Artificial Intelligence Program Boosts Patient Satisfaction

Using a dataset of electronic health records along with survey results, machine learning algorithms utilized artificial intelligence to communicate patient satisfaction improvement recommendations, according to a recent study published in the Institute of Electrical and Electronics Engineers’ Journal of Biomedical and Health Informatics, in partnership with Geisinger.

“Patient health care is like a journey. They need to interact with multiple health professionals across different service units throughout the entire length of stay,” said Ning Liu, the study’s lead author, in a press release.

“It’s important for providers to understand the needs of each patient group, like those receiving surgery, cancer treatments or emergency visits. We wanted to know what is most important for each group, and how do we interpret that from the data we receive?”

Researchers applied machine learning algorithms to a comprehensive dataset of electronic health records and survey results, converting the data into information that artificial intelligence could then turn into recommendations.

Survey results revealed that effective communication and respect between patients and their care team had a major impact on patient satisfaction. While efficiency of care and helpfulness in addressing concerns were the most important measures of success to survey respondents, pain management quality also proved to be crucial to patient satisfaction.

Many machine learning algorithms spit out reliable results, but few provide insight into how they reached those results, Liu explained. This particular model was unique in that it provided an interpretation of its findings, making it more user-friendly and easier to comprehend.

“If you apply for a credit card and get denied, that credit card company has to tell you why,” explained Liu in the press release.

“For our model, it has to tell us how it got its answer. This makes is easier for others to understand the data, making it a powerful tool for hospitals and health care systems at large. This helps them implement change to improve patient satisfaction across various levels, from the top down to the individual unit workers.”

The model has the potential to be useful in other industries as well, due to its usability. But for health care specifically, having a way to interpret patient satisfaction could have positive impacts on improving both satisfaction and health outcomes.

“I think this work encourages future research in the world of patient satisfaction combined with advanced analytics,” said Eric S. Reich, director of business intelligence and advanced analytics in Geisinger’s Steel Institute for Health Innovation said in the press release.

“Health care systems can use these findings to drive targeted improvements in patient satisfaction to the point where we know if patients with a certain set of characteristics are getting their knee replaced, then we believe these are the top three items that are going to ensure the patient has a very positive experience. To discover the key drivers behind patient satisfaction is a critical initiator for improving the quality of patient-centered health care.”

Patient satisfaction is an extremely important metric for hospitals, researchers stressed. Recent data even suggests that a patient’s insurance type could have a significant impact on their satisfaction. But it is often a measure that is misunderstood, and many health care professionals hit roadblocks in assessing and improving patient satisfaction.