Exploring a Large Language Model-Based Chatbot Use in Data Analysis: A Case Study of the Problems Related to the Do Not Attempt Resuscitation Order
Clinical Snapshot
PICO Framework
| P — Population | 100 healthcare professionals involved in do-not-attempt-resuscitation (DNAR) order decision-making |
| I — Intervention | Microsoft Copilot® large language model chatbot for qualitative data analysis |
| C — Comparator | Traditional researcher-conducted qualitative content analysis |
| O — Outcomes | Thematic categories identified, frequency of opinion categorization, interpretation differences between AI and human researchers |
Bottom Line
This case study explores the novel application of Microsoft Copilot® AI for analyzing healthcare professionals' perspectives on DNAR decision-making. While the research addresses an important clinical area and provides initial insights into AI-assisted qualitative analysis, the study has significant methodological limitations. The abstract lacks crucial details about data collection methods, ethical approvals, and analytical rigor. The comparison between AI and human researcher interpretations is intriguing, showing different emphases (AI on practical issues vs. researchers on communication), but without full methodological transparency, the reliability and validity of findings remain questionable. Healthcare professionals should view these preliminary findings with caution, particularly given the ethical sensitivity of DNAR decisions and the current limitations of AI in clinical contexts.
Key Findings
P Value: Not applicable for qualitative study
Effect Size: Frequency ranges 4-16 (Copilot®) and 2-16 (researchers)
Primary Outcome: 15 thematic categories identified describing DNAR-related issues
Nnt Or Sensitivity: AI particularly focused on patient/family roles and practical issues; researchers emphasized communication and documentation
Confidence Interval: Not applicable for qualitative study
Clinical Application
Limited by current AI technology capabilities and ethical considerations in clinical decision-making Relevant to Australian healthcare given similar DNAR protocols and end-of-life care frameworks, though specific regulatory considerations for AI integration would need evaluation Healthcare professionals involved in end-of-life decision-making and DNAR protocols
Abstract
The interpretative framework was used to explore how healthcare professionals (HCPs), artificial intelligence (AI), and researchers construct and negotiate meaning, trust, and authority in critical, highly ethical medical contexts. This case study aimed to explore and test the integration of the Microsoft Copilot® large language model (LLM) chatbot into ethically sensitive clinical decision-making (DM) to identify the problems HCPs face in do-not-attempt-resuscitation (DNAR) order-making and key areas for development. A sample of 100 HCPs' views was analyzed using qualitative content analysis. AI identified 15 thematic categories emerging from responses that described issues related to DNAR protocols and DM. The frequency of opinions in categories ranged from 4 to 16 (Copilot®) and from 2 to 16 (researchers). Based on a three-level frequency scale, AI's interpretations were especially evident in categories describing the roles of patients and families as well as practical issues related to DNAR orders. In contrast, the researchers focused on the importance of communication and documentation.
References
- 1.Saranto, K., Kivekäs, E., & Kuusisto, H. (2026). Exploring a Large Language Model-Based Chatbot Use in Data Analysis: A Case Study of the Problems Related to the Do Not Attempt Resuscitation Order. Studies in Health Technology and Informatics. https://doi.org/10.3233/SHTI260326
Related Research
Neurological sciences : official journal of the Italian Neurological Society and of the Italian Society of Clinical Neurophysiology
Suicide in neurodegenerative diseases: a systematic review.
30 July 2026
JMIR cancer
Multiturn Large Language Model-Based Conversational Agents for Patients With Cancer and Caregivers: Scoping Review
22 July 2026
Supportive care in cancer : official journal of the Multinational Association of Supportive Care in Cancer
A machine learning approach to profiling anxiety risk among cancer patients on treatment
19 July 2026
This content is for educational purposes for healthcare professionals only and does not constitute clinical advice. Clinical decisions should be based on individual patient assessment, current guidelines, and appropriate specialist consultation. Editorial Standards · Privacy Policy · Terms of Service