Huang, Yi, and Song, Insu (2022) Cardio Vec: Searching Heart Health Information Using ECG Signals. In: Proceedings of the 7th International Conference on Computational Intelligence and Applications. pp. 243-247. From: ICCIA 2022: IEEE 7th International Conference on Computational Intelligence and Applications, 24-26 June 2022, Nanjing, China.

PDF (Published Version) - Published Version Restricted to Repository staff only

1

Abstract

Health Social Networks (HSN s) provides a scalable, sustainable, and rich medical knowledge base. However, retrieving the right information from HSN can be time-consuming and challenging as users are often required to use the right keywords to search and filter relevant information. IoT provides a non-invasive, easy, low-cost way to collect patient data. However, the current IoT approaches cannot provide interpretable clinical information. IoT also cannot be directly interfaced with HSN s for searching health conditions. To overcome the disadvantages of both approaches, we develop an ECG-IoT search engine, called Cardio Vect. Cardio Vect converts ECG signals into human-readable clinical descriptions to interface ECG-IoT with HSN. This allows doctors and patients directly search relevant articles on the Internet and HSN s using ECG signals collected through IoT devices or portable ECG recorders. The search results achieved precision of 79.14% in top-one search results. Our proposed Cardio Vec improves the effectiveness and usefulness of loT and HSN for patients to find right information on cardiovascular diseases and learn about their potential health risks more easily and conveniently.

Actions (Repository Staff Only)

Item Control Page