As government involvement in U.S. health care deepens—through the Affordable Care Act, Meaningful Use, and the continued revisions and expansions of Medicaid and Medicare—the politically electric watchword is “socialism.”
Online, of course, social media is not a latent communist threat, but rather the most popular destination for internet users around the world.
People, whether out of fear for being left behind, or simply tickled by the ease with which they can publicize their lives, have been sharing every element of their public (and very often, their private) lives with ever-increasing zeal. Pictures, videos, by-the-minute commentary and updates, idle musings, blogs—the means by which people broadcast themselves are as numerous and diverse as sites on the web itself.
Even as the public decries government spying programs and panics at the news of the latest massive data-breach, the daily traffic to sites like Facebook and Twitter—especially through mobile devices—not only stays high, but continues to grow. These sites are designed around users volunteering personal information, from work and education information, to preferences in music, movies, politics, and even romantic partners.
So why not health data?
The hype around wearables is deafening. I say this from the perspective of someone who saw their application in chronic illness management 15 years ago. Of course, at that time, it was less about wearables and more about sensors in the home, but the concept was the same.
Over the years, we’ve seen growing signs that wearables were going to be all the rage. In 2005, we adopted the moniker ‘Connected Health’ and the slogan, “Bring health care into the day-to-day lives of our patients,” shortly thereafter. About 18 months ago, we launched Wellocracy, in an effort to educate consumers about the power of self-tracking as a tool for health improvement. All of this attention to wearables warms my heart. In fact, Fitbit (the Kleenex of the industry) is rumored to be going public in the near future.
So when the headline, “Here’s Proof that Pricey Fitness Wearables Really Aren’t Worth It,” came through on the Huffington Post this week, I had to click through and see what was going on. Low and behold this catchy headline was referring to a study by some friends (and very esteemed colleagues) from the University of Pennsylvania, Mitesh Patel and Kevin Volpp.
I’ve been thinking a lot about “big data” and how it is going to affect the practice of medicine. It’s not really my area of expertise– but here are a few thoughts on the tricky intersection of data mining and medicine.
First, some background: these days it’s rare to find companies that don’t use data-mining and predictive models to make business decisions. For example, financial firms regularly use analytic models to figure out if an applicant for credit will default; health insurance firms can predict downstream medical utilization based on historic healthcare visits; and the IRS can spot tax fraud by looking for fraudulent patterns in tax returns. The predictive analytic vendors are seeing an explosion of growth: Forbes recently noted that big data hardware/software and services will grow at a compound annual growth rate of 30% through 2018.
Big data isn’t rocket surgery. The key to each of these models is pattern recognition: correlating a particular variable with another and linking variables to a future result. More and better data typically leads to better predictions.
It seems that the unstated, and implicit belief in the world of big data is that when you add more variables and get deeper into the weeds, interpretation improves and the prediction become more accurate.Continue reading…
Earlier this week, we reported on the current rates of influenza-like illness (ILI), based on data from roughly one million patient visits on the athenahealth network. That report showed a steep increase in ILI rates for the week ending Saturday, December 13 (see previous post). It’s not certain that this season will be as severe as that of 2012-2013 (data for pediatrics suggests that is a real possibility); however, providers are testing for flu more consistently than previous years, and prescribing antivirals more often.
Our data shows that the number of flu tests ordered, per patient visit in which ILI is diagnosed, has risen each of the past two years (Figure 1, graph A). This season, providers are ordering flu tests at a rate of 0.53 tests per visit with an ILI diagnosis, compared to 0.37 for last season and 0.34 for 2012-2013. (Note: There can be multiple tests per patient visit, e.g. Type A and B.)
Physicians have always been in the information business. We have kept records of patient data regarding the vital signs, allergies, illnesses, injuries, medications, and treatments for the patients we serve. We seek knowledge from other physicians, whether that knowledge comes from the conclusions of experts from research published in a medical journal or the specialist down the hall. However, a physician will always benefit from additional good information such as the analysis of pooled data from our peers treating similar patients or from the patients themselves.
Over the next few years, vast new pools of data regarding the physiologic status, behaviors, environment, and genomes of patients will create amazing new possibilities for both patients and care providers. Data will change our understanding of health and disease and provide a rich new resource to improve clinical care and maximize patient health and well-being.
Patient Data Used by the Patient
Instead of a periodic handful of test results and a smattering of annual measurements in a paper chart, healthdata will increasingly be something that is generated passively, day by day, as a byproduct of living our lives and providing care. Much of the data will be generated, shared, and used outside of the health system. It will belong to patients who will use it to manage their lives and help them select physicians and other healthcare professionals to guide them in their quest for a long and healthy life.
Based on a patient’s preferences and needs, the data will flow to those who can best assist them in maintaining their health. It will reveal important and illuminating patterns that were not previously apparent, and with the right system in place, it will trigger awareness and alerts for patients and other providers that will guide behaviors and decisions.
The great promise of wearables for medicine includes the opportunity for health measurement to participate more naturally in the flow of our lives, and provide a richer and more nuanced assessment of phenotype than that offered by the traditional labs and blood pressure assessments now found in our medical record. Health, as we appreciate, exists outside the four walls of a clinical or hospital, and wearables (as now championed by Apple, Google, and others) would seem to offer an obvious vehicle to mediate our increasingly expansive perspective.
The big data vision here, of course, would be to develop an integrated database that includes genomic data, traditional EMR/clinical data, and wearable data, with the idea that these should provide the basis for more precise understanding of patients and disease, and provide more granular insight into effective interventions. This has been one of the ambitions of the MIT/MGH CATCH program, among others (disclosure: I’m a co-founder).
One of the challenges, however, is trying to understand the quality and value of the wearable data now captured. To this end, it might be useful to consider a evaluation framework that’s been developed for thinking about genomic testing, and which I’ve become increasingly familiar with through my new role at a genetic data management company. (As I’ve previously written, there are many parallels between our efforts to understand the value of genomic data and our efforts to understand the value of digital health data.)
The evaluation framework, called ACCE, seems to have been first published by Brown University researchers James Haddow and Glenn Palomaki in 2004, and focuses on four key components: Analytic validity, Clinical validity, Clinical utility, and Ethical, Legal, and Social Implications (ELSI). The framework continues to inform the way many geneticists think about testing today – for instance, it’s highlighted on the Center for Disease Control’s website (and CDC geneticist Muin Khoury was one of the editors of the book in which the ACCE was first published).
People are becoming more conscious about their health. It’s why fitness apps are booming and both Apple and Google are looking to get into the health game. But apps that try to go beyond simple calorie counting and movement tracking often struggle to gain traction with users.
Although people are open to sharing how many steps they’ve taken or how much they weigh, they’re more hesitant to share their personal medical details.
Here are some data-related fears consumers often have with healthcare apps:
- Personal medical information could get leaked. Revealing users’ medical information could be embarrassing and life shattering.
- Companies could use the data for marketing purposes. Imagine your spam getting smarter about your personal health details. Companies are already pinpointing viewers’ interests, and revealing this information could expose you to targeted email spam and calls tailored to your health issues. Members of Congress have already discussed legislation that would forbid medical apps from selling personal data without the user’s consent.
- Unqualified employees could access their information. Patients feel comfortable divulging medical information to a doctor, but they probably wouldn’t want the IT guy who supports the app to see and read their information.
There are many reasons people might hesitate to use your app. But by identifying potential concerns and considering them as you develop and market your app, you can quell their fears and ensure the long-term success of your medical app.Continue reading…
We need to design a system of health care that optimally meets the country’s needs while also being affordable and socially acceptable. Clinicians should be at the center of this debate if care delivery is to be designed in a way that puts quality of care before financial gain.
This challenge is too important to be left to politicians and policymakers. There is an urgent need for clinicians to step up, lead the debate and design a new future for health care. Placing professional responsibility for health outcomes in the hands of clinicians, rather than bureaucrats or insurance companies with vested interests, must be an ambition for all of us. We need to find the formula that meets the needs of the patients and communities we serve. A sincere collective effort by committed clinicians to design an effective system will lead to a health care system that has a democratic mandate and the appropriate focus on optimizing the outcomes patients and society need.
As clinicians enter the debate, they should keep three things in mind.
Promote the leadership role of clinicians
We need to help politicians and policymakers recognize the role of clinical leaders in shaping a transformed but effective health care system. Clinicians must redefine the debate so that it focuses first and foremost on patients and health outcomes. Cost effective care can and should be a byproduct of optimal care. Accomplishing this will provide a strong common purpose for efforts to address the challenges of designing outcome-based funding structures and improving access to care.
EMR adoption is skyrocketing, in no small part due to government incentives. The office of the national coordinator lauds this hockey-stick curve as a success. Advocates promise electronic records will improve patient care, reduce mistakes, and save healthcare costs. At the same time, doctors love to complain about implementation cost and poor usability. How can we reconcile these differing opinions? The truth is they are describing very different technologies. EMRs, the way they are implemented now, will not accomplish these goals. In fact, early adopters can become stuck at a rudimentary level of functionality, and the extensive feature lists described by meaningful use criteria fail to address the most basic needs for patient care.
I have been at medical institutions at different levels of technological development. Each has a different attitude toward the EMR; for some its loathing, others longing. Some devote resources to try to improve it, but others give up. I realized the parallels with Maslow’s Hierarchy of Needs, people are motivated to attain something only after their very basic needs have been fulfilled. So are EMRs good or bad? Well, it depends on where you are on the hierarchy.
The figure above describes the steps to building a technology infrastructure that will lead to improved patient care. Yes, incentives help us achieve some very basic needs, but the problem is that decisions and investments we make now will determine the ceiling as well.
When building software, requirements are everything.
And although good requirements do not necessarily lead to good software, poor requirements never do. So how does this apply to electronic health records? Electronic health records are defined primarily as repositories or archives of patient data. However, in the era of meaningful use, patient-centered medical homes, and accountable care organizations, patient data repositories are not sufficient to meet the complex care support needs of clinical professionals. The requirements that gave birth to modern EHR systems are for building electronic patient data stores, not complex clinical care support systems–we are using the wrong requirements.
Two years ago, as I was progressing in my exploration of workflow management, it became clear that current EHR system designs are data-centric and not care or process-centric. I bemoaned this fact in the post From Data to Data + Processes: A Different Way of Thinking about EHR Software Design. Here is an excerpt.
Do perceptions of what constitutes an electronic health record affect software design? Until recently, I hadn’t given much thought to this question. However, as I have spent more time considering implementation issues and their relationship to software architecture and design, I have come to see this as an important, even fundamental, question.
The Computer-based Patient Record: An Essential Technology for Health Care, the landmark report published in 1991 (revised 1998) by the Institute of Medicine, offers this definition of the patient record:
A patient record is the repository of information about a single patient. This information is generated by health care professionals as a direct result of interaction with the patient or with individuals who have personal knowledge of the patient (or with both).
Note specifically that the record is defined as a repository (i.e., a collection of data). There is no mention of the medium of storage (paper or otherwise), only what is stored. The definition of patient health record taken from the ASTM E1384-99 document, Standard Guide for Content and Structure of the Electronic Health Record, offers a similar view—affirming the patient record as a collection of data. Finally, let’s look at the definition of EHR as it appears in the 2009 ARRA bill that contains the HITECH Act:
ELECTRONIC HEALTH RECORD —The term ‘‘electronic health record’’ means an electronic record of health-related information on an individual that is created, gathered, managed, and consulted by authorized health care clinicians and staff. (123 STAT. 259)
Even here, 10 years later, the record/archive/repository idea persists. Now, back to the issue at hand: How has the conceptualization of the electronic health record as primarily a collection of data affected the design of software systems that are intended to access, manage, and otherwise manipulate said data?