Screening Eligibility Analytics

About the Customer & Challenges Faced:

In 2017, our client, a healthcare payer based in Pennsylvania, signed a five-year Bi-directional Data Exchange agreement with a health insurance provider as a part of the Population Health Management and Value-based Contract strategy. This enabled them to marshal resources from both organizations: EMR Data (produced by our client); Insurance Claims Data (produced by the insurance provider).

Taking advantage of this collaboration, our client wanted to design innovative initiatives to improve the health of its members, patients, and the community at large. From a population of more than one million members (of the insurance provider), they wanted to: identify individuals eligible for medical screening, and eligible individuals who have not availed of the medical screening facility.

Solution and Approach:

  • One of our clients — a large healthcare provider wanted to identify eligible individuals covered by who hadn’t availed of medical screening. This could mean that these individuals might get admitted to a hospital, avail healthcare services and claim insurance; adding to the cost curve for the payer. With a proper medical screening in place, misplaced risk calculations, actuarial decisions and both payer-provider cost-efficiency can be improved.​
  • framework provides out-of-the-box development platforms. framework provides out-of-the-box development platforms.  The project was started seamlessly with the relevant environments which were then created automatically. Development images configured based on pre-defined templates were installed on-premises or in a development VM within the infrastructure. This enabled authentication using LDAP, seamless project setup using Bitbucket, Jenkins and Docker (ensuring build and deployment without software compatibility issues).  ​
  • The framework made available by leverages the latest ML and DL tools while preparing models and includes Pachyderm-based data versioning, deployment using a Kubernetes orchestration system, Kubeflow and Spark-based ML and DL build and deployment, Istio-based service mesh enabled microservice architecture, and ELK based monitoring capability; contributing to reduction in latency time.​
  • The diverse healthcare data at our disposal, including patient records, patient claim history, patient demographics, etc. were added as exploratory variables by using libraries.’s MLOps framework allows establishing high-end Alluxio and Presto-based efficient data connectivity and collecting data from diverse sources. By using data versioning and connectivity libraries, data versions were easily controlled, stored in xpresso Data Model (XDM)-enabled data store. This enabled easy retrieval and storage of datasets/ files into internal XDM.
  • We used handcrafted Python-based algorithms and SQL to create ML algorithms that were used to design clustering mechanisms.  Business rules, adhering to HEDIS (Healthcare Effectiveness Data and Information Set — a widely used set of performance measures in the managed care industry, developed and maintained by the National Committee for Quality Assurance or NCQA) were incorporated into the algorithms. Clustering algorithms were created using the JavaScript library – D3 and also obtained from libraries, reducing the time to market.​
  • The attributes obtained were used for categorization (employing Pachyderm-based data versioning) and then performing univariate, bi-variate and Bag of Words analysis — for both structured and unstructured datasets through xpresso Exploratory Data Analysis (Data and Statistical Analysis).  Different datasets and their different versions were easily controlled and stored into xpresso Data Model (XDM)-enabled data store that enabled easy retrieval and storage of datasets/ files into internal XDM. This was achieved by using two excellent features of ​
  1. Data Connectivity Marketplace libraries​
  2. Data Versioning​
  • We provided a solution that enabled our client to zero in on individuals who were eligible yet hadn’t availed of medical screening; proceeding initially through using clustering algorithms to segregate individuals into relevant groups from the huge healthcare datasets made available to us. The output generated helped the client segregate individuals into groups so that actuaries could devise a unique strategy for each group and enabled the client to see a rise in income by around 35% due to the increase in the number of medical screenings. The solution also helped them to generate income from Quality Performance Measure (QPM) incentives that are awarded on a PMPM (per-member-per-month) basis.​


  • By using, one can leverage high-end data connectivity, efficient data versioning, perform exploratory data analysis and generate inferences using an intuitive process and through an industry-standardized manner.
  • The unique, containerized platform-centric approach offered by can be used to employ required infrastructure, deploy rapidly to multiple high-availability environments while aligning with best-in-class DevSecOps practices.
  • also brings in-depth QA-QC testing and logging frameworks, synchronous and asynchronous monitoring, and performance tracking ability.
  • also has SSO (single-sign-on) for various in-built tools and subsystems that make the platform access seamless throughout.​
  • In a nutshell, all the above features in a single plate under the same hood make an unbeatable AI Ops framework.

Have Any Questions?

Need more information about the platform?