Multidimensional Modeling to Maximize Adaptations to eXercise: The M3AX Trial Rationale and Study Design

Abstract

Age-related functional declines are thought to be caused by hallmark biological processes that manifest in physical, mental, and metabolic impairments compromising intrinsic capacity, healthspan and quality-of-life. Exercise is a multipotent treatment with promise to mitigate most aging hallmarks, but there is substantial variability in individual exercise responsiveness. This inter-individual response heterogeneity (IRH) was first extensively interrogated by Bouchard and colleagues in the context of endurance training. Our group has interrogated IRH in response to resistance training and combined training, and we have conducted trials in older adults examining dose titration and adjuvant treatments in attempts to boost response rates. Despite the work of many groups, the mechanisms underpinning IRH and effective mitigation strategies largely remain elusive. The National Institute on Aging (NIA) hosted a focused workshop in 2022 titled "Understanding heterogeneity of responses to, and optimizing clinical efficacy of, exercise training in old adults". This workshop spurred a dedicated NIA request for applications (RFA) with the major goal "to better understand factors underlying response variability to exercise training in older adults." We developed a two-phase Sequential Multiple Assignment Randomized Trial (SMART) in response to the RFA that will allow us to classify individual responsiveness to combined endurance and resistance training and interrogate potential mechanistic underpinnings (Phase I), followed by an approach to boost responsiveness (Phase II). Using deep in vivo, ex vivo, and molecular phenotyping, we will establish multidimensional biocircuitry of responsiveness and build predictive models, providing a basis for personalized exercise prescriptions.

Keywords: Combined Training; Geroscience; Heterogeneity; Skeletal Muscle.

Fig. 1.

Using the traditional clinical and rehabilitative practice of calculating MICDs to track progress or define treatment/intervention efficacy, we leveraged data from our previous large-scale combined ET+RT clinical trial in young individuals to generate MCIDs of exercise responsiveness. We selected an established distribution-based method to generate MCIDs based on % change from pre- to post-12 weeks of training for A) cardiorespiratory fitness (CRF) and B) functional muscle quality (fMQ). These MCID criteria generated the expected responder breakdown (‘−‘ = did not meet MCID, ‘+’ met MCID shown in the Punnet Square shown in C).

Fig. 2.

Overall trial design. The 2-phase SMART design is intended to determine what factors and mechanisms underlie inter-individual exercise response heterogeneity (IRH) among older adults. We employ a rigorous exercise prescription of combined endurance and resistance training to ensure direct translatability to public health recommendations. Phase I (12 week) is focused on interrogation which involves testing targeted hypotheses anchored to hallmarks of aging complemented by a multidimensional learning framework to decipher complex interrelationships among clinical, molecular, and behavioral phenotyping. Our modeling framework will produce integrated, multidimensional circuits predictive of responsiveness that contain modifiable factors for future study and precision exercise medicine. Phase II (10 week) will attempt mitigation by a targeted augmentation strategy for the older adults who do not attain minimum clinically important difference (MCID) scores for one or both primary outcomes (CRF and fMQ). Those in Phase II who meet both MCIDs will be randomized to test sustainability of training adaptations during free-living (vs. continuing the supervised intervention). Planned enrollment is therefore N=250 to account for up to 20% data missingness (data loss, QA/QC, attrition).

Fig. 3.

General participant flowthrough and expected burden from screening through end of the study.

Fig. 4:

Multidimensional learning framework to model and predict inter-individual exercise response heterogeneity. Step 1: Model inputs are curated independently within each data set, with each variable considered a feature. Step 2: Multidimensional, integrated phenomic, cellular, molecular multiomic and inter-tissue communication circuitry established using Recurrent Convolutional Neural Networks (RCNN). Baseline and longitudinal data from across domains (e.g., physical performance, molecular signatures) are concatenated and passed through a 1D convolutional layer to extract local temporal patterns. The output is then fed into parallel Long Short-Term Memory (LSTM) layers to capture sequential dependencies and temporal dynamics. Step 3: Outputs from each LSTM stream are fused and passed to a final dense output layer for identification of key features as determined using SHapley Additive exPlanations (SHAP) values. Step 4: Selected impactful features are based on two relevant criteria: good fit (i.e., high SHAP values) and actionable/modifiable. The most influential based on strength of relationship with responder classification will serve as inputs for predictive modeling of responsiveness.