- Big data. The Internet of Things. Population health management. Cognitive computing, machine learning, natural language processing, and informatics. PQRS, CPOE, MU, BI, and IG.
The healthcare information technology industry sometimes seems like a soupy swirl of buzzwords and acronyms, nebulously defined and poorly explained by those in the know.
When reading through regulations, proposed legislation, media articles or academic studies, it can be difficult to follow the path of emerging technologies or the course of the latest trends without fully understanding how certain terms connect with each other and with the day-to-day experience of healthcare providers.
What are the top ten most popular buzzwords used by industry experts, and how exactly do they relate to the overarching field of healthcare big data analytics? In alphabetical order, here are some of the most important terms to know during the healthcare industry’s ongoing technical revolution.
Accountable care is often used as a catch-all term for the organizational and financial changes required to embrace value-based reimbursement. From expanding office hours to tracking immunizations to rewarding providers for better patient outcomes, accountable care is about transforming workflows, technical infrastructure, and revenue cycles into a patient-centered care continuum.
The accountable care organization (ACO) formalizes these initiatives with a contract that requires a provider – or a coalition of several participants – to meet standardized quality measures. Many ACO contracts offer financial bonuses for high performance, and some risk-based arrangements penalize providers for failing to live up to expectations.
Accountable care is a high priority for Medicare and private insurers, all of whom are seeking more effective methods of controlling costs and improving outcomes.
All data is big data in the modern healthcare industry. At its core, big data is any data set that combines two or more sources to generate an insight unavailable from just a single stream of information. For example, some providers are merging historical patient data with real-time feeds of vital signs or lab results from their EHRs, providing a richer prediction of what might happen to a patient based on his or her past events and current condition.
Big data analytics is the foundation for many of the industry’s most promising and innovative care strategies. Effective and comprehensive population health management, discussed later in this article, requires the integration of clinical, administrative, demographic, socioeconomic, and patient-generated data sources to stratify risk, forge strong relationships, and provide meaningful preventative care.
Clinical decision support
Any technology that gives a provider a helping hand with diagnosis or treatment can technically be called a clinical decision support tool. More specifically, these technologies often use big data analytics to suggest the optimal course of treatment, flag allergies or drug interactions, remind providers of missed opportunities, or volunteer suggestions for diagnoses based on available patient information.
Advanced CDS tools are starting to leverage cognitive computing and graph database technology to make connections between disparate data sets in extraordinarily innovative ways. Providers can access dashboards and risk calculators at the point of care, which allows them to present critical information to patients and make collaborative, informed decisions. These technologies will continue to evolve rapidly as precision medicine and the learning health system evolve.
This discipline of data science combines health information management, computer programming, clinical experience, and EHR skills. Informaticists, who can have a nursing background, a medical degree, or a computer science education, are often responsible for configuring electronic health record workflows, designing new features and tools, developing algorithms and programs to generate reports, and aiding researchers working to solve problems in patient care.
Clinical informatics became a board certified sub-specialty for physicians at the end of 2013, but nurses have long been taking on the task of improving systems integration and interoperability, creating clinical care dashboards, and handling the increasing amount of quality and outcomes reporting required for participation in federal programs like the Physician Quality Reporting System (PQRS) and EHR Incentive Programs.
The American Health Information Management Association (AHIMA) has popularized the term information governance (IG), also known as data governance, in recent months as healthcare organizations struggle to come to terms with the sheer volume of big data that passes through their servers each and every day.
Information governance can be defined as an organization’s overall strategy to collect patient data, maintain a high level of data integrity, store and transmit information in a secure and compliant manner, and use clinical and administrative data effectively for organizational goals.
A strong and well-communicated information governance plan is the foundation for many other data-driven initiatives, like population health management, health information exchange, and accountable care.
Organizations are encouraged to follow AHIMA guidelines and other industry recommendations to generate accurate, complete, and standardized data sets that will ensure patient privacy, safety, and security across the care continuum.
Internet of Things
The definition of the Internet of Things is still evolving as healthcare organizations begin to explore the integration of smartphones, medical devices, consumer gadgets, and formalized electronic health records to create an interconnected platform for digital health.
Also known as the Internet of Everything, the IoT can include any device with an internet connection: pill bottles that automatically transmit refill requests, scales with Bluetooth that record weight in the patient’s EHR, smartphone apps that track sleep, diet, and exercise, fitness trackers and smart watches that generate reports, share research data, or deliver alerts, and implantable medical devices like pacemakers that can provide physicians with critical information about vital signs or emerging risks.
An exciting area of innovation for consumer developers and medical device makers alike, the Internet of Things is a nearly limitless way to provide healthcare organizations with all the patient data they could possibly need – and then some. Workflow challenges and interoperability concerns currently limit the effectiveness of many IoT devices, but numerous stakeholders are doing their best to address these challenges.
Electronic health records that functioned as little more than a clone of a paper chart were not initially designed to talk to each other very effectively. In the early days of health IT, proprietary data standards and limited cooperation across vendor lines left many providers with “walled garden” systems that cannot meet current expectations of health information exchange and cross-organizational collaboration.
Interoperability is the ability of a health information system to transmit and receive patient data in a usable manner no matter where or how the data originated. As the industry embraces the idea that data must flow across care settings for the good of the patient’s health, vendors have started to make a concerted effort to standardize their products and exchange data on a broad scale.
Private interoperability organizations, regional and state-level health information exchange organizations, standards bodies, and federal efforts on the part of CMS and the ONC are all contributing to the development of an interoperable ecosystem of data exchange.
While financial barriers and competitive attitudes amongst rival organizations are contributing to the slow and process of unknotting the health data pipelines, the healthcare industry has made significant progress in the past few years.
Learning health system
The goal of many of these health IT efforts is to create the learning health system. Defined by the Office of the National Coordinator as an interoperable, intelligent, and accessible collaborative ecosystem of patient-centered care, the learning health system is a long-term goal of healthcare reform.
The ONC has released several different roadmaps to help guide the industry towards these ambitions, which rely heavily on seamless health information exchange, robust population health management, and sophisticated big data analytics.
Population health management
In order to engage in accountable care, most effectively use scarce resources, and ensure that patients are getting the holistic care that they need, healthcare providers must enlist the help of recognized population health management strategies and their associated technologies.
Population health management can be defined as any activity that improves the health or care of a single patient by viewing that patient as one small piece of a broad group of his or her peers. This may mean using a risk score calculator based on big data analytics to pinpoint one patient’s likelihood of developing heart disease, or helping another patient manage her diabetes by drawing on engagement and adherence lessons learned from previous cases.
Chronic disease management and preventative care are both major facets of any effective population health management program, which may include health IT data analytics tools, human care coordinators, patient engagement features like mHealth apps or questionnaires, and collaborations with external organizations such as public health departments, schools, or employers.
Population health management is viewed as a proactive and cost-effective way to reduce spending, encourage healthy behaviors, and streamline provider workflows.
While population health management focuses on large groups of patients as a whole, precision medicine is concerned with highly specialized and individualized treatments based on how a specific person responds to a therapy. With the help of many of the “omics” fields, precision medicine can pinpoint a patient’s genetic risk of developing a certain cancer and then use features of her DNA to find the optimal treatment.
Precision medicine holds a great deal of hope for patients with extremely rare diseases, but may also contribute to breakthroughs in the diagnosis and treatment of unfortunately common conditions, such as Alzheimer’s and Parkinson’s diseases.
Researchers are currently pouring through truly massive big data sets to uncover new insights and make novel connections between cause and effect for a number of pressing concerns. With strong endorsements from the White House, lawmakers, academic research institutes, and specialized treatment centers across the nation, precision medicine may just be the wave of the future for the treatment of cancer, neurological diseases, and inherited conditions of all kinds.