- Systems to simplify medical language in patient portal lab result notes need an overhaul, concluded a study published in the Journal of Medical Internet Research.
These systems, known as natural language processing (NLP), can be effective in helping patients understand their clinical notes and other parts of the patient portal. Although granting patient access to health data is an integral patient engagement strategy, patients often lack the health literacy required for thorough understanding.
Vocabulary and simplification presents a key opportunity for helping patients better understand their lab result notes and use that information to improve their own health.
Several text simplifiers have been developed, but perhaps the most notable is the collaborative consumer health vocabulary (CHV).
“CHV is a collection of terms found to best represent the medical concepts for consumers; they are chosen because they are more comprehensible by patients when compared with their synonyms,” the research team explained.
“Hypothetically, the CHV can help in creating a more consumer-oriented version of radiology reports,” the team continued. “Yet, there is a lack of evidence on whether CHV is an appropriate source of lay terms that can simply replace medical terms used in the field of radiology, which has unique contexts and jargon.”
The researchers conducted an extensive analysis of the CHV, beginning by translating real patient lab results notes. Next, the researchers randomly selected nearly 800 clinical terms to analyze for content coverage, investigating lexical similarity, and finding trends in missing concepts.
Content coverage referred to the amount of terms the CHV was able to translate for patients. Lexical similarity referred to how similar the new words were, compared to the original language used in the note. The text simplifier is not useful if there is a lot of lexical similarity, the researchers said.
Overall, 88 percent of the words tested were translated for better patient understanding. The words that were not translated related to anatomical structures, anatomical descriptions, pathological variations, radiology techniques, and physiological descriptions.
Although CHV managed to successfully translate a vast majority of the selected terms, those terms that went untranslated were essential to patient understanding of a laboratory note.
The research team also found a lexical similarity rate of 77 percent, the researchers said.
“Although a decent percentage of similarity had been expected, the result surpassed our expectations,” the researchers said.
All said and done, about one in four CHV terms was distinct from the original word used in a radiology report, showing that the tool is of little use for patient understanding.
“This high level of similarity can be due to many reasons,” the research team explained. “It is either because some words in the reports are easy to grasp, a simpler explanation does not exist, or they are not explained to the consumer level in the CHV. All these factors are most likely relevant, but this matter requires more research to identify which one is dominant.”
However, the researchers acknowledged that changing the replacement CHV words could create syntax problems, affecting the readability of lab notes. The solution to this problem is not to improve the variability in CHV text simplifiers.
“As there is a large percentage of similarity, introducing changes in these terms can lead to little benefit while introducing a risk of avoidable syntactic errors,” the researchers said. “Therefore, a simplification tool should include a grammatical layer to maintain the parts of speech after terms’ replacements. In fact, such a component is vital for all replaced terms, not only the similar ones.”
More research is necessary to determine how to overhaul these more similar terms for patients, the researchers said. Offering a truly simplified word replacement is essential to addressing patient health literacy barriers. Determining how to improve word variability and readability will help make lab result notes more accessible for patients.