Five Reasons We Must Untrap Digital Health’s Big Data

We tend to think of Big Data as a Land of Oz where we can find any information we need. What is not appreciated by most in healthcare is that there is a lot of Big Data collected but most is not relevant data, nor is it easily located or even accessible. The implications of this are enormous. The true value proposition of Big Data in healthcare lies in how the data is analyzed and presented.  In my last post I discussed ways in which Big Data can be transformed into relevant data.  I will discuss five reasons why freeing up ‘trapped’ data is critical to making it relevant.

  1. Population health management. Analytics are the building blocks to population health management, one of the new drivers of healthcare payment models. It is interesting to note that a 2015 HIMSS Analytics Survey found that 67% of surveyed organizations had population health management programs in place but only 25% of them utilized an outside vendor solution to address their needs. Population health management’s purpose is to emphasize shared decision-making and care between the clinician and the patient with an emphasis on accomplishing this outside of the healthcare facility or clinic. While this has always been the aim, we now have digital tools which can facilitate this as well as the shortage of providers increasing the demand for such tools.
  2. Patient outcomes data. There is a major discrepancy between quality measures and patient outcomes. According to the National Quality Data Clearinghouse only 139 of its 1958 quality indicators are patient outcomes and 32 are patient-reported outcomes. As correctly pointed out in a recent piece in the New England Journal of Medicine, we have used evidence based medicine metrics as a substitute for patient outcomes.  The International Consortium for Health Outcomes Measurement (ICHOM) has already approved 20 sets of outcomes standards and projects to have over 50% of disease burden covered by 2017.  Patient outcomes data whether derived from data sets directly from the electronic health record (EHR) or from patient-derived data emanating from mobile or other digital technology is critical to determining outcomes. The problem lies in how to collect data that lie with disparate EHR or other digital formats.
  3. Support digital and mobile clinical trials. Imagine discrete data                                 from any individual clinical trial patient’s point of care (regardless of the provider’s EHR brand) coupled with direct patient-generated data delivered to a mobile clinical trial platform. Such a scenario is possible and will save Pharma and CROs huge amounts of money, improve accuracy and decrease lost or missing data. In addition, integration and interoperability between hospital records and data registries that flag patients seen urgently at a distant site helps save lives.  In this way a patient in a clinical study, even winding up in an out of town emergency room can ideally have pertinent data automatically sent to the clinical trial platform.
  4. Save money. Harnessing relevant data from Big Data can save money in many ways. As mentioned above, the costs of clinical trials can be markedly decreased. Organizations (governmental, healthcare enterprises, professional societies) who maintain clinical registries by definition require relevant longitudinal data. The ability to seamlessly collect relevant data automatically across disparate EHRs results in a more complete picture of the cancer or chronic disease patient with comorbidities. Doing so can hopefully improve outcomes translating in higher value based payment. In another example, it is not uncommon for a cardiac patient to be in separate mandated registries for coronary stents, a heart valve, and/or an implantable defibrillator.  A single database collecting all the longitudinal data on such a patient would save millions of dollars to the sponsor and the provider (via improving efficiencies of clinical data staff) in addition to contributing to outcomes measures in a more meaningful way.
  5. Other stakeholders need real-world evidence. Just as a picture is worth a thousand words, relevant collected data helps pain the real picture of the patient. Post marketing surveillance registries and studies of drugs and medical devices by industry need relevant discrete data sets provided in an efficient way. Payers need this data to determine true outcomes. Providers need relevant data to determine true outcome measures, quality metrics, and inputs for value based payment models.

One can see how static Big Data is useless without the ability to make it relevant by ‘untrapping’ it. The technology exists. It can save time, money, and address interoperability challenges.  The critical importance of patient outcomes becoming the focus of quality measures for use in new payment models, drug and device development, and clinical trials will drive adoption of such tools in the near future.


About davidleescher

David Lee Scher, MD is Founder and Director at DLS HEALTHCARE CONSULTING, LLC, which specializes in advising digital health technology companies, their partners, investors, and clients. As a cardiac electrophysiologist and pioneer adopter of remote patient monitoring, he understood early on the challenges that the culture and landscape of healthcare present to the development and adoption of digital technologies. He is a well-respected thought leader in mobile and other digital health technologies. Scher lectures worldwide on relevant industry topics including the role of tech in Pharma, patient advocacy, standards for development and adoption, and impact on patients and healthcare systems from clinical, risk management, operational and marketing standpoints. He is a Clinical Associate Professor of Medicine at Penn State College of Medicine.
This entry was posted in #digitalhealth, analytics, digital health, digital health technology, EHR, healthcare economics, Healthcare IT, medical apps, medical devices, mHealth, mobile health, pharma, technology, telehealth and tagged , , , , , , , , . Bookmark the permalink.

2 Responses to Five Reasons We Must Untrap Digital Health’s Big Data

  1. It is a great thing to untrap digital health’s big data but this is one of the most vulnerable. Security needs to catch up.

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s