Lumiata Case Study: Intelligent Pipeline Orchestration & Automation with Ascend
Customer Company Size
Mid-size Company
Region
- America
Country
- United States
Product
- Lumiata Insights
- Ascend’s Autonomous Dataflow Service
Tech Stack
- Apache Airflow
- Apache Spark
- Python
- Scala
Implementation Scale
- Enterprise-wide Deployment
Impact Metrics
- Productivity Improvements
- Cost Savings
- Innovation Output
Technology Category
- Platform as a Service (PaaS) - Data Management Platforms
- Analytics & Modeling - Big Data Analytics
Applicable Industries
- Healthcare & Hospitals
Applicable Functions
- Product Research & Development
- Quality Assurance
Use Cases
- Predictive Maintenance
Services
- Data Science Services
- System Integration
About The Customer
Lumiata is a company that is focused on making healthcare smarter. They work with major health providers to take data -- ranging from electronic medical records, claims, lab work, physician notes, and more -- and transform it into specific recommendations to improve patient outcomes and reduce delivery costs, known as Lumiata Insights. Their business is built on delivering this advanced data product. Given the foundational importance of data, Lumiata built a world-class team of highly sophisticated data engineers and data scientists. These teams leveraged modern technologies to build the data pipelines that would fuel their Insights product, including Airflow, Scala, and Spark. However, these tools also came with significant engineering overhead and the team’s productivity was being eroded as they battled with long iteration cycles and difficult maintenance.
The Challenge
Lumiata, a company focused on making healthcare smarter, was facing challenges with their data pipelines. They were using a mix of Apache Airflow, Apache Spark, Python and over 100,000 lines of custom code to create a Curated Table, which is the basis for their Data Science team to develop the Lumiata Insights. However, with increasing volumes of client data and faster SLA requirements, the process began to strain. Onboarding each new client required bespoke development and the over-extended data engineering team was responsible not only for this development, but also for maintaining and monitoring the pipelines, as well as the health and performance of the underlying Apache Spark jobs. The data science team required a certain amount of experimentation and iteration to develop the Lumiata Insights, but were completely dependent on data engineering to provide necessary adjustments to the Curated Table. This whole process would take six weeks or more, and induced a heavy maintenance burden to keep everything running. As the company looked to scale to take on more clients with their existing team, they needed a new approach.
The Solution
Lumiata opted to give Ascend’s Autonomous Dataflow Service (running on Amazon Web Services) a try. Within three weeks, they were able to migrate all their existing pipelines to the Ascend Service. Creating the Curated Table now involved only 2,000 lines of reusable code, reducing the total codebase to maintain by 98%. Ascend’s declarative programming model ensures the resulting code is focused solely on the data and logic development (not on executing tasks or infrastructure management), so both data engineering and data science teams can collaborate and iterate together clearly and quickly, without risk. Additionally, the automation that the Ascend Service provides fundamentally changed the scale with which they could work with data. When onboarding new datasets, the data engineering team can now ingest and work with all of the source columns with no extra code or complexity. And, since Ascend automatically converts all data to Parquet upon ingestion, they’ve been able to fully eliminate that time-consuming processing stage.
Operational Impact
Quantitative Benefit
Case Study missing?
Start adding your own!
Register with your work email and create a new case study profile for your business.
Related Case Studies.
Case Study
Hospital Inventory Management
The hospital supply chain team is responsible for ensuring that the right medical supplies are readily available to clinicians when and where needed, and to do so in the most efficient manner possible. However, many of the systems and processes in use at the cancer center for supply chain management were not best suited to support these goals. Barcoding technology, a commonly used method for inventory management of medical supplies, is labor intensive, time consuming, does not provide real-time visibility into inventory levels and can be prone to error. Consequently, the lack of accurate and real-time visibility into inventory levels across multiple supply rooms in multiple hospital facilities creates additional inefficiency in the system causing over-ordering, hoarding, and wasted supplies. Other sources of waste and cost were also identified as candidates for improvement. Existing systems and processes did not provide adequate security for high-cost inventory within the hospital, which was another driver of cost. A lack of visibility into expiration dates for supplies resulted in supplies being wasted due to past expiry dates. Storage of supplies was also a key consideration given the location of the cancer center’s facilities in a dense urban setting, where space is always at a premium. In order to address the challenges outlined above, the hospital sought a solution that would provide real-time inventory information with high levels of accuracy, reduce the level of manual effort required and enable data driven decision making to ensure that the right supplies were readily available to clinicians in the right location at the right time.
Case Study
Gas Pipeline Monitoring System for Hospitals
This system integrator focuses on providing centralized gas pipeline monitoring systems for hospitals. The service they provide makes it possible for hospitals to reduce both maintenance and labor costs. Since hospitals may not have an existing network suitable for this type of system, GPRS communication provides an easy and ready-to-use solution for remote, distributed monitoring systems System Requirements - GPRS communication - Seamless connection with SCADA software - Simple, front-end control capability - Expandable I/O channels - Combine AI, DI, and DO channels
Case Study
Driving Digital Transformations for Vitro Diagnostic Medical Devices
Diagnostic devices play a vital role in helping to improve healthcare delivery. In fact, an estimated 60 percent of the world’s medical decisions are made with support from in vitrodiagnostics (IVD) solutions, such as those provided by Roche Diagnostics, an industry leader. As the demand for medical diagnostic services grows rapidly in hospitals and clinics across China, so does the market for IVD solutions. In addition, the typically high cost of these diagnostic devices means that comprehensive post-sales services are needed. Wanteed to improve three portions of thr IVD:1. Remotely monitor and manage IVD devices as fixed assets.2. Optimizing device availability with predictive maintenance.3. Recommending the best IVD solution for a customer’s needs.
Case Study
HaemoCloud Global Blood Management System
1) Deliver a connected digital product system to protect and increase the differentiated value of Haemonetics blood and plasma solutions. 2) Improve patient outcomes by increasing the efficiency of blood supply flows. 3) Navigate and satisfy a complex web of global regulatory compliance requirements. 4) Reduce costly and labor-intensive maintenance procedures.
Case Study
Cloud-based healthcare solution for Royal Philips
Royal Philips wanted to launch its cloud-based healthcare solution HealthSuite Digital Platform in China to deliver services to help cope with challenges related to urbanization and population growth. Philips wanted to achieve this goal by combining mobile, cloud computing and big data technologies. To bring this platform and product to market, Philips required cloud computing and local technical service capabilities in China, in addition to a flexible IT infrastructure that could handle user requests.
