基于HSM_LDA模型的在线医院特色挖掘研究*
Research on online hospital feature mining based on HSM_LDA model
挖掘在线医院的医疗特色对在线医疗推荐具有十分重要的作用。本文提出了一种基于在线医院问诊文本的医院特色识别模型(Hospital SpecialSMedical based LDA, HSM_LDA)。该模型以医院ID作为文本划分依据,联合建模医院、主题、词汇三个变量,生成医院-主题(E)和主题-词汇(F)两个分布。通过“好大夫在线”健康平台提供的医院问诊文本作为实验数据集对结果进行验证,实验结果表明：HSM_LDA模型的医院特色识别精度为87%,达到了良好的效果。
Mining the medical characteristics of online hospitals plays a very important role in online medical recommendation. This paper proposes a Hospital Special Medical based LDA (HSM_LDA) model. This model takes hospital ID as the basis for text division, jointly models three variables of hospital, subject and vocabulary, and generates two distributions of hospital - subject (E) and subject - vocabulary (F). The hospital consultation text provided by Good Doctor Online health platform was used as the experimental data set to verify the results. The experimental results showed that the accuracy of hospital characteristic identification of HSM_LDA model was 87%, achieving a good effect.
潘玮、张楚、刘灵涛、翟菊叶、黄锦泉、刘玉文
医学研究方法计算技术、计算机技术
在线医院医院特色HSM_LDA模型主题识别医疗推荐
Online hospitalHospital characteristicsHSM_LDA modelopic identificationMedical recommendation
潘玮,张楚,刘灵涛,翟菊叶,黄锦泉,刘玉文.基于HSM_LDA模型的在线医院特色挖掘研究*[EB/OL].(2022-12-18)[2025-08-16].https://www.biomedrxiv.org.cn/article/doi/bmr.202305.00012.点此复制
评论