Table 5 Examples of evidence, inconclusive and not enough information (NEI) paired clinical research claims and abstracts.
From: A dataset for evaluating clinical research claims in large language models
Claim | Publication title + abstract | Label |
|---|---|---|
Cilostazol is Non-Inferior or Equivalent to Aspirin in terms of Numbers of Patients With First Occurrence of Stroke From start of treatment to end of follow-up period (follow-up periods: 29 months [Standard Deviation 16, range 1–59 months]). | […] Interpretation: Cilostazol seems to be non-inferior, and might be superior, to aspirin for prevention of stroke after an ischaemic stroke, and was associated with fewer haemorrhagic events. Therefore, cilostazol could be used for prevention of stroke in patients with non-cardioembolic stroke. […] | Evidence |
Nerve Block is Superior or Other to Periarticular Injection in terms of Post-Operative Pain Afternoon on post-operative Day 1, approximately 14:00. | […] RESULTS: Mean pain scores on the afternoon of POD 1 were not different between groups (PNB group: 2.9 [SD 2.4]; PAI group: 3.0 [SD 2.2]; 95% confidence interval, -0.8 to 0.6; p = 0.76). Mean pain scores taken at three times points on POD 1 were also similar between groups. […] | Inconclusive |
Topiramate is Superior or Other to Placebo in terms of Percent Drinking Days (%DD) Weekly, weeks 1–12, average. | Combined pharmacotherapies and behavioral interventions for alcohol dependence: the COMBINE study: a randomized controlled trial. […] | NEI |
