Understanding patient satisfaction with received healthcare services: A natural language processing approach

Abstract

Important information is encoded in free-text patient comments. We determine the most common topics in patient comments, design automatic topic classifiers, identify comments ' sentiment, and find new topics in negative comments. Our annotation scheme consisted of 28 topics, with positive and negative sentiment. Within those 28 topics, the seven most frequent accounted for 63% of annotations. For automated topic classification, we developed vocabulary-based and Naive Bayes ' classifiers. For sentiment analysis, another Naive Bayes ' classifier was used. Finally, we used topic modeling to search for unexpected topics within negative comments. The seven most common topics were appointment access, appointment wait, empathy, explanation, friendliness, practice environment, and overall experience. The best F-measures from our classifier were 0.52(NB), 0.57(NB), 0.36(Vocab), 0.74(NB), 0.40(NB), and 0.44(Vocab), respectively. F- scores ranged from 0.16 to 0.74. The sentiment classification F-score was 0.84. Negative comment topic modeling revealed complaints about appointment access, appointment wait, and time spent with physician.

Figure 1:

An example of an annotated file.

Figure 2:

Chart illustrating the flow of Patient feedback documents through our processing systems.

Figure 3:

Inter-annotation scores across three document batches (each containing 100 documents). Agreement statistic used is F1.

Figure 4:

Total n-gram counts and unique n-gram counts for each topic. Unigrams = light color (bottom); Bigrams = dark color (top).

Figure 5:

Distribution of positive and negative comments according to topic.