Tipping the Scales: A Corpus-Based Reconstruction of Adjective Scales in the McGill Pain Questionnaire
This work addresses pain assessment accuracy for medical diagnosis by validating and questioning the grouping categories in a widely used clinical tool.
The study reconstructed the adjective intensity orderings of the McGill Pain Questionnaire using patient forum data and NLP techniques, finding that only 4 out of 17 predicted relationships diverged from the original orderings, which was statistically significant at the 0.1 alpha level.
Modern medical diagnosis relies on precise pain assessment tools in translating clinical information from patient to physician. The McGill Pain Questionnaire (MPQ) is a clinical pain assessment technique that utilizes 78 adjectives of different intensities in 20 different categories to quantity a patient's pain. The questionnaire's efficacy depends on a predictable pattern of adjective use by patients experiencing pain. In this study, I recreate the MPQ's adjective intensity orderings using data gathered from patient forums and modern NLP techniques. I extract adjective intensity relationships by searching for key linguistic contexts, and then combine the relationship information to form robust adjective scales. Of 17 adjective relationships predicted by this research, only 4 diverge from the MPQ's orderings, which is statistically significant at the 0.1 alpha level. The results suggest predictable patterns of adjective use by people experiencing pain, but call into question the MPQ's categories for grouping adjectives.