The DOI matches its Crossref record; 47 of the 47 references it cites were found in a registry or an index; 12 of the 36 sources its claims cite were checked for support.
A Collaborative Approach to Support Medication Management in Older Adults with Mild Cognitive Impairment Using Conversational Assistants (CAs)
Open accessAbstract
Improving medication management for older adults with Mild Cognitive Impairment (MCI) requires designing systems that support functional independence and provide compensatory strategies as their abilities change. Traditional medication management interventions emphasize forming new habits alongside the traditional path of learning to use new technologies. In this study, we navigate designing for older adults with gradual cognitive decline by creating a conversational “check-in” system for routine medication management. We present the design of MATCHA - Medication Action To Check-In for Health Application, informed by exploratory focus groups and design sessions conducted with older adults with MCI and their caregivers, alongside our evaluation based on a two-phased deployment period of 20 weeks. Our results indicate that a conversational “check-in” medication management assistant increased system acceptance while also potentially decreasing the likelihood of accidental over-medication, a common concern for older adults dealing with MCI.
Overview
CoChat Summary
## TL;DR
The paper presents MATCHA, a Google Home Hub-based conversational assistant for medication management designed with and for older adults with mild cognitive impairment (MCI) and their carepartners. Across a 20-week two-phase deployment with 7 dyads, the system shifted from 18% engagement in Phase 1 to 67% in Phase 2 after design revisions, and participants reported greater confidence and support.
## Key findings
- In Phase 1, MATCHA generated 476 initiations and 84 interactions over 4 weeks, for an engagement rate of around 18%.
- After redesigns, Phase 2 produced 1120 initiations and 760 interactions over 16 weeks, for an engagement rate of around 67%.
- The modified System Usability Scale scores after Phase 1 were 84.66 for members and 86.16 for carepartners.
- Participants reported that the system’s check-in style, personalization, and touch-button options made it feel supportive, reduced onboarding friction, and helped address over-medication concerns; the paper also notes that all participating dyads in Phase 2 expressed the desire to continue using MATCHA after the study.
## Methods
- Design-based HCI study using exploratory focus groups and a scenario-based design session with older adults with MCI and their carepartners, all recruited from a larger hospital cognitive program.
- Deployed MATCHA on Google Home Hubs in two phases: 7 dyads for 4 weeks in Phase 1, then 5 dyads for 16 weeks in Phase 2, with 2 dyads dropping out between phases.
- Main analyses combined interaction logs, modified SUS responses, and qualitative interviews; Phase 2 also used inductive coding with multiple coders and inter-rater reliability to develop themes.
## Limitations
- The paper states that most participants had already been interacting with a CA for over a month before the study, so it would require more research to understand engagement when the system is newly introduced.
- Recruitment was limited to dyads in the cognitive program who could afford long-term therapeutic healthcare and were mainly from upper-middle and high-income households; the paper says the results are only representative of that program’s dyads.
- The study used only 2-person teams (member + spouse/adult child), so the paper notes future work is needed for multi-carepartner teams.
- Evident from the text: the study appears to involve a small, non-random sample and a single institutional context, which limits generalizability.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
8 Valid · 3 Not valid · 17 Not checked · 77 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“They reported that the usability of these products is signifcantly lower than the national average usability scale score [30].”
§ A Collaborative Approach to Support Medication Management in Older Adults with Mild Cognitive Impairment Using Conversational Assistants (CAs) > 2.2 Role of technology in Medication management in older adults
What the sources say
- Partly supportedcites [30] 30. Tejal Patel, Jessica Ivo, Sadaf Faisal, Aidan McDougall, Jillian Carducci, Sarah Pritchard, Feng Chang, et al. 2020. A prospective study of usability and workload of electronic medication adherence products by older adults, caregivers, and health care providers. Journal of medical Internet research 22, 6 (2020), e18073. sourceExperimental — accuracy not yet measured
The Usability section (page not provided) reports a mean System Usability Scale score of 52.28 across 21 products, supporting the finding that many scored relatively low. But the Principal Findings section (page not provided) says there is no benchmark for medication-adherence products, and the reported significance tests compare products with each other—not with a national average. The claimed significant difference from a national average is therefore unsupported. (LLM, conf=0.85)
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.
- Partly supported
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“While most of the existing work focuses on older adults and their interactions with CAs, the challenge of designing for compensatory cognitive support is underexplored, with the exception of a few studies that address cognitive behaviors as a result of MCI [20,45,46].”
§ A Collaborative Approach to Support Medication Management in Older Adults with Mild Cognitive Impairment Using Conversational Assistants (CAs) > 2.3 Adoption and use of CAs by older adults
What the sources say
- Not checked — no full text of the sourcecites [20] 20. Kathrin Koebel, Martin Lacayo, Madhumitha Murali, Ioannis Tarnanas, and Arzu Çöltekin. 2021. Expert Insights for Designing Conversational User Interfaces as Virtual Assistants and Companions for Older Adults with Cognitive Impairments. In International Workshop on Chatbot Research and Design. Springer, 23-38. source
- Not checked — no full text of the sourcecites [45] 45. John Vines, Gary Pritchard, Peter Wright, Patrick Olivier, and Katie Brittain. 2015. An age-old problem: Examining the discourses of ageing in HCI and strategies for future research. ACM Transactions on Computer-Human Interaction (TOCHI) 22, 1 (2015), 1-27. source
- Supportedcites [46] 46. Pierre Wargnier, Giovanni Carletti, Yann Laurent-Corniquet, Samuel Benveniste, Pierre Jouvelot, and Anne-Sophie Rigaud. 2016. Field evaluation with cognitively- impaired older adults of attention management in the embodied conversational agent louise. In 2016 IEEE International Conference on Serious Games and Applica- tions for Health (SeGAH). IEEE, 1-8. source
The Introduction (p. 3) identifies attention management for cognitively impaired older adults as this paper’s contribution, and the Experiments section (p. 5) includes three participants with MCI. As one of the cited examples, it supports the sentence’s exception for studies addressing cognitive difficulties associated with MCI; the Conversation Management section (p. 4) also describes prior work on detailed ECA interaction management as scarce. (LLM, conf=0.86)
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 support only part of this claim — read each source’s verdict below.
In the paper
“Some older adults with MCI also struggle with reduced awareness of their circadian rhythms, placing additional stress on their ability to adhere to routines [8,22].”
§ A Collaborative Approach to Support Medication Management in Older Adults with Mild Cognitive Impairment Using Conversational Assistants (CAs) > 2.1 Medication adherence in older adults: A persistent challenge
What the sources say
- Partly supportedcites [8] 8. Andy Cochrane, Ian H Robertson, and Andrew N Coogan. 2012. Association between circadian rhythms, sleep and cognitive impairment in healthy older adults: an actigraphic study. Journal of neural transmission 119, 10 (2012), 1233- 1239. sourceExperimental — accuracy not yet measured
The Introduction (p. 1) links circadian-rhythm disturbance with MCI, and the Discussion (p. 5) reports a later activity peak in participants with early cognitive decline. The paper does not establish reduced awareness of circadian rhythms or difficulty adhering to routines; its participants did not have clinical MCI diagnoses (Discussion, p. 5). (LLM, conf=0.83)
- Partly supportedcites [22] 22. Glenn J Landry and Teresa Liu-Ambrose. 2014. Buying time: a rationale for exam- ining the use of circadian rhythm and sleep interventions to delay progression of mild cognitive impairment to Alzheimer's disease. Frontiers in aging neuroscience 6 (2014), 325. sourceExperimental — accuracy not yet measured
The 'Mild cognitive impairment: circadian rhythms and sleep' section (page unavailable) reports altered circadian timing and disrupted sleep in adults with MCI. It does not report reduced awareness of circadian rhythms or say that such awareness places stress on adherence to routines. (LLM, conf=0.82)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“CAs have shown to provide useful and usable support for older adults with MCI across a variety of functions, from information searching to calendaring, especially when sufcient training is provided.”
§ A Collaborative Approach to Support Medication Management in Older Adults with Mild Cognitive Impairment Using Conversational Assistants (CAs) > 1 INTRODUCTION
What the sources say
- Partly supportedcites [46] 46. Pierre Wargnier, Giovanni Carletti, Yann Laurent-Corniquet, Samuel Benveniste, Pierre Jouvelot, and Anne-Sophie Rigaud. 2016. Field evaluation with cognitively- impaired older adults of attention management in the embodied conversational agent louise. In 2016 IEEE International Conference on Serious Games and Applica- tions for Health (SeGAH). IEEE, 1-8. sourceExperimental — accuracy not yet measured
The Related Work summary (p. 3) says that older adults with MCI or dementia successfully interacted with ECAs and that ECAs conveyed information and provided guidance effectively. The calendar example (Conversation Management, p. 4) involved younger adults with intellectual disability and healthy older adults, not older adults with MCI. Our copy does not establish information searching as a function or say that sufficient training was especially important. (LLM, conf=0.85)
boostedstates 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
Every source the paper cites for this claim was checked and supports it.
In the paper
“An important aspect of older adults and their usage of CAs is their tendency to anthropomorphize the device as a companion within their home environment [6,35].”
§ A Collaborative Approach to Support Medication Management in Older Adults with Mild Cognitive Impairment Using Conversational Assistants (CAs) > 2.3 Adoption and use of CAs by older adults
What the sources say
- Supportedcites [6] 6. Chen Chen, Janet G Johnson, Kemeberly Charles, Alice Lee, Ella T Lifset, Michael Hogarth, Alison A Moore, Emilia Farcas, and Nadir Weibel. 2021. Understanding Barriers and Design Opportunities to Improve Healthcare and QOL for Older Adults through Voice Assistants. In The 23rd International ACM SIGACCESS Conference on Computers and Accessibility. 1-16. source
Section 2.2 reports that older adults tend to treat smart-speaker voice assistants as people, including when seeking social interaction while lonely. This supports the companion interpretation; the paper presents it as a finding from prior research, not its own study. No page number is available in our copy. (LLM, conf=0.87)
- Supportedcites [35] 35. Alisha Pradhan, Leah Findlater, and Amanda Lazar. 2019. " Phantom Friend" or" Just a Box with Information" Personifcation and Ontological Categorization of Smart Speaker-based Voice Assistants by Older Adults. Proceedings of the ACM on Human-Computer Interaction 3, CSCW (2019), 1-21. source
Section 4.4 says older adults can perceive an in-home voice assistant as a companion when they desire social interaction. The Conclusions report instances of companionship, while clarifying that participants also sometimes viewed the device as an object. (LLM, conf=0.87)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
51 more claims · 2 with their cited sources checked
Create a free account to see all 105 claims and every source verdict.
- Probably not a substantial claim. 25
- It may state two separate claims as one. 35
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ A Collaborative Approach to Support Medication Management in Older Adults with Mild Cognitive Impairment Using Conversational Assistants (CAs) > 7 LEARNING FROM USE: DEPLOYMENT PHASE 2
“For Phase 2, the revised version of MATCHA was deployed to the Google Home Hubs of 5 dyads for a period of 16 weeks”
§ A Collaborative Approach to Support Medication Management in Older Adults with Mild Cognitive Impairment Using Conversational Assistants (CAs) > 8.1 Interaction Log and Engagement Analysis
“Figure 5: Weekly Engagement Rate Trend for all Dyads for 20 Weeks During Phase 2”
Citations
Cites
Mild cognitive impairment as a diagnostic entity
Petersen, R. C. (2004) · Journal of Internal Medicine · doi:10.1111/j.1365-2796.2004.01388.x · Cited by 7,864 · cited 1×
“Mild Cognitive Impairment is defned as an intermediate stage of cognition situated between the expected decline due to aging and the more signifcant decline associated with dementia and Alzheimer’s disease [33].”
Background(2018) · Neurology · doi:10.1212/wnl.0000000000004826 · Cited by 2,183 · cited 1×
“6% of the population above 65 will develop MCI [34].”
BackgroundMedication Adherence: WHO Cares?
Brown, M. T., & Bussell, J. K. (2011) · Mayo Clinic Proceedings · doi:10.4065/mcp.2010.0575 · Cited by 1,928
What Makes a Good Conversation?: Challenges in Designing Truly Conversational Agents
Clark, L., Pantidi, N., Cooney, O., Doyle, P., Garaialde, D., Edwards, J., Spillane, B., Gilmartin, E., Murad, C., Munteanu, C., et al. (2019) · Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3290605.3300705 · Cited by 461 · cited 1×
“They provide a natural language based support to enable access to information and services for everyday interactions [7].”
BackgroundAn Age-Old Problem: Examining the Discourses of Ageing in HCI and Strategies for Future Research
Vines, J., Pritchard, G., Wright, P., Olivier, P., & Brittain, K. (2015) · ACM Transactions on Computer-Human Interaction · doi:10.1145/2696867 · Cited by 461 · cited 1×
“with technology currently focus on the roadblocks stemming from the technological stereotypes associated with older adults, who are often “defned by their defcits rather than capabilities” [32, 44].”
BackgroundThinking Outside the Pillbox — Medication Adherence as a Priority for Health Care Reform
Cutler, D., & Everett, W. (2010) · New England Journal of Medicine · doi:10.1056/nejmp1002305 · Cited by 459 · cited 1×
“in [30] reviewed these challenges in a usability and workload comparison of 21 commercially-available electronic medication adherence products with older adults and caregivers such in [9].”
BackgroundUse of Intelligent Voice Assistants by Older Adults with Low Technology Use
Pradhan, A., Lazar, A., & Findlater, L. (2020) · ACM Transactions on Computer-Human Interaction · doi:10.1145/3373759 · Cited by 285 · cited 1×
“There is a potential to develop systems which integrate and utilize the connection that older adults form with CAs and provide them a more coherent experience [36].”
BackgroundDetection methods and strategies for improving medication compliance
Bond, W. S., & Hussar, D. A. (1991) · American Journal of Health-System Pharmacy · doi:10.1093/ajhp/48.9.1978 · Cited by 241
Pradhan, A., Findlater, L., & Lazar, A. (2019) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3359316 · Cited by 223
Medication Adherence in Older Adults With Cognitive Impairment: A Systematic Evidence-Based Review
Campbell, N. L., Boustani, M. A., Skopelja, E. N., Gao, S., Unverzagt, F. W., & Murray, M. D. (2012) · The American Journal of Geriatric Pharmacotherapy · doi:10.1016/j.amjopharm.2012.04.004 · Cited by 206 · cited 1×
“Most medication management interventions support building habits over time by providing an integrative system for reminders or alerts [5, 31].”
Background
Research works printed but not linked: 2
- 10.5555/3021319.3021378 · doi:10.5555/3021319.3021378
- Jelte Barachia van Waterschoot, IHE Hendrickx, Arif Khan, Catia Cucchiarini, Helmer Strik, LFM ten Bosch, and Rob Tieben. 2021. Spoken Conversational Agents for Older Adults. Who Are the Stakeholders and What Do They Expect?(2021).
Cited by
Xygkou, A., Ang, C. S., Siriaraya, P., Kopecki, J. P., Covaci, A., Kanjo, E., & She, W. J. (2024) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642538 · Cited by 74
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 44
“Most participants preferred familiar methods and wanted VAs to adapt to their current practices, aligning with findings for individuals with MCI [52].”
InfluentialCzech, E., Soubutts, E., Eardley, R., & O’Kane, A. A. (2023) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3580733 · Cited by 27
“While HCI researchers have examined how technologies, including smart home and voice assistant technologies, for coordinating care [11, 26, 38, 43, 65, 85] can affect care relationship dynamics, few have looked at how these relationships are affected by the discourse around these specific technologies and during the o…”
BackgroundTalking ‘bout my Generation … or not?
Petrie, H. (2023) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3544549.3582742 · Cited by 21
“Some of the studies stated only that participants were over 60 or 65, several studies gave no information about how they defned the older population at all, or only gave an implicit defnition by mentioning ages in relation to previous research [33, 38, 39].”
ResultMilella, F., Russo, D. D., & Bandini, S. (2023) · OBM Geriatrics · doi:10.21926/obm.geriatr.2304262 · Cited by 17
Metadata
- Authors
- Mathur, N., Dhodapkar, K., Zubatiy, T., Li, J., Jones, B., & Mynatt, E.
- Affiliations
- Georgia Institute of Technology (US)
- Northeastern University (US)
- Venue
- Proceedings of the 24th International ACM SIGACCESS Conference on Computers and Accessibility
- Publisher
- ACM
- Published
- 2022-10-22
- Pages
- 1-14
- OpenAlex
- W4307136618
- Semantic Scholar
- 0a69f3eafb87d340d2af8005685b6f386cdd8278
- Cited by
- 45
- References
- 32
- Citations by year
- 2026: 11 · 2025: 16 · 2024: 12 · 2023: 6
- FWCI
- 29.43
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) (publishedVersion, cc-by)
- Topics
- Health Sciences › Medicine › Geriatrics and Gerontology › Technology Use by Older Adults
- Health Sciences › Medicine › Geriatrics and Gerontology › Pharmaceutical Practices and Patient Outcomes
- Physical Sciences › Computer Science › Human-Computer Interaction › Innovative Human-Technology Interaction
- Keywords
- medication management, mild cognitive impairment, older adults, chatbots, matcha, caregiver support, compensatory strategies, functional independence, system acceptance, technology acceptance, cognitive decline
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: A Collaborative Approach to Support Medication Management in Older Adults with Mild Cognitive Impairment Using Conversational Assistants (CAs). https://app.cochat.ai/papers/10.1145/3517428.3544830
- The paper
- Mathur, N., Dhodapkar, K., Zubatiy, T., Li, J., Jones, B., & Mynatt, E. (2022). A Collaborative Approach to Support Medication Management in Older Adults with Mild Cognitive Impairment Using Conversational Assistants (CAs). Proceedings of the 24th International ACM SIGACCESS Conference on Computers and Accessibility. https://doi.org/10.1145/3517428.3544830
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.