Using Weather and Playing Surface to Predict the Occurrence of Injury in Major League Soccer Games: A Case Study

Landset, Sara; Bergeron, Michael F.; Khoshgoftaar, Taghi M.

doi:10.1109/iri.2017.86

Cited by 4 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In another 2018 paper by Carey et al, also exploring hamstring injury prediction and risk factors, SVM benefited substantially from data pre-processing, although it was ultimately outperformed by simple logistic regression [ 17 ]. Using non-physiological data, a 2017 paper predicting in-game injuries in Major League Soccer found that SVMs were the most accurate of several tested algorithms, including logistic regression, multilayer perceptron, and random forest [ 18 ]. However, in the recent literature, including two 2021 papers comparing efficacy of ML algorithms, SVMs have proven less effective than other algorithms [ 19 , 20 ].…”

Section: Reviewmentioning

confidence: 99%

An Overview of Machine Learning Applications in Sports Injury Prediction

Amendolara,

Pfister,

Settelmayer

et al. 2023

Cureus

View full text Add to dashboard Cite

Use injuries, i.e., injuries caused by repetitive strain on the body, represent a serious problem in athletics that has traditionally relied on historic datasets and human experience for prevention. Existing methodologies have been frustratingly slow at developing higher precision prevention practices. Technological advancements have permitted the emergence of artificial intelligence and machine learning (ML) as promising toolsets to enhance both injury mitigation and rehabilitation protocols. This article provides a comprehensive overview of recent advances in ML techniques as they have been applied to sports injury prediction and prevention. A comprehensive literature review was conducted searching PubMed/Medline, Institute of Electrical and Electronics Engineers (IEEE)/Institute of Engineering and Technology (IET), and ScienceDirect. Ovid Discovery and Google Scholar were used to provide additional aggregate results and a grey literature search. A focus was placed on papers published from 2017 to 2022. Algorithms of interest were limited to K-Nearest Neighbor (KNN), K-means, decision tree, random forest, gradient boosting and AdaBoost, and neural networks. A total of 42 original research papers were included, and their results were summarized. We conclude that given the current lack of open source, uniform data sets, as well as a reliance on dated regression models, no strong conclusions about the real-world efficacy of ML as it applies to sports injury prediction can be made. However, it is suggested that addressing these two issues will allow powerful, novel ML architectures to be deployed, thus rapidly advancing the state of this field, and providing validated clinical tools.

show abstract

Section: Reviewmentioning

confidence: 99%

An Overview of Machine Learning Applications in Sports Injury Prediction

Amendolara,

Pfister,

Settelmayer

et al. 2023

Cureus

View full text Add to dashboard Cite

show abstract

“…SVM gained a significant advantage from data pre-processing in another work published in 2018 by Carey et al, which likewise investigated the prediction of hamstring injuries and the associated risk variables [32], despite the fact that it was eventually surpassed by straightforward logistic regression. In a study published in 2017 that predicted in-game injuries in Major League Soccer using non-physiological data, the authors discovered that SVM were the most accurate of many investigated methods, including random forest, multilayer perceptron and logistic regression [33]. SVMs, on the other hand, have been shown to be less successful than other machine learning algorithms in recent research [34][35], including two publications published in 2021 that compare the effectiveness of several ML techniques.…”

Section: Support Vector Machinesmentioning

confidence: 99%

Injury Prediction in Sports using Artificial Intelligence Applications: A Brief Review

Kumar,

Reddy

et al. 2023

Journal of Robotics and Control

View full text Add to dashboard Cite

Avoiding injuries in sports has always depended on historical records and human experience. This is despite using injuries being a major and unsolvable issue. The development of more precise preventative procedures using the now available approaches has been excruciatingly sluggish. The development of artificial intelligence (AI) and machine learning (ML) as potentially valuable procedures to improve damage prevention and recovery procedures has been made possible by technological advances that have made these areas more accessible. This article presents a detailed summary of ML approaches as they have been used to predict and anticipate sports injuries to this point in time. The research conducted over the last five years has been collated, and its results have been untaken. Assuming the present absence of accessible sources, standardized statistics, and a dependence on obsolete deterioration prototypes, it is impossible to draw any definitive conclusions regarding the real-world effectiveness of machine learning in terms of its application to the prediction of sports injuries. However, it has been hypothesized that resolving these two problems would make it possible to deploy innovative, strong machine-learning architectures, which will hasten the process of increasing the state of this area while also offering proven clinical tools.

show abstract

“…These were the main subject of several studies and, although the main objective was not to predict the final result, some of them were focused on analyzing the impact of the weather on different features of the game, such as the distances run by players, injuries, successful passes, etc. For example, Landset et al [12] tried to analyze the occurrence of injuries by considering weather conditions and the playing surface. They applied nine classifiers, and the results showed that SVM outperformed other methods.…”

Section: Introductionmentioning

confidence: 99%

The Effect of Weather in Soccer Results: An Approach Using Machine Learning Techniques

et al. 2020

View full text Add to dashboard Cite

The growing popularity of soccer has led to the prediction of match results becoming of interest to the research community. The aim of this research is to detect the effects of weather on the result of matches by implementing Random Forest, Support Vector Machine, K-Nearest Neighbors Algorithm, and Extremely Randomized Trees Classifier. The analysis was executed using the Spanish La Liga and Segunda division from the seasons 2013–2014 to 2017–2018 in combination with weather data. Two tasks were proposed as part of this study: the first was to find out whether the game will end in a draw, a win by the hosts or a victory by the guests, and the second was to determine whether the match will end in a draw or if one of the teams will win. The results show that, for the first task, Extremely Randomized Trees Classifier is a better method, with an accuracy of 65.9%, and, for the second task, Support Vector Machine yielded better results with an accuracy of 79.3%. Moreover, it is possible to predict whether the game will end in a draw or not with 0.85 AUC-ROC. Additionally, for comparative purposes, the analysis was also performed without weather data.

show abstract

Using Weather and Playing Surface to Predict the Occurrence of Injury in Major League Soccer Games: A Case Study

Cited by 4 publications

References 19 publications

An Overview of Machine Learning Applications in Sports Injury Prediction

An Overview of Machine Learning Applications in Sports Injury Prediction

Injury Prediction in Sports using Artificial Intelligence Applications: A Brief Review

The Effect of Weather in Soccer Results: An Approach Using Machine Learning Techniques

Contact Info

Product

Resources

About