Clinical significance versus statistical significance: Does it matter in clinical practice?

To the Editor, We read Roy et al.’s[1] article, recently published in your esteemed journal, with great interest. We would like to highlight our concerns related to the expression of statistical significance as clinical significance in practical scenarios. The authors obtained a difference of 0.48 in the visual analogue scale (VAS) score at 36 h (P < 0.001). They concluded based on this result without defining a clinically significant difference in VAS for the primary outcome.[1,2] As per the literature, the minimum clinically significant difference in VAS to differentiate pain between two groups is 13 mm or 1.3 cm.[2-4] Although a mean difference of 0.48 in VAS is statistically significant, it may not be clinically significant.[1-4] So, extrapolation of the results obtained in this study for the general population may not be reliable. Authors also reported time to perform block as a statistically significant outcome (mean difference 2.2 min, P < 0.001), but the 2–3 min difference clinically looks insignificant. As per the conclusion, ‘The 4-in-1 block provides non-inferior analgesia compared to the established iPACK plus ACB’, however, the authors have not mentioned anything about the inferiority of the study in sample size calculation.[1,2] Financial support and sponsorship Nil. Conflicts of interest There are no conflicts of interest.