Piotr Kula, Associate Partner
Electronic health records, Hub/specialty pharmacy data, and patient claims have the power to help companies fine-tune commercial activities, better target customers, and discover more insights into the patient journey than ever before. However, companies need to be able to organize and pull insights from this data quickly.
Beghou Consulting developed ARMADA to address this need. Built on Apache Spark with Databricks, ARMADA allows commercial teams to manage and analyze vast amounts of data efficiently. Since debuting ARMADA, which stands for Adaptable, Resilient Multiprocessing Architecture for Data Analytics, in April 2019, Beghou has quickly implemented the technology with a half-dozen life sciences companies.
Some benefits of using ARMADA include:
- Unprecedented visibility into data processes: Companies can now track warehouse status, data delivery schedules, data field origin, complex data manipulations, business logic, and downstream dependencies in real time through a user-friendly interface.
- Scale with data needs: ARMADA’s robust and dynamically scaling architecture can handle data volumes of any size—up to the largest life sciences industry databases (hundreds of terabytes) with ability to scale for the future.
- Increased control over data: Commercial operations teams can view the status of data processing around the clock or decide to manage all processing and analysis in-house.
- View customizable monitoring dashboard: ARMADA enables companies to compile information about their jobs and data sources, provides summaries of job completions, and runs performance metrics.
ARMADA has already been proven to help companies uncover insights five times faster than traditional processing methods. An ad-hoc claims analysis for 38 GB (~93 million rows, five products) found that ARMADA could process the average dose size per treatment by drug in ~5 minutes, reimbursement rate for specific treatment in ~1.5 minutes, and patient re-treatment rates by product in ~6 minutes.