Sport Science: Progress, Hubris, and Humility

Modelling Training Adaptation in Swimming Using Artificial Neural Network Geometric Optimisation

This study aims to model training adaptation using Artificial Neural Network (ANN) geometric optimisation. Over 26 weeks, 38 swimmers recorded their training and recovery data on a web platform. Based on these data, ANN geometric optimisation was used to model and graphically separate adaptation from maladaptation (to training). Geometric Activity Performance Index (GAPI), defined as the ratio of the adaptation to the maladaptation area, was introduced. The techniques of jittering and ensemble modelling were used to reduce overfitting of the model. Correlation (Spearman rank) and independence (Blomqvist β) tests were run between GAPI and performance measures to check the relevance of the collected parameters. Thirteen out of 38 swimmers met the prerequisites for the analysis and were included in the modelling. The GAPI based on external load (distance) and internal load (session-Rating of Perceived Exertion) showed the strongest correlation with performance measures. ANN geometric optimisation seems to be a promising technique to model training adaptation and GAPI could be an interesting numerical surrogate to track during a season.

Futureproofing triathlon: expert suggestions to improve health and performance in triathletes

Background

Given the multi-modal nature of triathlon (swimming, cycling, running), training for a triathlon event has numerous potential health benefits including physical fitness. However, triathletes also have a high prevalence of health issues including overuse injury, illness, fatigue, and burnout. To address the ongoing prevalence of health issues, roundtable discussions were organized at the International Triathlon Union Science of Triathlon 2017 conference to develop strategic objectives deemed necessary to “futureproof triathlon”. Futureproofing as a concept serves to design new approaches and ways of thinking to reduce consequences in the future. In this case, the futureproof process aimed to develop key recommendations for triathlon.

Methods

This qualitative study had 22 participants including athletes, coaches, practitioners, academics, and policy makers who participated in roundtable discussions at the Science of Triathlon conference. Seven of these participants completed follow-up semi-structured interviews on the same topics. The data collected from the roundtable discussions and the semi-structured interviews was analyzed using thematic analysis.

Results

Five main themes were produced: “Critical appraisal and application of knowledge”; “Integrated approaches to developing, disseminating, and using research and expertise”; “Appropriate development and use of measures for monitoring training and recovery”; “Knowing your athletes and adopting holistic approaches to athlete/person-development”, and; “Challenging accepted cultural and sporting norms”. Participants indicated the need to reduce the knowledge gap between research and practice as well as a more collaborative approach to triathlon research development amongst coaches/practitioners and academics. It was stated that current monitoring tools require more research to determine which are most useful to informed decision making for coaches/practitioners. It was cautioned that data driven assessments should be used judiciously and be athlete centered. Triathlon as a sport should also have a greater focus on healthy participation and development of youth athletes.

Conclusions

A series of applied implications were developed based on these five themes as guiding principles for how to futureproof triathlon. Additionally, roundtable and interview participants who held varying positions and opinions within the sport of triathlon agreed that the unique challenge of training for and competing in a triathlon should not be forgotten in the futureproofing of the sport.