Doctor Recommendation Model for Pre-Diagnosis Online in China: Integrating Ontology Characteristics and Disease Text Mining

Objective: The recommendation model takes the real consultation data from online as the research object, fully testifying its effectiveness. Specifically, this model would make recommendation to patients on department and doctors based on patients' information of symptoms, diagnosis and geographical location, as well as doctor's specialty and their department. Methods: Methods: Utilizing crawler technique, five hospital departments were selected from the online medical service platform. a dataset consisting of 20000 consultation questions by patients were built. Through the application of Python and MySQL algorithms, replacing semantic dictionary retrieval or word frequency statistics, word vectors were utilized to measure similarity between patients' pre-diagnosis and doctors' specialty, forming a recommendation framework on medical departments or doctors based on the above-obtained sentence similarity measurement. Results: In the online medical field, compared with traditional recommendation method, the model proposed in the paper is of higher recommendation accuracy and feasibility in terms of department and doctor recommendation effectiveness. Conclusions: The proposed online pre-diagnosis doctor recommendation model integrates ontology characteristics and disease text mining. The model gives a relatively more accurate recommendation advice. Furthermore, the model also gives full consideration on patients” location factors. As a result, the proposed online pre-diagnosis doctor recommendation model would improve patients' online consultation experience and offline treatment convenience, enriching the value of online prediagnosis data.