AI chatbots versus human healthcare professionals: a systematic review and meta-analysis of empathy in patient care
Abstract
Background: Empathy is widely recognised for improving patient outcomes ranging from reduced pain and anxiety to improved patient satisfaction, and its absence can cause harm. Meanwhile, use of artificial intelligence (AI)-based chatbots in healthcare is rapidly expanding, with one in five general practitioners (GPs) using generative AI to assist with tasks such as writing letters. Several studies suggest that these AI-based technologies are sometimes more empathic than human healthcare professionals (HCPs). However, the evidence in this area is mixed and has not been synthesised. Objective: To conduct a systematic review of studies that compare empathy of AI technologies with human HCP empathy. Methods: We searched multiple databases for studies comparing AI chatbots using large language models (e.g., GPT-3.5, GPT-4) with human HCPs on empathy measures. We assessed risk of bias with ROBINS-I and synthesised findings using random-effects meta-analysis where feasible, whilst avoiding double counting. Results: Our search identified 15 studies (2023-2024). Thirteen studies reported statistically significantly higher empathy ratings for AI, with only two studies situated in dermatology favouring human responses. Meta-analysis of 13 studies with data suitable for pooling, all utilising ChatGPT-3.5/4, showed a standardised mean difference (SMD) of 0.87 (95% CI, 0.54-1.20) favouring AI (p<0.00001). Conclusion: Our findings indicate that, in text-only scenarios, AI chatbots are…
How strong is the evidence?
Evidence Hub reads this as a meta-analysis, done in people. Its evidence level is 1 of 5 (Highest · pooled evidence). Pooled evidence from several studies sits at the top of the evidence pyramid.
Read the paper
Related studies
- Improving sleep quality leads to better mental health: A meta-analysis of randomised controlled trials
- Tocilizumab in patients with severe COVID-19: a retrospective cohort study
- A new aging measure captures morbidity and mortality risk across diverse subpopulations from NHANES IV: A cohort study
- Fruit, vegetable, and legume intake, and cardiovascular disease and deaths in 18 countries (PURE): a prospective cohort study
- Are noise and air pollution related to the incidence of dementia? A cohort study in London, England
- Long COVID symptoms and duration in SARS-CoV-2 positive children — a nationwide cohort study
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.