DOS - Data Operating System
Health Catalyst Data Operating System (DOS™) is Health Catalyst’s response to a simple truth: The future of healthcare will be centered around the broad and more effective use of data
DOS is a healthcare-specific, open, flexible, and scalable data platform that allows customers to integrate and organize their disparate data sources to enable analytics. It serves as a digital backbone, allowing customers to extract data from transactional source systems, combine disparate data sets into a unified source of truth and query the dataset directly. DOS is primarily a cloud-based technology that we typically provide through Microsoft Azure and through our private data center.
DOS was designed and purpose-built to handle the complex, ever-evolving nature of healthcare-specific data. This includes healthcare-specific terminology, data governance, and metadata management. By creating healthcare-specific data models to organize industry-specific data, we enable faster and more repeatable analytics and insights. We have developed the capabilities to turn these insights into actions by connecting our analytics into the workflow systems, such as an Electronic Medical Records (EMR).
Differentiating attributes of our DOS include:
- Data warehouse. Our innovative late-binding architecture has a proven track record of agility and adaptability to new rules, vocabularies, and data content. Our open and flexible platform enables database-level querying and custom analytics use-cases.
- Source connectors. Our platform is designed to quickly ingest data from the numerous information systems and siloed data sources that our customers possess. The DOS data management console enables customers to manage robust ETL processes and scheduling.
- Reusable data logic. Registries, value sets, and other data logic sit on top of the raw data and can be accessed, reused, and updated through open APIs, enabling customer and third-party application development. We update hundreds of registries, value sets, and measure logic regularly. This reusable, healthcare data content enables customers to achieve analytic value more quickly than leveraging homegrown or cross-industry products and services.
- Machine learning. Embedded within DOS are machine learning algorithms that our customers can easily leverage for predictive analytics. In some instances, customers can build their own machine learning data pipelines within DOS.
- Terminology services. By standardizing the complex language used to code entries in various health records and clinical systems, DOS facilitates decision support, consistent reporting, and analytics and interoperability.
- Closed-loop EMR integration. Bridges the gap between insight and action by reducing data lag, interjecting knowledge at the point of decision-making, including back into the workflow of source systems, such as an EMR.
- Text processing. Enables the extraction of additional data currently trapped in various unstructured text blocks.
- Real-time streaming and interoperability. Near or real-time data streaming from the source all the way to the expression of that data through DOS, supporting both transaction-level exchange of data and analytic processing.
- Big data. Ability to access, organize, and analyze massive and unique, structured and unstructured, data sets allows us to drive differentiated analytic insights for our customers.