Translate this page into:
Evaluating Chatbots as Nursing Assistants in Palliative Care: A Narrative Review
, Masoud Etedali1, Mehdi Safarabadi2, Hamed Parnikh3, Hooman Mohammad Talebi1,
*Corresponding author: Hooman Mohammad Talebi, Department of Nursing, Khomein University of Medical Sciences, Khomein, Iran. nursehooman@yahoo.com
-
Received: ,
Accepted: ,
How to cite this article: Jafari Dehnayebi M, Etedali M, Safarabadi M, Parnikh H, Mohammad Talebi H. Evaluating Chatbots as Nursing Assistants in Palliative Care: A Narrative Review. Indian J Palliat Care. 2026;32:129-36. doi: 10.25259/IJPC_144_2025
Abstract
Artificial intelligence (AI) powered chatbots are emerging tools to support healthcare providers, especially in palliative care, by delivering information, emotional support and practical assistance to patients and caregivers. This study aimed to perform a Strengths, Weaknesses, Opportunities and Threats (SWOT) analysis of chatbots acting as nursing assistants in palliative care, to elucidate their potential benefits, challenges and future directions. We conducted a narrative review of articles published between January 2020 and March 2025. Two reviewers independently searched relevant databases and screened studies according to predefined inclusion criteria. Extracted data were synthesised using the SWOT framework, and findings were reported in a narrative format. AI-powered chatbots in palliative care offer strengths such as enhanced patient support, symptom monitoring and mental health check-ins, but suffer from weaknesses such as inaccurate information and poor integration with health records. Opportunities include educational potential and personalised care, while threats include privacy concerns, regulatory gaps and resistance from healthcare professionals. Over-reliance on technology could also undermine empathetic, human-centred care. This review shows that AI-powered chatbots in palliative care can improve communication and personalised monitoring. However, challenges such as accuracy, data security and funding need to be addressed. Future studies should focus on long-term outcomes and cost-benefit analyses.
Keywords
Artificial intelligence
Nursing
Palliative care
Virtual assistants
INTRODUCTION
Recent significant evolutions of artificial intelligence (AI) have had a considerable impact across numerous domains.[1]Among these, the healthcare sector is one area where AI is rapidly evolving and has capitalised on these developments. Specifically, AI-based technologies, by offering advanced and innovative tools, have greatly enhanced the quality of healthcare services. They have also streamlined treatment processes by assisting physicians and nurses with accurate and timely disease diagnosis and patient care.[2] AI technologies are transforming healthcare by providing unmatched opportunities to improve patient care, enhance clinical processes and promote research in medical fields.[3]
One of the most significant and practical AI tools in healthcare is chatbots, which have attracted considerable attention in recent years. These tools, by offering AI-driven services, are viewed as a promising platform to support physicians and nurses in delivering patient care.[4,5] Chatbots are increasingly utilised in the healthcare industry due to their efficiency in providing immediate, accurate responses and their ease of access.[6,7] The application of chatbots in medical sciences is varied and extensive, encompassing patient education, nurse training and the management of care for chronic patients post-discharge or recovery after surgery.[4,5,8]
In this regard, one significant area where chatbots have found substantial application is in palliative care.[9] Palliative care encompasses a variety of services aimed at alleviating pain and suffering in patients with chronic or advanced diseases, particularly those nearing the end of their lives. This approach to care integrates physical symptom management with comprehensive psychological, social and spiritual support for patients and their families.[7,10] Chatbots have the potential to be effective in the realm of palliative care. AI-powered chatbots can effectively educate patients and raise their awareness of palliative care.[9] In this context, chatbots can play a crucial role, from providing educational information about disease status and care to offering psychological support and managing emotional crises faced by patients and their families.[11] Furthermore, one connection between AI and palliative care lies in the ability of chatbots to assist nurses in delivering personalised and effective care, thereby reducing their workload.[9,11]
While the use of chatbots in palliative care is rapidly expanding, many questions remain regarding their effectiveness, acceptance, technical challenges and ethical considerations. For instance, questions arise about whether chatbots can effectively serve as nursing assistants. Can this technology enhance the experiences of patients and nurses, or does it introduce new challenges? Moreover, how can this technology be leveraged to improve the quality of care while upholding ethical and professional standards?
The goal of this study is to conduct a comprehensive review based on a Strengths, Weaknesses, Opportunities and Threats (SWOT) analysis to evaluate chatbots as nursing assistants in palliative care. This study seeks to examine and analyse the strengths, weaknesses, opportunities and threats associated with the use of chatbots in this field. By exploring these aspects, we can gain a more comprehensive insight into the efficacy of this technology in palliative care and position it as a practical and effective tool within healthcare systems. In addition, the findings of this study can serve as a guide for researchers, policymakers and clinical professionals in optimising the application of chatbots in this area.
MATERIALS AND METHODS
A narrative review was conducted to analyse and synthesise studies concerning the utilisation of chatbots as nursing assistants in palliative care settings. This narrative review explored the use of chatbots in palliative care by applying a SWOT analysis. The methodology was enhanced by adapting best practices from prior research on chatbot implementation in healthcare, including a systematic search strategy, a structured SWOT framework and data extraction methods customised for healthcare settings. These techniques were further refined to specifically address the distinct challenges of palliative care, allowing for a more thorough evaluation of chatbot applications.
Eligibility criteria
Inclusion was limited to studies that investigated the implementation or evaluation of chatbots or conversational agents used by nursing assistants within palliative care settings. Inclusion was limited to peer-reviewed empirical studies published in English between January 2020 and March 2025 to ensure relevance to current practices. Excluded studies were those that: (1) Did not involve nursing assistants or palliative care settings. (2) We were not peer-reviewed (e.g., opinion pieces, commentaries, or technical reports). (3) Lacked empirical data (e.g., conference abstracts). (4) Focused solely on other professional groups, such as registered nurses.
Search strategy
A comprehensive search of literature was performed between January 2020 and March 2025 across four major electronic databases: PubMed, Scopus, CINAHL and Google Scholar. The search strategies were employed in the databases, as shown in Table 1. Search terms included a combination of keywords and Medical Subject Headings related to ‘nursing assistants’, ‘chatbots’ and ‘palliative care’. Boolean operators (AND/OR) were used to enhance sensitivity.
| Database | Search strategy |
|---|---|
| PubMed | (‘Nursing assistants’ [MeSH Terms] OR ‘nursing assistant’ [Title/Abstract] OR ‘nurse aide’ [Title/Abstract]) AND (‘chatbots’ [MeSH Terms] OR ‘conversational agents’ [Title/Abstract] OR ‘virtual assistants’ [Title/Abstract] OR ‘artificial intelligence’ [MeSH Terms]) AND (‘palliative care’ [MeSH Terms] OR ‘end-of-life care’ [Title/Abstract] OR ‘hospice care’ [MeSH Terms]) |
| CINAHL | (MH ‘Nursing Assistants’ OR TI ‘nursing assistant’ OR TI ‘nurse aide’) AND (MH ‘Chatbots’ OR TI ‘conversational agent’ OR TI ‘virtual assistant’ OR MH ‘Artificial Intelligence’) AND (MH ‘Palliative Care’ OR TI ‘end-of-life care’ OR MH ‘Hospice Care’) |
| Scopus | TITLE-ABS-KEY ([‘nursing assistant’ OR ‘nurse aide’] AND [‘chatbot’ OR ‘conversational agent’ OR ‘virtual assistant’ OR ‘artificial intelligence’] AND [‘palliative care’ OR ‘end-of-life care’ OR ‘hospice care’]) |
| Google Scholar | (‘Chatbot’ OR ‘conversational agent’) AND (‘nursing assistant’ OR ‘nurse assistant’ OR ‘nursing support’) AND (‘palliative care’ OR ‘end-of-life care’) AND (‘evaluation’ OR ‘assessment’ OR ‘usability’ OR ‘acceptability’) |
MeSH: Medical Subject Headings
Study selection
Two independent reviewers (M. JD and H. MT) screened all titles and abstracts based on predefined inclusion and exclusion criteria. A preferred reporting items for systematic reviews and meta-analyses (PRISMA) flowchart was used to show the selection process [Figure 1]. Full texts of potentially eligible studies (n = 17) were retrieved for in-depth assessment. Discrepancies between reviewers were discussed to reach agreement, and a third reviewer (M.S.) was engaged when needed.
Data extraction
Data were extracted using a standardised form capturing the following: Study title, authors, year, study objectives, methodology, population, setting, chatbot application features, outcomes measured and key findings. Extracted data were reviewed independently by two reviewers to ensure consistency and completeness.
Data synthesis
A thematic narrative synthesis was conducted. Extracted findings were grouped into recurring categories related to chatbot functionality, user outcomes, implementation challenges and ethical considerations. Themes were refined through iterative comparison and discussion among reviewers. Patterns across studies were identified to highlight gaps, emerging trends and future research directions.
RESULTS
Initial searches yielded 621 results. Seventeen studies were finally selected and used for a narrative review. Table 2 demonstrates the details of the selected studies.
| Study title | Authors | Year | Summary |
|---|---|---|---|
| Chatbot Performance in Defining and Differentiating Palliative Care, Supportive Care, Hospice Care | Kim et al.[14] | 2024 | This study assesses how ChatGPT, Bard and Bing define palliative, supportive and hospice care, finding inconsistent accuracy that limits their reliability for patient education. |
| Conversational Agents in Palliative Care: Potential Benefits, Risks and Next Steps | Schenker et al.[38] | 2024 | The article explores the growing role of chatbots in palliative care. It highlights their use for providing basic information, facilitating initial conversations and referring patients for specialised care. Potential benefits include increased access and efficiency, while risks include misinformation and loss of human touch. |
| AI in Palliative Care: A Systematic Review | Ahmad et al.[20] | 2021 | This systematic review explores the use of AI in palliative care, with an emphasis on machine learning and natural language processing techniques. It identifies key uses such as survival prediction, setting care goals and analysing conversations to guide clinical communication. |
| Exploring Applications of AI in Critical Care Nursing: A Systematic Review | Porcellato et al.[25] | 2025 | The study reviews how AI technologies are being integrated into critical care nursing. While AI demonstrates promising potential in decision-making and research, the wide variability in methodologies across studies prevents strong conclusions. |
| A Systematic Review of AI-Powered Chatbot Interventions for Managing Chronic Illness | Kurniawan et al.[12] | 2024 | The review investigates the impact of AI-powered chatbots in chronic illness management. Results show enhanced patient education, improved health behaviour, increased satisfaction and effectiveness in delivering cognitive-behavioural therapy. |
| Exploring the Role of Chatbots in Enhancing Patient Communication and Support in Nursing Care | Alhejaili et al.[13] | 2024 | This article highlights chatbots’ role in patient support, noting benefits such as better interaction and lower costs, but also challenges with empathy and privacy. It suggests EHR and voice integration as the next steps. |
| An Overview of the Role of AI in Palliative Care: A Quasi-Systematic Review | Bork-Zalewska et al.[15] | 2025 | AI’s role in palliative care is explored, with machine learning models helping to predict patient survival and support clinical decision-making. However, the technology still lacks the capacity for empathetic communication and often provides inconsistent information. |
| The Integration of AI into Critical Care Nursing | Bourgault[16] | 2025 | The article outlines guidelines for ethical AI use in critical care nursing, including transparency, independent peer review and protection of patient data. It emphasises the importance of regulating AI applications to ensure patient safety and legal compliance. |
| How Can AI Be Used in Palliative Care? | Chua et al.[17] | 2022 | Explores AI tools, including chatbots, in palliative care to improve patient management and communication. Though promising, the article stresses the need for validation of AI tools in clinical environments. |
| Chatbots in Palliative Care: A New Frontier in Holistic Care? | Singh et al.[19] | 2024 | The article explores chatbots in palliative care, noting their role in diagnosis, care planning and prognosis, while emphasising the need for clinical oversight. |
| Using AI to Analyse and Teach Communication in Healthcare | Butow et al.[39] | 2020 | This article discusses the evidence on the reliability and validity of AI coding, its use in communication training and evaluation, and the challenges and future prospects in this area. |
| Exploring the Efficacy of AI in Delivering Hospice Information | Ross et al.[21] | 2023 | Evaluates how ChatGPT and Bard respond to hospice-related questions. Bard generally provided more cautious and visually aided answers, while ChatGPT sometimes lacked sources. The study suggests chatbots can enhance public understanding of hospice care. |
| Debunking Palliative Care Myths: Assessing the Performance of AI Chatbots | Gondode et al.[9] | 2024 | This study tested ChatGPT and Google Gemini in identifying and correcting palliative care myths. Gemini showed perfect accuracy; ChatGPT achieved a 93.3% true positive rate. Both tools show promise in improving patient education and decision-making. |
| AI in Healthcare Delivery: Prospects and Pitfalls | Olawade et al.[23] | 2024 | The review highlights the advantages of AI in healthcare enhanced diagnostics, personalisation and task automation while also noting challenges such as algorithmic bias, data quality and regulatory gaps. Recommendations include ethical frameworks and safety protocols. |
| Delirium Management and Prevention in Hospitals: Evaluation of Clinical Needs and Design of a Conceptual Framework with a Conversational Agent | Alghamdi et al.[22] | 2022 | This study examined challenges in delirium care for hospitalised adults over 65. Using a mixed-methods approach, it identified practice gaps and informed the design of an automated delirium assessment and management system, a conceptual framework with a conversational agent to support delirium management. |
| Online Learning in Palliative Care Education of Undergraduate Medical Students: A Realist Synthesis | Martucci et al.[18] | 2023 | This realist synthesis examined internet-based palliative care education for medical students, identifying key factors to guide effective design and improve learning outcomes. |
| Exploring the Use of Generative AI in Systematic Searching: A Comparative Case Study of a Human Librarian, ChatGPT-4 and ChatGPT-4 Turbo | Chen and Feng[24] | 2025 | This study compared ChatGPT-4 and Turbo with a human librarian in literature searching, showing AI can enhance but not replace expert input in systematic reviews. |
AI: Artificial intelligence
SWOT analysis of chatbot integration
Based on the 17 selected studies, a SWOT analysis identified the following:
Strengths
AI-powered chatbots have demonstrably enhanced patient support and engagement in palliative care. By enabling real-time symptom monitoring, medication reminders and post-discharge check-ins, these tools alleviate nursing workload and boost patient satisfaction.[12] Beyond logistical tasks, conversational agents can deliver brief cognitive-behavioural therapy modules and mental-health check-ins critical for palliative patients at risk of anxiety and depression.[12]Moreover, their non-judgmental interface provides a gentle entry point for sensitive discussions around goals of care and advance directives.[13]
Weaknesses
Despite these advantages, chatbots often generate incomplete or inaccurate information, limiting their reliability as standalone educational or clinical resources.[14,15] Integration with electronic health record systems remains piecemeal, preventing seamless incorporation into existing nursing workflows.[16] Equally important, AI outputs require continuous human validation to safeguard clinical accuracy and preserve the empathetic nuance crucial in palliative nursing.[13,17]
Opportunities
The educational potential of chatbots is vast: they can reinforce palliative care concepts for patients, families and trainees through interactive, on-demand learning modules.[14,18] Advances in natural language processing and machine learning promise ever-more personalised risk stratification and care-planning suggestions, tailoring support to individual patient profiles.[19,20] Frameworks such as the automated delirium assessment and management system illustrate how specialised conversational agents can be adapted to other high-need clinical scenarios, extending chatbot utility across the care continuum Alghamdi et al.[21,22]
Threats
The deployment of chatbots in palliative settings raises significant privacy and consent concerns: handling sensitive health data demands robust encryption, transparent optin mechanisms and clear accountability protocols (Olwade et al. and Bourgault et al.).[16,23] In the absence of specific regulatory frameworks for AI in healthcare, legal ambiguity may delay implementation or expose institutions to liability. Resistance from healthcare professionals rooted in digital-literacy gaps and fears of role displacement can also undermine adoption unless addressed through targeted training and change-management strategies (Porcellato et al.[24,25] Finally, over-reliance on technology risks eroding the human empathy and clinical judgment that lies at the heart of high-quality palliative nursing.[13]
DISCUSSION
The integration of AI-powered chatbots into palliative care has attracted considerable attention for their potential to enhance patient engagement, alleviate nursing workloads and streamline communication. However, while promising, these technologies face notable challenges in delivering accurate, empathetic and personalised care. This discussion draws comparisons with related studies in mental health, oncology, mHealth and end-of-life care to explore the broader implications and future directions for chatbot applications in palliative care.
Mental health chatbots: Randomized Controlled Trial (RCT)-driven efficacy
Analyses indicated that, utilising Chatbots in palliative care may alleviate psychological symptoms. Accordingly, Fitzpatrick et al. conducted a 2-week RCT comparing Woebot to an information-only e-book in college students with self-reported anxiety or depression, finding a significant reduction in patient health questionnaire-9 (PHQ-9) scores (−5.5 vs. −2.1; p < 0.05) and high engagement (mean 12.1 interactions).[26] A follow-up RCT in postpartum women (n = 192) showed greater mood improvements among those with elevated baseline depression when using Woebot versus treatment-as-usual, underscoring the value of embedding manualised cognitive behavioural therapy (CBT) modules within a chatbot interface.[27] These studies illustrate that palliative-care chatbots could adopt fully automated, evidence-based psychotherapeutic frameworks complete with structured dialogue sessions and mood tracking to achieve measurable symptom relief and engagement.
Relational agents in end-of-life care preparation
Utami, Bickmore, Nikolopoulou and Paasche-Orlow designed a virtual palliative-care coach to discuss spiritual needs, symptom management and advance directives with older adults in their last year of life.[28] Their experiment reported significant reductions in both state and death anxiety, alongside increased intent to complete legal end-of-life documents, demonstrating that agent persona, voice and pacing can foster emotional trust and preparatory behaviours, which aligns with the findings of our study. Moreover, palliative-care chatbots should therefore integrate relational-agent techniques such as empathic nonverbal cues and adaptive conversational pacing to bridge the ‘affective gap’ seen in purely text-based models.
Oncology chatbots: Transparency and clinical alignment
A 2021 PubMed Centra review of oncology chatbot applications highlights their use in diagnosis support, treatment monitoring and patient education, but emphasises limitations in algorithmic transparency, data privacy and user trust.[29] More recently, Lawson and Hristidis (2025) analysed AI chatbots in cancer education, cautioning that opaque reasoning processes and unverified content can mislead patients and recommending clear source citations and alignment with evidence-based protocols.[30] For palliative-care chatbots, adopting oncology best practices such as confidence indicators, reference linking and iterative clinician review can mitigate misinformation risks and bolster patient confidence.
Broader health-care chatbot landscape
A rapid review of healthcare chatbots (2017–2023) categorised roles into patient support, care management, education and administrative assistance, while noting variability in evaluation rigour and inclusivity.[31] Laranjo et al.’s 2018 systematic review found only one RCT across 14 agents, highlighting a general paucity of robust efficacy and safety assessments.[32]
Subsequent reviews have called for improved personalisation, adapting dialogue content, tone and pacing to individual needs, yet note that few systems implement explicit behaviour-change techniques or demographic tailoring.[33]A 2020 Journal of Medical Internet Research (JMIR) review reported mixed evidence on usability and effectiveness across 31 conversational agents, stressing the need for standardised outcome measures and health-economic evaluations.[34]Moreover, a 2019 scoping review identified critical gaps in acceptability, safety and longitudinal impact, underscoring an urgent need for user-centred co-design and regulatory frameworks.[35]
Implications for palliative-care chatbots
Palliative-care chatbots can enhance patient support by integrating evidence-based interventions, such as CBT modules, with mood monitoring and feedback.[36] Relational design, including voice and avatars, is crucial for building trust and empathy, as seen in end-of-life care models. To ensure transparency and safety, chatbots should implement confidence scores, source citations and clinician oversight, following best practices from oncology chatbots. Standardising evaluations with common metrics, such as symptom scores and quality of life, will enable cross-study comparisons.[37-39] Co-designing with patients, caregivers, and healthcare professionals ensures chatbots meet real-world needs. By incorporating these principles, palliative-care chatbots can provide reliable, empathetic support while complementing human care.[9]
Limitations
Despite the rigour applied in this narrative integrative review, several limitations must be acknowledged. First, restricting the inclusion criteria to English language, peer-reviewed studies published between January 2020 and March 2025 may have led to language and publication bias, excluding relevant research published in other languages or presented in grey literature formats such as dissertations, white papers or preprints. Second, the variability in study designs, chatbot technologies evaluated and outcome measures across the included studies introduced significant heterogeneity, which limited the ability to perform direct comparisons or conduct a meta-analysis.
Third, the reliance on four major databases, PubMed, Scopus, CINAHL and Google Scholar, while comprehensive, may have omitted studies indexed in specialised databases (e.g. Institute of Electrical and Electronics Engineers Xplore and PsycINFO) where AI or digital health research is also frequently reported. Fourth, given the emerging nature of chatbot use in palliative care, many included studies were exploratory or descriptive in nature, with limited longitudinal data, small sample sizes and lack of randomised controlled trials, which constrains the generalizability of findings. Fifth, the evolving capabilities of AI and rapid technological advancements imply that some findings could become outdated quickly, limiting the long-term applicability of this review. Finally, although steps were taken to enhance methodological rigour, such as independent screening, dual data extraction, and consultation with a third reviewer, subjectivity inherent in thematic narrative synthesis cannot be entirely eliminated, posing a potential risk of interpretative bias.
CONCLUSION
This integrative review demonstrates that deploying AI-powered chatbots as nursing assistants in palliative care can substantially enhance patient–provider communication, streamline information delivery and enable continuous, personalised monitoring. To realise these benefits, stakeholders must address critical challenges, improving chatbot accuracy, strengthening data security and securing sustainable funding for implementation. Future studies are encouraged to explore the long-term evaluations of clinical outcomes, cost-benefit analyses and strategies to foster user acceptance and ethical governance frameworks.
Acknowledgements:
The authors sincerely thank all individuals who contributed to the successful completion of this study, especially colleagues and peer reviewers whose valuable insights helped improve the quality of this manuscript.
Ethical approval:
The Institutional Review Board approval is not required.
Declaration of patient consent:
Patient’s consent was not required as there are no patients in this study.
Conflicts of interest:
There are no conflicts of interest.
Use of artificial intelligence (AI)-assisted technology for manuscript preparation:
The authors confirm that they have used artificial intelligence (AI)-assisted technology solely for language refinement and to improve the clarity of writing. No AI assistance was employed in the generation of scientific content, data analysis or interpretation.
Financial support and sponsorship: Nil.
References
- CHAT-GPT and artificial intelligence in medical endocrine system and interventions. Euras J Chem Med Petrol Res. 2024;3:197-209.
- [Google Scholar]
- The use of artificial intelligence to diagnose the disease. bio web of Conferences 2024
- [CrossRef] [Google Scholar]
- Ethical considerations in the use of artificial intelligence and machine learning in health care: a comprehensive review. Cureus. 2024;16:e62443.
- [Google Scholar]
- A nurse versus a chatbot-the effect of an empowerment program on chemotherapy-related side effects and the self-care behaviors of women living with breast cancer: a randomized controlled trial. BMC Nurs. 2023;22:102.
- [CrossRef] [PubMed] [Google Scholar]
- Chatbot-assisted care management. Prof Case Manag. 2022;27:19-25.
- [CrossRef] [PubMed] [Google Scholar]
- Effectiveness of designing a knowledge-based artificial intelligence chatbot system into a nursing training program: a quasi-experimental design. Nurse Educ Today. 2024;137:106159.
- [CrossRef] [PubMed] [Google Scholar]
- Assessment of readability, reliability, and quality of chatgpt®, bard®, gemini®, copilot®, perplexity® responses on palliative care. Medicine (Baltimore). 2024;103:e39305.
- [CrossRef] [PubMed] [Google Scholar]
- Nursing education in the age of artificial intelligence powered chatbots (AI-Chatbots): are we ready yet? Nurse Educ Today. 2023;129:105917.
- [CrossRef] [PubMed] [Google Scholar]
- Debunking palliative care myths: assessing the performance of artificial intelligence chatbots (ChatGPT vs. Google Gemini) Indian J Palliat Care. 2024;30:284-7.
- [CrossRef] [PubMed] [Google Scholar]
- The ethical dimensions of utilizing artificial intelligence in palliative care. Nurs Ethics. 2024;32:1285-96.
- [CrossRef] [PubMed] [Google Scholar]
- Incorporating artificial intelligence in palliative care: opportunities and challenges. Hosp Palliat Med Int J. 2024;7
- [CrossRef] [Google Scholar]
- A systematic review of artificial intelligence-powered (ai-powered) chatbot intervention for managing chronic illness. Ann Med. 2024;56:2302980.
- [CrossRef] [PubMed] [Google Scholar]
- Exploring the role of chatbots in enhancing patient communication and support in nursing care. J Int Crisis Risk Commun Res. 2024;7:2242.
- [Google Scholar]
- Chatbot performance in defining and differentiating palliative care, supportive care, hospice care. J Pain Symptom Manage. 2024;67:e381-91.
- [CrossRef] [PubMed] [Google Scholar]
- An overview of the role of artificial intelligence in palliative care: A quasi-systematic review. Palliat Med Pract. 2025;19:312-9.
- [CrossRef] [Google Scholar]
- The integration of artificial intelligence into critical care nursing. Crit Care Nurse. 2025;45:6-7.
- [CrossRef] [PubMed] [Google Scholar]
- Enhancing serious illness communication using artificial intelligence. NPJ Digit Med. 2022;5:14.
- [CrossRef] [PubMed] [Google Scholar]
- Online learning in palliative care education of undergraduate medical students: a realist synthesis. Palliat Care Soc Pract. 2023;17:26323524231218279.
- [CrossRef] [PubMed] [Google Scholar]
- Chatbots in palliative care-a new frontier in holistic care? 2024. bmj support palliat care blog. Available from: y. [Last accessed on 2025 Apr 20]
- [Google Scholar]
- 120 Artificial intelligence in palliative care: a systematic review to identify how novel data analytic technologies are used in the management of people with serious illness. BMJ. 2021;11:A52-2-A.
- [CrossRef] [PubMed] [Google Scholar]
- Exploring the efficacy of artificial intelligence in delivering hospice information. Innov Aging. 2023;7(Suppl 1):1037.
- [CrossRef] [Google Scholar]
- Delirium management and prevention in hospitals: evaluation of clinical needs and design of a conceptual framework with a conversational agent [doctoral dissertation] Cleveland, OH: Case Western Reserve University; 2022.
- [Google Scholar]
- Enhancing mental health with artificial intelligence: current trends and future prospects. J Med Surg Public Health. 2024;3:100099.
- [CrossRef] [Google Scholar]
- Exploring the use of generative artificial intelligence in systematic searching: a comparative case study of a human librarian, ChatGPT-4 and ChatGPT-4 Turbo. IFLA J. 2025;51:84-93.
- [CrossRef] [Google Scholar]
- Exploring applications of artificial intelligence in critical care nursing: a systematic review. Nurs Rep. 2025;15:55.
- [CrossRef] [PubMed] [Google Scholar]
- 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 Ment Health. 2017;4:e19.
- [CrossRef] [PubMed] [Google Scholar]
- Feasibility and impact of a mental health chatbot on postpartum mental health: a randomized controlled trial. AJOG Glob Rep. 2023;3:100165.
- [CrossRef] [PubMed] [Google Scholar]
- Talk about death: end of life planning with a virtual agent, intelligent virtual agents Cham: Springer International Publishing; 2017.
- [CrossRef] [Google Scholar]
- Chatbot for health care and oncology applications using artificial intelligence and machine learning: systematic review. JMIR Cancer. 2021;7:e27850.
- [CrossRef] [PubMed] [Google Scholar]
- Evidence-based analysis of ai chatbots in oncology patient education: implications for trust, perceived realness, and misinformation management. J Cancer Educ. 2025;40:482-9.
- [CrossRef] [PubMed] [Google Scholar]
- Roles, users, benefits, and limitations of chatbots in health care: rapid review. J Med Internet Res. 2024;26:e56930.
- [CrossRef] [PubMed] [Google Scholar]
- Conversational agents in healthcare: a systematic review. J Am Med Inform Assoc. 2018;25:1248-58.
- [CrossRef] [PubMed] [Google Scholar]
- The Personalization of conversational agents in health care: systematic review. J Med Internet Res. 2019;21:e15360.
- [CrossRef] [PubMed] [Google Scholar]
- The Effectiveness of artificial intelligence conversational agents in health care: systematic review. J Med Internet Res. 2020;22:e20346.
- [CrossRef] [PubMed] [Google Scholar]
- Conversational agents in health care: scoping review and conceptual analysis. J Med Internet Res. 2020;22:e17158.
- [CrossRef] [PubMed] [Google Scholar]
- An overview of chatbot-based mobile mental health apps: insights from app description and user reviews. JMIR Mhealth Uhealth. 2023;11:e44838.
- [CrossRef] [PubMed] [Google Scholar]
- Artificial intelligence for psychotherapy: a review of the current state and future directions. Indian J Psychol Med. 2024;47:314-25.
- [CrossRef] [PubMed] [Google Scholar]
- Conversational agents in palliative care: potential benefits, risks, and next steps. J Palliat Med. 2024;27:296-300.
- [CrossRef] [PubMed] [Google Scholar]
- Using artificial intelligence to analyse and teach communication in healthcare. The breast. 2020;. ;50:49-55.
- [CrossRef] [PubMed] [Google Scholar]