pith. machine review for the scientific record. sign in

arxiv: 2604.26214 · v1 · submitted 2026-04-29 · 💻 cs.HC

Recognition: unknown

Exploring the Feasibility and Acceptability of AI-Mediated Serious Illness Conversations in the Emergency Department

Hasibur Rahman , Kenji Numata , Evelyn T Lai , Maria Cheriyan , Adrian Haimovich , Kei Ouchi , Smit Desai
Authors on Pith no claims yet

Pith reviewed 2026-05-07 13:29 UTC · model grok-4.3

classification 💻 cs.HC
keywords AI conversational agentserious illness conversationsemergency departmentfeasibilityacceptabilityolder adultsvoice AIhallucination risks
0
0 comments X

The pith

A voice AI agent conducted serious illness conversations with most older adults in the emergency department and was rated acceptable and feasible.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper tests whether a voice-based AI can hold brief, structured discussions about values and goals with older patients in the busy emergency department, where clinicians rarely have time for such talks. In a study of 55 patients, most finished the conversation and gave the interaction positive ratings for acceptability and feasibility, including feeling heard and understood at levels similar to those reported with human clinicians. The work also documents specific problems that arose, such as the AI making unprompted diagnostic statements. If the approach holds, it could let emergency care teams incorporate patient priorities into decisions even when time is short.

Core claim

We evaluated ED GOAL-AI, a voice-based conversational agent designed for brief structured values discussions, in a case study with 55 older adults presenting to the emergency department. Most participants completed the conversation. They reported the interaction as acceptable and feasible, with ratings of feeling heard and understood comparable to those given for interactions with clinicians. The study also recorded critical failure modes, including boundary violations through hallucinated diagnostic statements, underscoring the need for careful boundary setting and participatory design before wider use.

What carries the argument

The ED GOAL-AI voice-based conversational agent for brief, structured values discussions with older adults in the ED.

If this is right

  • Serious illness conversations could occur more often in time-pressured emergency departments.
  • Patient values and goals could be documented earlier, potentially guiding high-stakes decisions.
  • Boundary-setting techniques would be required to limit AI statements outside the intended values discussion.
  • Participatory design with patients and clinicians could reduce the observed failure modes before scaling.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same structured prompting approach might be tested in other rushed clinical environments such as intensive care or pre-operative holding areas.
  • Linking the AI output directly to the electronic health record could create a persistent record of patient priorities for later care teams.
  • Repeated exposure to the agent in follow-up visits could be studied to see whether patients become more comfortable discussing values over time.

Load-bearing premise

Self-reported feedback from a convenience sample of 55 patients at one site, without long-term follow-up or detailed statistical analysis, is sufficient to show feasibility and that hallucination risks can be managed through boundary setting.

What would settle it

A larger multi-site study in which a majority of patients report the AI conversation as unacceptable or in which hallucinated statements repeatedly cause patient distress or confusion.

Figures

Figures reproduced from arXiv: 2604.26214 by Adrian Haimovich, Evelyn T Lai, Hasibur Rahman, Kei Ouchi, Kenji Numata, Maria Cheriyan, Smit Desai.

Figure 1
Figure 1. Figure 1: ED GOAL-AI for emergency-department serious illness conversations (SICs). SICs can reduce unwanted aggressive interventions and improve end-of-life care, but clinician time constraints in the ED limit scalability (left). ED GOAL-AI (middle) is a voice-based, locally hosted, fine-tuned LLM agent that facilitates brief, structured SICs by guiding patients through five core values questions. In a case study w… view at source ↗
Figure 2
Figure 2. Figure 2: A patient uses ED GOAL-AI on a tablet in the ED while research staff remains present for technical sup￾port without prompting or directing the discussion. Photo shared with patient’s permission; identifying details have been redacted. verbal consent. Enrolled participants completed a single conver￾sation with ED GOAL-AI lasting approximately 5 minutes, a du￾ration informed by the efficacy of brief negotiat… view at source ↗
Figure 3
Figure 3. Figure 3: Acceptability ratings for ED GOAL-AI across four dimensions (1–5 Likert; higher is more acceptable): acceptability, respectfulness, question clarity, and ease of conversation. Most participants rated the ED GOAL-AI as completely acceptable. system behavior, and participatory design with patients and clini￾cians to determine what AI should and should not do in moments of acute vulnerability [3, 54]. We posi… view at source ↗
read the original abstract

Serious illness conversations (SICs) align care with patients' values, goals, and preferences, yet they rarely occur in emergency departments (EDs), where time constraints and emotional burden often leave clinicians making high-stakes decisions without documented insight into what matters most to patients. We present a case study of ED GOAL-AI, a voice-based conversational agent for brief, structured values discussions with older adults in the ED, evaluated with 55 patients for feasibility and acceptability. Most participants completed the conversation and reported the interaction as acceptable and feasible, with ratings of feeling heard and understood comparable to clinicians. However, we also observed critical failure modes, including boundary violations such as hallucinated diagnostic statements, highlighting ethical and emotional risks. This work points to early promise for AI-mediated SICs while underscoring the need for careful boundary setting and participatory design before broader deployment.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The paper presents a case study of ED GOAL-AI, a voice-based conversational agent for conducting brief, structured serious illness conversations (SICs) with older adults in the emergency department (ED). Evaluated with 55 patients, the work claims that most participants completed the conversation, rated the interaction as acceptable and feasible, and provided ratings of feeling heard and understood that were comparable to clinician-led discussions. The authors also document critical failure modes, including hallucinated diagnostic statements, and conclude that the approach shows early promise but requires careful boundary setting and participatory design prior to broader use.

Significance. If the reported outcomes are substantiated with fuller methodological detail and analysis, the study would offer a valuable early empirical demonstration of AI-mediated SICs in a high-stakes ED environment. It contributes concrete observations on both acceptability metrics and ethical risks (e.g., hallucination), which can inform participatory design and safety protocols in healthcare HCI. The direct clinical deployment setting is a strength, providing real-world grounding rather than simulated data.

major comments (2)
  1. [Methods] Methods section: The manuscript does not report recruitment criteria, inclusion/exclusion standards, sample size justification, or the exact protocol used for obtaining and comparing clinician ratings of 'feeling heard and understood.' Because the central feasibility and acceptability claims rest entirely on completion rates and self-reported Likert-style outcomes from this 55-patient convenience sample, the absence of these details prevents evaluation of selection bias, comparability, or statistical validity.
  2. [Results] Results section: No error bars, confidence intervals, or pre-specified statistical tests are provided for the claim that patient ratings were 'comparable to clinicians.' Without these, the descriptive summary of acceptability cannot securely support the feasibility conclusion, especially given the acknowledged hallucination failures and lack of a control arm or long-term follow-up.
minor comments (2)
  1. [Abstract] Abstract: Explicitly state the sample size (n=55) and note the single-site convenience sampling in the opening sentence to better contextualize the feasibility claims for readers.
  2. [Discussion] Discussion: Expand the limitations paragraph to address the absence of a control condition and the implications of self-report bias for the 'comparable to clinicians' assertion.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their constructive and detailed feedback on our manuscript. The comments have prompted us to improve the clarity and rigor of our reporting on this feasibility case study. We address each major comment below and have made corresponding revisions to the manuscript.

read point-by-point responses

  1. Referee: [Methods] Methods section: The manuscript does not report recruitment criteria, inclusion/exclusion standards, sample size justification, or the exact protocol used for obtaining and comparing clinician ratings of 'feeling heard and understood.' Because the central feasibility and acceptability claims rest entirely on completion rates and self-reported Likert-style outcomes from this 55-patient convenience sample, the absence of these details prevents evaluation of selection bias, comparability, or statistical validity.

    Authors: We agree that greater methodological detail is warranted to allow proper evaluation of the study. In the revised manuscript we have expanded the Methods section to specify the recruitment criteria (older adults aged 65+ presenting to the ED), inclusion and exclusion standards (e.g., ability to provide consent, English proficiency, exclusion of acute delirium or severe cognitive impairment), and a sample-size rationale grounded in feasibility-study guidelines. We have also added the precise protocol for the clinician ratings: two independent, blinded clinicians scored a random subset of 20 audio-recorded conversations on the same 'feeling heard and understood' Likert item, with inter-rater reliability statistics now reported. Potential selection bias associated with the convenience sample is now explicitly discussed in the Limitations subsection. revision: yes

  2. Referee: [Results] Results section: No error bars, confidence intervals, or pre-specified statistical tests are provided for the claim that patient ratings were 'comparable to clinicians.' Without these, the descriptive summary of acceptability cannot securely support the feasibility conclusion, especially given the acknowledged hallucination failures and lack of a control arm or long-term follow-up.

    Authors: We accept this criticism and have revised the Results section to include error bars and 95% confidence intervals around the key acceptability and feeling-heard ratings. We have clarified that the statement of comparability to clinician ratings is descriptive only; no pre-specified inferential statistical tests were planned or performed, consistent with the exploratory nature of a feasibility case study. The absence of a control arm and long-term follow-up is acknowledged as a design limitation inherent to this initial real-world deployment; we have expanded the Discussion to frame the contribution as early observational evidence rather than comparative efficacy data. The hallucination failures remain prominently reported as a critical safety concern. revision: partial

Circularity Check

0 steps flagged

No circularity: direct empirical case study with observational results only

full rationale

This paper is a qualitative/observational case study reporting completion rates, self-reported acceptability scores, and failure modes from 55 ED patients interacting with a voice-based AI agent. No equations, fitted parameters, predictive models, or derivation chains appear in the abstract or described content. Claims rest on direct participant data rather than any self-definitional loops, fitted inputs renamed as predictions, or load-bearing self-citations. The reader's assessment of 0.0 circularity is confirmed; the work contains no mathematical structure that could reduce to its inputs by construction.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

This is an empirical feasibility study rather than a theoretical paper, so the ledger contains only standard domain assumptions from human-subjects research. No free parameters or invented entities are introduced.

axioms (1)
  • domain assumption Patient self-reports of acceptability and feeling heard accurately capture the quality and safety of the AI interaction.
    The study relies on these subjective ratings as primary evidence without objective measures of conversation fidelity or clinical outcomes.

pith-pipeline@v0.9.0 · 10471 in / 1389 out tokens · 115785 ms · 2026-05-07T13:29:55.745841+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

63 extracted references · 32 canonical work pages

  1. [1]

    Anand Avati, Kenneth Jung, Stephanie Harman, Lance Downing, Andrew Ng, and Nigam H Shah. 2018. Improving palliative care with deep learning.BMC medical informatics and decision making18 (2018), 55–64

    2018

  2. [2]

    Back, Robert M

    Anthony L. Back, Robert M. Arnold, James A. Tulsky, Walter F. Baile, and Kelly A. Fryer-Edwards. 2003. Teaching communication skills to medical oncology fellows. Journal of Clinical Oncology: Official Journal of the American Society of Clinical Oncology21, 12 (June 2003), 2433–2436. doi:10.1200/JCO.2003.09.073

    work page doi:10.1200/jco.2003.09.073 2003

  3. [3]

    Lisanne Bainbridge. 1983. Ironies of automation.Automatica19, 6 (1983), 775–779. doi:10.1016/0005-1098(83)90046-8

    work page doi:10.1016/0005-1098(83)90046-8 1983

  4. [4]

    Rachelle Bernacki, Mathilde Hutchings, Judith Vick, Grant Smith, Joanna Pal- adino, Stuart Lipsitz, Atul A Gawande, and Susan D Block. 2015. Development of the Serious Illness Care Program: a randomised controlled trial of a palliative care communication intervention.BMJ open5, 10 (2015), e009032

    2015

  5. [5]

    Rachelle E Bernacki, Susan D Block, et al. 2014. Communication about serious illness care goals: a review and synthesis of best practices.JAMA internal medicine 174, 12 (2014), 1994–2003

    2014

  6. [6]

    Bernstein, J

    E. Bernstein, J. Bernstein, and S. Levenson. 1997. Project ASSERT: an ED-based intervention to increase access to primary care, preventive services, and the substance abuse treatment system.Annals of Emergency Medicine30, 2 (Aug. 1997), 181–189. doi:10.1016/s0196-0644(97)70140-9

    work page doi:10.1016/s0196-0644(97)70140-9 1997

  7. [7]

    Bickmore, Lisa Caruso, Kerri Clough-Gorr, and Tim Heeren

    Timothy W. Bickmore, Lisa Caruso, Kerri Clough-Gorr, and Tim Heeren. 2005. ‘It’s just like you talk to a friend’ relational agents for older adults.Interacting with Computers17, 6 (Dec. 2005), 711–735. doi:10.1016/j.intcom.2005.09.002

    work page doi:10.1016/j.intcom.2005.09.002 2005

  8. [8]

    Confinement and the center of the gauge group,

    Julie W. Childers, Hailey Bulls, and Robert Arnold. 2023. Beyond the NURSE Acronym: The Functions of Empathy in Serious Illness Conversations.Journal of pain and symptom management65, 4 (April 2023), e375–e379. doi:10.1016/j. jpainsymman.2022.11.029

    work page doi:10.1016/j 2023

  9. [9]

    Isaac S Chua, Christine S Ritchie, and David W Bates. 2022. Enhancing serious illness communication using artificial intelligence.NPJ digital medicine5, 1 (2022), 14

    2022

  10. [10]

    Andrea Cuadra, Maria Wang, Lynn Andrea Stein, Malte F Jung, Nicola Dell, Deborah Estrin, and James A Landay. 2024. The illusion of empathy? notes on displays of emotion in human-computer interaction. InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems. 1–18

    2024

  11. [11]

    Fiellin, Michael V

    Gail D’Onofrio, David A. Fiellin, Michael V. Pantalon, Marek C. Chawarski, Patricia H. Owens, Linda C. Degutis, Susan H. Busch, Steven L. Bernstein, and Patrick G. O’Connor. 2012. A brief intervention reduces hazardous and harmful drinking in emergency department patients.Annals of Emergency Medicine60, 2 (Aug. 2012), 181–192. doi:10.1016/j.annemergmed.20...

    work page doi:10.1016/j.annemergmed.2012.02.006 2012

  12. [12]

    Pantalon, Linda C

    Gail D’Onofrio, Michael V. Pantalon, Linda C. Degutis, David A. Fiellin, and Patrick G. O’connor. 2005. Development and implementation of an emergency practitioner-performed brief intervention for hazardous and harmful drinkers in the emergency department.Academic Emergency Medicine: Official Journal of the Society for Academic Emergency Medicine12, 3 (Ma...

    work page doi:10.1197/j.aem.2004.10.021 2005

  13. [13]

    Katherine Easton, Stephen Potter, Remi Bec, Matthew Bennion, Heidi Christensen, Cheryl Grindell, Bahman Mirheidari, Scott Weich, Luc de Witte, Daniel Wolsten- holme, and Mark S. Hawley. 2019. A Virtual Agent to Support Individuals Living With Physical and Mental Comorbidities: Co-Design and Acceptability Testing. Journal of Medical Internet Research21, 5 ...

    work page doi:10.2196/12996 2019

  14. [14]

    Kathleen Kara Fitzpatrick, Alison Darcy, and Molly Vierhile. 2017. Delivering Cognitive Behavior Therapy to Young Adults With Symptoms of Depression and Anxiety Using a Fully Automated Conversational Agent (Woebot): A Randomized Controlled Trial.JMIR mental health4, 2 (June 2017), e19. doi:10.2196/mental.7785

    work page doi:10.2196/mental.7785 2017

  15. [15]

    Norton, AAHPM Research Committee Writing Group, Rebecca A

    Robert Gramling, Susan Stanek, Susan Ladwig, Elizabeth Gajary-Coots, Jenica Cimino, Wendy Anderson, Sally A. Norton, AAHPM Research Committee Writing Group, Rebecca A. Aslakson, Katherine Ast, Ronit Elk, Kimberly K. Garner, Robert Gramling, Corita Grudzen, Arif H. Kamal, Sangeeta Lamba, Thomas W. LeBlanc, Ramona L. Rhodes, Eric Roeland, Dena Schulman-Gree...

  16. [16]

    2016), 150–154

    Feeling Heard and Understood: A Patient-Reported Quality Measure for the Inpatient Palliative Care Setting.Journal of Pain and Symptom Management 51, 2 (Feb. 2016), 150–154. doi:10.1016/j.jpainsymman.2015.10.018

    work page doi:10.1016/j.jpainsymman.2015.10.018 2016

  17. [17]

    Yuexing Hao, Zeyu Liu, Robert N Riter, and Saleh Kalantari. 2024. Advancing patient-centered shared decision-making with ai systems for older adult cancer Conference acronym ’XX, June 03–05, 2018, Woodstock, NY Rahman et al. patients. InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems. 1–20

    2024

  18. [18]

    Carmen HM Houben, Martijn A Spruit, Miriam TJ Groenen, Emiel FM Wouters, and Daisy JA Janssen. 2014. Efficacy of advance care planning: a systematic review and meta-analysis.Journal of the American Medical Directors Association 15, 7 (2014), 477–489

    2014

  19. [19]

    Yu Lun Hsu, Yun-Rung Chou, Chiao-Ju Chang, Yu-Cheng Chang, Zer-Wei Lee, Rokas Gipiškis, Rachel Li, Chih-Yuan Shih, Jen-Kuei Peng, Hsien-Liang Huang, Jaw-Shiun Tsai, and Mike Y. Chen. 2025. PreCare: Designing AI Assistants for Advance Care Planning (ACP) to Enhance Personal Value Exploration, Pa- tient Knowledge, and Decisional Confidence. doi:10.48550/arX...

    work page doi:10.48550/arxiv.2505.09115 2025

  20. [20]

    Lei Huang, Weijiang Yu, Weitao Ma, Weihong Zhong, Zhangyin Feng, Haotian Wang, Qianglong Chen, Weihua Peng, Xiaocheng Feng, Bing Qin, and Ting Liu. 2025. A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions.ACM Transactions on Information Systems43, 2 (March 2025), 1–55. doi:10.1145/3703155 arXiv:2311.05232 [cs]

    work page doi:10.1145/3703155 2025

  21. [21]

    Huynh, Tamal J

    Anh L. Huynh, Tamal J. Roy, Kierra N. Jackson, Alyona G. Lee, Winston Liaw, and M. Mahbub Hossain. 2026. Applications of artificial intelligence-based conversational agents in healthcare: A systematic umbrella review.International Journal of Medical Informatics207 (March 2026), 106204. doi:10.1016/j.ijmedinf. 2025.106204

    work page doi:10.1016/j.ijmedinf 2026

  22. [22]

    Sunyoung Kim and Abhishek Choudhury. 2021. Exploring older adults’ percep- tion and use of smart speaker-based voice assistants: A longitudinal study.Com- puters in Human Behavior124 (Nov. 2021), 106914. doi:10.1016/j.chb.2021.106914

    work page doi:10.1016/j.chb.2021.106914 2021

  23. [23]

    Corinna Klingler, Jürgen in der Schmitten, and Georg Marckmann. 2016. Does facilitated Advance Care Planning reduce the costs of care near the end of life? Systematic review and ethical considerations.Palliative Medicine30, 5 (2016), 423–433

    2016

  24. [24]

    Elaine Kong, Kuo-Ting Huang, and Aakash Gautam. 2024. Envisioning Possibili- ties and Challenges of AI for Personalized Cancer Care. InCompanion Publication of the 2024 Conference on Computer-Supported Cooperative Work and Social Com- puting. 415–421

    2024

  25. [25]

    Peter Lee, Sebastien Bubeck, and Joseph Petro. 2023. Benefits, Limits, and Risks of GPT-4 as an AI Chatbot for Medicine.New England Journal of Medicine388, 13 (March 2023), 1233–1239. doi:10.1056/NEJMsr2214184 _eprint: https://www.nejm.org/doi/pdf/10.1056/NEJMsr2214184

    work page doi:10.1056/nejmsr2214184 2023

  26. [26]

    Robert Y Lee, Lyndia C Brumback, William B Lober, James Sibley, Elizabeth L Nielsen, Patsy D Treece, Erin K Kross, Elizabeth T Loggers, James A Fausto, Charlotta Lindvall, et al . 2021. Identifying goals of care conversations in the electronic health record using natural language processing and machine learning. Journal of pain and symptom management61, 1...

    2021

  27. [27]

    I Hear You, I Feel You

    Yi-Chieh Lee, Naomi Yamashita, Yun Huang, and Wai Fu. 2020. "I Hear You, I Feel You": Encouraging Deep Self-disclosure through a Chatbot. InProceedings of the 2020 CHI Conference on Human Factors in Computing Systems (CHI ’20). Association for Computing Machinery, New York, NY, USA, 1–12. doi:10.1145/ 3313831.3376175

    work page arXiv 2020

  28. [28]

    Brenna Li, Ofek Gross, Noah Crampton, Mamta Kapoor, Saba Tauseef, Mohit Jain, Khai N Truong, and Alex Mariakakis. 2024. Beyond the Waiting Room: Patient’s Perspectives on the Conversational Nuances of Pre-Consultation Chatbots. In Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems. 1–24

    2024

  29. [29]

    Charlotta Lindvall, Chih-Ying Deng, Edward Moseley, Nicole Agaronnik, Areej El-Jawahri, Michael K Paasche-Orlow, Joshua R Lakin, Angelo Volandes, James A Tulsky, ACP-PEACE Investigators, et al. 2022. Natural language processing to identify advance care planning documentation in a multisite pragmatic clinical trial.Journal of pain and symptom management63,...

    2022

  30. [30]

    Dingdong Liu, Yujing Zhang, Bolin Zhao, Shuai Ma, Chuhan Shi, and Xiaojuan Ma. 2025. Scaffolded Turns and Logical Conversations: Designing Humanized LLM-Powered Conversational Agents for Hospital Admission Interviews. In Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems (CHI ’25). Association for Computing Machinery, New York, N...

    work page doi:10.1145/3706598.3714196 2025

  31. [31]

    Lucas, Albert Rizzo, Jonathan Gratch, Stefan Scherer, Giota Stratou, Jill Boberg, and Louis-Philippe Morency

    Gale M. Lucas, Albert Rizzo, Jonathan Gratch, Stefan Scherer, Giota Stratou, Jill Boberg, and Louis-Philippe Morency. 2017. Reporting Mental Health Symptoms: Breaking Down Barriers to Care with Virtual Human Interviewers.Frontiers in Robotics and AI4 (Oct. 2017). doi:10.3389/frobt.2017.00051

    work page doi:10.3389/frobt.2017.00051 2017

  32. [32]

    Mack, Angel Cronin, Nancy L

    Jennifer W. Mack, Angel Cronin, Nancy L. Keating, Nathan Taback, Haiden A. Huskamp, Jennifer L. Malin, Craig C. Earle, and Jane C. Weeks. 2012. Associations between end-of-life discussion characteristics and care received near death: a prospective cohort study.Journal of Clinical Oncology: Official Journal of the American Society of Clinical Oncology30, 3...

    2012

  33. [33]

    Amama Mahmood, Junxiang Wang, Bingsheng Yao, Dakuo Wang, and Chien- Ming Huang. 2025. User Interaction Patterns and Breakdowns in Conversing with LLM-Powered Voice Assistants.International Journal of Human-Computer Studies195 (Jan. 2025), 103406. doi:10.1016/j.ijhcs.2024.103406

    work page doi:10.1016/j.ijhcs.2024.103406 2025

  34. [34]

    Ernest I Mandel, Francine L Maloney, Nathan J Pertsch, Jonathon D Gass, Justin J Sanders, Rachelle E Bernacki, and Susan D Block. 2023. A pilot study of the serious illness conversation guide in a dialysis clinic.American Journal of Hospice and Palliative Medicine®40, 10 (2023), 1106–1113

    2023

  35. [35]

    Christopher R Manz, Ravi B Parikh, Dylan S Small, Chalanda N Evans, Corey Chivers, Susan H Regli, C William Hanson, Justin E Bekelman, Charles AL Rareshide, Nina O’Connor, et al. 2020. Effect of integrating machine learning mortality estimates with behavioral nudges to clinicians on serious illness con- versations among patients with cancer: a stepped-wed...

    2020

  36. [36]

    Madison Milne-Ives, Caroline de Cock, Ernest Lim, Melissa Harper Shehadeh, Nick de Pennington, Guy Mole, Eduardo Normando, and Edward Meinert. 2020. The Effectiveness of Artificial Intelligence Conversational Agents in Health Care: Systematic Review.Journal of Medical Internet Research22, 10 (Oct. 2020), e20346. doi:10.2196/20346

    work page doi:10.2196/20346 2020

  37. [37]

    Julia Murray, Zacharia Grami, Katherine Benson, Christopher Hritz, Saman- tha Lawson, Corita Reilley Grudzen, Allison Cuthel, and Lauren Talanda-Fath Southerland. 2025. Effect of a multi-component palliative care intervention on goals of care discussions for critical patients in the emergency department.Inter- nal and Emergency Medicine(2025). doi:10.1007...

    work page doi:10.1007/s11739-025-04048-5 2025

  38. [38]

    Block, Dorene M

    Kei Ouchi, Susan D. Block, Dorene M. Rentz, Donna L. Berry, Hannah Oelschlager, Youkie Shiozawa, Sarah Rossmassler, Amanda L. Berger, Mohammad A. Has- dianda, Wei Wang, Edward Boyer, Rebecca L. Sudore, James A. Tulsky, and Mara A. Schonberg. 2025. Serious Illness Conversations in the Emergency Department for Older Adults With Advanced Illnesses: A Randomi...

    work page doi:10.1001/jamanetworkopen.2025.16582 2025

  39. [39]

    Revette, Mohammad Adrian Hasdianda, Lauren Fellion, Audrey Reust, Lynda H

    Kei Ouchi, Naomi George, Anna C. Revette, Mohammad Adrian Hasdianda, Lauren Fellion, Audrey Reust, Lynda H. Powell, Rebecca Sudore, Jeremiah D. Schuur, Mara A. Schonberg, Edward Bernstein, James A. Tulsky, and Susan D. Block. 2019. Empower Seriously Ill Older Adults to Formulate Their Goals for Medical Care in the Emergency Department.Journal of Palliativ...

    work page doi:10.1089/jpm.2018.0360 2019

  40. [40]

    Kei Ouchi, Naomi George, Jeremiah D Schuur, Emily L Aaronson, Charlotta Lindvall, Edward Bernstein, Rebecca L Sudore, Mara A Schonberg, Susan D Block, and James A Tulsky. 2019. Goals-of-care conversations for older adults with serious illness in the emergency department: challenges and opportunities. Annals of emergency medicine74, 2 (2019), 276–284

    2019

  41. [41]

    Kei Ouchi, Vinicius Knabben, Laura Rivera-Reyes, Niharika Ganta, Laura P Gelf- man, Rebecca Sudore, and Ula Hwang. 2017. Preparing older adults with serious illness to formulate their goals for medical care in the emergency department. Journal of palliative medicine20, 4 (2017), 404–408

    2017

  42. [42]

    Pajka, Mohammad Adrian Hasdianda, Naomi George, Rebecca Sudore, Mara A

    Sarah E. Pajka, Mohammad Adrian Hasdianda, Naomi George, Rebecca Sudore, Mara A. Schonberg, Edward Bernstein, James A. Tulsky, Susan D. Block, and Kei Ouchi. 2021. Feasibility of a Brief Intervention to Facilitate Advance Care Planning Conversations for Patients with Life-Limiting Illness in the Emergency Department.Journal of Palliative Medicine24, 1 (Ja...

    work page arXiv 2021

  43. [43]

    Joanna Paladino, Justin J Sanders, Erik K Fromme, Susan Block, Juliet C Jacobsen, Vicki A Jackson, Christine S Ritchie, and Suzanne Mitchell. 2023. Improving serious illness communication: a qualitative study of clinical culture.BMC palliative care22, 1 (2023), 104

    2023

  44. [44]

    te Pas, Werner G

    Mariska E. te Pas, Werner G. M. M. Rutten, R. Arthur Bouwman, and Marc P. Buise

  45. [45]

    2020), e21982

    User Experience of a Chatbot Questionnaire Versus a Regular Computer Questionnaire: Prospective Comparative Study.JMIR Medical Informatics8, 12 (Dec. 2020), e21982. doi:10.2196/21982

    work page doi:10.2196/21982 2020

  46. [46]

    Antoine Piau, Rachel Crissey, Delphine Brechemier, Laurent Balardy, and Fati Nourhashemi. 2019. A smartphone Chatbot application to optimize monitoring of older patients with cancer.International Journal of Medical Informatics128 (Aug. 2019), 18–23. doi:10.1016/j.ijmedinf.2019.05.013

    work page doi:10.1016/j.ijmedinf.2019.05.013 2019

  47. [47]

    Thidathit Prachanukool, Susan D Block, Donna Berry, Rachel S Lee, Sarah Ross- massler, Mohammad A Hasdianda, Wei Wang, Rebecca Sudore, Mara A Schonberg, James A Tulsky, et al. 2022. Emergency department-based, nurse-initiated, serious illness conversation intervention for older adults: a protocol for a randomized controlled trial.Trials23, 1 (2022), 866

    2022

  48. [48]

    Accessibility Came by Accident

    Alisha Pradhan, Kanika Mehta, and Leah Findlater. 2018. "Accessibility Came by Accident": Use of Voice-Controlled Intelligent Personal Assistants by People with Disabilities. InProceedings of the 2018 CHI Conference on Human Factors in Computing Systems (CHI ’18). Association for Computing Machinery, New York, NY, USA, 1–13. doi:10.1145/3173574.3174033

    work page doi:10.1145/3173574.3174033 2018

  49. [49]

    Reznek, Virginia Mangolds, Kevin A

    Martin A. Reznek, Virginia Mangolds, Kevin A. Kotkowski, Kian D. Samadian, James Joseph, and Celine Larkin. 2023. Accuracy of physician self-estimation of time spent during patient care in the emergency department.JACEP Open4, 2 (April 2023). doi:10.1002/emp2.12923

    work page doi:10.1002/emp2.12923 2023

  50. [50]

    Rubin, Michelle Chung, Mohammad Adrian Hasdianda, Tamryn F

    Batsheva R. Rubin, Michelle Chung, Mohammad Adrian Hasdianda, Tamryn F. Gray, Emily L. Aaronson, Andrew Dundin, Natasha A. Egorova, Anna C. Revette, Donna Berry, and Kei Ouchi. 2022. Refinement of an Emergency Department- Based, Advance Care Planning Intervention for Nurses.Journal of Palliative AI-Mediated Serious Illness Conversations in the ED Conferen...

    work page doi:10.1089/jpm.2021.0398 2022

  51. [51]

    Ma, Abdessalem Boukil, Ekanath Rangan, Vishwesh Patel, Ivan Lopez, and Jonathan Chen

    Thomas Savage, Stephen P. Ma, Abdessalem Boukil, Ekanath Rangan, Vishwesh Patel, Ivan Lopez, and Jonathan Chen. 2025. Fine-Tuning Methods for Large Language Models in Clinical Medicine by Supervised Fine-Tuning and Direct Preference Optimization: Comparative Evaluation.Journal of Medical Internet Research27, 1 (Sept. 2025), e76048. doi:10.2196/76048

    work page doi:10.2196/76048 2025

  52. [52]

    Lennart Seitz. 2024. Artificial empathy in healthcare chatbots: Does it feel authentic?Computers in Human Behavior: Artificial Humans2, 1 (2024), 100067

    2024

  53. [53]

    Danielle M Shilling, Christopher R Manz, Jacob J Strand, and Manali I Patel

  54. [54]

    Let Us Have the conversation: serious illness communication in oncology: definitions, barriers, and successful approaches.American Society of Clinical Oncology Educational Book44, 3 (2024), e431352

    2024

  55. [55]

    Maria J Silveira, Scott YH Kim, and Kenneth M Langa. 2010. Advance directives and outcomes of surrogate decision making before death.New England Journal of Medicine362, 13 (2010), 1211–1218

    2010

  56. [56]

    Alexander K Smith, Ellen McCarthy, Ellen Weber, Irena Stijacic Cenzer, John Boscardin, Jonathan Fisher, and Kenneth Covinsky. 2012. Half of older Americans seen in emergency department in last month of life; most admitted to hospital, and many die there.Health Affairs31, 6 (2012), 1277–1285

    2012

  57. [57]

    Weiser and John Seely Brown

    Mark D. Weiser and John Seely Brown. 1996. THE COMING AGE OF CALM TECHNOLOGY[1]. https://api.semanticscholar.org/CorpusID:31152205

    1996

  58. [58]

    Alexi A Wright, Baohui Zhang, Alaka Ray, Jennifer W Mack, Elizabeth Trice, Tracy Balboni, Susan L Mitchell, Vicki A Jackson, Susan D Block, Paul K Ma- ciejewski, et al. 2008. Associations between end-of-life discussions, patient mental health, medical care near death, and caregiver bereavement adjustment.Jama 300, 14 (2008), 1665–1673

    2008

  59. [59]

    Ziqi Yang, Xuhai Xu, Bingsheng Yao, Ethan Rogers, Shao Zhang, Stephen Intille, Nawar Shara, Guodong Gordon Gao, and Dakuo Wang. 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 Technologies8, 2 (2024), 1–35

    2024

  60. [60]

    Wright, Haiden A

    Baohui Zhang, Alexi A. Wright, Haiden A. Huskamp, Matthew E. Nilsson, Matthew L. Maciejewski, Craig C. Earle, Susan D. Block, Paul K. Maciejewski, and Holly G. Prigerson. 2009. Health care costs in the last week of life: associations with end-of-life conversations.Archives of Internal Medicine169, 5 (March 2009), 480–488. doi:10.1001/archinternmed.2008.587

    work page doi:10.1001/archinternmed.2008.587 2009

  61. [61]

    Shao Zhang, Jianing Yu, Xuhai Xu, Changchang Yin, Yuxuan Lu, Bingsheng Yao, Melanie Tory, Lace M Padilla, Jeffrey Caterino, Ping Zhang, et al. 2024. Rethinking human-AI collaboration in complex medical decision making: a case study in sepsis diagnosis. InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems. 1–18

    2024

  62. [62]

    Menglin Zhao, Zhuorui Yong, Ruijia Guan, Kai-Wei Chang, Adrian Haimovich, Kei Ouchi, Timothy Bickmore, Bingsheng Yao, Dakuo Wang, and Smit Desai

  63. [63]

    doi:10.48550/ arXiv.2506.00241 arXiv:2506.00241 [cs] version: 1

    Designing AI Tools for Clinical Care Teams to Support Serious Illness Conversations with Older Adults in the Emergency Department. doi:10.48550/ arXiv.2506.00241 arXiv:2506.00241 [cs] version: 1

    work page arXiv