Real-time healthcare compliance analytics can keep patients alive and well

Big Data Evangelist, IBM

Healthcare isn't slavery. Nobody, other than those who are unconscious or otherwise incapacitated, is an involuntary consumer of pharmaceuticals, treatments and other expressions of the medical arts.

Doctors aren't slave masters, so their "orders" are in fact recommendations that you can ignore, but at your own peril. In the engagement between medical practitioners and their customers, good-faith compliance is the patient's responsibility. Physicians can be sued for malpractice, but they can't be held responsible if their patients ignore their advice, withhold critical information, fail to take prescribed medicines or refuse to show up for appointments.

High-quality healthcare is a relationship of reciprocal trust between medical practitioners and their customers. If patients question their doctors' skills and integrity, they can always seek out alternatives (or, worst-case scenario, file malpractice and other civil suits). If doctors suspect their patients of non-compliance, they can break off the relationship. Or, more typically, doctors can try to salvage the relationship by looking into whether there may be any extenuating circumstances. For example, patients who are suffering from dementia may simply forget to show up for appointments, take their meds or avoid foods that might aggravate other conditions from which they're suffering. Likewise, as this recent article notes, "[some] patients often cannot follow doctors' orders because they face bigger challenges such as homelessness, financial instability, joblessness and emotional or mental issues."

Image courtesy of Openclipart and used with permission

In these cases, medical professionals must intervene in some way before it's too late. As the cited article states, "ignoring doctors' orders often lands patients in the hospital, perhaps suffering from a new complaint or worsening medical problem that takes longer and costs more to treat. Each year, about 125,000 people in the United States with treatable ailments die because they don't take their medication correctly, according to a New England Journal of Medicine report....More than half the 3.8 billion prescriptions written annually are taken incorrectly or not at all, the article said. Poor compliance is linked to between 33% and 69% of drug-related adverse effects that result in hospital admissions. And the Journal of General Internal Medicine reported that poor compliance is associated with approximately one-fourth of nursing home admissions."

Not only are lives at stake, but noncompliance also raises costs across the entire healthcare system. This impacts everybody, even the majority of patients who faithfully obey doctor's instructions. Insurance companies simply pass on the collateral costs of noncompliance to us all through higher premiums, co-pays and so on.

Medical professionals are between the proverbial rock and hard place when trying to determine whether, how and why patients are failing to comply. On one hand, their ability to help people depends on having intimate, current and accurate knowledge of people's physical conditions and behaviors. On the other hand, doctors can't be Big Brother, engaging in 24x7 surveillance of their patients' private lives and wielding the power to punish recalcitrants.

However, physicians can, within the bounds of privacy and propriety, use analytics to assess who might or might not be compliant. Using those insights, the healthcare system might identify the most appropriate interventions to minimize the impacts of noncompliance on healthcare outcomes. The agents of intervention might be case managers, social workers or even the caregivers themselves.

The cited article discusses a community health plan that is aggregating data from many sources to assess which patient segments might pose a noncompliance risk. The health plan has used big data analytics to determine that people with multiple or chronic conditions are the highest at-risk segments. The plan has incorporated these insights into its care management processes, enabling it to target interventions to these specific segments.

Privacy watchdogs may get nervous, but it will be interesting to see how this and similar healthcare initiatives leverage the Internet of Things (IoT) and quantified self (QS) technologies going forward.

What if at-risk populations can be incentivized to use IoT/QS-enabled pill-dispensers in their homes? What if they can be persuaded to wear IoT/QS-enabled devices that monitor whether they're taking their exact prescribed dosages, engaging in the prescribed therapeutic activities and otherwise following doctor's orders? And what if patients can be sent real-time reminders when they've failed to comply? In all these ways, people can be nudged to get back on the prescribed path immediately and gently, in a way that respects their privacy.

Personalized, real-time targeting of noncompliance interventions would be blessing for some at-risk populations, such as dementia patients. But it would be draconian and intrusive for others. As these technologies come into widespread use for personalized healthcare, the thicket of ethical dilemmas will grow thornier.