Free EMR Newsletter Want to receive the latest news on EMR, Meaningful Use, ARRA and Healthcare IT sent straight to your email? Join thousands of healthcare pros who subscribe to EMR and HIPAA for FREE!!

How the Young Unity Health Score Company Handles The Dilemmas of Health IT Adoption

Posted on June 25, 2018 I Written By

Andy Oram is an editor at O'Reilly Media, a highly respected book publisher and technology information provider. An employee of the company since 1992, Andy currently specializes in open source, software engineering, and health IT, but his editorial output has ranged from a legal guide covering intellectual property to a graphic novel about teenage hackers. His articles have appeared often on EMR & EHR and other blogs in the health IT space. Andy also writes often for O'Reilly's Radar site (http://oreilly.com/) and other publications on policy issues related to the Internet and on trends affecting technical innovation and its effects on society. Print publications where his work has appeared include The Economist, Communications of the ACM, Copyright World, the Journal of Information Technology & Politics, Vanguardia Dossier, and Internet Law and Business. Conferences where he has presented talks include O'Reilly's Open Source Convention, FISL (Brazil), FOSDEM, and DebConf.

I have been talking to a young company called Unity Health Score with big plans for improving the collection and sharing of data on patients. Their 55-page business plans covers the recruitment of individuals to share health data, the storage of that data, and services to researchers, clinicians, and insurers. Along the way, Unity Health Score tussles with many problems presented by patient data.
Unity Health Score logo
The goals articulated for this company by founder Austin Jones include getting better data to researchers and insurers so they can reduce costs and find cures, improving communications and thus care coordination among clinicians and patients, and putting patients in control of their health data so they can decide where it goes. The multi-faceted business plan covers:

  • Getting permission from patients to store data in a cloud service maintained by Unity Health Score
  • Running data by the patients’ doctors to ensure accuracy
  • Giving patients control over what researchers or other data users receive their data, in exchange for monetary rewards
  • Earning revenue for the company and the patients by selling data to researchers and insurers
  • Helping insurers adjust their plans based on analysis of incoming data

The data collected is not limited to payment data or even clinical data, but could include a grab-bag of personal data, such financial and lifestyle information. All this might yield health benefits to analytics–after all, the strategy of using powerful modern deep learning is being pursued by many other health care entities. At the same time, Jones plans to ensure might higher quality data than traditional data brokers such as Acxiom.

Now let’s see what Unity Health Score has to overcome to meet its goals. These challenges are by no means unique to these energetic entrepreneurs–they define the barriers faced by institutions throughout health care, from the smallest start-up to the Centers for Medicare & Medicaid Services.

Outreach to achieve a critical mass of patients
We can talk for weeks about quality of care and modernizing cures, but everybody who works in medicine agrees that the key problem we face is indifference. Most people don’t want to think too much about their health, are apathetic when presented with options, and stubbornly resist the simplist interventions–even taking their prescribed medication. So explaining the long-term benefits of uploading data and approving its use will be an uphill journey.

Many app developers seek adoption by major institutions, such as large insurers, hospital conglomerates, and HMOs like Kaiser. This is the smoothest path toward adoption by large numbers of consumers, and Unity Health Score includes a similar plan in its business model, According to Jones, they will require the insurance company to reduce premiums based on each patient’s health score. In return, they should be able to use the data collected to save money.

Protecting patient data
Health data is probably the most sensitive information most of us produce over our lifetimes. Financial information is important to keep safe, but you can change your bank account or credit card if your financial information is leaked–you can’t change your medical history. Security and privacy guarantees are therefore crucial for patient records. Indeed, the Unity Health Score business plan cites fears of privacy as a key risk.

Although some researchers have tried distributed patient records, stored in some repository chosen by each individual, Unith Health Score opts for central storage, like most current personal health records. This not only requires great care to secure, but places on them the burden of persuading patients that the data really will be used only for purposes chosen by the patients. Too many apps and institutions play three-card Monte with privacy policies, slipping in unauthorized uses (just think back to the recent Facebook/Cambridge Analytica scandal), so Internet users have become hypervigilant.

Unity Health Score also has to sign up physicians to check data for accuracy. This, of course, should be the priority for any data entered into any medical record. Because doctors’ time is going more and more toward the frustrating task of data entry, the company offers an enticing trade-off: the patients takes the time to enter their data, and the doctor merely verifies its accuracy. Furthermore, a consolidated medical record online can be used to speed check-in times on visits and to make data sharing on mobile devices easier.

Making the data useful
Once the patients and clinicians join Unity Health Score, the company has to follow through on its promise. This is a challenge with multiple stages.

First, much of the data will be in unstructured doctors’ notes. Jones plans to use OCR, like many other health data aggregators, to extract useful information from the notes. OCR and natural language processing may indeed be more accurate than relying on doctors to meticulously fill out dozens of structured fields in a database. But there is always room for missed diagnoses or allergies, and even for misinterpretations.

Next, data sources must be harmonized. They are likely to use different units and different lexicons. Although many parts of the medical industry are trying to standardize their codings, progress is incomplete.

The notion of a single number defining one’s health is appealing, but it might be too crude for many uses. Whether you’re making actuarial predictions (when will the individual die, or have to stop working?), estimating future health care costs, or guessing where to allocate public health resources, details about conditions may be more important than an all-encompassing number. However, many purchasers of the Unity Health Score information may still find the simplicity of a single integer useful.

Making the service attractive to data purchasers
The business plan points out that most rsearch depends on large data sets. During the company’s ramp-up phase–which could take years–they just won’t have enough patients suffering from a particular condition to interest many researchers, such as pharma companies looking for subjects. However, the company can start by selling data to academic researchers, who often can accomplish a lot with a relatively small sample. Biotech, pharma, and agencies can sign up later.

Clinicians may warm to the service much more quickly. They will appreciate having easy access to patient data for emergency room visits and care coordination in general. However, this is a very common use case for patient data, and one where many competing services are vying for a business niche.

Aligning goals of stakeholders
In some ways I have saved the hardest dilemma for last. Unity Health Care is trying to tie together many sets of stakeholders–patients, doctors, marketers, researchers, insurers–and between many of these stakeholders there are irreconcilable conflicts.

For instance, insurers will want the health score to adjust their clients’ payments, charging more for sick people. This will be feared and resented by people with pre-existing conditions, who will therefore withhold their information. In some cases, such insurer practices will worsen existing disparities for the poor and underpriviledged. The Unity Health Score business plan rejects redlining, but there may be subtler practices that many observers would consider unethical. Sometimes, incentives can also be counterproductive.

Also, as the business plan points out, many companies that currently purchase health data have goals that run counter to good health: they want to sell doctors or patients products that don’t actually help, and that run up health care costs. Some purchasers are even data thieves. Unity Health Score has a superior business model here to other data brokers, because it lets the patients approve each distribution of their data. But doing so greatly narrows the range of purchasers. Hopefully, there will be enough ethical health data users to support Unity Health Score!

This is an intriguing company with a sophisticated strategy–but one with obstacles to overcome. We can all learn from the challenges they face, because many others who want to succeed in the field of health care reform will come up against those challenges.

Machine Learning and AI in Healthcare – #HITsm Chat Topic

Posted on February 28, 2018 I Written By

John Lynn is the Founder of the HealthcareScene.com blog network which currently consists of 10 blogs containing over 8000 articles with John having written over 4000 of the articles himself. These EMR and Healthcare IT related articles have been viewed over 16 million times. John also manages Healthcare IT Central and Healthcare IT Today, the leading career Health IT job board and blog. John is co-founder of InfluentialNetworks.com and Physia.com. John is highly involved in social media, and in addition to his blogs can also be found on Twitter: @techguy and @ehrandhit and LinkedIn.

We’re excited to share the topic and questions for this week’s #HITsm chat happening Friday, 3/2 at Noon ET (9 AM PT). This week’s chat will be hosted by Corinne Stroum (@healthcora) on the topic “Machine Learning and AI in Healthcare.”

Machine learning is hitting a furious pace in the consumer world, where AI estimates how long your food will take to arrive and targets you with the purchases you can’t resist. This week, we’ll discuss the implications of this technology as we translate it to the healthcare ecosystem.

Current machine learning topics of interest to healthcare range from adaptive and behavior-based care delivery pathways to the regulation of so-called “black box” systems those that cannot easily explain the reasons with which they made a prediction.

Please join us for this week’s #HITsm chat as we discuss the following questions:

T1: The Machine Learning community is currently discussing FAT: Fairness, Accountability, & Transparency. What does this mean in healthIT? #HITsm

T2: How can machine learning integrate naturally in clinical and patient facing workflows? #HITsm

T3: What consumer applications of machine learning are best suited for transition to the healthcare setting? #HITsm

T4: The FDA regulates software AS a medical device and IN a medical device. How do you envision this distinction today, and do you foresee it changing? #HITsm

T5: What successes have you seen in healthcare machine learning? Are particular care settings better suited for ML? Where do you see that alignment? #HITsm

Bonus: Is there a place for machine learning black box predictions? #HITsm

Upcoming #HITsm Chat Schedule
3/9 – HIMSS Break – No #HITsm Chat

3/16 – TBD

3/23 – TBD

We look forward to learning from the #HITsm community! As always, let us know if you’d like to host a future #HITsm chat or if you know someone you think we should invite to host.

If you’re searching for the latest #HITsm chat, you can always find the latest #HITsm chat and schedule of chats here.

Machine Learning, Data Science, AI, Deep Learning, and Statistics – It’s All So Confusing

Posted on November 30, 2017 I Written By

John Lynn is the Founder of the HealthcareScene.com blog network which currently consists of 10 blogs containing over 8000 articles with John having written over 4000 of the articles himself. These EMR and Healthcare IT related articles have been viewed over 16 million times. John also manages Healthcare IT Central and Healthcare IT Today, the leading career Health IT job board and blog. John is co-founder of InfluentialNetworks.com and Physia.com. John is highly involved in social media, and in addition to his blogs can also be found on Twitter: @techguy and @ehrandhit and LinkedIn.

It seems like these days every healthcare IT company out there is saying they’re doing machine learning, AI, deep learning, etc. So many companies are using these terms that they’ve started to lose meaning. The problem is that people are using these labels regardless of whether they really apply. Plus, we all have different definitions for these terms.

As I search to understand the differences myself, I found this great tweet from Ronald van Loon that looks at this world and tries to better define it:

In that tweet, Ronald also links to an article that looks at some of the differences. I liked this part he took from Quora:

  • AI (Artificial intelligence) is a subfield of computer science, that was created in the 1960s, and it was (is) concerned with solving tasks that are easy for humans, but hard for computers. In particular, a so-called Strong AI would be a system that can do anything a human can (perhaps without purely physical things). This is fairly generic, and includes all kinds of tasks, such as planning, moving around in the world, recognizing objects and sounds, speaking, translating, performing social or business transactions, creative work (making art or poetry), etc.
  • Machine learning is concerned with one aspect of this: given some AI problem that can be described in discrete terms (e.g. out of a particular set of actions, which one is the right one), and given a lot of information about the world, figure out what is the “correct” action, without having the programmer program it in. Typically some outside process is needed to judge whether the action was correct or not. In mathematical terms, it’s a function: you feed in some input, and you want it to to produce the right output, so the whole problem is simply to build a model of this mathematical function in some automatic way. To draw a distinction with AI, if I can write a very clever program that has human-like behavior, it can be AI, but unless its parameters are automatically learned from data, it’s not machine learning.
  • Deep learning is one kind of machine learning that’s very popular now. It involves a particular kind of mathematical model that can be thought of as a composition of simple blocks (function composition) of a certain type, and where some of these blocks can be adjusted to better predict the final outcome.

Is that clear for you now? Would you suggest different definitions? Where do you see people using these terms correctly and where do you see them using them incorrectly?