Big data has its limits in predicting how patients with chronic conditions will need and use healthcare, says this HealthAffairs blog post. The authors say more focus should be put on understanding patient-reported information.
They conclude:
“By asking patients about their ability to manage chronic disease, we stand a better chance of identifying which patients are most in need of additional services. Patient-reported outcome measure instruments have been costly to administer, but this will be less of an issue as we transition to electronic health records and more routinely capture patient-reported measures in daily practice. Going forward, we need to determine how patient-reported data can best contribute to prediction tools and to design and validate instruments that can reliably connect patient data to actionable outcomes.
“Provider intuition and patient self-knowledge are valuable additions to the data bytes collected from medical claims and clinical information systems. Today, capturing and applying this information is largely an art. Going forward, analytics will need to adapt so that this valuable but nuanced information can more readily and effectively blend with clinical and financial data, allowing provider organizations to better care for the highest risk patients.”
“We’ve survived for a lot of years with regards to small data, and now there’s just been an onslaught of accumulation of information, everything from your mobile phone to your car,” T. Scott Law, founder and CEO of revenue-cycle-management services provider Zotec Partners, told Becker’s. “Everything you do is collecting data points that can be impactful for business.”
Becker’s noted that “With data, gut reactions and personal bias have been essentially eliminated from business decisions because the data provide many of the sought-after answers.”
“For example, one radiology practice conducts 300,000 procedures per year, which generates approximately 250,000 claims per year. One claim requires about 350 data elements. That equates to 87,500,000 pieces of data elements each year from just one radiology practice. Four practices with similar case volumes would generate nearly 350 million data elements a year, such as social data, demographic information, social patterns, clinical data and buying patterns, including when patients like to pay their bill.”
Becker’s reported that “Zotec Partners’ platform draws from the troves of data to create personas of individuals and payers to optimize the billing process by determining an individual’s propensity to pay or the propensity for friction. Knowing these tendencies ahead of time allows hospitals to tailor billing interactions and collection techniques to individuals to minimize friction and maximize collections.”
“Based on a person’s characteristics and tendencies, hospitals can decide how to best interact with an individual and ultimately collect money. For example, a patient’s demographics can suggest the likelihood that he will respond to a text message notification about medical bills versus receiving bills in the mail.”