Improving Patient Experience with Insights from Patient Comments

Learn how Opinosis Analytics uses Text Analytics on feedback data to assist with customer experience transformation.

Customer Problem

A general hospital in Canada, with about 300,000 patient visits a year noticed that they had mixed patient reviews on the Web and were looking to improve internal operations so that they can provide a better patient experience and start limiting negative comments. They also needed to understand areas of excellence to replicate it in all areas of their practice. 

As their comments are mostly scattered around the Web and are highly unstructured in nature, it’s not easy for them to pick up on trend in complaints (or praises).  Realizing that this is a problem that could use Text Analytics, they tapped into our services. 

Our Process

1. Understanding the Technical Challenges

Our first step was to understand the type of questions the hospital wants answered and to get an understanding of data that was available for analysis internally (if any) in addition to reviews on the Web. 

 2. Data gathering

Since privately managed data was limited, we gathered patient reviews from across the Web. Our crawler looked at sources such as, and as these are online venues where patients leave detailed free-form feedback.

3. Text & Sentiment Analysis 

Once the data gathering pipeline was set-up, our NLP experts aggregated all the reviews, preprocessed it and performed a series of text and sentiment analysis. We leveraged our very own state-of-the-art tools that we customized to answer questions that the hospital was interested in. 

4. Summarization

After our data analysis was complete (all questions answered), we summarized the results, separated signal from noise and delivered our findings to the hospital in their chosen format. This document would be the key to making strategic decisions to provide a better patient experience. 

Samples of Our Work


As a result of our partnership, the hospital gained several important insights that is going to help them drive changes. This includes learning that:

  1. Most of the negative comments had been fairly recent. 
  2. Most of the negative comments were caused by etiquette of hospital staff, primarily nurses.
  3. ER wait times were too long ( > 1 hour )
  4. Patients had little complaint about the hospital facility. Many of them felt it was clean and spacious.
  5. Patients generally thought the doctors were very competent
Braced with this information, the hospital can now take the next steps towards addressing their problems and further investigating issues such as the potential reasons for spike in recent negative comments. The hospital aims to redo the analysis in subsequent quarters to look for improvements in specific aspects that we investigated. 

Have a question or need help with a similar problem? Get in touch!