Author Affiliations: College of Nursing, Chungnam National University, Daejeon, Republic of Korea (Dr Cha); Nell Hodgson Woodruff School of Nursing, Emory University, Atlanta, GA, USA (Dr Cha); and College of Nursing, Chonnam National University, Gwangju, Republic of Korea (Dr Lee).
Comput Inform Nurs. 2024 May 1;42(5):355-362. doi: 10.1097/CIN.0000000000001114.
This study aimed to identify the main themes from exit interviews of adult patients with type 2 diabetes after completion of a diabetes education program. Eighteen participants with type 2 diabetes completed an exit interview regarding their program experience and satisfaction. Semistructured interview questions were used, and the interviews were auto-recorded. The interview transcripts were preprocessed and analyzed using four natural language processing-based text-mining techniques. The top 30 words from the term frequency and term frequency-inverse document frequency each were derived. In the N-gram analysis, the connection strength of "diabetes" and "education" was the highest, and the simultaneous connectivity of word chains ranged from a maximum of seven words to a minimum of two words. Based on the CONvergence of iteration CORrelation (CONCOR) analysis, three clusters were generated, and each cluster was named as follows: participation in a diabetes education program to control blood glucose, exercise, and use of digital devices. This study using text mining proposes a new and useful approach to visualize data to develop patient-centered diabetes education.
本研究旨在从 2 型糖尿病患者完成糖尿病教育计划后的离职访谈中确定主要主题。18 名 2 型糖尿病患者完成了关于其项目体验和满意度的离职访谈。采用半结构化访谈问题，并自动记录访谈内容。使用四种基于自然语言处理的文本挖掘技术对访谈记录进行预处理和分析。从词频和逆文档频率中分别得出前 30 个词。在 N 元组分析中，“糖尿病”和“教育”的连接强度最高，词链的同时连接度从最多七个词到最少两个词不等。基于迭代相关一致性 (CONCOR) 分析的汇聚，生成了三个聚类，每个聚类分别命名为：参与糖尿病教育计划以控制血糖、运动和使用数字设备。本研究使用文本挖掘提出了一种新的有用方法来可视化数据，以制定以患者为中心的糖尿病教育计划。
