A Statistical Framework to Interpret Individual Response to Intervention: Paving the Way for Personalized Nutrition and Exercise Prescription

Abstract

The concept of personalized nutrition and exercise prescription represents a topical and exciting progression for the discipline given the large inter-individual variability that exists in response to virtually all performance and health related interventions. Appropriate interpretation of intervention-based data from an individual or group of individuals requires practitioners and researchers to consider a range of concepts including the confounding influence of measurement error and biological variability. In addition, the means to quantify likely statistical and practical improvements are facilitated by concepts such as confidence intervals (CIs) and smallest worthwhile change (SWC). The purpose of this review is to provide accessible and applicable recommendations for practitioners and researchers that interpret, and report personalized data. To achieve this, the review is structured in three sections that progressively develop a statistical framework. Section 1 explores fundamental concepts related to measurement error and describes how typical error and CIs can be used to express uncertainty in baseline measurements. Section 2 builds upon these concepts and demonstrates how CIs can be combined with the concept of SWC to assess whether meaningful improvements occur post-intervention. Finally, section 3 introduces the concept of biological variability and discusses the subsequent challenges in identifying individual response and non-response to an intervention. Worked numerical examples and interactive Supplementary Material are incorporated to solidify concepts and assist with implementation in practice.

Issues in the determination of ‘responders’ and ‘non‐responders’ in physiological research

“…Approaches for this notion have been forwarded recently by Swinton et al (2018) and Hopkins (2018). Importantly, these approaches involve the SDir, directly accounting for the random within-subject variability that is present.…”

“…Importantly, these approaches involve the SDir, directly accounting for the random within-subject variability that is present. Again, there are online calculators for this step, such as the one we mentioned in Section 5.3, in addition to dedicated spreadsheets (Swinton et al, 2018). Then the proportion of people predicted to be above or below a certain response threshold is estimated using the characteristics of the normal distribution.…”

“…F I G U R E 2The hypothetical distribution of responses (free from random within-subject variability) for a population of interest(Hopkins, 2018). The net mean change is the baseline-adjusted and control group-adjusted mean treatment effect for the sample TA B L E 3 Use of the standard deviation for individual responses (SDir) to estimate the proportion of predicted responders, predicted trivial responders and predicted adverse responders in each of the three populations of interest according to the approach reported bySwinton et al (2018) The net mean change is the baseline-adjusted and control group-adjusted mean treatment effect for the sample TA B L E 3 Use of the standard deviation for individual responses (SDir) to estimate the proportion of predicted responders, predicted trivial responders and predicted adverse responders in each of the three populations of interest according to the approach reported bySwinton et al (2018) …”

Moving beyond threshold-based dichotomous classification to improve the accuracy in classifying non-responders

“…Because the sample size used to calculate TE impacts the certainty in the estimated TE value, adjusting the width of CIs with different multiples is a recommended approach to accommodate studies with sample sizes less than 50 (Swinton et al. ).…”

“…), which fails to consider “non‐response” within the context of meaningful benefit (Swinton et al. ).…”