Article
A Machine-Learning Approach to Measure the Anterior
Cruciate Ligament Injury Risk in Female Basketball Players
Juri Taborri
1,
* , Luca Molinaro
1,2
, Adriano Santospagnuolo
3
, Mario Vetrano
3
, Maria Chiara Vulpiani
3,4
and Stefano Rossi
1
Citation: Taborri, J.; Molinaro, L.;
Santospagnuolo, A.; Vetrano, M.;
Vulpiani, M.C.; Rossi, S. A
Machine-Learning Approach to
Measure the Anterior Cruciate
Ligament Injury Risk in Female
Basketball Players. Sensors 2021, 21,
3141. https://doi.org/10.3390/
s21093141
Academic Editor: Yvonne Tran
Received: 1 April 2021
Accepted: 28 April 2021
Published: 30 April 2021
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2021 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
1
Department of Economics, Engineering, Society and Business Organization (DEIM), University of Tuscia,
01100 Viterbo, Italy; luca.molinaro@unitus.it (L.M.); stefano.rossi@unitus.it (S.R.)
2
Motustech—Sport & Health Technology c/o Marilab, Ostia Lido, 00012 Rome, Italy
3
Physical Medicine and Rehabilitation Unit, Sant‘Andrea Hospital, “Sapienza” University of Rome,
00189 Rome, Italy; adrianosantospagnuolo1@hotmail.it (A.S.); mario.vetrano@uniroma1.it (M.V.);
mariachiara.vulpiani@gmail.com (M.C.V.)
4
Sports Medicine Institute CONI Rome, 00197 Rome, Italy
* Correspondence: juri.taborri@unitus.it; Tel.: +39-07-6135-7049
Abstract:
Anterior cruciate ligament (ACL) injury represents one of the main disorders affecting
players, especially in contact sports. Even though several approaches based on artificial intelligence
have been developed to allow the quantification of ACL injury risk, their applicability in training
sessions compared with the clinical scale is still an open question. We proposed a machine-learning
approach to accomplish this purpose. Thirty-nine female basketball players were enrolled in the
study. Leg stability, leg mobility and capability to absorb the load after jump were evaluated through
inertial sensors and optoelectronic bars. The risk level of athletes was computed by the Landing Error
Score System (LESS). A comparative analysis among nine classifiers was performed by assessing the
accuracy, F1-score and goodness. Five out nine examined classifiers reached optimum performance,
with the linear support vector machine achieving an accuracy and F1-score of 96 and 95%, respectively.
The feature importance was computed, allowing us to promote the ellipse area, parameters related to
the load absorption and the leg mobility as the most useful features for the prediction of anterior
cruciate ligament injury risk. In addition, the ellipse area showed a strong correlation with the LESS
score. The results open the possibility to use such a methodology for predicting ACL injury.
Keywords:
machine learning; inertial sensors; basketball; ACL injury; leg stability; leg mobility; load
absorption; Landing Error Scoring System
1. Introduction
Basketball is one of the most widespread team sports with more than 450 million
amateur and professional players in the world [
1
]. During both training sessions and
competitions, athletes are asked to perform dynamic movements, requiring also physical
contact between players. Moreover, basketball is a vertical sport, which requires jump-
ing and landing activities two or three times more often than other team games, such
as soccer and volleyball [
2
]. These aspects lead to a high incidence of injuries among
basketball players; specifically, the knee joint has been demonstrated as the most com-
monly stressed and injured body area [
3
]. Among others, anterior cruciate ligament (ACL)
rupture can be considered as the most debilitating injury, often leading to extended rest
periods before the return to play [
4
]. In addition, ACL injury, together with ankle sprains,
has the main incidence in female basketball players; in fact, 16% of them may incur an
ACL injury during their career. It is worth highlighting, as the risk of ACL rupture in
female players is up to eight times more than male players [
5
]. The treatment of ACL
injury always requires reconstructive surgery, which leads to the absence from playing
field for at least six months, and a rehabilitation program that may be not sufficient to
Sensors 2021, 21, 3141. https://doi.org/10.3390/s21093141 https://www.mdpi.com/journal/sensors
