An Overview of Machine Learning Applications in Sports Injury Prediction

Using markerless motion analysis to quantify sex and discipline differences in external mechanical work during badminton match play

The high prevalence of overuse injuries in badminton poses a major threat to player development and success, with current training 'load' metrics insufficient for capturing the physical demands. This study quantified the external mechanical work performed during badminton match play across different sexes and disciplines. An eight-camera system captured fourteen male and fourteen female competitive (University to national level) badminton players competing across a total of nine singles and six doubles matches. Markerless pose estimation (HRNet) was used to drive a kinematic model (OpenSim) of each player and compute mass-normalised external mechanical work and power for 30 points per match. A linear mixed effects model found normalised work and power to be greater in men's vs. women's matches (effect size [ES] ± 90% CI = 0.60 ± 0.29 and 1.10 ± 0.48, respectively). Normalised work and power were also greater in singles vs. doubles matches (ES = 0.44 ± 0.29 and 0.47 ± 0.44, respectively). Interestingly, discipline differences were greatest among the most skilled players (e.g. ES = 0.88 ± 0.49 for first-team males). These findings highlight the importance of additional strength training and adequate recovery for elite male players to manage the high physical demands of singles match play.

A Machine Learning Model for Post-Concussion Musculoskeletal Injury Risk in Collegiate Athletes

BACKGROUND

Emerging evidence indicates an elevated risk of post-concussion musculoskeletal injuries in collegiate athletes; however, identifying athletes at highest risk remains to be elucidated.

OBJECTIVE

The purpose of this study was to model post-concussion musculoskeletal injury risk in collegiate athletes by integrating a comprehensive set of variables by machine learning.

METHODS

A risk model was developed and tested on a dataset of 194 athletes (155 in the training set and 39 in the test set) with 135 variables entered into the analysis, which included participant's heath and athletic history, concussion injury and recovery-specific criteria, and outcomes from a diverse array of concussion assessments. The machine learning approach involved transforming variables by the weight of evidence method, variable selection using L1-penalized logistic regression, model selection via the Akaike Information Criterion, and a final L2-regularized logistic regression fit.

RESULTS

A model with 48 predictive variables yielded significant predictive performance of subsequent musculoskeletal injury with an area under the curve of 0.82. Top predictors included cognitive, balance, and reaction at baseline and acute timepoints. At a specified false-positive rate of 6.67%, the model achieves a true-positive rate (sensitivity) of 79% and a precision (positive predictive value) of 95% for identifying at-risk athletes via a well-calibrated composite risk score.

CONCLUSIONS

These results support the development of a sensitive and specific injury risk model using standard data combined with a novel methodological approach that may allow clinicians to target high injury risk student athletes. The development and refinement of predictive models, incorporating machine learning and utilizing comprehensive datasets, could lead to improved identification of high-risk athletes and allow for the implementation of targeted injury risk reduction strategies by identifying student athletes most at risk for post-concussion musculoskeletal injury.

Comparison of machine learning and nomogram to predict 30-day in-hospital mortality in patients with acute myocardial infarction combined with cardiogenic shock: a retrospective study based on the eICU-CRD and MIMIC-IV databases

BACKGROUND

To evaluate the predictive utility of machine learning and nomogram in predicting in-hospital mortality in patients with acute myocardial infarction complicated by cardiogenic shock (AMI-CS), and to visualize the model results in order to analyze the impact of these predictors on the patients' prognosis.

METHODS

A retrospective analysis was conducted on 332 adult patients who were diagnosed with AMI-CS and admitted to the ICU for the first time within the eICU Collaborative Research Database (eICU-CRD). AdaBoost, XGBoost, LightGBM, Random Forest and logistic regression nomogram were developed utilizing the random forest recursive elimination (RF-RFE) and least absolute shrinkage and selection operator (LASSO) algorithms for feature selection.

RESULTS

Compared to the machine learning models, the nomogram demonstrated superior predictive accuracy for mortality in patients with AMI-CS, with an AUC value of 0.869 (95% CI: 0.803, 0.883) and an F1 score of 0.897 for the internal test set of nomogram, and an AUC of 0.770 (95% CI: 0.702, 0.801) and an F1 score of 0.832 for the external validation set.

CONCLUSIONS

Nomogram enhance the interpretability and transparency of the models, leading to more reliable prognostic predictions for AMI-CS patients. This facilitates clinicians in making precise decisions, thereby enhancing patient prognosis.

Predicting Sprint Potential: A Machine Learning Model Based on Blood Metabolite Profiles in Young Male Athletes

This study aims to utilize male blood metabolite signatures for (i) distinguishing between healthy individuals and athletes, thereby optimizing the athlete screening process; and (ii) predicting athletic performance in 100, 200, and 400 m sprints, enhancing precompetition preparation and intervention strategies. Initially, we employed nontargeted metabolomics to analyze the blood metabolome of healthy individuals (n = 10) and athletes (n = 10), identifying differential expressed metabolites (DEMs) potentially related to athletic performance through differential analysis, consensus clustering, WGCNA, and UMAP analysis. Subsequently, using LASSO-Cox analysis, we refined our selection to two core DEMs: HMDB0012085 (Sphingomyelin (d18:0/14:0)) and HMDB0009224 (Phosphatidylethanolamine(20:0/18:1(9Z))) associated with athletic performance. We then applied targeted metabolomics to measure the levels of these DEMs in a larger cohort, including healthy individuals (n = 50) and athletes (n = 100), revealing a significant increase in the levels of HMDB0012085 and HMDB0009224 in athletes compared to healthy individuals. Utilizing 13 machine learning classification methods, we demonstrated that the levels of HMDB0012085 and HMDB0009224 in blood effectively differentiate between healthy individuals and athletes. Notably, HMDB0012085 exhibits greater feature importance across multiple algorithms compared to HMDB0009224. Specifically, in decision trees (94.1 vs. 5.9), random forests (60.7 vs. 39.3), gradient boosting trees (91.5 vs. 8.5), CatBoost (61.7 vs. 38.3), ExtraTrees (64.7 vs. 35.3), and XGBoost (74.5 vs. 25.5). Finally, we found a significant negative correlation between the levels of HMDB0012085 and HMDB0009224 in whole blood and sprint times for 100, 200, and 400 m races. In conclusion, HMDB0012085 and HMDB0009224 in whole blood hold promise as biomarkers for predicting athletic potential in males.

A Machine Learning Model for Post-Concussion Musculoskeletal Injury Risk in Collegiate Athletes

Background

Emerging evidence indicates an elevated risk of post-concussion musculoskeletal (MSK) injuries in collegiate athletes; however, identifying athletes at highest risk remains to be elucidated.

Objective

The purpose of this study was to model post-concussion MSK injury risk in collegiate athletes by integrating a comprehensive set of variables by machine learning.

Methods

A risk model was developed and tested on a dataset of 194 athletes (155 in the training set and 39 in the test set) with 135 variables entered into the analysis, which included participant's heath and athletic history, concussion injury and recovery specific criteria, and outcomes from a diverse array of concussions assessments. The machine learning approach involved transforming variables by the Weight of Evidence method, variable selection using L1-penalized logistic regression, model selection via the Akaike Information Criterion, and a final L2-regularized logistic regression fit.

Results

A model with 48 predictive variables yielded significant predictive performance of subsequent MSK injury with an area under the curve of 0.82. Top predictors included cognitive, balance, and reaction at Baseline and Acute timepoints. At a specified false positive rate of 6.67%, the model achieves a true positive rate (sensitivity) of 79% and a precision (positive predictive value) of 95% for identifying at-risk athletes via a well calibrated composite risk score.

Conclusion

These results support the development of a sensitive and specific injury risk model using standard data combined with a novel methodological approach that may allow clinicians to target high injury risk student-athletes. The development and refinement of predictive models, incorporating machine learning and utilizing comprehensive datasets, could lead to improved identification of high-risk athletes and allow for the implementation of targeted injury risk reduction strategies by identifying student-athletes most at risk for post-concussion MSK injury.

Gear Classification in Skating Cross-Country Skiing Using Inertial Sensors and Deep Learning

The aim of this current work is to identify three different gears of cross-country skiing utilizing embedded inertial measurement units and a suitable deep learning model. The cross-country style studied was the skating style during the uphill, which involved three different gears: symmetric gear pushing with poles on both sides (G3) and two asymmetric gears pushing with poles on the right side (G2R) or to the left side (G2L). To monitor the technique, inertial measurement units (IMUs) were affixed to the skis, recording acceleration and Euler angle data during the uphill tests performed by two experienced skiers using the gears under study. The initiation and termination points of the tests were controlled via Bluetooth by a smartphone using a custom application developed with Android Studio. Data were collected on the smartphone and stored on the SD memory cards included in each IMU. Convolutional neural networks combined with long short-term memory were utilized to classify and extract spatio-temporal features. The performance of the model in cross-user evaluations demonstrated an overall accuracy of 90%, and it achieved an accuracy of 98% in the cross-scene evaluations for individual users. These results indicate a promising performance of the developed system in distinguishing between different ski gears within skating styles, providing a valuable tool to enhance ski training and analysis.

Exploring CrossFit performance prediction and analysis via extensive data and machine learning

BACKGROUND

The analysis of athletic performance has always aroused great interest from sport scientist. This study utilized machine learning methods to build predictive models using a comprehensive CrossFit (CF) dataset, aiming to reveal valuable insights into the factors influencing performance and emerging trends.

METHODS

Random forest (RF) and multiple linear regression (MLR) were employed to predict performance in four key weightlifting exercises within CF: clean and jerk, snatch, back squat, and deadlift. Performance was evaluated using R-squared (R2) values and mean squared error (MSE). Feature importance analysis was conducted using RF, XGBoost, and AdaBoost models.

RESULTS

The RF model excelled in deadlift performance prediction (R2=0.80), while the MLR model demonstrated remarkable accuracy in clean and jerk (R2=0.93). Across exercises, clean and jerk consistently emerged as a crucial predictor. The feature importance analysis revealed intricate relationships among exercises, with gender significantly impacting deadlift performance.

CONCLUSIONS

This research advances our understanding of performance prediction in CF through machine learning techniques. It provides actionable insights for practitioners, optimize performance, and demonstrates the potential for future advancements in data-driven sports analytics.

[Prediction of risk of in-hospital death in patients with chronic heart failure complicated by lung infections using interpretable machine learning]

OBJECTIVE

To predict the risk of in-hospital death in patients with chronic heart failure (CHF) complicated by lung infections using interpretable machine learning.

METHODS

The clinical data of 1415 patients diagnosed with CHF complicated by lung infections were obtained from the MIMIC-IV database. According to the pathogen type, the patients were categorized into bacterial pneumonia and non-bacterial pneumonia groups, and their risks of in-hospital death were compared using Kaplan-Meier survival curves. Univariate analysis and LASSO regression were used to select the features for constructing LR, AdaBoost, XGBoost, and LightGBM models, and their performance was compared in terms of accuracy, precision, F1 value, and AUC. External validation of the models was performed using the data from eICU-CRD database. SHAP algorithm was applied for interpretive analysis of XGBoost model.

RESULTS

Among the 4 constructed models, the XGBoost model showed the highest accuracy and F1 value for predicting the risk of in-hospital death in CHF patients with lung infections in the training set. In the external test set, the XGBoost model had an AUC of 0.691 (95% CI: 0.654-0.720) in bacterial pneumonia group and an AUC of 0.725 (95% CI: 0.577-0.782) in non-bacterial pneumonia group, and showed better predictive ability and stability than the other models.

CONCLUSION

The overall performance of the XGBoost model is superior to the other 3 models for predicting the risk of in-hospital death in CHF patients with lung infections. The SHAP algorithm provides a clear interpretation of the model to facilitate decision-making in clinical settings.

Predictive model for identifying mild cognitive impairment in patients with type 2 diabetes mellitus: A CHAID decision tree analysis

BACKGROUND

As the population ages, mild cognitive impairment (MCI) and type 2 diabetes mellitus (T2DM) become common conditions that often coexist. Evidence has shown that MCI could lead to reduced treatment compliance, medication management, and self-care ability in T2DM patients. Therefore, early identification of those with increased risk of MCI is crucial from a preventive perspective. Given the growing utilization of decision trees in prediction of health-related outcomes, this study aimed to identify MCI in T2DM patients using the decision tree approach.

METHODS

This hospital-based case-control study was performed in the Endocrinology Department of Xiangya Hospital affiliated to Central South University between March 2021 and December 2022. MCI was defined based on the Petersen criteria. Demographic characteristics, lifestyle factors, and T2DM-related information were collected. The study sample was randomly divided into the training and validation sets in a 7:3 ratio. Univariate and multivariate analyses were performed, and a decision tree model was established using the chi-square automatic interaction detection (CHAID) algorithm to identify key predictor variables associated with MCI. The area under the curve (AUC) value was used to evaluate the performance of the established decision tree model, and the performance of multivariate regression model was also evaluated for comparison.

RESULTS

A total of 1001 participants (705 in the training set and 296 in the validation set) were included in this study. The mean age of participants in the training and validation sets was 60.2  ±  10.3 and 60.4  ±  9.5 years, respectively. There were no significant differences in the characteristics between the training and validation sets (p > .05). The CHAID decision tree analysis identified six key predictor variables associated with MCI, including age, educational level, household income, regular physical activity, diabetic nephropathy, and diabetic retinopathy. The established decision tree model had 15 nodes composed of 4 layers, and age is the most significant predictor variable. It performed well (AUC = .75 [95% confidence interval (CI): .71-.78] and .67 [95% CI: .61-.74] in the training and validation sets, respectively), was internally validated, and had comparable predictive value compared to the multivariate logistic regression model (AUC = .76 [95% CI: .72-.80] and .69 [95% CI: .62-.75] in the training and validation sets, respectively).

CONCLUSION

The established decision tree model based on age, educational level, household income, regular physical activity, diabetic nephropathy, and diabetic retinopathy performed well with comparable predictive value compared to the multivariate logistic regression model and was internally validated. Due to its superior classification accuracy and simple presentation as well as interpretation of collected data, the decision tree model is more recommended for the prediction of MCI in T2DM patients in clinical practice.