In an era when a growing number of patients are using social media to describe their patient experiences, some health care professionals are suggesting that mining the “cloud of patient experience” could be an interesting way to help professionals improve that experience.
The idea is proposed in a “viewpoint” article entitled “Harnessing the cloud of patient experience: using social media to detect poor quality healthcare” published online by BMJ Quality and Safety in January 2013. The authors, F. Greaves, D Ramirez-Cano, C Millett, A Darzi and L Donaldson, of the Department of Primary Care and Public Health, Imperial College London, say that:
“We believe the increasing availability of patients’ accounts of their care on blogs, social networks, Twitter and hospital review sites presents an intriguing opportunity to advance the patient-centred care agenda and provide novel quality of care data.”
They outline how collecting and aggregating patients’ descriptions of their experiences on the internet could be used to detect both poor and high quality clinical care. The process involves “natural language processing and sentiment analysis to transform unstructured descriptions of patient experience on the internet into usable measures of healthcare performance.” The authors conclude by discussing whether these new techniques could detect poor performance before conventional measures of healthcare quality could.
Many industries use data mining to gather business intelligence and detect trends in markets. The financial industry uses it to develop credit scores. Actuaries use it to assess risk for insurance companies. Other applications include quality assurance, cross-selling, fraud detection, stock market prediction, direct marketing and customer retention, to name just a few.
In all of these examples, people use computers to turn large amounts of unstructured data into usable knowledge that can help predict outcomes and improve performance.
If you’ve had a hospital stay recently, you probably received a questionnaire asking you to rate your experience. The purpose of these questionnaires is to gather feedback that leads to improved performance. A local hospital administrator told me recently that these ratings affect hospitals’ compensation by several percent – a powerful motive to improve.
But people are often reluctant to offer negative feedback – especially to people that their health depends on. They don’t want to be “problem patients” that providers shun; they have a natural tendency to want to say positive things TO the people they deal with. However, under the veil of anonymity that the Internet provides, they frequently show no restraint in saying negative things ABOUT their experiences with people, companies and institutions. I call this the Venting Effect. When you have a negative experience, just getting all those boiling feelings out of your head helps manage the pain.
Professionals can improve healthcare by capturing and analyzing this information. The hospital administrator mentioned above told me a poignant story about how his staff reduced lung infections after surgery from nearly 50 percent to virtually zero within five years. They used “best practices” determined from mining CDC data. Broadening the scope to include data mined from social networks may yield equally beneficial results.