ECSS Paris 2023: OP-AP10
INTRODUCTION: Anti-doping programs aim to protect fairness in competition and athlete health; however, conventional testing approaches are costly, invasive, and limited by narrow detection windows. The Athlete Biological Passport (ABP) provides a longitudinal monitoring framework but requires repeated biological sampling and substantial resources, limiting scalability. The Athlete Performance Passport (APP) has emerged as a complementary, non-invasive approach based on longitudinal performance data, yet empirical validation using advanced artificial intelligence (AI) methods remains limited, particularly in elite weightlifting characterized by complex performance trajectories. This study evaluated an AI-driven APP framework for detecting performance anomalies in elite male weightlifting. METHODS: Competition records were obtained from the official website of International Weightlifting Federation (IWF), comprising 28,831 entries from 1998 to 2022. Recurrent neural networks were used to model individual performance trajectories and predict expected total lifted weight at each athlete’s final competition. Performance residuals, defined as deviations between observed and predicted outcomes, were extracted and combined with demographic and performance variables to train an XGBoost classifier for estimating doping sanction status. Model interpretability was assessed using explainable artificial intelligence techniques based on Shapley additive explanations. RESULTS: The recurrent neural network demonstrated strong predictive accuracy, achieving an R² of 0.726 with stable performance across bootstrap resampling. The classification model showed good discriminative ability, with a receiver operating characteristic area under the curve of 0.831 on the internal test set and 0.738 in external validation. Explainable AI analysis identified total lifted weight, body weight, and performance residuals as the strongest contributors to sanction classification, indicating that longitudinal deviations provided additional information beyond absolute performance levels. CONCLUSION: An AI-driven APP framework can effectively identify performance anomalies consistent with doping-related enhancement in elite male weightlifting. Performance-based longitudinal monitoring represents a scalable and cost-effective complement to biological testing and has practical relevance for applied sports science by supporting targeted anti-doping strategies, enhancing athlete health protection, and promoting fairness in competition.
Read CV Yuntae JuECSS Paris 2023: OP-AP10
INTRODUCTION: Ladies Gaelic Football (LGF) is one of the largest female participated sports in Europe with over 200,000 registered participants. Teams aim to maintain possession whilst outscoring the opposition. Turnovers (TO) are a key characteristic of LGF, defined as a player in possession surrendering the ball to the opposition (1). Turnover rate, expressed as the percentage of possessions lost is a key indicator of possession dominance (2). In elite LGF winning teams reporting significantly lower TO rate compared to losing teams (1). This study aims to identify the main causes of turnovers in LGF, describe their characteristics, and examine how they influence team success. METHODS: 22 games (978 Turnovers) from the 2025 season have been analysed using Nacsport Elite. 11 new variable definitions for turnover causes have been validated and defined. Validity and reliability of data collection have been completed and found within an acceptable range <0.05. Statistical analysis was conducted using SPSS version 29. RESULTS: Winning teams reported a significantly lower TO rate (46% v 61%) (p ≤0.20) and are more successful at turning their opposition in advanced areas of the pitch. Kick pass was the highest cause of TOs for winning (28%) and losing teams (31%). Second half (51%) and quarter 1 (27%) reported highest occurrence of TOS. Winning teams were significantly better at converting TOs to shots (13±3 v 8±3) and scores (9±3 v 4±2) and goals (p≤0.05). Turnovers occurring in the defensive third had the highest Net point per TO return for both winning (0.58 net point per TO) and losing teams (0.52 net points per TO). CONCLUSION: Winning teams are significantly better at maintaining and using possession. They reported significantly lower TO rates and significantly higher conversions of TOs to shots, scores and goals. In light of the recent rule changes proposed by the LGFA this research provides an up to date benchmark profile for LGF performance. Thus, helping to assess the potential impact of the proposed rules on the game. 1. Kelly G, McKenna O, Courtney S, Collins K, Bradley J, Martin D. Benchmarking successful performances in elite Ladies Gaelic football. Int J Perform Anal Sport. 2022;22(1):51–65. 2. McGuigan K, Hughes M, Martin D. Performance indicators in club level Gaelic football. Int J Perform Anal Sport. 2018 Sep 3;18(5):780–95.
Read CV Aoife Mc ColganECSS Paris 2023: OP-AP10
INTRODUCTION: Techniques and tactics, the key competitive metrics in modern football, are the main factors affecting players' competitive performance. Prior studies on women's football mostly focused on single events or independent age groups, without considering age differences. By analysing post-match summary reports from the FIFA U-17, U-20, and senior Women's World Cups, this study conducted a cross-age longitudinal comparison to quantify the impact of age differences on the technical and tactical performance of female footballers in various positions. Findings offer scientific insights to support coaches in optimizing training programs. METHODS: Generalized linear mixed models were established using IBM SPSS Statistics 27, and magnitude-based inference was applied to estimate the mean changes. When significant interaction effects between age and positions were detected, Sidak post-hoc comparison analysis was performed. Data were sourced from the 2025 U-17, 2024 U-20, and 2023 Women's World Cups post-match summary reports of non-red-card matches(144 matches). Positions included forwards (FWs), defenders (DFs), and midfielders (MFs). Metrics for full-match players included 11 offensive metrics (such as take-ons and passes) and 12 defensive metrics (such as clearances and tackles). RESULTS: Significant interaction effects were observed in take-ons, passes, line breaks attempted, possession interruptions, and clearances (P < 0.05). Compared with the senior team, U17 FWs showed a large increase in take-ons (ES = 1.11), whereas U20 FWs showed a moderate decrease (ES = -0.74); U17 DFs showed a large increase in take-ons (ES = 1.83), while U17 and U20 DFs showed slight-to-moderate decreases in passes and take-ons (ES = -0.77 to -0.31); U17 MFs showed moderate-to-large increases in take-ons and possession interruptions (ES = 0.61 to 1.41), and U17 and U20 MFs showed slight-to-moderate decreases in passes and line breaks attempted (ES = -0.94 to -0.36). Relative to the U17, U20 FWs showed a substantial decrease in take-ons (ES = -1.85); U20 DFs showed slight-to-large decreases in take-ons and possession interruptions (ES = -2.61 to -0.42); U20 MFs showed small-to-moderate decreases in take-ons, possession interruptions and clearances (ES = -2.35 to -0.53). CONCLUSION: The results show that age differences exert position-specific effects on only five metrics. Take-ons across all positions and possession interruptions for DFs and MFs show marked fluctuations with age, first decreasing and then increasing. Passes for DFs show a gradual, progressive increase. Passes and line breaks attempted for MFs remain stable during youth, with significant increases at senior level. Clearances for MFs show a phased characteristic, with significant differences only observed in youth. These trends reflect that partial technical and tactical performance may shift from talent to system driven with age, finally achieving the high integration of ability and tactics. Targeted training is necessary for female footballers.
Read CV Shibo SunECSS Paris 2023: OP-AP10