Human-AI collaboration in clinical reasoning: a UK replication and interaction analysis.

AI / informaticsDiagnosis (Berlin, Germany)· Apr 2026

Human-AI collaboration in clinical reasoning: a UK replication and interaction analysis.

Justin Healy, Jonathan Kossoff, Matthew Lee, Christian Hasford

Read paper

AI Evaluation & GovernanceAI / informaticsClinical practiceQ2IF 2.1

UK physicians assisted by an large language model scored significantly lower than the large language model alone.

Human-AI collaboration in clinical reasoning: a UK replication and interaction analysis.

Justin Healy … Christian Hasford

Diagnosis (Berlin, Germany) · Apr 2026 · Q2 in General Medicine

Background

A paper from Goh et al. found that a large language model (large language model) working alone outperformed American clinicians assisted by the same large language model in diagnostic reasoning tests (Goh E, Gallo R, Hom J, Strong E, Weng J, Kerman H, et al.

Purpose

We aimed to replicate this experiment in a UK setting and explore how interactions with the large language model might explain the observed gaps in performance.

Methods

22 participants answered structured questions on four clinical vignettes.

n = 22 participants

21.3

Results

21.3

percentage points

with AI help, physicians scored notably worse than the AI alone

n = 22 participants

More results

There was significant heterogeneity in the degree of large language model-assisted improvement (SD 12.8 %).

Qualitative analysis revealed that only 30 % of case questions were directly posed to the large language model, which suggests that under-utilisation of the large language model contributed to the observed performance gap.

“

Conclusion

While access to an large language model can improve diagnostic accuracy, realising the full potential of human-AI collaboration may require a focus on training clinicians to integrate these tools into their cognitive workflows and on designing systems that make these integrations the default rather than an optional extra.

Human-AI collaboration in clinical reasoning: a UK replication and interaction analysis.

Human-AI collaboration in clinical reasoning: a UK replication and interaction analysis.

Related papers