Matsuda Shinichi, Ohtomo Takumi, Okuyama Masaru, Miyake Hiraku, Aoki Kotonari
Drug Safety Division, Chugai Pharmaceutical Co Ltd, Tokyo, Japan.
Initiative Inc, Tokyo, Japan.
JMIR Form Res. 2023 Sep 14;7:e48534. doi: 10.2196/48534.
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.
This study aimed to create a model that quantifies patient satisfaction based on diverse patient-written textual data.
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.
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 t=5.392, P<.001), indicating that the model quantifies the psychological and emotional changes associated with the cancer diagnosis notification.
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.
测量患者满意度是医疗护理的关键环节。先进的自然语言处理（NLP）技术能够从文本数据中提取和分析高层次的见解；然而，从患者那里获得的数据往往有限。
本研究旨在创建一个基于多样化患者撰写的文本数据来量化患者满意度的模型。
我们为这项横断面研究构建了一个基于神经网络的NLP模型，使用1994年至2020年期间在互联网上用日语撰写的疾病博客的文本内容。我们从56357篇患者撰写的疾病博客中提取了约2000万个句子，并使用回归方法构建了一个预测患者满意度指数（PSI）的模型。在评估模型的有效性后，在癌症告知前后对48例乳腺癌患者的PSI进行预测，以检查癌症诊断的情感影响。
我们使用169个句子的测试集评估了预测的和由人类标注的实际PSI值之间的相关性。该模型通过检测句子中的细微差别成功地量化了患者满意度，效果极佳（斯皮尔曼相关系数[ρ]=0.832；均方根误差[RMSE]=0.166；P<0.001）。此外，癌症告知期的PSI显著低于之前的对照期（分别为-0.057和-0.012；双侧t=5.392，P<0.001），表明该模型量化了与癌症诊断告知相关的心理和情绪变化。
我们的模型展示了量化患者不满以及识别疾病过程中显著情绪变化的能力。这种方法也可能有助于发现常规医疗实践中的问题。
