The Key to Leveraging a Data-Informed Organization
Twenty years ago, business priorities within a healthcare organization were largely determined by a few select executive visionaries. Today, the most successful healthcare organizations use data to validate ideas and further refine them through advanced studies and predictive models.
The data-driven healthcare organization has matured with recent advances in data technologies, the rise of artificial intelligence and machine learning capabilities, and the availability of high-performance hardware and storage efficient via commercial cloud (AWS, Azure, Google Cloud). This influx of technology and talent into the market has lowered the barrier to entry for data-driven intelligence. Market competition and large-scale innovation have reduced the learning curve as well as the cost.
The essential role of a solid data architecture – and how to achieve it
Becoming a data-driven healthcare organization starts with having a strong data architecture. Data should be secure, but easily accessible to those who need it. Data must be inexpensive to store in extremely large volumes, but systems must be able to traverse it in seconds or less. Complex data such as JSON or images should be accessible through standard query languages such as SQL.
Enter the Healthcare Data Lake – a collection of datasets focused on patient claim history, analytical results from quality measurement and risk adjustment programs, clinical data from health record systems electronics and the social determinants of health data. By eliminating the barriers of siled data sources in different formats, Data Lake creates a comprehensive, consolidated data source for healthcare organizations to access on demand to support a variety of clinical use cases. and commercial.
Common misconceptions about data lakes
When I first heard the term “Data Lake” and started to investigate, the all-encompassing promise of a global data source sounded a bit daunting; as something that would be very big, messy and difficult to manage and value. It’s not an uncommon perception – and not entirely unfounded. However, when properly implemented, a data lake offers speed, accuracy, and ease of integration with the organization’s current tools and workflows, avoiding these major data lake misconceptions:
#1 – “A data lake is complex and with this volume of data, it would take weeks to update.”
Some data lakes support data refreshes within hours. It can take two weeks to populate the same data into a healthcare organization’s own on-site data warehouse.
#2 – “This massive amount of data will be too difficult to use and understand.”
The most effective data lakes are those that provide access to high levels of structured data – where all sources can be connected through common keys, with data dictionaries that describe the data elements.
#3 – “We’ve already spent years and millions of dollars building our own analytics data warehouse and we don’t want to throw away all that work.”
This is not an either/or proposition. The technologies that power data lakes often use data sharing and replication to move data between regions and even between clouds or in private data centers. Data lakes can be an extension and enrichment of existing data warehouses.
#4 – “If I’m using a third-party data lake, my team can’t connect all of their analytics tools to it.”
Tools such as SageMaker, SAS or even line-of-business applications can securely connect to the data lake. This means healthcare organizations can view the data lake as an extension of their current datasets and encourage direct connectivity when needed.
Leverage a health data lake for your clinical and business initiatives
Data lakes are historically made up of structured and unstructured raw data; the more structured the data, the easier it is to understand and use for a wide range of use cases. Some data lakes also allow for the integration of additional data sources, which means healthcare organizations can enrich their data for more complete and meaningful insights to drive their clinical and business initiatives.
Let’s explore a few use cases of data lake for healthcare:
– Leverage clinical data to identify populations or diagnoses that may be underreported for risk and quality programs
– Equip care managers with access to real-time clinical data to proactively prevent avoidable emergency room visits, hospitalizations, etc.
– Integrate meaningful clinical results into provider report sheets
– Monitor opioid prescription patterns to identify potential patient safety issues and detect potential cases of fraud, waste and abuse
– Evaluate member care seeking models for use in benefit design, network and quality initiatives
Use Case Example: Improving Cancer Screening Rates in Seniors
A health plan wants to understand where to focus its patient awareness campaigns to improve cancer screening rates in the elderly, so the data analyst connects to the data lake, captures non-compliant patients for metrics relevant cancer screening using a basic SQL query, groups by zip code and displays the results in tabular form. The analyst then creates a heat map to visually display where patient-specific measurement deviations are concentrated using a visualization tool. The outreach manager can use this report to quickly identify a few locations to focus outreach and inform their staffing model for interventions. As a result, a project that previously would have taken months to complete can now be completed in days, accelerating value creation for members and the organization.
Now is the time to discover the value of a health data lake
If your organization uses data to inform clinical and business decisions and you’re not investing in a cloud-based data lake, now is a great time to start. A healthcare data lake can accelerate the creation of value for your organization – enabling you to confidently merge and enrich your complex and disparate data to support analytics, business intelligence and analytics initiatives. exploring data that positively impacts care delivery and your bottom line.
The data-driven healthcare organization is here.
About Tom Laughlin
Tom Laughlin is an expert in healthcare data management and analytics, with nearly 20 years of experience developing technology solutions that enable organizations to improve healthcare outcomes and economics. He currently leads Solutions Engineering at Inovalon, where he and his team focus on customizing software solutions to meet the unique needs of health plan customers.