Clinical Data Registries, Their Impact on Patient Outcomes, and How AI Can Help

Patient registries are an invaluable source of information about the health of patients with a specific diagnosis, condition, or procedure. As centralized databases, they help to advance research and improve quality of care by compiling the huge volume of diverse healthcare data, including clinical history, medical care, test results, and demographics. Because they provide access to patient data from hospitals countrywide, and even worldwide, patient registries help:

  • Provide comprehensive background information about specific disease states/conditions
  • Inform routine clinical practice and disease management
  • Monitor treatment outcomes
  • Contribute to best practices in patient care
 

In this blog post, we look specifically at the challenges and opportunities associated with cardiovascular registries and the technological innovations that can help reduce the resources required for patient registry data entry.

Cardiovascular Registries and Their Impact on Patient Outcomes

Cardiovascular registries provide a wealth of knowledge for patients, healthcare providers, and clinical researchers. Given the costs, high utilization rate, and complications of cardiovascular procedures, regular monitoring of registry data is useful, particularly when the data are measured against national benchmark databases and public reports. One large suite of cardiovascular registries is the National Cardiovascular Data Registry (NCDR®) from the American College of Cardiology (ACC).

The NCDR includes:

 

 

The ACC is a non-profit medical organization of nearly 50k members, whose goal is to enhance the lives of cardiovascular patients through innovation, knowledge, and collaboration. The ACC sets stringent qualification criteria for accreditation; creates health policy, standards and guidelines; and operates national cardiovascular registries to measure and improve cardiovascular care.

Over 5.4k hospitals and outpatient providers worldwide take part in the NCDR, contributing millions of patient records. The data in these registries provide unified, actionable information to physicians and healthcare organizations (HCOs). HCOs that participate in the registries use the information to ensure they are meeting best practice guidelines, are using the appropriate treatments, set and maintain quality initiatives, and measure patient outcomes.

The real-world data available through registries can provide insights that are challenging to obtain during randomized clinical trials. During the pandemic, registries that collect COVID-19-related data have also been particularly helpful to understand the potential cardiac impact of the virus. Further, the databases are sources of information for surveillance as well as decision-making by regulators. For example, the feasibility of conducting prospective, active surveillance via national clinical registries for near real-time safety assessments of new medical devices (aspiration thrombectomy catheters) was recently demonstrated using the NCDR CathPCI Registry.

AI Can Automate Cardiovascular Registries

While patient and cardiovascular registries can have a significant impact on improving patient outcomes, there are limitations to conventional, manual methods of data abstraction to populate the registries — especially as patient data grow exponentially in volume. The amount of human resources consumed by manually abstracting data often results in a cumbersome, costly, and error-prone process.

 

To address these limitations, organizations are turning to artificial intelligence (AI) to automate data abstraction. Leveraging AI to populate clinical registries can:

 

  • Provide high-quality, accurate, complete data: AI can handle more data, from more sources, quicker, and with greater accuracy than humans. Methods such as natural language processing (NLP) can quickly and accurately translate unstructured data in free-text forms, such as pathology reports and clinical notes, a task that is virtually impossible for data abstractors.
  • Allow better investment of time and resources: Given that HCOs typically use human resources dedicated to updating registries, clinical abstraction and other related processes put a strain on an organization’s resources. Automating data abstraction frees up clinicians’ time to focus on caring for their patients and quality initiatives to improve patient care overall.
  • Creates uniform, standardized data: AI can normalize data to FHIR industry standards, meaning the data can be shared more readily between an organization’s data storage and reporting systems as well as other registries.
 

The result — AI-enabled, smart solutions that activate clinical data to improve the care of patients with cardiac conditions, all while informing research on innovative interventions and procedures.

How Carta Healthcare Supports Optimized Registry Completion

Carta Healthcare’s Atlas, an AI-assisted abstraction solution, helps organizations access the deep reaches of their data that are missed due to resource limitations, providing more accurate clinical registry completion, increased data availability, and the opportunity to drive greater value from those data. Atlas can reduce the amount of resources registry participation consumes, freeing up clinicians’ time while providing more accurate and efficient submission. With the help of our technology, registries allow healthcare providers to set up a virtuous feedback cycle, improving quality initiatives and patient care.

Read more about data registries and how Carta’s industry-leading, AI-driven technology allows HCOs to collect, analyze, and act on their data, creating a quality, trustworthy dataset whose value fuels data-driven decisions that ultimately improve care delivery.