Applied Health Analytics: An evolution in health analytics 1 Applied Health Analytics: An evolution in health analytics
Applied Health Analytics: An evolution in health analytics Executive Summary Today s healthcare providers facing a rapidly changing delivery system and the requirement to manage not only the quality of their patients healthcare but also the cost of their healthcare. While providers want to care for their patients, they find themselves ill equipped to meet these challenges and, as a result, feel frustrated and discouraged with today s healthcare environment. Today s point-of-care technology is primarily focused on record keeping and provides very little support to providers in their efforts to both manage a patient s healthcare and reduce healthcare costs. To accomplish those goals, providers require access to information about the entire range of providers treating the patient including the diagnoses, procedures and costs being rendered by those providers. However, the sheer volume of this data is overwhelming and precludes any reasonable review in the short timeframe allowed by today s office visit. Providers require analytics tools that will digest the data, produce concise patient-centric summary information and allow the provider to quickly and effectively respond to issues with quality, utilization and compliance with treatment plans. However, conventional analytics systems have failed to evolve from their original use in supporting the requirements of policy makers and insurance plans. These systems continue to produce vast amounts of statistical information and focus on the same factors and information that drive healthcare policy, plan design and reimbursement models. The result of rethinking this problem is a new form of healthcare analytics referred to as, applied health analytics. Applied health analytics focuses on identifying and delivering a subset of patient-centric information that specifically pertains to point-of-care operations and generates concise actionable insights. 2 Applied Health Analytics: An evolution in health analytics
The development of the applied health analytics methodology defined several key principles and produced a core set of specific actionable insights. These insights are expressed as succinct task lists that allow providers to efficiently and effectively resolve issues and deliver positive improvements in a patient s healthcare as well as reduced healthcare costs. In effect, applied analytics transforms the Triple Aim from an aspirational framework into an operational objective. As a field of study, analytics has existed for millennia. However, the science of analytics took a huge leap forward in the 1960 s when various universities used the newly available power of computers to create statistical analysis systems. And healthcare was a primary catalyst for that leap. Development of one of the earliest systems, Statistical Analysis System (SAS), was actually funded by a grant from the National Institutes of Health 1. These analytics systems are focused on identifying patterns in data and their ability to find and define those patterns grew along with the advances in computing power. Initial development of SAS and other analytics systems began in the mid-1960 s with the systems reaching commercial viability during the mid-1970 s. Throughout the 1980 s and the 1990 s, these health analytics systems were largely relegated to the academic world, governmental agencies and major health insurance companies. In the academic environment, these tools were used to examine patterns within comorbidities and develop improved treatment guidelines. Governmental agencies, such as HCFA, used health analytics to evaluate and develop the reimbursement models for managed care health systems such as Medicare Advantage. Insurance companies leveraged health analytics to substantially refine both their actuarial systems and their managed care reimbursement models along with identifying optimal practice patterns. One of the pioneers in population health analytics is Johns Hopkins. The Johns Hopkins School of Public Health was established in 1916 and, by the 1980 s had earned a solid reputation as a leader in the development of statistical models for healthcare. Having 3 Applied Health Analytics: An evolution in health analytics
access to the mainframe systems needed to develop analytics systems, the staff at Johns Hopkins began work on a model that would allow providers to objectively assess and quantify the health risk presented by an individual patient. The result was the Johns Hopkins ACG system, one of the most widely used and thoroughly tested health risk assessment and predictive models in the U.S. healthcare industry. Unfortunately, the insights and efficiencies being produced by these health analytics systems were largely unavailable to point-of-care providers. For that matter, health analytics were of little interest to healthcare providers who operated in a predominately volume based fee-for-service environment. The lack of incentives within the U.S. healthcare industry prevented the widespread use of information technology that was, by the arrival of the millennium, pervasive in almost every other industry. As late as 2006, fewer than 10% of all U.S. hospitals possessed an integrated EMR system. 2 Physicians were just as far behind the technology curve. In 2008, surveys found that fewer than 40% of physician practices had an EMR system. 3 That situation changed radically in 2009 with the passage of the Health Information Technology for Economic and Clinical Health Act (HITECH). The HITECH Act implemented several initiatives that served to drive interoperable EMR adoption in the U.S. By the end of 2009, EMR adoption had reached nearly 50% and by 2013 roughly 80% of office physicians were using EMR systems. 4 5 However, another challenge quickly became apparent. Continuing shifts in the American healthcare model created a critical need to leverage the point-of-care technology for much more than record keeping. In 2010, on the heels of the HITECH Act, the American healthcare system implemented the Patient Protection and Affordable Care Act (PPACA). ACA implemented a broad spectrum of changes in the U.S. healthcare system but perhaps the most prevalent change was a surge in value-based reimbursement models and risk sharing. While health insurance payers had long assumed virtually all financial risk associated with the U.S. healthcare system, the need to control costs and reduce health insurance prices became an overriding economic concern. The cost of healthcare was presenting an imminent threat to the continued viability of the U.S. employer-based health insurance system. 4 Applied Health Analytics: An evolution in health analytics
Family health insurance premiums had reached an average of $15,022/year 6 in an economy with a median household income of $49,276 7. In an effort to manage those costs and reduce health insurance prices, payers implemented value-based reimbursement models that shifted large portions of the financial risk down to both patients and providers in the form of High Deductible Health Plans (HDHP) and shared risk provider contracts. For providers, this was an entirely new challenge to their traditional business model. A challenge that would require many of the same analytics tools and the expertise that payers had developed to manage the healthcare costs of a patient population. Leveraging the expansion of point-of-care technology and the growth of value-based contracts in both the public and private markets, an avalanche of analytics vendors appeared almost overnight. By 2015, nearly all health systems vendors were touting analytics as part of their offerings. Originally designed to serve academics, payers and governments, these population health analytics systems generated reams of reports that analyzed mountains of claim, clinical and financial data from every conceivable angle and level of detail. While the analytics technology had now become far more accessible to providers, the ability to understand and apply that deluge of data and information remained beyond the capabilities of most healthcare delivery organizations. This is the problem that forced a rethinking of conventional healthcare analytics and prompted the development of applied health analytics. Applied analytics is an evolutionary change that reduces complex population health analytics into key elements that can be applied to the day-to-day operations of a healthcare delivery organization. In essence, applied analytics is based on finding and delivering those crucial bits of information known as actionable insights. In their simplest form, actionable insights are clear, concise and achievable opportunities to effect a positive change in a situation or status. For example, producing a report on the average price of procedures is not an actionable insight for providers. Providers can do little if anything to affect prices. Conversely, placing an entry in a patient s record regarding poor compliance on a specific medication therapy is an actionable insight. 5 Applied Health Analytics: An evolution in health analytics
The methodology used to implement applied analytics is defined by a few key principles. The first key principle of applied analytics is that it focuses on a small subset of the myriad of measures and metrics that are produced by health analytics. This subset of actionable insights contains only those issues and opportunities that relate to a specific patient or provider and can be directly affected by providers working at the point of care. The second principle of applied analytics is that the components of this subset can also be directly transformed into tasks and organized around the operational roles within a primary care delivery organization. In general, these tasks are segregated into management tasks and point of care tasks. Management tasks are typically presented as exception reports. These reports focus on specific providers and patient cohorts that require increased support and coordination from the organization. Examples of these reports could include providers exhibiting excessive utilization relative to peers, providers with lagging performance in quality measures or patient cohorts requiring advanced care management programs. Point of care tasks are generated as concise bulleted lists focused on an individual patient. For example, these tasks could include specific gaps in care, poor medication compliance, maintaining accurate risk scoring and care coordination with specific specialists. In all cases, these tasks are focused on resolving outstanding issues and opportunities identified through the use of health analytics. The third principle of applied analytics is that the individuals who are assigned responsibility for resolving exceptions or completing tasks must possess both the skills and the authority to needed to successfully resolve the issue. For example, tasks that require a clinical order must be assigned to roles that have the authority to issue clinical orders or are covered by a standing order from an appropriate authority. Management tasks must be assigned to roles that have the knowledge and authority needed to communicate, negotiate and issue final decisions related to those exceptions. The fourth and final principle of applied analytics is perhaps the most challenging because it is hindered by limitations in today s EMR technology. In order to maximize the efficiency 6 Applied Health Analytics: An evolution in health analytics
and effectiveness of applied analytics, tasks must be presented at the optimal time and place for completing the tasks. Although management tasks are more flexible with regard to timing and location, a concise list of patient focused tasks must be delivered to the provider at the point of care. Regrettably, a significant percentage of today s primary care practices remain paper based with automation that only addresses appointment scheduling or claims submission. Even those practices that have implemented EMR systems face challenges from vendors who demand exorbitant fees to allow integration of external systems with the EMR. Nonetheless, financial necessity will overcome these challenges and the ability to dramatically improve the coordination, efficiency and effectiveness of healthcare in the U.S. healthcare market will be achieved. In summary, applied health analytics brings a new level of simplicity to healthcare and, as da Vinci is often credited with saying, Simplicity is the ultimate sophistication. The next stage in the evolution of health analytics will be an exponential reduction in the volume and complexity of the information being produced. Actionable insights will be delivered directly to the point-of-care where steps to improve patient health can be immediately implemented. These insights will allow providers to transform the triple aim from an aspirational framework into an operational objective. Applied health analytics will enable a more effective and more efficient healthcare delivery system that empowers the provider, focuses on specific tasks and builds population health one patient at a time. 7 Applied Health Analytics: An evolution in health analytics
Sources 1 https://en.wikipedia.org/wiki/sas_institute#cite_note-agrestimeng2012-7 2 Smaltz, Detlev and Eta Berner. The Executive s Guide to Electronic Health Records. (2007, Health Administration Press) p.03 3 National Center for Health : United States, 2008]. Retrieved 15 December 2009. 4 Are More Doctors Adopting EHRs? Retrieved 31 March 2011 5 Office-based Physician Electronic Health Record Adoption. dashboard.healthit.gov. Retrieved 2017-01-18. Why Citra? Citra s patient-centric technology platform aggregates clinical, financial, and patient information from multiple sources to create a holistic perspective of a provider s panel and individual patient interventions within the health care ecosystem. 6 http://www.commonwealthfund.org/~/media/files/publications/issue-brief/2012/dec/premiums/pdf_schoen_ state_trends_premiums_deductibles_2003_2011_exhibits.pdf 7 Median Household Income in the United States (MEHOINUSA646N), https://fred.stlouisfed.org/series/mehoinusa646n Increased Quality Increased Patient Satisfaction Achieve the Quadruple AIM! Lowered Cost Improved Provider Satisfaction Citra ensures that the right information is available to the care team and provides care capabilities to support the patients engagement in issues related to optimal health outcomes. P P P P As additional services are anticipated, care extensions are available from Citra to schedule, redirect and / or service patient needs to improve patient satisfaction, quality of service and financial outcomes. Improved care and gaps (in care) closure rates Care plan development and management by the extended (Citra) care team Discharge plans are incorporated into longitudinal (chronic condition) care plan to avoid readmissions and associated costs/penalties 8 Applied Health Analytics: An evolution in health analytics Learn more about how we make the business of healthcare simple: www.citrahealth.com