Evaluating Computer Agents for Patient Comprehension of Medication Information

Azevedo, Renato F. L.; Morrow, Daniel G.; Gu, Kuangxiao; Huang, Thomas S.; Hasegawa‐Johnson, Mark; Graumlich, James F.; Sadauskas, Victor; Sakakini, Tarek; Bhat, Suma; Willemsen‐Dunlap, Ann; Halpin, Donald J.

doi:10.1037/e511542018-001

Cited by 3 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some have examined specific ways in which an IVA may address needs of older adults, including health (e.g., asking the IVA to read to those with visual impairment, supporting wellbeing with healing music, or tracking health indicators) (McCloud et al, 2022;Trajkova & Martin-Hammond, 2020). Though studies have identified needs and/or reported on applications using IVAs that focus on one of more of the 5Ms [e.g., Medications (Azevedo et al, 2018), Mind (Kim, 2021;Rampioni et al, 2021;Ruggiano et al, 2021), Mobility (Luo et al, 2021)], none of them have utilized the comprehensive Geriatrics 5Ms framework to examine how IVAs might assist older adults with common healthrelated needs.…”

Section: Discussionmentioning

confidence: 99%

Ascertaining Whether an Intelligent Voice Assistant Can Meet Older Adults’ Health-Related Needs in the Context of a Geriatrics 5Ms Framework

Lifset,

Charles,

Farcas

et al. 2023

Gerontology and Geriatric Medicine

View full text Add to dashboard Cite

The Geriatrics 5Ms: Medications, Mind, Mobility, what Matters most and Multicomplexity is a framework to address the complex needs of older adults. Intelligent Voice Assistants (IVAs) are increasingly popular and have potential to support health-related needs of older adults. We utilized previously collected qualitative data on older adults’ views of how an IVA may address their health-related needs and ascertained their fit into the Geriatrics 5Ms framework. The codes describing health challenges and potential IVA solutions fit the framework: (1) Medications: difficulty remembering medications. Solution: reminders. (2) Mind: isolation, anxiety, memory loss. Solution: companionship, memory aids. (3) Mobility: barriers to exercise. Solution: incentives, exercise ideas. (4) Matters most: eating healthy foods. Solution: suggest and order nutritious foods, (5) Multicomplexity; managing multimorbidity. Solution: symptom tracking and communicating with health care professionals. Incorporating the 5Ms framework into IVA design can aid in addressing health care priorities of older adults.

show abstract

Section: Discussionmentioning

confidence: 99%

Ascertaining Whether an Intelligent Voice Assistant Can Meet Older Adults’ Health-Related Needs in the Context of a Geriatrics 5Ms Framework

Lifset,

Charles,

Farcas

et al. 2023

Gerontology and Geriatric Medicine

View full text Add to dashboard Cite

show abstract

“…To address this issue, we are developing a conversational agent (CA), or virtual provider, to deliver health information in portal environments. Ideally, the CA will emulate best practices for face-to-face communication but will also be capable of delivering a wide range of health information to diverse patients (see Morrow et al, 2017, for more detail, and Azevedo et al, 2017, for an initial evaluation of a CA prototype for patient portals).…”

Section: Discussionmentioning

confidence: 99%

Contextualizing numeric clinical test results for gist comprehension: Implications for EHR patient portals.

Morrow

Azevedo

García‐Retamero

et al. 2019

Journal of Experimental Psychology: Applied

Self Cite

View full text Add to dashboard Cite

Patient portals to Electronic Health Record (EHR) systems are underused by older adults because of limited system usability and usefulness, including difficulty understanding numeric information. We investigated whether enhanced context for portal messages about test results improved responses to these messages, comparing verbally, graphically, and video-enhanced formats. Older adults viewed scenarios with fictitious patient profiles and messages describing results for these patients from cholesterol or diabetes screening tests indicating lower, borderline, or higher risk levels. These messages were conveyed by standard format (table of numerical test scores) or one of the enhanced formats. Verbatim and gist memory for test results, risk perception, affective response, attitude toward and intention to perform self-care behaviors, and satisfaction were measured. Verbally and video enhanced context improved older adults’ gist but not verbatim memory compared to the standard format, suggesting we were successful in designing messages that highlight gist-based information. Little evidence was found for benefits related to the graphically enhanced format. Although verbally and video enhanced formats improved gist memory and message satisfaction, they had less impact on the other responses to the messages. However, these responses reflected level of risk: As risk associated with test results increased, positive affect decreased whereas negative affect, perceived risk, behavioral attitudes, and intentions increased, as predicted by behavioral change theories.

show abstract

“…A CA (developed using the Virtual Human Toolkit; https://vhtoolkit.ict.usc.edu/; Hartholt et al, 2013) told older adults how to take two medications for Type II diabetes. A female CA was used (Figure 1) because we earlier found older and younger adults tend to prefer receiving medication instructions from female human-looking CAs rather than male or highly stylized CAs (Azevedo et al, 2018).…”

Section: Methodsmentioning

confidence: 99%

“…Answers to the interview questions were transcribed and segmented into separate idea units or comments. Two of the investigators reviewed and discussed the comments in order to develop a set of topic codes, drawing on existing taxonomies in the CA literature (Azevedo et al, 2019;Ryu & Baylor, 2005; Hayes-Roth, Maldonado & Moraes, 2002; Heidig & Clarebout, 2011). Each comment was coded separately by the two investigators for topic and valence (negative, neutral, positive) with respect to the agent (inter-rater reliability = 81.6%).…”

Section: Participantsmentioning

confidence: 99%

Closing the Loop in Computer Agent/Patient Communication

Morrow,

Azevedo,

Sari

et al. 2020

Proceedings of the Human Factors and Ergonomics Society Annual

View full text Add to dashboard Cite

While patient-centered communication supports patient self-care, providers rarely have enough time to consistently use patient- centered communication techniques. Technology has potential to support patient-centered communication, but frequently older adults prefer face-to-face communication with providers. Conversational agents (CAs) may support provider communication with older adults by emulating best practices from face-to-face communication. We investigated older adults’ response to a prototype CA communication system that served as a virtual provider and presented medication instructions using teachback, a recommended best practice that involves asking patients questions to ‘close the communication loop’. Older adults were told how to take medications by a CA who used (or did not use) teachback, and then were interviewed. Older adults were open to interacting with the CA and thought it would help support self-care. They thought the CA was a more effective teacher when using teachback and that this interactive strategy helped them remember the instructions. However, teachback did not improve instruction memory.

show abstract

Evaluating Computer Agents for Patient Comprehension of Medication Information

Cited by 3 publications

References 0 publications

Ascertaining Whether an Intelligent Voice Assistant Can Meet Older Adults’ Health-Related Needs in the Context of a Geriatrics 5Ms Framework

Ascertaining Whether an Intelligent Voice Assistant Can Meet Older Adults’ Health-Related Needs in the Context of a Geriatrics 5Ms Framework

Contextualizing numeric clinical test results for gist comprehension: Implications for EHR patient portals.

Closing the Loop in Computer Agent/Patient Communication

Contact Info

Product

Resources

About