| Author: | JIANG, Junfeng |
| Title: | Online medical-consultation recommendation system with topic model |
| Advisors: | Li, Jing Amelia (COMP) |
| Degree: | M.Sc. |
| Year: | 2021 |
| Subject: | Medical consultation Medical technology Medical informatics Medical telematics Hong Kong Polytechnic University -- Dissertations |
| Department: | Department of Computing |
| Pages: | iii, vi, 42 pages : color illustrations |
| Language: | English |
| Abstract: | Online medical consultation is a very common method for seeking medical services. Users consult according to their own situation and seek diagnosis through social media or professional websites. With the continuous improvement of the smart medical system, the online consultation system is gradually replacing the service model of manual consultation and has become a new direction for the future development of the medical industry. At present, for most online consultation services, patients are still in a passive service mode. Patients need to choose doctors according to the specialty classification of medical websites or according to the selection of body parts. Due to the lack of professional medical knowledge, patients are prone to blindness when choosing doctors, and the selection of high-quality doctors is too concentrated. They are unable to choose the right doctor for consultation according to their own condition, which makes their own consultation and treatment efficiency inefficient and also As a result, online medical resources cannot be rationally used. Therefore, this article focuses on the in-depth discussion and research on personalized doctor recommendation in medical consultation services, and recommends the most suitable doctor for the patient's condition through in-depth exploration of the patient's condition. We use social media information and neural networks to build a recommendation network, which takes patients' questions as input to study recommendations based on online consultation information. Here, we use latent topics word based on the patient's consultation information, and use the topic information to further use the neural recommendation system to automatically generate the most suitable doctor recommendation. Our model consists of two parts of neural network. The first part is the Neural Topic Model (NTM) used to obtain topic information, and the latter part is the Recurrent Recommender Network (RRN) used to make recommendations. Our experiments are conducted on two large Chinese and English data sets. These two data sets come from online medical consultation platforms and social media. We use two evaluation metrics, MAP and nDCG, and the experimental results on two data sets show that our recommendation model is better than the latest model. Experimental results show that our recommendation model is better than the latest model. |
| Rights: | All rights reserved |
| Access: | restricted access |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 5822.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 1.65 MB | Adobe PDF | View/Open |
Copyright Undertaking
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item:
https://theses.lib.polyu.edu.hk/handle/200/11384