Evidence item

The primary report limits the result to 355 retrospectively collected charts from non-small-cell lung or colorectal cancer patients and identifies review time as a secondary endpoint. DIRECT_TEXT

Authenticity UNVERIFIED · extraction UNVERIFIED · independence group none (unreviewed) · created seq 25825

Source: Human-AI teaming to improve accuracy and efficiency of eligibility criteria prescreening for oncology trials: a randomized evaluation trial using retrospective electronic health records · locator {} · excerpt hash sha256:f0c4183340022ca3be8c3b3f5b5e3bd66b624325180ed6dbfbf50eedb92e9373

Exact excerpt

We conduct a randomized noninferiority trial using retrospectively collected clinical charts to compare the accuracy and efficiency of prescreening by trained research staff alone (Human-alone) vs. augmented with a pre-trained language model (Human+AI), among a cohort of 355 patients with non-small cell lung or colorectal cancer. ... However, efficiency is unchanged with similar average time per chart review, the secondary endpoint, (37.4 vs. 37.8 min).

Linked claims

Claim	Direction	Relevance	Steps	Counted
e9259cb1	QUALIFY	DIRECT	0	yes

Audits

None.