ArticleWorld journal of urology2025
Patient insights into empathy, compassion and self-disclosure in medical large language models: results from the IPALLM III study.
Article in World journal of urology, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 3 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
3 citing papers in PubMed.
- [Large language models as a communication and organizational infrastructure in urology: evidence, limitations, and clinical responsibility].Urologie (Heidelberg, Germany) · 2026Review
- [Artificial intelligence in daily urological care: results of the AI barometer].Urologie (Heidelberg, Germany) · 2026Article
- Readability of Chatbot Responses in Prostate Cancer and Urological Care: Objective Metrics Versus Patient Perceptions.Current oncology (Toronto, Ont.) · 2025Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
11 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
purposeLarge language models (LLMs) offer promising applications in healthcare communication, including the provision of medical information and simulation of empathetic responses. However, the extent to which patients perceive such interactions as empathetic remains unclear. This study explores urological patients’ perceptions of empathy and compassion in interactions with an LLM-powered chatbot, as well as their willingness to disclose personal information.
methodsA total of 292 patients scheduled for urological counselling interacted with a GPT-4-powered chatbot to ask questions related to their medical condition. Participants subsequently completed a survey evaluating human-likeness, perceived empathy and compassion. Comparisons were drawn between chatbot and physician interactions regarding empathy, perceived prejudice and willingness to disclose sensitive information.
resultsOf 292 patients 63% (184/292) reported enjoying the chatbot interaction, with 77% (225/292) expressing satisfaction with the conversational flow, and 67% (196/292) describing its responses as human-like. Despite these positive impressions, 56% (164/292) disagreed that the chatbot made them feel cared for and 40% (117/292) found it lacked empathy. Additionally, 61% (178/292) disagreed that the chatbot was as empathetic as human physicians. Regarding self-disclosure, 77% (225/292) expressed a preference for sharing sensitive information with a human physician. Regression analysis revealed that patients with higher educational levels were more sceptical of the suitability of the chatbot for self-disclosure and empathy.
conclusionsWhile urological patients valued the accessibility and conversational flow of the LLM-powered chatbot, they overwhelmingly preferred urologists for empathetic communication and personal disclosures. These findings suggest that AI systems must either be refined for empathetic interactions or be used only in settings where empathy is less essential. TRIAL REGISTRATION NUMBER: DRKS-ID:00034906, registered on 16th of August 2024.
Indexed as
Identifiers
40810905What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.