Multimodal Injury Risk and Performance Prediction in Tennis Using Weighted Ensemble Learning

Weihao Qu; Dongyang Wang; Ling Zheng; Francisco E. Alvarez; Shobharani Polasa; Jiacun Wang

cs.LGAug 21, 2026

Multimodal Injury Risk and Performance Prediction in Tennis Using Weighted Ensemble Learning

Authors: Weihao Qu, Dongyang Wang, Ling Zheng, Francisco E. Alvarez, Shobharani Polasa, Jiacun Wang

Organizations: Department of Computer Science and Software Engineering Monmouth University, West Long Branch, NJ 07764, USA

Abstract

Machine learning has had a positive impact on the sports industry, with one of its most promising applications being the prediction of athlete performance and injury risk. Recent advances have employed state-of-the-art models to improve prediction accuracy, yet progress remains limited by data availability and the reliance on subjective observations or expert assessments. To address these limitations, researchers in sports such as soccer, basketball, and wrestling have begun integrating heterogeneous data sources, such as wearable device readings, with traditional subjective assessments. However, similar multimodal approaches remain underexplored in tennis. In this work, we propose a multimodal weighted ensemble learning framework, Predictive Athlete Readiness for Tennis (PART), to monitor athlete wellness and estimate near-term injury risk in tennis players. PART processes a wide range of inputs, including physiological metrics, training and match data, sleep information from wearable devices, self-reported questionnaires, vertical jump assessments, and motion analysis from match-play videos. From these modalities, specialized machine learning and deep learning models independently extract four athlete-specific characteristics: overall wellness, injury risk, physical capability, and playing style. To overcome the complexity of combining these diverse modalities, PART employs a supervised weighted ensemble integration strategy, assigning adaptive weights to each predictive model based on its reliability. Evaluation of multimodal data collected from nine collegiate tennis players demonstrates that PART achieves strong performance in monitoring athlete wellness and estimating near-term injury susceptibility. Beyond collegiate athletes, the framework also shows promise for recreational tennis players, offering personalized insights to mitigate injury risk and optimize performance.

Figures & tables

Fig. 1 : System architecture of $\mathtt{PART}$ .

Panel of Figure 2 — Fig. 2 : Examples of author-controlled inputs: (a) questionnaire; (b) vertical jump test; and (c) match-play video. WHOOP participant data are shown in Figure 3 (b).

Panel of Figure 3 — Fig. 3 : Collected Data Sample: (a) The result of questionnaire on reported injury locations from participants (b) Sample of the sleep, heart rate, recovery score tracked by WHOOP device (c) The Vertical jump data sample from Sparta testing.

Model	MAE	R 2 Score
Baseline Linear Regression	$16.81\pm 12.48$	$-0.81\pm 2.50$
Linear Regression	$21.62\pm 19.54$	$-2.89\pm 3.62$
Polynomial Regression	$316.91\pm 454.91$	$-1688.51\pm 2009.61$
Lasso Regression	$10.72\pm 2.78$	$0.38\pm 0.23$
Gradient Boosting	$9.76\pm 1.00$	$0.43\pm 0.10$
XGBoost	$8.04\pm 1.87$	$0.65\pm 0.12$

TABLE I : Regression Performance (Overall Wellness)

Panel of Figure 5 — Fig. 4 : Regression and classifier results. (a) XGBoost regression: actual versus predicted recovery scores. The $R^{2}$ value shown reflects a representative test fold; the cross-validated mean is $0.65\pm 0.12$ (Table I ). (b) The confusion matrix for the XGBoost classifier.

95% confidence intervals shown as mean $\pm$ margin of error.
Model	AUC-ROC	Accuracy	F1 Score (Injury)
Logistic Regression	0.61 $\pm$ 0.01	0.48 $\pm$ 0.09	0.40 $\pm$ 0.01
XGBoost	0.64 $\pm$ 0.01	0.74 $\pm$ 0.01	0.43 $\pm$ 0.01
Decision Tree	0.65 $\pm$ 0.01	0.74 $\pm$ 0.01	0.43 $\pm$ 0.02
Random Forest	0.64 $\pm$ 0.01	0.74 $\pm$ 0.01	0.43 $\pm$ 0.01

TABLE II : Classification Performance (Injury Risk)

Player	Overall	Injury	Physical	Style	Final
ID	Well (OWS)	Risk (IR)	Cap (PCS)	Wt	ARS
P1	82	0.25	75	1.2	64.54
P2	78	0.30	72	1.4	52.50
P3	85	0.15	82	1.0	83.95
P4	75	0.30	65	1.6	43.75
P5	88	0.15	80	1.2	70.25

TABLE III : Sample Training Dataset (One Week Period)

Fig. 5 : ARS tracking during and after ankle sprain (April 2024). The plot shows a increasing trend in ARS score during recovery period.

Fig. 6 : ARS tracking during match series (February 2024). The plot shows a gradual decrease in ARS following three consecutive matches (indicated by university logos), reflecting accumulated fatigue.

Multimodal Sensor Fusion

Multimodal sensor fusion combines data from different sensors to improve perception, tracking, localization, and prediction.

See all 417 papers

Aug 25, 2026

Multimodal Injury Risk Prediction in Tennis

Machine learning has had a significant positive impact on the prediction of athlete performance and injury risk. Most works in this field rely on subjective observations and expert assessments, which restrict their effectiveness. In sports like soccer, basketball, and wrestling, some studies attempt to address this challenge by integrating data from alternative sources, such as readings from wearable devices, alongside traditional subjective observations and expert assessments to enhance accuracy. However, similar research in tennis remains largely unexplored. In this paper, we propose a multimodal Predictive Athlete Readiness framework for Tennis (PART) to assess both performance and injury risk in tennis players. By leveraging machine learning and deep learning techniques, PART processes multiple sources of data collected from nine collegiate tennis players, including physiological metrics, training and match data, sleep data from wearable devices, self-reported information via daily questionnaires, jump assessments, and motion analysis from match play videos. PART captures four characteristics of tennis players: overall wellness, injury risk, physical capability, and playing style. By integrating these four characteristics by supervised learning, it is capable of providing a holistic assessment of the tennis athlete's condition, along with advanced forecasts of specific body areas at risk such as the upper body (e.g., elbows) or lower body (e.g., knees). Our evaluation, conducted with data from nine collegiate tennis players, shows that PART achieves strong performance in predicting both overall wellness and injury risk. Additionally, our framework also shows promise for recreational tennis players, who often suffer from injuries due to incorrect playing techniques.

Francisco Erramuspe Alvarez, Shobharani Polasa, Weihao Qu +2

Department of Computer Science and Software Engineering Monmouth University West Long Branch, USA

Topic pending

Ask PDF

Oct 6, 2026

TTNet: Multi-Task Deep Learning for Table Tennis Player Analysis with Smart Racket

The AI CUP 2025 Precise Analysis of Table Tennis Smart Racket Data Competition introduced smart table tennis rackets that collect extensive player swing data, enabling research on table tennis big data. These data support in-depth analysis of players' return techniques and swing-force consistency, improving the accuracy of player skill assessment. This study focuses on six-axis sensor data collected by smart table tennis rackets and proposes TTNet, a novel deep learning model with multitask learning capabilities, to advance table tennis data analysis and related applications. TTNet combines convolutional neural networks (CNNs), residual networks (ResNet), and self-attention mechanisms to simultaneously predict four player attributes: gender, playing hand, years of experience, and skill level. We adopt a two-stage training strategy that incorporates data augmentation and task-specific loss functions to improve generalization on imbalanced data. Our approach achieved second place on the official competition leaderboard.

Ko-Hsun Chen, Xiang-Wei Ke, Hsien-Cheng Huang +1

Department of Computer Science and Engineering, Yuan Ze University, Taoyuan, Taiwan

Multi-Task Learning

Ask PDF

Apr 16, 2026

An unsupervised decision-support framework for multivariate biomarker analysis in athlete monitoring

Purpose. Athlete monitoring is constrained by small cohorts, heterogeneous biomarker scales, limited feasibility of repeated sampling, and the lack of reliable injury ground truth. These limitations reduce the interpretability and utility of traditional univariate and binary risk models. This study addresses these challenges by proposing an unsupervised multivariate framework to identify latent physiological states in athletes using real data. Methods. We propose a modular computational framework that operates in the joint biomarker space, integrating preprocessing, clinical safety screening, unsupervised clustering, and centroid-based physiological interpretation. Profiles are learned exclusively from amateur soccer players during a competitive microcycle. Synthetic data augmentation evaluates robustness and scalability. Ward hierarchical clustering supports monitoring and etiological differentiation, while Gaussian Mixture Models (GMM) enable structural stability analysis in high-dimensional settings. Results. The framework identifies coherent profiles that distinguish mechanical damage from metabolic stress while preserving homeostatic states. Synthetic data augmentation demonstrates feasibility and detection of latent silent risk phenotypes typically missed by univariate monitoring. Structural analyses indicate robustness under augmentation and higher-dimensional settings. Conclusion. The framework enables interpretable identification of latent physiological states from multivariate biomarker data without injury labels. By distinguishing mechanisms and revealing silent risk patterns not captured by conventional monitoring, it provides actionable insights for individualized athlete monitoring and decision making.

Fernando Barcelos Rosito, Sebastião De Jesus Menezes, Simone Ferreira Sturza +2

1*Federal University of Health Sciences of Porto Alegre (UFCSPA), RS, Brazil. · 2Levino Inova, AC, Brazil.

Unsupervised Clustering

Ask PDF

Abstract

Multimodal Sensor Fusion

Explore similar work

Multimodal Injury Risk Prediction in Tennis

TTNet: Multi-Task Deep Learning for Table Tennis Player Analysis with Smart Racket

An unsupervised decision-support framework for multivariate biomarker analysis in athlete monitoring