Talk2Care: An LLM-based Voice Assistant for Communication between Healthcare Providers and Older Adults
Open accessThe DOI matches its Crossref record; 135 of the 135 references it cites were found in a registry or an index; 33 of the 64 sources its claims cite were checked for support.
Abstract
Despite the plethora of telehealth applications to assist home-based older adults and healthcare providers, basic messaging and phone calls are still the most common communication methods, which suffer from limited availability, information loss, and process inefficiencies. One promising solution to facilitate patient-provider communication is to leverage large language models (LLMs) with their powerful natural conversation and summarization capability. However, there is a limited understanding of LLMs' role during the communication. We first conducted two interview studies with both older adults (N=10) and healthcare providers (N=9) to understand their needs and opportunities for LLMs in patient-provider asynchronous communication. Based on the insights, we built an LLM-powered communication system, Talk2Care, and designed interactive components for both groups: (1) For older adults, we leveraged the convenience and accessibility of voice assistants (VAs) and built an LLM-powered conversational interface for effective information collection. (2) For health providers, we built an LLM-based dashboard to summarize and present important health information based on older adults' conversations with the VA. We further conducted two user studies with older adults and providers to evaluate the usability of the system. The results showed that Talk2Care could facilitate the communication process, enrich the health information collected from older adults, and considerably save providers' efforts and time. We envision our work as an initial exploration of LLMs' capability in the intersection of healthcare and interpersonal communication.
Overview
CoChat Summary
## TL;DR
Talk2Care is a pilot LLM-powered voice assistant and provider dashboard designed to improve asynchronous communication between older adults at home and healthcare providers. Across interviews and user studies with 10 older adults and 9 providers, the system was reported to improve usability, enrich shared health information, and reduce providers’ effort and time.
## Key findings
- In the need-finding interviews, older adults and providers both described communication breakdowns in existing methods: providers were hard to reach, messages were often unclear or incomplete, and older adults had accessibility and literacy challenges.
- In the older-adult user study, the VA system had an average SUS score of 75.5±17.1 and participants rated it as simple to understand (4.6±0.5), accurate in understanding their words (4.3±0.8), reliable (4.2±1.0), and supportive for home-based healthcare needs (4.2±1.0).
- In the provider user study, the dashboard had an average SUS score of 85.8±9.8; providers also reported low task load on NASA-TLX (mental demand 2.2±1.0, physical demand 1.4±0.5, temporal demand 1.7±0.9, effort 2.0±1.1, frustration 1.1±0.3, performance 6.1±0.6).
- Providers rated the system helpful for communication with older adults (4.6±0.5 out of 5) and for offloading work (4.4±0.9), and 5 out of 9 said the dashboard could assist triage and prioritization.
## Methods
- The paper used a mixed design: two semi-structured interview studies for need-finding, followed by two scenario-based user studies evaluating a pilot system.
- Sample: 10 older adults (65+ years old, living in single-family homes in the northeastern U.S.) and 9 healthcare providers (including physicians, nurse practitioners, and related professionals).
- Analysis and evaluation: interview transcripts were analyzed with thematic analysis; user studies used questionnaires including SUS and NASA-TLX, plus exit interviews and comparison against traditional asynchronous messaging/phone-call workflows.
## Limitations
- The paper states that the user-study sample sizes were limited: 10 older adults and 9 healthcare providers.
- The paper states that participants were recruited from a university pool and may have had higher education, digital literacy, or better understanding of LLMs than other groups, so results may not generalize to other populations.
- The paper states that providers were mainly physicians rather than a wider range of roles; it suggests future work include broader patient and provider populations.
- Evident from the text: the system is a proof-of-concept prototype and the evaluation focused mainly on usability and perceived benefits, not on module-level performance such as question quality, summary quality, or risk-prediction accuracy.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures











Verification
Claims the paper makes
6 Valid · 16 Not valid · 7 Not checked · 163 Own results and interpretations
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“multiple studies have raised concerns about using LLMs for healthcare scenarios, due to their inconsistency, potential errors, and bias in clinical work [17,55,64]”
§ Talk2Care: An LLM-based Voice Assistant for Communication between Healthcare Providers and Older Adults > 2.3 Large Language Models for Healthcare
What the sources say
- Not checked — no full text of the sourcecites [17] 17. Johnna Blair and Saeed Abdullah. 2019. Understanding the Needs and Challenges of Using Conversational Agents for Deaf Older Adults. In Companion Publication of the 2019 Conference on Computer Supported Cooperative Work and Social Computing (CSCW '19 Companion). Association for Computing Machinery, New York, NY, USA, 161-165. https://doi.org/10.1145/3311957.3359487 source
- Not checked — no full text of the sourcecites [55] 55. Mohit Jain, Pratyush Kumar, Ishita Bhansali, Q. Vera Liao, Khai Truong, and Shwetak Patel. 2018. FarmChat: A Conversational Agent to Answer Farmer Queries. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. 2, 4, Article 170 (dec 2018), 22 pages. https://doi.org/10.1145/3287048 source
- Could not verifycites [64] 64. Clemens Kruse, Joanna Fohn, Nakia Wilson, Evangelina Nunez Patlan, Stephanie Zipp, Michael Mileski, et al. 2020. Utilization barriers and medical outcomes commensurate with the use of telehealth among older adults: systematic review. JMIR medical informatics 8, 8 (2020), e20359. sourceExperimental — accuracy not yet measured
The Methods section on risk of bias and the Results section on bias within studies discuss the quality and selection bias of telehealth studies, not LLMs. Searches for LLMs and for clinical AI errors or bias found no passage addressing the cited claim. (LLM, conf=0.76)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“digital messages could be lost due to providers' hasty schedules [69]”
§ Talk2Care: An LLM-based Voice Assistant for Communication between Healthcare Providers and Older Adults > 1 INTRODUCTION
What the sources say
- Could not verifycites [69] 69. Gibbeum Lee, Volker Hartmann, Jongho Park, Dimitris Papailiopoulos, and Kangwook Lee. 2023. Prompted LLMs as Chatbot Modules for Long Open-domain Conversation. In Findings of the Association for Computational Linguistics: ACL 2023. 4536-4554. https://doi.org/10.18653/v1/2023.findings-acl.277 arXiv:2305.04533 [cs] sourceExperimental — accuracy not yet measured
The Modular Prompted Chatbot section (p. 2) discusses how a chatbot processes and retains conversational information, not whether providers miss digital messages. Searches for lost digital messages and providers’ rushed schedules found no passage addressing that claim. (LLM, conf=0.76)
hedgedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“getting feedback and progress via asynchronous messages is time-consuming”
§ Talk2Care: An LLM-based Voice Assistant for Communication between Healthcare Providers and Older Adults > 1 INTRODUCTION
What the sources say
- Could not verifycites [69] 69. Gibbeum Lee, Volker Hartmann, Jongho Park, Dimitris Papailiopoulos, and Kangwook Lee. 2023. Prompted LLMs as Chatbot Modules for Long Open-domain Conversation. In Findings of the Association for Computational Linguistics: ACL 2023. 4536-4554. https://doi.org/10.18653/v1/2023.findings-acl.277 arXiv:2305.04533 [cs] sourceExperimental — accuracy not yet measured
The cited paper’s C.3 Crowdworker Instruction (p. 11) describes evaluating chatbot responses, and B.1 Full Single Model Evaluation (p. 9) discusses response latency. Neither addresses whether obtaining feedback and progress updates through asynchronous messages is time-consuming. Searches for that phrase and for delayed communication about updates found no supporting passage. (LLM, conf=0.73)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“studies have also pointed out the limited use of these VAs by older adults due to usability barriers, cultural gaps, lack of explainability, and flexibility [18,44,49,108,131]”
§ Talk2Care: An LLM-based Voice Assistant for Communication between Healthcare Providers and Older Adults > 1 INTRODUCTION
What the sources say
- Partly supportedcites [18] 18. Ann Blandford, Janet Wesson, René Amalberti, Raed AlHazme, and Ragad Allwihan. 2020. Opportunities and challenges for telehealth within, and beyond, a pandemic. The Lancet Global Health 8, 11 (2020), e1364-e1365. sourceExperimental — accuracy not yet measured
In the paper’s main text (page not provided), Blandford et al. say telehealth must be easy to use, flexible, and tailored to users’ needs, and they discuss cultural differences relevant to data sharing. The paper does not report limited use of virtual assistants by older adults or identify lack of explainability as a cause. (LLM, conf=0.82)
- Partly supportedcites [44] 44. Kristen R Haase, Theodore Cosco, Lucy Kervin, Indira Riadi, and Megan E O'Connell. 2021. Older adults' experiences with using technology for socialization during the COVID-19 pandemic: Cross-sectional survey study. JMIR aging 4, 2 (2021), e28010. sourceExperimental — accuracy not yet measured
The Results (Facilitators to Web-Based Socialization; page unavailable) link older adults’ willingness to use socialization technology to its user-friendliness and report requests for clearer instructions. The paper concerns technology such as Zoom, not virtual assistants; our copy does not establish limited VA use or identify cultural gaps, lack of explainability, or lack of flexibility as its causes. (LLM, conf=0.86)
- Not matchedcites [49] 49. Sandra G Hart and Lowell E Staveland. 1988. Development of NASA-TLX (Task Load Index): Results of empirical and theoretical research. In Advances in psychology. Vol. 52. Elsevier, 139-183.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Could not verifycites [108] 108. Reed V. Tuckson, Margo Edmunds, and Michael L. Hodgkins. 2017. Telehealth. New England Journal of Medicine 377, 16 (Oct. 2017), 1585-1592. https://doi.org/10.1056/NEJMsr1503323 Publisher: Massachusetts Medical Society _eprint: https://doi.org/10.1056/NEJMsr1503323. sourceExperimental — accuracy not yet measured
The Telehealth and Patient Engagement sections discuss telehealth tools and patient-facing apps, but do not address older adults’ use of virtual assistants or the proposed reasons for limited use. Searches for older adults, voice assistants, and the specified barriers found no passage supporting the attributed claim. (LLM, conf=0.75)
- Not checked — no full text of the sourcecites [131] source
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“Given the limited work in multi-stakeholder contexts [58], our work uncovers AI's capability to address challenges in patient-provider communication.”
§ Talk2Care: An LLM-based Voice Assistant for Communication between Healthcare Providers and Older Adults > 6.1 AI-Empowered Healthcare Work
What the sources say
- Could not verifycites [58] 58. Eric L Johnson and Eden Miller. 2022. Remote patient monitoring in diabetes: how to acquire, manage, and use all of the data. Diabetes Spectrum 35, 1 (2022), 43-56. sourceExperimental — accuracy not yet measured
The citation is attached to the assertion that work in multi-stakeholder contexts is limited, not to the citing authors’ finding about AI. The paper discusses roles for patients, clinicians, and clinic staff in remote diabetes monitoring (Abstract, page unavailable), but does not assess how much research exists in multi-stakeholder contexts. Searches for that research-gap claim found no supporting passage. (LLM, conf=0.73)
plainstates a possible cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
72 more claims · 1 with their cited sources checked
Create a free account to see all 192 claims and every source verdict.
- It may state two separate claims as one. 55
- Probably not a substantial claim. 79
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“More recent advancements with voice-based conversational agents28 could interact with patients over the phone to overcome barriers with the writing and typing typically required of traditional questionnaires, and also increase access for patients who are of lower socioeconomic status, limited English proficiency, or elderly.29–32”
From Review of Artificial Intelligence for Clinical Use in Alzheimer's Disease and Related Dementias (2026) · cites this paper as [32]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Recent efforts to incorporate LLMs into voice-based interactions for older adults have shown improvement in conversational aspects [26, 63]”
From Situated Understanding of Errors in Older Adults' Interactions with Voice Assistants: A Month-Long, In-Home Study (2026) · cites this paper as [63]
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“Current challenges include cost, time required for clinicians to administer tests, specific training even for the most common assessments (e.g., MMSE, MoCA), and language and cultural biases that complicate interpretation in medically under-served populations.6,32,51”
From Review of Artificial Intelligence for Clinical Use in Alzheimer's Disease and Related Dementias (2026) · cites this paper as [32]
Experimental — accuracy not yet measured
Citations
Cites
Development of NASA-TLX (Task Load Index): Results of Empirical and Theoretical Research
(1988) · Advances in Psychology · doi:10.1016/s0166-4115(08)62386-9 · Cited by 15,003
SUS: A 'Quick and Dirty' Usability Scale
(1996) · Usability Evaluation In Industry · doi:10.1201/9781498710411-35 · Cited by 8,989
Kung, T. H., Cheatham, M., Medenilla, A., Sillos, C., De Leon, L., Elepaño, C., Madriaga, M., Aggabao, R., Diaz-Candido, G., Maningo, J., et al. (2023) · PLOS Digital Health · doi:10.1371/journal.pdig.0000198 · Cited by 4,115
Dorsey, E. R., & Topol, E. J. (2016) · New England Journal of Medicine · doi:10.1056/nejmra1601705 · Cited by 1,211
Cascella, M., Montomoli, J., Bellini, V., & Bignami, E. (2023) · Journal of Medical Systems · doi:10.1007/s10916-023-01925-4 · Cited by 1,120
The ethics of AI in health care: A mapping review
Morley, J., Machado, C. C. V., Burr, C., Cowls, J., Joshi, I., Taddeo, M., & Floridi, L. (2020) · Social Science & Medicine · doi:10.1016/j.socscimed.2020.113172 · Cited by 1,105 · cited 1×
“Talk2Care is intentionally designed to not provide health advice due to the concern about AI reliability in healthcare [24, 55, 82].”
BackgroundTuckson, R. V., Edmunds, M., & Hodgkins, M. L. (2017) · New England Journal of Medicine · doi:10.1056/nejmsr1503323 · Cited by 907
The State of Telehealth Before and After the COVID-19 Pandemic
Shaver, J. (2022) · Primary Care: Clinics in Office Practice · doi:10.1016/j.pop.2022.04.002 · Cited by 863
AudioPaLM: A Large Language Model That Can Speak and ListenPreprint
Rubenstein, P. K., Asawaroengchai, C., Nguyen, D. D., Bapna, A., Borsos, Z., Quitry, F. D. C., Chen, P., Badawy, D. E., Han, W., Kharitonov, E., et al. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2306.12925 · Cited by 671
Beede, E., Baylor, E., Hersch, F., Iurchenko, A., Wilcox, L., Ruamviboonsuk, P., & Vardoulakis, L. M. (2020) · Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3313831.3376718 · Cited by 614 · cited 1×
“For healthcare professionals, researchers have also leveraged LLMs to support public health interventions [58], clinical pre-screening [48, 115], risk prediction [16, 42, 63, 86] and information processing [9, 10, 26, 64, 84, 85].”
Background
Research works printed but not linked: 2
- Farah Magrabi, Elske Ammenwerth, Jytte Brender McNair, Nicolet F De Keizer, Hannele Hyppönen, Pirkko Nykänen, Michael Rigby, Philip J Scott, Tuulikki Vehko, Zoie Shui-Yee Wong, et al. 2019. Artificial intelligence in clinical decision support: challenges for evaluating AI and practical implications. Yearbook of medical informatics 28, 01 (2019), 128--134.
- Brendan Spillane, Emer Gilmartin, Christian Saam, Benjamin R Cowan, and Vincent Wade. 2018. ADELE: Care and Companionship for Independent Aging.. In ICAHGCA@ AAMAS. 18--24.
Cited by
From language to action: a review of large language models as autonomous agents and tool users
Chowa, S. S., Alvi, R., Rahman, S. S., Rahman, M. A., Raiaan, M. A. K., Islam, M. R., Hussain, M., & Azam, S. (2026) · Artificial Intelligence Review · doi:10.1007/s10462-025-11471-9 · Cited by 50
“Future research should enhance LLM agents’ scalability, adaptability, and real-time operational capacity, for deployment in multimodal and domain-specific environments [72,77,85,102].”
Clinical insights: A comprehensive review of language models in medicine
Neveditsin, N., Lingras, P., & Mago, V. (2025) · PLOS Digital Health · doi:10.1371/journal.pdig.0000800 · Cited by 37
“Among these, the GPT series [19] has advanced text generation capabilities while establishing the foundation for interactive applications.”
Voice Assistants for Health Self-Management: Designing for and with Older Adults
Mahmood, A., Cao, S., Stiber, M., Antony, V. N., & Huang, C. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713839 · Cited by 50
Yang, B., Guo, Y., Xu, L., Yan, Z., Chen, H., Xing, G., & Jiang, X. (2025) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3712286 · Cited by 72
ASHABot: An LLM-Powered Chatbot to Support the Informational Needs of Community Health Workers
Ramjee, P., Chhokar, M., Sachdeva, B., Meena, M., Abdullah, H., Vashistha, A., Nagar, R., & Jain, M. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713680 · Cited by 69
Metadata
- Authors
- Yang, Z., Xu, X., Yao, B., Rogers, E., Zhang, S., Intille, S., Shara, N., Gao, G. G., & Wang, D.
- Affiliations
- University of Michigan (US)
- Massachusetts Institute of Technology (US)
- Rensselaer Polytechnic Institute (US)
- Northeastern University (US)
- MedStar Health Research Institute (US)
- Johns Hopkins University (US)
- ORCID
- Venue
- Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
- Published
- 2024-05-13
- Volume
- 8
- Issue
- 2
- Pages
- 1-35
- ISSN
- 2474-9567 (ISSN-L)
- OpenAlex
- W4396919238
- Cited by
- 120
- References
- 89
- Citations by year
- 2026: 50 · 2025: 64 · 2024: 6
- FWCI
- 102.62
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies (publishedVersion, cc-by)
- DSpace@MIT (Massachusetts Institute of Technology) (submittedVersion, cc-by-nc)
- Topics
- Health Sciences › Medicine › Geriatrics and Gerontology › Technology Use by Older Adults
- Health Sciences › Medicine › Public Health, Environmental and Occupational Health › Telemedicine and Telehealth Implementation
- Health Sciences › Health Professions › Health Information Management › Innovation in Digital Healthcare Systems
- Keywords
- large language models, voice assistants, patient-provider communication, older adults, asynchronous communication, telemedicine, conversational interfaces, usability evaluation, user needs
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-09-29, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-09-29 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Talk2Care: An LLM-based Voice Assistant for Communication between Healthcare Providers and Older Adults. https://app.cochat.ai/papers/10.1145/3659625
- The paper
- Yang, Z., Xu, X., Yao, B., Rogers, E., Zhang, S., Intille, S., Shara, N., Gao, G. G., & Wang, D. (2024). Talk2Care: An LLM-based Voice Assistant for Communication between Healthcare Providers and Older Adults. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies. https://doi.org/10.1145/3659625
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.