RESUMEN
BACKGROUND: Measuring patient satisfaction is a crucial aspect of medical care. Advanced natural language processing (NLP) techniques enable the extraction and analysis of high-level insights from textual data; nonetheless, data obtained from patients are often limited. OBJECTIVE: This study aimed to create a model that quantifies patient satisfaction based on diverse patient-written textual data. METHODS: We constructed a neural network-based NLP model for this cross-sectional study using the textual content from disease blogs written in Japanese on the Internet between 1994 and 2020. We extracted approximately 20 million sentences from 56,357 patient-authored disease blogs and constructed a model to predict the patient satisfaction index (PSI) using a regression approach. After evaluating the model's effectiveness, PSI was predicted before and after cancer notification to examine the emotional impact of cancer diagnoses on 48 patients with breast cancer. RESULTS: We assessed the correlation between the predicted and actual PSI values, labeled by humans, using the test set of 169 sentences. The model successfully quantified patient satisfaction by detecting nuances in sentences with excellent effectiveness (Spearman correlation coefficient [ρ]=0.832; root-mean-squared error [RMSE]=0.166; P<.001). Furthermore, the PSI was significantly lower in the cancer notification period than in the preceding control period (-0.057 and -0.012, respectively; 2-tailed t47=5.392, P<.001), indicating that the model quantifies the psychological and emotional changes associated with the cancer diagnosis notification. CONCLUSIONS: Our model demonstrates the ability to quantify patient dissatisfaction and identify significant emotional changes during the disease course. This approach may also help detect issues in routine medical practice.
RESUMEN
BACKGROUND: Gaining insights that cannot be obtained from health care databases from patients has become an important topic in pharmacovigilance. OBJECTIVE: Our objective was to demonstrate a use case, in which patient-generated data were incorporated in pharmacovigilance, to understand the epidemiology and burden of illness in Japanese patients with systemic lupus erythematosus. METHODS: We used data on systemic lupus erythematosus, an autoimmune disease that substantially impairs quality of life, from 2 independent data sets. To understand the disease's epidemiology, we analyzed a Japanese health insurance claims database. To understand the disease's burden, we analyzed text data collected from Japanese disease blogs (tobyoki) written by patients with systemic lupus erythematosus. Natural language processing was applied to these texts to identify frequent patient-level complaints, and term frequency-inverse document frequency was used to explore patient burden during treatment. We explored health-related quality of life based on patient descriptions. RESULTS: We analyzed data from 4694 and 635 patients with systemic lupus erythematosus in the health insurance claims database and tobyoki blogs, respectively. Based on health insurance claims data, the prevalence of systemic lupus erythematosus is 107.70 per 100,000 persons. Tobyoki text data analysis showed that pain-related words (eg, pain, severe pain, arthralgia) became more important after starting treatment. We also found an increase in patients' references to mobility and self-care over time, which indicated increased attention to physical disability due to disease progression. CONCLUSIONS: A classical medical database represents only a part of a patient's entire treatment experience, and analysis using solely such a database cannot represent patient-level symptoms or patient concerns about treatments. This study showed that analysis of tobyoki blogs can provide added information on patient-level details, advancing patient-centric pharmacovigilance.