We all know that data is important. Over the past two decades, business intelligence has become ubiquitous across industries, enabling organizations to collect, analyze and visualize vast amounts of information to make informed decisions. Today, those same tools, enhanced with advanced artificial intelligence, machine learning, and powerful analytics, have emerged as an important asset in healthcare, an area that remains a study of technological extremes.
On the one hand, clinical environments are increasingly characterized by some of the most advanced technologies, sophisticated imaging innovations and medical devices connected to the discoveries of genomics and personalized medicine that challenge the boundaries of supercomputing. On the other hand, core business processes such as approvals continue to rely on outdated methods, from faxing to paperwork.
Most surprising, however, at a time when data is considered the new “oil”, is the continuing inability of physicians to obtain, consolidate and use the “all health” data they need to determine the best course of care, achieve positive outcomes for patients and maximize the financial success of their practices. The resulting data gap is significant.
Bridging a gap only to find another
Significant progress has been made in recent years to bridge the data gap between payers and suppliers. Despite the vast volume of clinical data in their possession, physicians have historically struggled to access population-level intelligence held by payers. In contrast, payers had insight into trends shaping patient cohorts but had limited intelligence on the crucial nuances of care that dramatically impact individual patient outcomes.
The shift from a paid approach to a value-based care approach quickly clarified the importance of bridging this critical data gap and forced taxpayers and practices to more effectively share information to address performance and incentives. to payments. Significant gains followed, although the shift to a values-based approach revealed the importance and absence of an equally fundamental gap, namely the absence of data on ‘whole health’.
What is “total health” data and why is it important?
“Total health” data is information that, when combined with traditional clinical data, allows practices to have a full impact on the one metric that matters most: patient outcomes. For this reason, and because value-based approaches depend on results, ‘total health’ data is also what allows practices to excel in moving to incentivized payment models, including HEDIS and star ratings, which impact profitability. .
From a data science perspective, “total health” data must therefore include information relevant to each patient’s outcome. This includes SDOH, insights into mental and behavioral health and diagnoses and insights gained through the use of mobile devices, all consolidated on a platform that allows non-technical clinical users to discover useful information with the powerful algorithms and models offered by modern machine learning applications. A quick exploration of each of these data categories reveals why it is critical that practices include them in patient assessments and care regimens.
Research shows that 80% of an individual’s health is determined by factors other than access to quality care. Recently, the Physicians Foundation noted that eight out of ten physicians “believe the United States cannot improve health outcomes or reduce health care costs without addressing the social factors of health.”
Unsurprisingly, patients who cannot afford medication or go to appointments face ancillary health issues. The results can be tragic. For example, we now know that black Americans in many rural areas died at a 34% higher rate during the Omicron outbreak than white Americans in the same communities due to SDOH.
Fortunately, SDOH data, when accessible and used at the practice level, makes a difference. In fact, a responsible care organization recently analyzed expensive emergency room visits and found that many patients lived in the same poor neighborhood. Further analysis with machine learning applications found an extreme increase in emergency room visits on hot days, an indicator that led doctors to realize that patients’ homes lacked air conditioning, a fact that exacerbated health conditions. existing health. The non-clinical and counterintuitive step of purchasing cohort air conditioners dramatically reduced emergency room visits and made the ACO more profitable.
Mental health data
Behavioral and physical health are, of course, linked to mental health problems often associated with comorbidities, including substance abuse, eating disorders, anxiety and depression. As the National Institute on Drug Abuse notes, “about half of people suffering from a mental illness will also experience a substance use disorder at some point in their life and vice versa.”
Failure to adhere to treatment and drug plans is also a significant problem, and substance abuse can be a factor in suicide, the leading cause of death for many age groups. Clearly, practices benefit if they know the challenges to patients’ mental and behavioral health before completing patient assessments and as they work to ensure healthy outcomes.
Mobile device data
The pandemic has greatly accelerated the use of mobile smartphones and made them the primary communication channel for many patients and providers, from scheduling appointments to participating in consultations via telemedicine. Numerous mobile applications are now also available to track patient progress. Examples include those that track activity levels, blood pressure, and blood sugar, all of which are important factors for conditions like hypertension and diabetes.
Practices, therefore, should be able to include cell phone data in patient assessments and update electronic health records and treatment plans with real-time data.
Clearly, it is important that doctors and practices incorporate “total health” data into their health equity and value-based care efforts; however, it is a process that shouldn’t be taken alone. Any steps to incorporate external or new sources of patient data into the study should be undertaken with a partner who understands the regulatory issues associated with personally identifiable information and has a deep understanding of how the data will be stored, safeguarded and analyzed. Finally, the partner should be well versed in how practices can use the intelligence they acquire with the many intuitive AI, machine learning, and business intelligence tools now available to business users.
Jeffery Springer is Senior Vice President of Product Management at CitiusTech.