Data driven decision making is a key business imperative for Healthcare companies in the current data rich era. This not only helps in their decision-making process, but also assists in catering to key business personas. As such, it is very important for Healthcare organizations to have the Data and Analytics strategy aligned to the company’s vision and mission coupled with execution.

LTIMindtree’s Leni – a virtual analyst, is a cloud-native, scalable technology layer for data engineering and advanced analytics. Using advanced connectors of Leni, data from various healthcare applications, social media and medical devices is ingested into a data store for visualization. With its in-built NLP (natural language processing) capabilities, Leni approximates a human data scientist.

Leni’s cognitive insights engine is a part-rules/part-ML providing user feedback based self-learning module and generates comprehensive insights-based recommendations by detecting not only the historically observed but also the emerging trends in the data. Leni enables business users with intelligence assisted self-service analytics through its simple & easy interface and a conversational layer for exploration.

With these functionalities and right set of data Leni helps in prescriptive, descriptive and predictive analysis in the entire healthcare ecosystem for sales growth, customer retention, fraud detection and prevention. It can answer key questions relevant to customer segmentation and can identify consumers to reach out through characteristic profiling payer type, demographics, and psychographics. For healthcare providers, Leni assists in analyzing data to improve care, predict adverse outcomes, and determine population at risk for illness. For health insurance payers, Leni helps improve growth though product analysis and customer experience, reduce cost through predictive claims analysis and prevention of fraud.

Using the features of Leni, health insurance organizations will be most benefited in few of the following business areas:

• Healthcare products analysis based on retail and group member enrollments
• Cost benefit analysis based on provider claims against a product linked to member enrollments
• Healthcare fraud analysis based on high value and frequency of claim submitted by provider
• Claims analysis during manual adjudication of claim using historical claims data
• Prediction of increase in claims by analyzing claims matching to patient health records