ArticleCroatian medical journal2025
Patients prefer human psychiatrists over chatbots: a cross-sectional study.
Article in Croatian medical journal, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 4 papers, 1 of them a synthesis that pooled it.
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
4 citing papers in PubMed, 1 synthesis or guideline pooled it.
- Application of artificial intelligence and psychosocial functioning in psychosis: a systematic review and meta-analysis.Frontiers in psychiatry · 2025Pooled it
- A Meta-Analysis of the Acceptance of Artificial Intelligence in Psychotherapy.Behavioral sciences (Basel, Switzerland) · 2026Review
- ChatGPT Clinical Use in Mental Health Care: Scoping Review of Empirical Evidence.JMIR mental health · 2025Article
- Patients prefer human psychiatrists over chatbots: a letter to the editor.Croatian medical journal · 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
6 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
aimTo rate the level of patients' satisfaction with responses on questions regarding mental health provided by human psychiatrists, pharmacists, and chatbot platforms.
methodsThis cross-sectional study enrolled 89 patients who were pharmacologically treated for their mental disorder in one institution in Croatia and one in Bosnia and Herzegovina during October 2023. They asked psychiatrists, pharmacists, ChatGPT, and one Croatian chatbot questions about their mental disorder and medications and rated the satisfaction with the responses.
resultsAlmost half of the patients had used ChatGPT before the study, and only 12.4% had used the Croatian platform. The patients were most satisfied with the information provided by psychiatrists (4.67 out of 5 about mental disorder and 4.51 about medications), followed by pharmacists (3.94 about medications), ChatGPT (3.66 about mental disorder and 3.45 about medications), and the Croatian platform (3.66 about mental disorder and 3.44 about medications). Almost half of the participants believed it was easier for them to put a question to a psychiatrist than to a chatbot, and only 10% claimed it was easier to ask ChatGPT.
conclusionPatients with mental health disorders were more satisfied with responses from their psychiatrists than from chatbots, and satisfaction with chatbots' knowledge on mental disorders and medications was still too low to justify their usage in these patients.
Indexed as
Identifiers
40047157PMC11947973What Socratic 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 Socratic graph.