Clinical Informatics Building Blocks

In the realm of clinical informatics, regulatory frameworks provided by bodies like the Centers for Medicare & Medicaid Services (CMS) and the Office of the National Coordinator for Health Information Technology (ONC) establish essential guidelines and standards, ensuring compliance and fostering a secure environment for data exchange. Interoperability enables seamless communication among diverse healthcare systems and stakeholders, thereby enhancing care coordination and decision-making.

Policy & Regulations

In the United States, policies and regulations related to health information technology are largely advanced through the ONC. The ONC is part of the US Department of Health and Human Services and is charged with advancing the development of national health information technology (IT) capabilities and establishing expectations and standards for data sharing.

CMS sets forth rules and regulations governing the administration, quality, reimbursement, and utilization of healthcare services provided to Medicare and Medicaid beneficiaries.

Together, the ONC and CMS collaborate closely to ensure alignment between national health IT priorities and CMS initiatives, promoting the seamless exchange of health information, enhancing care coordination, and driving innovation to achieve better outcomes.

Additional agencies with a role in developing healthcare IT policy and regulations include the following:

The Food and Drug Administration (FDA) regulates medical devices, including clinical decision support tools and artificial intelligence.
The Agency for Healthcare Research and Quality (AHRQ) develops evidence to advance the quality of health care.
Health Level Seven International (HL7) develops standards for transporting data between systems.

Latest Health IT Policy News

Health Data, Technology, and Interoperability (HTI-1): Certification Program Updates, Algorithm Transparency, and Information Sharing Final Rule | January 2024
- Read the AAN’s submitted comments
2023 Report to Congress: Update on the Access, Exchange, and Use of Electronic Health Information Through Trusted Networks | March 2024
Trusted Exchange Framework and Common Agreement: Version 2.0 of the Common Agreement | April 2024

Overview of Interoperability

As defined by HIMSS, interoperability is “the ability of different information systems, devices and applications (systems) to access, exchange, integrate and cooperatively use data in a coordinated manner, within and across organizational, regional and national boundaries, to provide timely and seamless portability of information and optimize the health of individuals and populations globally.”

Interoperability is essential for the consistent delivery of high-quality neurological care, and maximizing electronic health record (EHR) interoperability is one of the AAN’s principles for health care delivery.

Practice Top 5

Learn the top 5 key facts you should know about interoperability.

For those who participate in CMS’s Quality Payment Program, promoting interoperability makes up a significant part of a practice’s Traditional Merit-Based Incentive Payment System (MIPS) score. Learn more with the AAN’s Top 5 Things to Know about Promoting Interoperability.

Interoperability Resources

Browse resources on the role of interoperability in healthcare.

Health Information Standards

Standards are the backbone of interoperability. They define how data should be structured to ensure health systems are able to share, store, and interpret information uniformly. Standards in healthcare include:

Terminology Standards—These are healthcare code sets and classification systems, such as ICD for diagnoses, CPT for procedures, SNOMED for clinical concepts, LOINC for lab observations, and RxNorm for clinical drugs. The Unified Medical Language System (UMLS ) Metathesaurus contains over 100 healthcare terminologies, classifications, and ontologies.

Content Standards—These provide guidelines for organizing electronic documentation and determining the necessary information. Content standards ensure medical data is presented clearly and comprehensively. Examples of content standards include:

Transport Standards—These standards facilitate transmission of data between different health systems. They define the format, document architecture, data elements, and application programming interfaces (APIs) to use in data exchange. Examples of transport standards include:

Privacy and Security Standards—These establish administrative and technical rules for protecting sensitive health data from misuse, unauthorized access, or disclosure.

People and Processes

The true power of informatics lies in its holistic approach, which integrates not just technology but also the individuals—healthcare professionals and patients—and the processes governing their interactions. Through this synergy, informatics not only optimizes healthcare delivery but cultivates a culture of continuous improvement, ultimately leading to better patient outcomes and a more efficient healthcare ecosystem.

Resources for Improving Processes in Practice and the Usability of Health IT Systems

Additional resources specific to certain EHRs can be found in electronic health record learning management systems (e.g., Epic UserWeb and Oracle Health Learning).

Resources on Change Management and Engaging Patients and Caregivers in Care Delivery

Data Analytics and Management

HIMSS defines analytics as “the systematic use of data and related business insights developed through applied analytical disciplines (e.g., statistical, contextual, quantitative, predictive, cognitive, other models) to drive fact-based decision making for planning, management, measurement, and learning. Analytics may be descriptive, predictive, or prescriptive. Advanced forms of analytics are often organized into data science."

Descriptive Analytics

(HIMSS) Descriptive analytics is the analysis of historical data to understand what has happened in the past, focusing on summarizing and visualizing data to provide insights into patterns, trends, and relationships.

Example: Analyzing electronic health record (EHR) data to generate reports on patient demographics, disease prevalence, and healthcare utilization rates over time. Operational and quality improvement reports of clinical processes, for example, fall into this category.

Predictive Analytics

Predictive analytics is the analysis of historical data and statistical algorithms to forecast future events or outcomes, aiming to identify patterns and trends in data that can be used to predict likely future scenarios.

Example: Developing a predictive model to estimate the likelihood of readmission for patients with heart failure based on clinical variables such as age, comorbidities, and previous hospitalizations.

Prescriptive Analytics

Prescriptive analytics recommends actions or interventions based on insights derived from descriptive and predictive analytics. It goes beyond predicting outcomes to provide actionable recommendations for decision-making.

Example: Suggesting personalized treatment plans for glioblastoma patients based on predictive modeling of treatment response and clinical outcomes, considering factors such as genetic markers, tumor characteristics, and treatment history.

Examples of Data Analytics in Neurology

Predicting readmission in epilepsy
Population health for chronic disease management in multiple sclerosis
Process improvement in acute stroke

Adoption Model for Analytics Maturity (AMAM)

HIMSS has developed a roadmap for analytics adoption in healthcare institutions (Adoption Model for Analytics Maturity AMAM). AMAM has 7 stages, with 0 being the earliest, least mature adoption, and 7 being the most advanced/complex implementations with predictive analytics capabilities. These stages can be considered best practices in implementing healthcare analytics systems as well as obtaining a broad-strokes overview of the extent of the possibilities achievable with analytics tools.