Artificial neural network accurately predicts hepatitis B surface antigen seroclearance.

PLoS One · 2014 · PMC4051672 · PMID 24914537

Europe PMC DOI

hedged sentence

0.0630

closest p · 1.3× alpha

0.0630

boldest claim

The sentences

showed a trendP = 0.063so close (0.05 < p ≤ 0.1)

It was 0.757 (95%CI = 0.672–0.829) which was still significantly higher than that of HBV DNA (AUROC 0.604, 95%CI = 0.513–0.690; P = 0.013), and showed a trend to be better than those of LRM and qHBsAg level (AUROC 0.670, 95%CI = 0.581–0.751, P = 0.063; 0.670, 95%CI = 0.581–0.751, P = 0.063 respectively) ( Table 4 ).

also in 53,322 other papers

Quoted from the open-access full text in Europe PMC under the licence the publisher applied. The sentence is reproduced exactly as published; the emphasis is ours.