Healthcare News & Insights

Data analytics holds promise of dramatically improving outcomes for patients with autoimmune disease

Many industries are using data analytics to make predictions about future events and use them to their advantage. But can this technology benefit the healthcare industry? In this guest post, Chase Spurlock, PhD, founder and CEO of a data analytics company, and Michael Fleming, MD, founding director, chairman and chief medical officer for a company that provides continuing education for healthcare providers, explain how predictive data analytics can help hospitals improve outcomes and avoid readmission penalties.


Hospitals and health systems moving toward value-based care models are poised to increase their use of predictive data analytics to provide better and more comprehensive population health management services to patients.

This movement to embrace predictive analytics, which has been gathering steam over the past several years, will be especially important as hospitals seek to improve their capabilities to forecast, detect and monitor chronic conditions, especially autoimmune diseases. The technology, in conjunction with traditional care, can play a vital role in improving health outcomes for patients while also helping hospitals avoid costly readmission penalties.

Up to 50 million Americans – 15% of the population – suffer from an autoimmune disease, according to the American Autoimmune Related Diseases Association. Direct healthcare costs for treating autoimmune diseases total $100 billion a year or more – and that’s just for seven of the most prevalent forms of the disease (there are between 80 and 100 different types of autoimmune diseases that have been identified by researchers). Those treatment costs exceed expenditures for other chronic conditions and diseases. In comparison, spending on cancer-related health care in 2015 was much lower, estimated at $80 billion, according to the American Cancer Society.

Game-changer for hospitals and health systems

An ever-increasing number of studies, such as this one from Stanford Medicine, are showing that predictive data analytics technology can deliver life-changing diagnostic information for healthcare providers. The analytics platforms – using sophisticated algorithms built with artificial intelligence and machine learning tools – can analyze millions of healthcare claims and electronic medical records. Predictive models are then created that can confirm existing diagnoses and identify patients who were undetected or misdiagnosed.

Provider-friendly reports generated from the “big data black boxes” will help clinicians better detect disease, improve treatment plans and correct misdiagnosis. Additionally, risk scores based on population health data can be devised that signal which patients may be heading toward readmission within Medicare’s Hospital Readmissions Reduction Program’s (HRRP) 30-day window – potentially leading to immense cost savings. As of 2017, hospitals had been levied nearly $1.9 billion in readmissions penalties since the start of HRRP in October 2012.

Detecting patients with autoimmune disease

The ability to find and predict autoimmune disease through data can be life-changing. Autoimmune diseases are difficult to detect early because the symptoms can be nonspecific, leading to a multi-year clinical journey to rule in or out the underlying cause. Historically, patients with an autoimmune disease have needed to wait for their symptoms to progress before a definitive diagnosis was made and treatment begun.

It can take three to five years to diagnose autoimmune diseases like MS using traditional methods, which can include spinal taps, MRIs and other testing. During that time there’s a possibility of misdiagnosis, and misdiagnosis rates for MS and other autoimmune diseases can be 10% or greater. A multicenter study published by Andrew J. Solomon and Brian G. Weinshenker in Current Neurology and Neuroscience Reports in 2013 revealed that 50% of patients who had been incorrectly diagnosed with MS carried the misdiagnosis for at least three years.

The cost of providing health care for patients with an autoimmune disease tends to increase prior to a definitive diagnosis and then accelerates rapidly if patients experience adverse events, including relapses or flares. Predictive analytics tools can uncover patterns within large datasets that will facilitate an early diagnosis so a treatment plan can be put in place to help improve patient health, reduce costs, and lessen the frequency and severity of adverse events.

These tools could help change the way payors approach patient reimbursements. In a paper published in the February issue of Health Affairs, researchers at Oregon Health & Science University/Oregon State University College of Pharmacy specifically cited MS as “emblematic of many chronic conditions whose treatment increasingly involves the use of high-cost specialty drugs that are often rigidly managed” by payors. The authors noted, “Despite increases in the number and diversity of disease-modifying therapies for MS, prices have risen rapidly over the past two decades. The rise in high coinsurance cost-sharing models, coupled with escalating drug prices, means that patients will increasingly face prohibitive out-of-pocket spending.”

What the future holds

The healthcare industry is on the cusp of harnessing the power and promise of predictive analytics, and hospitals and health systems will play a vital role. A January 2019 Deloitte survey about hospital payment models noted, “Most health systems’ technology adoption strategies are focused on organizing clinical data and information and adopting EHR systems and analytics capabilities to interpret the data. These technologies will likely continue to be critical.” Deloitte researchers stressed that hospitals must “derive meaningful information from data to monitor patients” and that “new ways of collecting, processing, and analyzing data” will be critical.

We believe these new approaches will include improved data analytics platforms capable of analyzing multiple datasets – comprising billions of data points – that can uncover patterns and help predict outcomes. New technologies will analyze insurance claims data, electronic medical records and even real-time sources, such as Fitbits and similar wearable devices, to provide a more comprehensive view of a patient than ever before.

The incorporation of these data sources and information that help define the social determinants of health will provide clinicians with a holistic view of a patient’s health that we have never seen before. The predictive and prescriptive potential of data analytics will change how health care is delivered and lead to significant advances in treatment that will forever improve the lives of patients with chronic disease.

Dr. Chase Spurlock is the founder and CEO of IQuity, a Nashville-based data analytics company that works with stakeholders to predict, detect and monitor disease to lower the cost of health care and improve outcomes by finding and fixing autoimmune disease.

Dr. Michael Fleming is past president of the American Academy of Family Physicians and the Louisiana Academy of Family Physicians. He is founding director, chairman and chief medical officer for Antidote Education Company, which offers continuing education for healthcare providers.


Subscribe Today

Get the latest and greatest healthcare news and insights delivered to your inbox.

Speak Your Mind