Study on an Intelligent Review System for Online Health Information Queries by the Elderly

DOI: https://doi.org/10.62517/jmhs.202605222

Author(s)

Ying Wang, Yutong Li, Shaohan Chen, Mei Wang*

Affiliation(s)

College of Medical Information and Artificial Intelligence, Shandong First Medical University and Shandong Academy of Medical Sciences, Tai'an, Shandong, China *Corresponding Author.

Abstract

The Internet has become the main channel for Chinese elderly netizens to obtain health information. But these elderly people have low digital literacy. In addition, the health information on the network is both correct and wrong. And many websites are not designed for the elderly. So these problems may affect their health and use up unnecessary medical resources. To solve these problems, we have developed and put into practice the 'Silver Smart Care' Intelligent Review System. This system has four parts that work together in a loop. These components include Azure Artificial Intelligence (AI) for problem discovery, Transformer Bidirectional Encoder Representation (BERT) for semantic analysis, Long Short-Term Memory (LSTM) for trend prediction, and an interface designed for older users. Therefore, the system can filter information, identify abnormal queries, provide correct medical advice, and share personalized health education content. Experimental results show that the system can find 91.3% of abnormal queries and 89.7% of the health information. For the elderly users, the efficiency in completing tasks improves to 80.5%, the time spent searching for information is reduced and the interface satisfaction reaches 9 out of 10.

Keywords

Health Information Review; Anomaly Detection; Age-friendly Design; BERT; LSTM

References

[1] China Internet Network Information Center. (2024). The 54th Statistical Report on the Development of the Internet in China. Beijing. [2] Wang Sufang, Zhou Yuhan. (2022). A Study on the Ability of Older Adults to Evaluate Health Information on Social Media and Factors Influencing Its Improvement. Library and Information Service. 66(24):14-29. [3] European Commission. (2022). Proposal for a Regulation of the European Parliament and of the Council on the European Health Data Space (EHDS). Brussels. [4] Hu Chuntao, Qin Jinkang, Chen Jingmei, Zhang Liang. (2023). Deep Learning-Based Identification of Misinformation in Health Information. Computer Engineering and Applications. 59(15):234-240. [5] Deng S L, Xia S D. (2022). Research on the Current Status and Influencing Factors of Older Adults' Ability to Discriminate Online Health Information. Library and Information Service. 66(10):89-98. [6] Hou Guanhua, Liu Qiong. (2025). A Study on Age‑Friendly Guided Design of Information Representation in Online Health Information Systems. Journal of Packaging Science. 17(1):78-86. [7] Li Jian, Zhang Yansong. (2024). Research on the Development of SHEC. Dalian: Northeast University of Finance and Economics Press. [8] Yu Zhangxian, Mao Yuqing, Hu Kongfa. (2020). Deep Learning‑Based Identification of False Health Information. Software Guide. 19(3):1-7. [9] Wang Ling, Chen Shouqiang. (2023). LSTM‑Based Prediction and Risk Early Warning of Elderly Health Time‑Series Data. Chinese Journal of Digital Medicine. 18(5):45-49. [10] Wang Weixuan, Shang Shaomei. (2024). Reflection on High-Quality Development of Smart Health Data. Strategic Study of CAE, 26(6): 32-42.