近期，上海金融智能工程技术研究中心韩景倜教授团队发表SSCI一区论文一篇。

论文信息：An intelligent medical guidance and recommendation model driven by patient-physician communication data.

Published in：Frontiers in Public Health（SCI/SSCI一区，IF:6.461）

摘要：Based on the online patient-physician communication data, this study  used natural language processing and machine learning algorithm to  construct a medical intelligent guidance and recommendation model.  First, based on 16,935 patient main complaint data of nine diseases,  this study used the word2vec, long-term and short-term memory neural  networks, and other machine learning algorithms to construct intelligent  department guidance and recommendation model. Besides, taking  ophthalmology as an example, it also used the word2vec, TF-IDF, and  cosine similarity algorithm to construct an intelligent physician  recommendation model. Furthermore, to recommend physicians with better  service quality, this study introduced the information amount of  physicians' feedback to the recommendation evaluation indicator as the  text and voice service quality. The results show that the department  guidance model constructed by long-term and short-term memory neural  networks has the best effect. The precision is 82.84%, and the F1-score  is 82.61% in the test set. The prediction effect of the LSTM model is  better than TextCNN, random forest, K-nearest neighbor, and support  vector machine algorithms. In the intelligent physician recommendation  model, under certain parameter settings, the recommendation effect of  the hybrid recommendation model based on similar patients and similar  physicians has certain advantages over the model of similar patients and  similar physicians.