Higher Patient Satisfaction: The Only Metric That Matters

Healthcare

THE CHALLENGE.

In the world of healthcare, it goes without saying that patient success is counted amongst the top factors of success. A lot of people don’t realize that in the United States, all hospital patients are surveyed to assess the care provider, known as Consumer Assessment of Healthcare Providers and Systems survey (otherwise known as CAHPS).

Recently, the team at Pegasus One was asked to use our experience to analyze a massive volume of this survey data using Machine Learning and artificial intelligence (AI). The reason to do so was simple: not only did we need to help a healthcare client better understand their patient’s needs, but we also had to deliver precise, decision driving insights for our client using both clinical background data and feedback from the patients.

Higher Patient Satisfaction: The Only Metric That Matters

Healthcare

THE CHALLENGE.

In the world of healthcare, it goes without saying that patient success is counted amongst the top factors of success. A lot of people don’t realize that in the United States, all hospital patients are surveyed to assess the care provider, known as Consumer Assessment of Healthcare Providers and Systems survey (otherwise known as CAHPS).

Recently, the team at Pegasus One was asked to use our experience to analyze a massive volume of this survey data using Machine Learning and artificial intelligence (AI). The reason to do so was simple: not only did we need to help a healthcare client better understand their patient’s needs, but we also had to deliver precise, decision driving insights for our client using both clinical background data and feedback from the patients.

APPROACH.

Pegasus One studied data from more than 30,000 different patients, all of whom had visited our client’s facilities over a two year period of time. We assessed issues like responsiveness, pain management, communication and more. This data was correlated to backgrounds of those patients.

During our analysis, various decision-tree were used along with custom regression models hypothesis testing, to holistically understand the variables at play and they impacted each other.

RESULTS.

Analysis

Analyzed 30,000 CAHPS records

Identification

Identified key factors leading to lower patient satisfaction

Recommendation

Recommended specific improvements for increasing patient satisfaction

VALUE.

At the end of the project, we were able to deliver a comprehensive set of patient satisfaction analytics, a series of acute observations and informed, and data-driven recommendations for further improvements that could be made to their health network. We also suggested changes that included resource allocation planning ensuring effective staffing for a number of unique circumstances they were likely to face, all of which will help them improve patient satisfaction even more in both the short and long-term.