worth it,” he said.

data saving lives, entrepreneurship, healthcare, policy, rapid learning health systems

US pricing transparency initiatives…

It looks like they’re moving in the right direction in the US… 11 states have established pricing databases already, but I’d be surprised if they’d incorporated sophisticated visualisation/prediction tools like I+PLUS.

Washington State Officials Want To Lift Veil On Health Care Pricing

TOPICS: STATES, HEALTH COSTS

By Lisa Stiffler, The Seattle Times

FEB 05, 2014

This story was produced in collaboration with 

What if you had a headache that wouldn’t go away? At the area’s top trauma center, a brain MRI will cost more than $4,600, while an imaging center on the Eastside will charge $900.

Need your tonsils out? A Kirkland nasal-and-sinus clinic will charge you $2,200, but the surgery will be nearly $7,000 at a Seattle hospital. Which would you choose?

A prime objective of the Affordable Care Act is to bring down America’s health-care costs, which are the highest per person in the world. But how can the U.S. shrink its medical bills if patients are almost always buying health care with no idea what it costs?

Washington has been able to do little to shed light on health-care costs, and the state last year earned an “F ” for its cost-transparency laws, according to groups promoting health-care reform.

That soon could change.

Gov. Jay Inslee and some state lawmakers are pushing for new rules that would create a database listing hundreds of medical procedures, what they will cost at clinics and hospitals statewide, and information about the quality of the medical providers.

“We made a decision with the Affordable Care Act to use competition to control costs,” said Bob Crittenden, Inslee’s senior health-policy adviser. “Competition requires a number of things. You need enough information to make decisions, and we don’t have that right now.”

The proposal has backing from many big players in medicine and business, but the support is not universal. The state’s largest insurance companies — Regence Blue Shield and Premera Blue Cross — oppose requirements to share the treatment prices they’ve privately negotiated with clinics and hospitals.

There’s also the challenge of pairing cost data with information about the quality of a doctor or hospital. After all, who wants the cheapest physician if he’s also the worst?

And there are questions whether transparency can drive down prices. Hospitals and clinics have been consolidating, creating fewer, bigger companies and less competition. Lifesaving drugs and treatments might be available from only one company or location, giving patients little choice.

The biggest question is whether patients will seek this information and use it to shop more wisely. Transparency supporters think the public is ready for them to pull back the curtain on cost and quality.

“More information will beget more curiosity,” said Mary McWilliams, executive director of the Washington Health Alliance, a nonprofit that has earned national kudos for tracking the quality of health-care delivery.

“I think people have assumed it’s all the same quality and all the same cost,” she said. “Getting them to recognize that it’s not all the same is the first threshold.”

“Huge price variation”

When Jeff Rice was dinged $200 for cholesterol blood work that should have cost $20, the Tennessee-based physician turned his frustration into a business opportunity.

In 2008, Rice launched Healthcare Bluebook, a company that collects data on what insurance companies pay for medical care, then calculates a “fair price” for procedures from allergy tests to heart surgery. Consumers can search for prices for free online and use the information as a benchmark to shop around.

“Many patients don’t know there is this huge price variation,” Rice said.

There are other transparency tools available, but all have their limitations. Many insurance companies have online cost-comparison tools for their customers. A recent search on the Aetna site found prices for roughly 30 common procedures, while Regence lists prices for 350 services.

On the quality side, the Washington Health Alliance publishes “Community Checkup Report,” which evaluates the quality of doctors, clinics and hospitals. The national Leapfrog Group scores hospitals.

In coming months, lawmakers in Olympia will consider various proposals to expand and greatly improve such transparency. One bill would require insurance companies to enhance their shopping tools to include price and quality information side-by-side.

Recent hearing

A more controversial proposal would create an “All-Payer Claims Database.” Hospitals and clinics have a “billed” rate for services, but insurance companies negotiate lower “allowed” rates, the amount they agree to actually pay for a procedure. The legislation would require payers — mostly insurance companies — to reveal what they are spending on services at different locations, so the data could be compiled into a database available to everyone.

At a recent hearing for the bill, representatives from the Washington State Hospital Association, Washington State Medical Association, Seattle Metropolitan Chamber of Commerce and the National Federation of Independent Business all testified in support of creating the database.

Only Regence and Premera officials spoke against it.

The insurance companies carefully guard the rates they negotiate. They consider it proprietary information they are not keen to share with competitors, health-care providers and others.

“We simply do not believe that [the All-Payer Claims Database] has any history of demonstrating any meaningful cost or quality improvement,” said Premera’s Len Sorrin, at the hearing.

The companies do, however, support cost tools for their own customers. A spokesman for Regence testified that searching for prices drives patients to lower-cost options.

Databases in 11 states

So far, at least 11 states have created these databases in various forms, and many more are interested. Most of the databases were built in 2008 or later, and there’s little information on their effects on costs or quality.

But the world of health insurance is changing. Deductibles — the amount a patient must pay before an insurance company starts covering medical bills — are going up. More than one-third of insured workers have deductibles of $1,000 or more, and many plans also have “coinsurance,” which sets a percentage of medical bills patients must pay even if they’ve reached their deductible cap.

Gone are the days of visiting the doctor and paying a $15 copay. Patients are more frequently footing the bill.

“When it’s your money, you ask a lot more questions about what things cost,” said Rice, the founder of Bluebook.

But shopping for health care can be more complicated than buying other essentials.

Transparency supporters like to illustrate the influence of price by comparing it with buying gasoline. Most drivers check the posted per-gallon price before filling up. If one station offered gas at $4 a gallon, they would drive past the pump offering it for $20 a gallon — a degree of price difference seen in some medical services.

But is that the right metaphor? What if you’re driving on fumes and there’s no other pump for miles around? When you’re a desperate shopper, chances are you’ll pony up if you can.

Challenges, limitations

Some argue that by publishing the cost information, the cheaper locations will raise their prices rather than the expensive sites dropping theirs. Douglas Conrad, a professor in the University of Washington’s School of Public Health, called that argument a red herring. Over time, he said, the prices come down, whether through market forces or action by antitrust authorities.

The relationships patients develop with their doctors pose potentially more difficult complications.

Conrad acknowledges the challenges and limitations to how much influence transparency can exert on the health-care system, but he thinks it can make a positive difference.

“If price and quality information get out there, and there is a push by the state to force transparency where it’s been difficult to get … that could change things,” Conrad said. “The promise is there.”

We want to hear from you: Contact Kaiser Health News
data saving lives, healthcare, healthy habits, policy, quantified self, rapid learning health systems

Prescribing the BlueStar diabetes app

  • analyzes logged blood glucose
  • offers advice based on trends
  • sends a report to clinicians
  • WellDoc are chasing the money with insurers
  • Endorsed by Dr Katz

If they want Dr uptake, they will need to be able to fund scaled change management programs just like the drug companies do

  • Will Docs Write Rx for Apps?

Published: Jan 16, 2014 | Updated: Jan 16, 2014

By Kristina Fiore, Staff Writer, MedPage Today

Doctors can now write scripts for the first prescription-only app — but the question remains whether they’ll pick up a prescription pad to write for mobile technology.

The app, BlueStar, is a tracker for patients with diabetes. It analyzes logged blood glucose data and offers advice based on trends it detects — such as telling patients to adjust their diets based on sugar levels after meals. Clinicians also receive a report on their patients’ progress.

Parent company WellDoc just won $20 million in venture financing for the app, and the company has a track record of success with online disease management tools and applications. WellDoc’s argument is that better blood sugar control will lead to better patients outcomes, and, thus, less spending on healthcare in the long run.

FDA approved the BlueStar app in 2010 as a device, but the company’s strategy has recently focused on insurance and reimbursement. In June, WellDoc announced that BlueStar would be reimbursed as a pharmacy benefit for employees of a handful of top companies, including Ford Motor Company, RiteAid, and DexCom.

Only a handful of apps has been approved since the FDA’s social media guidance was released in September, but experts suspect that more app companies may be moving in the direction of requiring prescriptions in order to monetize their efforts.

Patrick Brady, a spokesperson for WellDoc, told MedPage Today that the program is out in full force and doctors are currently writing prescriptions for BlueStar.

Patients whose health plans don’t cover BlueStar can get the app by working with a customer advocacy team at WellDoc, he added. The team coordinates directly with the patient’s physician to negotiate with insurers.

In a statement from when the BlueStar app was launched in June, Richard Bergenstal, MD, a past president of the American Diabetes Association, said that in the “era of healthcare reform, it’s important that payers recognize that patients must have access to proven, novel digital tools.”

Many other clinicians contacted by MedPage Today said they’d feel comfortable writing a prescription for an app.

“I have looked at some of the data supporting the role of technology like this in the management of diabetes, and I think it may be the [wave] of the future,” said Fernando Ovalle, MD, an endocrinologist at the University of Alabama at Birmingham.

David Katz, MD, of Yale’s Prevention Research Center, said he would feel comfortable writing the script provided patients were comfortable using it. “Overall, the literature suggests that extending our reach with technology that allows patient coaching to be continuous between office visits can be very effective,” Katz said.

Johnson Thomas, MD, an endocrinology fellow in New York City who developed anendocrinology reference app called Endo Tools, also said patient comfort would be a major factor, since “not all patients are tech-savvy.”

Still, he said if the app can deliver “timely, actionable advice” to patients in order to achieve better glucose control, it would be worth it.

Sue Kirkman, MD, of the University of North Carolina at Chapel Hill, said a prescription app could be helpful, but its usefulness may be limited in that the patients “who want the app and are willing to enter data and respond to prompts may already be the more proactive ones.”

Kirkman added that she hopes potential insurer reimbursement for apps opens the door wider to support of reimbursement for self-management tools such as contact with diabetes educators.

“Right now, pretty much only face-to-face visits are covered, not the ongoing contacts by phone, fax, email, etc., that are really needed to help someone sustain behavior changes and self-manage their diabetes optimally,” she said.

 

 

data saving lives, healthcare, healthy habits, policy, quantified self, rapid learning health systems

SMS supports diabetes self-care

  • Research into Auto SMS in chronic disease published in Health Affairs
  • HBA1C reduced
  • Costs of care reduced
  • Satisfaction with care increased
  • Content included reminders, questions and allowed for responses

Auto TXTing May Boost Diabetes Self-Care

Published: Feb 3, 2014

By David Pittman, Washington Correspondent, MedPage Today

Patients with diabetes who received a text message reminder about checking their blood sugar or refilling their medicines saw improvements in clinical outcomes and lower healthcare costs, researchers said.

The 74 patients enrolled in CareSmarts, a mobile phone-based program that provides automated self-management support, had HbA1c glucose levels that went from an average of 7.9% before the 6-month study period to an average of 7.2% afterward (P=0.01), reported Shantanu Nundy, MD, managing director at Evolent Health, in Arlington, Va., and colleagues in Health Affairs.

Costs also fell 8.8% in the intervention group, with a decline in the number and costs of outpatient visits, they added. No changes in clinical outcomes (P=0.08) or costs were seen in the 274 patients who were not enrolled in CareSmarts and made up the control group.

“Our study offers early evidence that [mobile health] can enable healthcare organizations to effectively support patients beyond the traditional healthcare setting and achieve the triple aim of better health, better healthcare, and lower costs,” they wrote.

Patients with type 1 or type 2 diabetes with access to a personal cell phone were recruited for the study at the University of Chicago. Participants were responsible for any text messaging costs charged by their phone carriers, but they were given a $25 cash incentive at the completion of the study.

The average age of the study-arm patients was 53 and nearly 70% were African American, with an average diabetes duration of 8 years. One-third of patients had well-controlled diabetes (HbA1c of 7% or less). Of the 74 patients, 67 completed the 6-month program.

The text messages included reminders (“Time to check your blood sugar”) and questions, such as “Do you need refills of any of your medications?” The patients responded by text, and healthcare providers followed up depending on the responses. The patients also received educational materials.

The intervention group saw improvements in glycemic control (P=0.01) and reported better satisfaction with overall care (P=0.04), according to the authors.

However, broader use of such text messaging tools will require federal guidance and regulations, they cautioned.

“Although we found a business case for the use of [mobile health], the diffusion and sustainability … depends on a supportive policy environment,” they wrote.

While the FDA recently said it wouldn’t regulate mobile apps that don’t interface with an FDA-regulated device, such as glucometers and blood pressure monitors, uncertainty remains about apps used as an accessory to a medical device or those that support medical decision-making.

“In addition, more work is needed to clarify the overlapping roles of the FDA, the Office of the National Coordinator for Health Information Technology, and the Federal Communications Commission,” the authors wrote.

Nundy and colleagues called for government-driven privacy guidelines around provider-to-patient communication through mobile apps, saying organizations are “less likely to develop innovative programs in this area.”

Diabetes care has been one field with a large number of mobile apps for clinicians and patients to better monitor and control the disease. Some applications require a provider’s prescription.

This research was partially funded by the Alliance to Reduce Disparities in Diabetes of the Merck Foundation and received support from the Chicago Center for Diabetes Translation Research.

Nundy co-founded mHealth Solutions, a mobile health software company that provided the software for this research, but reported that he no longer has a financial relationship with the company. He also reported a grant from Agency for Healthcare Research and Quality’s Health Services Research Training Program.

One co-author is co-founder and owner of mHealth Solutions.

Other co-authors reported support from National Institute of Diabetes and Digestive and Kidney Diseases and the Robert Wood Johnson Foundation.