• Drug Coverage
  • Hypertrophic Cardiomyopathy (HCM)
  • Vaccines: 2023 Year in Review
  • Eyecare
  • Urothelial Carcinoma
  • Women's Health
  • Hemophilia
  • Heart Failure
  • Vaccines
  • Neonatal Care
  • Type II Inflammation
  • Substance Use Disorder
  • Gene Therapy
  • Lung Cancer
  • Spinal Muscular Atrophy
  • HIV
  • Post-Acute Care
  • Liver Disease
  • Pulmonary Arterial Hypertension
  • Safety & Recalls
  • Biologics
  • Asthma
  • Atrial Fibrillation
  • Type I Diabetes
  • RSV
  • COVID-19
  • Cardiovascular Diseases
  • Breast Cancer
  • Prescription Digital Therapeutics
  • Reproductive Health
  • The Improving Patient Access Podcast
  • Blood Cancer
  • Ulcerative Colitis
  • Respiratory Conditions
  • Multiple Sclerosis
  • Digital Health
  • Population Health
  • Sleep Disorders
  • Biosimilars
  • Plaque Psoriasis
  • Leukemia and Lymphoma
  • Oncology
  • Pediatrics
  • Urology
  • Obstetrics-Gynecology & Women's Health
  • Opioids
  • Solid Tumors
  • Autoimmune Diseases
  • Dermatology
  • Diabetes
  • Mental Health

Connect the dots with predictive data


Integrating and leveraging data will improve quality of care and decrease costs.

DATA HAS GONE FROM being a byproduct of the Information Age to its most valuable resource. Mining, refining and using the data generated by nearly every health encounter has been proclaimed as the next revolution. 

The hopes are high for big data in healthcare. The right data in the right hands at the right time is expected to dramatically improve the quality of care while decreasing costs. But there are many challenges to overcome along that path.

“The data is there, it’s integrating and leveraging it that is the key challenge,” says David Jeans, vice president of Corporate Analytics at CDPHP, a health plan based in Albany, N.Y. “Getting patient care data-going beyond claims data-and integrating it is driving richer analytics.”

So far, the healthcare industry has largely been focused on using data, especially claims data, to identify what has already happened. For example, has the rate of diabetes among a certain age group increased or declined? Collecting and disseminating that information is no small feat, and it can reveal important red flags that can improve the quality of care and lower costs. However, it just scratches the surface of what would be possible if data could be used to predict what will happen.

“When we can identify potential risks and prevent them from ever occurring, that means we’ve eliminated the need for care,” Jeans says. “If we can prevent someone from developing diabetes, then we improve their health and reduce costs as a whole.”

But the industry is still a long way from broad use of predictive data.

“Only about half of medical practices in the United States are based on true evidence and clear science,” says Mark Boxer, executive vice president and chief information officer at Cigna. “A lot of times, practices are still based on physicians’ training or regional habits.” 

Part of that reason is the difficulty in getting research into the hands of the providers. According to Boxer, it takes between 10 and 19 years for new evidence uncovered by research to be implemented by front-line clinicians.


For analytics to realize its full promise in healthcare will require disparate groups of people to collect and share data with each other in a standard way. 

“We’ve got data in EMRs (electronic medical records) and EHRs (electronic health records), clinical data, lab data, pharmaceutical data, images … data is everywhere,” says Boxer. “But in many cases it’s not connected, not sharable and our ability to link that data to individuals is limited. We have to connect those dots.”

The first connection should be between payers and providers, Jeans says.

“That’s the first step: exposing data so at the point of care there’s more data for providers to make better judgments,” he says. “At the moment, I see a prevalence around gaps in care. A primary care physician may not know whether a diabetic has or hasn’t had an eye exam, for example. Getting those kinds of gaps identified and putting them into an actionable form is one of the earliest types of uses we need to focus on.”

Beyond the industry fragmentation aspect, data collection and access gets even more granular and more challenging. Tying data to a member’s profile would allow healthcare professionals to predict their behavior, such as whether they are likely to fill a prescription, and respond accordingly. 

Jeans says one way to help overcome the big data challenges faced by the healthcare industry would be to establish a national patient identifier program.

“There is major reluctance to go down that path, but not having it is hampering our progress in this space,” he says. “Tying data together to get a complete view of clinical history is daunting.”

The Healthcare Information and Management Systems Society (HIMSS) has asked Congress on a number of occasions to study patient identification issues, suggesting patients could have unique numbers to match them with their health data that might be contained in various places throughout the delivery system. Privacy concerns have thwarted the identifier initiative, but Jeans says it needs to be addressed.

“We need more analytics to provide better care, but there’s a competing view that prevents the information from being shared due to privacy concerns,” he says. “We have to get the data to the people who can analyze it if we want to get value from it.”


Industry fragmentation is a high hurdle, but a complete picture of members’ health must go beyond data collected by their primary care physicians, specialists and lab results. A complete picture would include data created and collected by the members themselves.

The explosion of mobile computing has turned consumers into more efficient data collectors. About half of U.S. adults have smart phones, according to a Pew Internet & American Life Project survey conducted last fall. And those smartphones have apps that track vitals such as caloric intake, glucose levels, blood pressure, heart rate, exercise, sleep patterns and more. 

Boxer says this “instrumenting of the consumer” has a lot of potential. Imagine an iPhone app automatically populating a member’s health record as he checks his glucose levels. A particular reading could trigger an alert to the member and his physician with information to help them prevent a more severe episode. Imagine if the physician could also tie that data in with information from the member’s exercise and calorie counter apps. 

“Getting a real-time profile of a member’s health will address healthcare’s challenges revolving around cost and quality of care,” Boxer says.

To get to that point will require government agencies, health service companies, physicians and clinicians coming together to collaborate and invest in technology. In one step toward that goal, National Institutes of Health (NIH) Director Francis S. Collins, MD, has announced plans to recruit a new senior scientific position: the Associate Director for Data Science. The associate director will lead a series of NIH-wide strategic initiatives that collectively aim to capitalize on the exponential growth of biomedical research data, such as from genomics, imaging and electronic health records. 

“There is an urgent need and increased opportunities for advanced collaboration and coordination of access to, and analysis of, the rapidly expanding collections of biomedical data,” Dr. Collins said in a press release. “NIH aims to play a catalytic lead role in addressing these complex issues-not only internally, but also with stakeholders in the research community, other government agencies and private organizations involved in scientific data generation, management and analysis.”  MHE

Related Videos
Related Content
© 2024 MJH Life Sciences

All rights reserved.