AI in Healthcare

AI use cases WildFire implemented in health insurance vertical

Client: Medium size health insurer

Problem: A medium size health insurer was looking to increase their hit rate in claims management with little effort. They had few different goals.

– Increase hit rate

– Reduce manual intervention

Our solution: We worked with the insurer to understand all the rules they used to flag which claims were incorrect. We implemented a machine learning based solution which was more accurate and reduced manual effort by decreasing false alerts.

Results: The insurer was able to increase hit rate by 25% and reduce manual work by 90%.

Client: Medium size health insurer

Problem: A medium size health insurer was looking to optimize their pricing. They had few different goals.

– Maximize profit

– Maximize brand exposure

– Increase market share

Our solution: We preprocessed and structured a very large amount of member and competitor pricing and other data. We built 3 different models for the 3 goals above using various machine learning techniques. The models were optimized for increased accuracy using additional data.

Results: The insurer was able to maximize profit by 0.5%, increase brand exposure and increase market share.

Client: A large health insurer

Problem: A large health insurer was looking to detect patients at risk for early intervention. They had these goals.

– Better population health

– Early detection of patients at risk of different diseases

Our solution: We worked with various stakeholders and their innovation team to identify their goals and sources of all relevant data. We processed lots of historic claims data to find patterns of who can be potentially at risk of different diseases. We developed machine learning models which could predict patients at risk for early intervention.

Results: The insurer was able to increase early detection by 30% and hence was able to reduce claims significantly.

Client: A small heath insurer

Problem: A small health insurer was looking to offer new products.

They had few different goals.

– Increase market share

– Increase profit

Our solution: We worked with various stakeholders and their innovation team to identify their goals and sources of all relevant data. We sourced competitor pricing data. We developed deep learning models which could recommend policy structure and pricing information which has maximum profitability and better healthcare for its members.

Results: The insurer was able to develop new products and enter new markets.

Client: A small health insurer

Problem: A small health insurer was looking to develop a chatbot to help their customer service teams to handle call volumes. They had few different goals.

– Better customer support

– Reduce level 2 and level 3 call volume which was expensive

Our solution: We worked with their technology and business to develop an AI based chatbot and using all their historic call data. The bot was used by their customer service to answer all member questions and was able to reduce level 2 and 3 support.

Results: The insurer was able to deploy this chatbot in multiple regions in short period of time and saw significant gains in efficiency and better customer service.

 


To learn more about other use cases and company updates, please sign up here

Email sign up