The Science of Emotion.

The Science of Emotion: 

By Richard B. Siegrist Jr., MS, MBA, CPA, Chief Executive Officer; and Susan Madden, MS, Vice President for Product Analytics, Press Ganey Associates The Science of Emotion Presented By: Rishikesh Limaye

Introduction: 

Introduction Cleveland Clinic Health System Low Patient satisfaction scores Information within the comments had not been analyzed Chief Experience officer decided to look at the comments of patients during surveys. Grouping into meaningful categories. To present the issue in a way that the physicians could identify with and solve.

Purpose/WHY : 

Purpose/WHY C omments made by patients - a rich source of information on their feelings and reactions to a health care experience. To systematically capture thoughts and feelings in a way that can be turned into actions to improve patient care and patient satisfaction . Written comments – text – are known as “unstructured” data, that is, data that cannot be easily quantified or analyzed .

Process/HOW: 

Process/HOW Text analytics and sentiment analysis is used Sentiment analysis - based on natural language processing software, analyze the linguistic relationships and connections between words, as well as the syntax and context of phrases By mining comments to identify what is causing scores to be high or low

Pilot Study: 

Pilot Study 12 Hospitals Categorization models to extract and to place information into various “ buckets”. Each comment or part of a comment was placed into multiple categories, along with its sentiment rating .

Example: 

Example

Pilot Study Results: 

Pilot Study R esults Comments processed using the Categorization Model “People, Place, Process” Digging into the weakest area of place three main types of problems identified: hallway noise, roommate/TV noise and temperature/environmental noise . The analysis revealed specific issues that could be improved with targeted interventions, and also identified food that received very positive ratings and thus was not area to be concerned about.

Importance: 

Importance To develop actionable insights such as early warnings or alerts, root-cause analyses, trending over time, and identifying the intensity of reactions and feelings to improve focus on the most important issues. To measure the impact of targeted interventions over time - results of the action can be measured by trending the volume of comments and their sentiment scores over subsequent periods. To easily identify individuals for reward and recognition programs, as well as best practices that inspire highly positive comments from patients. To quickly identify serious issues of safety, privacy violations and service recovery.

The Future: 

The Future S tandard reports summarizing the key areas or issues that are generating strongly positive and negative sentiments among patients in order to help focus improvement efforts. Sentiment analysis can be used to analyze comments from all types of surveys extended to all survey products. Sources of unstructured data are not only limited to satisfaction surveys. Hospital web sites, blogs and social media sites could be additional sources of information.

Conclusion: 

Conclusion Satisfaction scores are becoming increasingly important as measures of quality and are tied to reimbursement. Sentiment analysis can provide the meaning behind the scores and give hospitals the ability to design targeted and effective improvement efforts. It may help in making a difference by reaching from good to very good, or from usually to always Sentiment Analysis can also provide a competitive advantage. A long term goal of developing loyalty and strong feelings between health care providers and patients can be achieved.

PowerPoint Presentation: 

THE END