{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T10:49:55Z","timestamp":1782989395708,"version":"3.54.5"},"reference-count":0,"publisher":"IOS Press","isbn-type":[{"value":"9781643686707","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T00:00:00Z","timestamp":1782950400000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,7,2]]},"abstract":"<jats:p>The rising percentages of diabetes patients continue to stress the global healthcare system. As general practitioners do not have the time to monitor all patients, hybrid human-AI interaction could provide a solution. We propose a knowledge-based dialogue agent that leverages Reinforcement Learning (RL) and Knowledge Graphs (KG) to achieve adaptive interactions. In this paper, we use a hierarchical architecture, decomposing the problem into a master component and two specialized workers: a knowledge acquisition worker gathering information about the user and a recommendation worker providing lifestyle change recommendations to patients. The two workers are driven by two KGs: a medical graph and a user graph. Our proposed method uses a Relational Graph Attention Network (RGAT) Encoder and a Cross-Graph Attention module to encode and fuse the information included in both graphs. Based on experimentation on both a state-of-the-art dataset (MovieLens) and a synthetic diabetes dataset, we show that the master component learns an effective policy for selecting the right worker. Future work includes benchmarking our approach against real-world patient data, and integrating the method in a real application to verify real world performance.<\/jats:p>","DOI":"10.3233\/faia260529","type":"book-chapter","created":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T09:57:38Z","timestamp":1782986258000},"source":"Crossref","is-referenced-by-count":0,"title":["Knowledge-Driven Adaptive Interaction in a Healthcare Dialogue Agent"],"prefix":"10.3233","author":[{"given":"Efthymios","family":"Grigorakis","sequence":"first","affiliation":[{"name":"Information and Computing Sciences, Utrecht University, the Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shihan","family":"Wang","sequence":"additional","affiliation":[{"name":"Information and Computing Sciences, Utrecht University, the Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maaike","family":"de Boer","sequence":"additional","affiliation":[{"name":"dep Data Science, TNO, the Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"7437","container-title":["Frontiers in Artificial Intelligence and Applications","HHAI 2026"],"original-title":[],"link":[{"URL":"https:\/\/ebooks.iospress.nl\/pdf\/doi\/10.3233\/FAIA260529","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T09:57:39Z","timestamp":1782986259000},"score":1,"resource":{"primary":{"URL":"https:\/\/ebooks.iospress.nl\/doi\/10.3233\/FAIA260529"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,2]]},"ISBN":["9781643686707"],"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/faia260529","relation":{},"ISSN":["0922-6389","1879-8314"],"issn-type":[{"value":"0922-6389","type":"print"},{"value":"1879-8314","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,2]]}}}