Currently accepted at: JMIR Formative Research
Date Submitted: Nov 12, 2025
Date Accepted: Mar 27, 2026
This paper has been accepted and is currently in production.
It will appear shortly on 10.2196/87704
The final accepted version (not copyedited yet) is in this tab.
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Optimizing Multi-Call Memory in AI Healthcare Communication: A Mixed-Effects Analysis of Engagement and Satisfaction Outcomes
ABSTRACT
Background:
Multi-call memory capabilities in AI-powered health communication systems show promise for enhancing patient engagement, but their impact on engagement and patient satisfaction remains unclear.
Objective:
To evaluate the relationship between multi-call memory usage and key patient experience metrics including call duration and satisfaction scores in an AI-powered healthcare communication system.
Methods:
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 (minutes), Net Promoter Score (NPS), and patient satisfaction ratings. We analyzed the full dataset and relevant subsets (completed calls only, memory-using calls only) to assess robustness of findings.
Results:
Memory usage significantly increased call duration, with each additional memory extending conversations by 2.47 minutes (95% CI: 2.03, 2.91; p<0.001). This effect was consistent across sensitivity analyses, though attenuated in completed calls only (+0.54 minutes per memory, p=0.004). Memory usage showed no significant association with patient satisfaction across any analysis. Given that a small subset of calls used any memories and satisfaction data were available only for completed calls, the study may have been underpowered to detect an association between memory use and NPS or satisfaction ratings.
Conclusions:
Multi-call memory usage may significantly enhance behavioral engagement in AI healthcare conversations but may not impact patient satisfaction measures. 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 healthcare organizations implementing memory-enabled AI communication systems.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.