{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T04:23:22Z","timestamp":1793075002004,"version":"4.5.0"},"reference-count":21,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Form Res"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Multicall memory capabilities in AI-powered health care communication systems show promise for enhancing patient engagement, but their impact on engagement and patient satisfaction remains unclear.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study evaluated the relationship between multicall memory usage and key patient experience metrics, including call duration and satisfaction scores, in an AI-powered health care communication system.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n We conducted a retrospective analysis of 4415 AI care agent calls from 4189 patients using linear mixed-effects models to account for multiple calls per patient. The primary predictor was the number of memories used per call. Outcomes included call duration (in minutes), net promoter score, and patient satisfaction ratings. We analyzed the full dataset and relevant subsets (completed calls only and memory-using calls only) to assess the robustness of the findings.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n Memory usage was significantly associated with increased call duration, with each additional memory associated with an extension of 2.47 minutes (95% CI 2.03-2.91;\n P<\/jats:italic>\n <.001). This effect was consistent across sensitivity analyses, though it was attenuated in completed calls only (+0.54 min per memory;\n P<\/jats:italic>\n =.004). Memory usage showed no significant association with patient satisfaction across any analysis. Given that only a small subset of calls used memories and satisfaction data were available only for completed calls, the study may have been underpowered to detect an association between memory use and net promoter score or satisfaction ratings.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n Multicall memory usage is significantly associated with enhanced behavioral engagement. The findings reveal a disconnect between engagement duration and patient-reported experience, suggesting that memory optimization strategies should focus on behavioral engagement metrics while considering factors beyond usage quantity for patient satisfaction. These results provide evidence-based guidance for health care organizations implementing memory-enabled AI communication systems.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/87704","type":"journal-article","created":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T18:25:07Z","timestamp":1774635907000},"page":"e87704-e87704","source":"Crossref","is-referenced-by-count":1,"title":["Multicall Memory in an AI Care Agent for Chronic Care Management Among Older Adults: Retrospective Observational Study"],"prefix":"10.2196","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4526-9252","authenticated-orcid":false,"given":"Markel","family":"Sanz Ausin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3438-3313","authenticated-orcid":false,"given":"Akash","family":"Chaurasia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3001-3447","authenticated-orcid":false,"given":"Alex","family":"Miller","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2060-3568","authenticated-orcid":false,"given":"Jonathan David","family":"Agnew","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5041-4285","authenticated-orcid":false,"given":"Rae","family":"Lasko","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6259-6676","authenticated-orcid":false,"given":"Mariska","family":"Raglow-Defranco","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1362-9127","authenticated-orcid":false,"given":"Michelle","family":"Voisard","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6469-2064","authenticated-orcid":false,"given":"Saad","family":"Godil","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6684-4158","authenticated-orcid":false,"given":"Subhabrata","family":"Mukherjee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,8,21]]},"reference":[{"issue":"1","key":"R1","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1055\/s-0039-1688757","article-title":"Assistive conversational agent for health coaching: a validation study","volume":"58","author":"Fadhil","journal-title":"Methods Inf Med"},{"key":"R2","doi-asserted-by":"crossref","unstructured":"Shamekhi A Bickmore T Lestoquoy A Gardiner P . Augmenting group medical visits with conversational agents for stress management behavior change. Presented at: Persuasive Technology: Development and Implementation of Personalized Technologies to Change Attitudes and Behaviors (PERSUASIVE 2017); Apr 4-6, 2017:55-67; Amsterdam, The Netherlands. [doi: 10.1007\/978-3-319-55134-0_5]","DOI":"10.1007\/978-3-319-55134-0_5"},{"issue":"2","key":"R3","doi-asserted-by":"publisher","DOI":"10.2196\/diabetes.8590","article-title":"A fully automated conversational artificial intelligence for weight loss: longitudinal observational study among overweight and obese adults","volume":"2","author":"Stein","journal-title":"JMIR Diabetes"},{"key":"R4","doi-asserted-by":"crossref","unstructured":"Trinh H Shamekhi A Kimani E Bickmore TW . Predicting user engagement in longitudinal interventions with virtual agents. Presented at: IVA \u201918: Proceedings of the 18th International Conference on Intelligent Virtual Agents; Nov 5-8, 2018:9-16; Sydney, New South Wales, Australia. [doi: 10.1145\/3267851.3267909]","DOI":"10.1145\/3267851.3267909"},{"key":"R5","doi-asserted-by":"crossref","unstructured":"Chen J Chen C Walther JB Sundar SS . Do you feel special when an AI doctor remembers you? Individuation effects of AI vs. human doctors on user experience. Presented at: Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems; May 8-13, 2021; Yokohama, Japan. [doi: 10.1145\/3411763.3451735]","DOI":"10.1145\/3411763.3451735"},{"key":"R6","doi-asserted-by":"publisher","DOI":"10.1016\/j.ibmed.2022.100064","article-title":"Artificial intelligence (AI) to improve chronic pain care: evidence of AI learning","volume":"6","author":"Piette","journal-title":"Intell Based Med"},{"key":"R7","doi-asserted-by":"crossref","unstructured":"Zhang Z Chao D Bickmore T Paasche-Orlow M . Maintaining continuity in longitudinal, multi-method health interventions using virtual agents: the case of breastfeeding promotion. Presented at: Intelligent Virtual Agents Lecture Notes in Computer Science (IVA 2014); Aug 27-29, 2014:504-513; Boston, Massachusetts, USA. [doi: 10.1007\/978-3-319-09767-1_61]","DOI":"10.1007\/978-3-319-09767-1_61"},{"issue":"11","key":"R8","doi-asserted-by":"publisher","DOI":"10.2196\/17065","article-title":"Artificial intelligence chatbot for depression: descriptive study of usage","volume":"4","author":"Dosovitsky","journal-title":"JMIR Form Res"},{"key":"R9","doi-asserted-by":"crossref","unstructured":"Matari\u0107 MJ . Human-machine and human-robot interaction for long-term user engagement and behavior change. Presented at: Proceedings of the 25th Annual International Conference on Mobile Computing and Networking (MobiCom 2019); Oct 21-25, 2019; Los Cabos, Mexico. [doi: 10.1145\/3300061.3300141]","DOI":"10.1145\/3300061.3300141"},{"key":"R10","unstructured":"Bickmore T Schulman D . Embodied agents for long-term interaction [Dissertation]. Northeastern University; 2013. URL: https:\/\/repository.library.northeastern.edu\/files\/neu:915\/fulltext.pdf [Accessed 01-06-2026]"},{"key":"R11","doi-asserted-by":"crossref","unstructured":"Jo E Jeong Y Park S Epstein DA Kim YH . Understanding the impact of long-term memory on self-disclosure with large language model-driven chatbots for public health intervention. Presented at: Proceedings of the CHI Conference on Human Factors in Computing Systems; May 11-16, 2024; Honolulu, HI, USA. [doi: 10.1145\/3613904.3642420]","DOI":"10.1145\/3613904.3642420"},{"issue":"5","key":"R12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s12369-023-01076-z","article-title":"Building long-term human\u2013robot relationships: examining disclosure, perception and well-being across time","volume":"16","author":"Laban","journal-title":"Int J of Soc Robotics"},{"issue":"5","key":"R13","doi-asserted-by":"publisher","DOI":"10.2196\/37302","article-title":"Adherence and engagement with a cognitive behavioral therapy-based conversational agent (Wysa for chronic pain) among adults with chronic pain: survival analysis","volume":"6","author":"Sinha","journal-title":"JMIR Form Res"},{"key":"R14","doi-asserted-by":"crossref","unstructured":"McFadyen J Habicht J Dina LM Harper R Hauser TU Rollwage M . AI-enabled conversational agent increases engagement with cognitive-behavioral therapy: a randomized controlled trial. medRxiv. Preprint posted online on Nov 2, 2024. [doi: 10.1101\/2024.11.01.24316565]","DOI":"10.1101\/2024.11.01.24316565"},{"key":"R15","doi-asserted-by":"crossref","unstructured":"Cox SR Lee YC Ooi WT . Comparing how a chatbot references user utterances from previous chatting sessions: an investigation of users\u2019 privacy concerns and perceptions. Presented at: Proceedings of the 11th International Conference on Human-Agent Interaction (HAI \u201923); Dec 4-7, 2023:105-114; Gothenburg, Sweden. [doi: 10.1145\/3623809.3623875]","DOI":"10.1145\/3623809.3623875"},{"issue":"1","key":"R16","doi-asserted-by":"publisher","DOI":"10.1186\/s12910-021-00574-x","article-title":"The anatomy of electronic patient record ethics: a framework to guide design, development, implementation, and use","volume":"22","author":"Jacquemard","journal-title":"BMC Med Ethics"},{"issue":"20","key":"R17","doi-asserted-by":"publisher","first-page":"3311","DOI":"10.3390\/electronics11203311","article-title":"GDPR compliant data storage and sharing in smart healthcare system: a blockchain-based solution","volume":"11","author":"Bai","journal-title":"Electronics"},{"issue":"1","key":"R18","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-48034-3","article-title":"Neural networks memorise personal information from one sample","volume":"13","author":"Hartley","journal-title":"Sci Rep"},{"issue":"6","key":"R19","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1038\/s42256-020-0186-1","article-title":"Secure, privacy-preserving and federated machine learning in medical imaging","volume":"2","author":"Kaissis","journal-title":"Nat Mach Intell"},{"key":"R20","unstructured":"45 CFR 46. US Department of Health and Human Services. URL: https:\/\/www.hhs.gov\/ohrp\/regulations-and-policy\/regulations\/45-cfr-46\/index.html [Accessed 01-06-2026]"},{"key":"R21","unstructured":"Guidance regarding methods for de-identification of protected health information in accordance with the Health Insurance Portability and Accountability Act (HIPAA) privacy rule. US Department of Health and Human Services. URL: https:\/\/www.hhs.gov\/hipaa\/for-professionals\/special-topics\/de-identification\/index.html [Accessed 17-07-2025]"}],"container-title":["JMIR Formative Research"],"original-title":[],"language":"en","deposited":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T16:13:43Z","timestamp":1787328823000},"score":1,"resource":{"primary":{"URL":"https:\/\/formative.jmir.org\/2026\/1\/e87704"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,21]]},"references-count":21,"URL":"https:\/\/doi.org\/10.2196\/87704","relation":{},"ISSN":["2561-326X"],"issn-type":[{"value":"2561-326X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,21]]},"article-number":"v10i1e87704"}}