Extended Data Fig. 6: Clinician-AI collaboration and clinically significant errors.

Subgroup analysis of the data presented in Fig. 5 illustrates that (a) clinician-AI collaboration produced an improvement in ratings for the subgroup of AI reports that had clinically significant errors (with MIMIC-CXR p values given by p^* = 2.6x10⁻³, p^** = 1.5x10⁻⁷, p^*** = 2.9x10⁻⁸ and with IND1 p values given by p^* = 6.3x10⁻⁷, p^** = 4.0x10⁻⁸ p^*** = 1.3x10⁻⁵), whereas (b), there was little or no improvement for the subgroup of AI reports that did not have clinically significant errors (with MIMIC-CXR p values given by p^* = 1.2x10⁻², p^** = 1.2x10⁻² and with IND1 p values given by p^* = 3.2x10⁻²). As before, significant differences (p < 0.05) between clinician-AI results and AI-only results calculated using a one-sided Chi-squared are indicated by asterisks. This suggests that the positive impact of clinician-AI collaboration is largely attributable to edits in AI reports that had clinically significant errors. Data for all panels is presented as mean values and error bars show 95% confidence intervals for the cumulative preference scores.