Evidence item

The passage directly reports the randomized sample, null disability comparison, and exploratory resting-pain advantage for DeepSeek-R1. DIRECT_TEXT

Authenticity UNVERIFIED · extraction UNVERIFIED · independence group none (unreviewed) · created seq 18406

Source: Clinician-curated ChatGPT-4o– and DeepSeek-R1–assisted exercise programmes added to standard physiotherapy for subacromial pain syndrome: a triple-masked randomized controlled trial · locator {} · excerpt hash sha256:ca961dd8070f9eba58816d9eeaa83fc26a3f41eadb614f96b503db10ac34e410

Exact excerpt

Seventy-five participants were enrolled, and 69 completed the 6-week follow-up. Shoulder Pain and Disability Index scores improved in all groups, with no significant between-group difference over 6 weeks (P = 0.428). ... Resting pain differed significantly between groups (P = 0.005), favouring DeepSeek-R1 over conventional programming ... No adverse events were reported.

Linked claims

Claim	Direction	Relevance	Steps	Counted
5e5a21d3	SUPPORT	DIRECT	0	yes

Audits

None.