2024, Retos, 58, 1125-1133

© Copyright: Federación Española de Asociaciones de Docentes de Educación Física (FEADEF) ISSN: Edición impresa: 1579-1726. Edición Web: 1988-2041 (https://recyt.fecyt.es/index.php/retos/index)

Forecasting sports-related injuries using wearable devices and data analysis methods
Pronóstico de lesiones relacionadas con el deporte mediante el uso de dispositivos vestibles y métodos
de análisis de datos
*Moldir Kizdarbekova, **Balnur Kenjayeva, ***Mirambek Murzabekov
*Khoja Akhmet Yassawi International Kazakh-Turkish University (Kazakhstan), **International University of Tourism and
Hospitality (Kazakhstan), ***Korkyt Ata Kyzylorda University (Kazakhstan)

Resumen. Este estudio investiga la eficacia de la tecnología vestible en la predicción de las tasas de lesiones entre los atletas, centrán-
dose tanto en lesiones menores como en lesiones graves. Durante un período de 20 semanas, 80 estudiantes de cultura física fueron
divididos en un grupo experimental, que utilizó dispositivos vestibles para el monitoreo de datos en tiempo real, y un grupo de control
que empleó métodos de entrenamiento tradicionales. El estudio utilizó una gama de sensores vestibles para recopilar datos fisiológicos
y biomecánicos completos, que fueron analizados utilizando herramientas personalizadas basadas en Python. Los resultados indicaron
una reducción significativa en las lesiones menores dentro del grupo experimental, confirmando la hipótesis de que la tecnología vestible
puede disminuir la incidencia de lesiones a través de ajustes de entrenamiento personalizados. Sin embargo, el impacto en las lesiones
graves no fue estadísticamente significativo, destacando las limitaciones de la tecnología para predecir y prevenir lesiones agudas. Esta
investigación subraya el potencial de los dispositivos vestibles para mejorar la seguridad de los atletas a través de percepciones basadas
en datos, pero también señala la necesidad de realizar más estudios para comprender y aprovechar completamente la tecnología en la
prevención de lesiones más graves. Los hallazgos tienen implicaciones importantes para la ciencia deportiva, sugiriendo un cambio de
paradigma hacia regímenes de entrenamiento más integrados tecnológicamente para optimizar los resultados de salud y el rendimiento
en las poblaciones atléticas.
Palabras clave: tecnología vestible, prevención de lesiones en atletas, monitoreo de datos en tiempo real, ciencia deportiva, análisis
de datos biomecánicos, lesiones menores, lesiones graves, ajustes personalizados de entrenamiento.

Abstract. This study investigates the effectiveness of wearable technology in predicting injury rates among athletes, focusing on both
micro and severe injuries. Over a 20-week period, 80 physical culture students were divided into an experimental group, using wear-
able devices for real-time data monitoring, and a control group employing traditional training methods. The study utilized a range of
wearable sensors to collect comprehensive physiological and biomechanical data, which was analyzed using custom Python-based tools.
Results indicated a significant reduction in micro injuries within the experimental group, affirming the hypothesis that wearable tech-
nology can decrease injury incidence through personalized training adjustments. However, the impact on severe injuries was not sta-
tistically significant, highlighting the technology's limitations in predicting and preventing acute injuries. This research underscores the
potential of wearable devices to enhance athlete safety through data-driven insights but also points to the need for further studies to
fully understand and leverage technology in preventing more serious injuries. The findings have important implications for sports
science, suggesting a paradigm shift towards more technologically integrated training regimes to optimize health outcomes and perfor-
mance in athletic populations.
Keywords: wearable technology, athlete injury prevention, real-time data monitoring, sports science, biomechanical data analysis,
micro injuries, severe injuries, personalized training adjustments.

Fecha recepción: 01-08-24. Fecha de aceptación: 10-08-24

Balnur Kenjayeva
[email protected]

Introduction analytics allows for the identification of patterns and risk

factors associated with injuries, enabling timely interven-
Sports and physical activities are integral to maintaining tions (Sprouse et al., 2024; Tursynova et al., 2022).
a healthy lifestyle; however, they are often accompanied by The predictive power of wearable technology is under-
the risk of injuries that can have long-term consequences on pinned by its ability to monitor subtle changes in perfor-
the well-being and economic situation of athletes (Reid et mance and biomechanics, which often precede the onset of
al., 2022). The incidence and severity of sports-related in- injuries (Kim et al., 2024). By analyzing these changes, re-
juries have spurred significant research into preventive searchers can identify when an athlete is at a higher risk of
strategies. Among these, wearable technology has emerged injury due to factors such as fatigue, improper form, or ex-
as a promising tool to mitigate injury risks through real- cessive load (Thomas et al., 2023; Okilanda et al., 2024).
time monitoring and data analytics (Davies et al., 2024). This proactive approach to injury prevention is critical in
Wearable technology in sports has rapidly evolved, of- sports, where the physical demands can vary significantly
fering unprecedented opportunities to gather extensive data across different disciplines and levels of competition (Qi et
on athlete performance and physiological responses in real- al., 2024).
time (Omarov et al., 2022). These devices are capable of Moreover, the quantification of mechanical loads and
capturing a wide range of biometric and kinematic data, in- their correlation with injury risks has been extensively stud-
cluding heart rate, acceleration, and muscle activity, which ied. High mechanical loads, especially when coupled with
are crucial for assessing the athlete’s condition and predict- poor conditioning or inadequate recovery, significantly
ing potential injury risks (Kárason et al., 2024; Tursynova contribute to the risk of injury (Marco et al., 2024;
et al., 2023). The integration of this data through advanced Kusmiyati et al., 2024). Wearable technology facilitates the

-1125- Retos, número 58, 2024 (septiembre)

2024, Retos, 58, 1125-1133
© Copyright: Federación Española de Asociaciones de Docentes de Educación Física (FEADEF) ISSN: Edición impresa: 1579-1726. Edición Web: 1988-2041 (https://recyt.fecyt.es/index.php/retos/index)

measurement of these loads in real-world training and com- reviews the literature on the application of wearable tech-
petitive environments, providing insights that can guide the nology in sports, focusing on injury prediction and preven-
design of training programs that balance performance im- tion.
provement with injury prevention (Nagorna et al., 2024; Early studies on wearable technology in sports primarily
Moral Moreno et al., 2024). focused on basic biometric monitoring, such as heart rate
The role of body mass index (BMI) in sports injuries is and caloric expenditure (Del-Valle-Soto et al., 2024).
well-documented; however, it is important to note that a However, the scope has significantly expanded to include
higher BMI does not always signify increased fat mass, as it biomechanical and physiological data collection, which are
can also reflect greater muscle mass, particularly in athletes. more directly relevant to injury prevention (Yang et al.,
This distinction is crucial because a high muscle mass BMI 2024). For instance, Tan et al. (2023) demonstrated that
may not necessarily elevate injury risk in the same way that wearable sensors could accurately measure joint angles and
a high fat mass BMI does. It can even confer certain protec- muscle forces, which are critical indicators of potential in-
tive benefits against injuries due to stronger musculoskele- jury.
tal support (Cleary, 2024; Kumar et al., 2024). Therefore, A significant advancement in the field was highlighted
while wearable devices offer a novel approach to monitor by Chang et al. (2023), who used accelerometers to predict
the impacts of BMI on athlete performance and injury risk, the onset of fatigue, a key risk factor for injuries in athletes.
their application must be carefully calibrated to differenti- Similarly, Hannay et al. (2024) utilized wearable GPS units
ate the type of mass contributing to BMI. This ensures the to track athletes' movements and identify patterns that pre-
development of personalized training and intervention pro- cede common injuries like hamstring strains. These studies
grams that are truly reflective of an individual athlete’s underscore the potential of wearables not only to monitor
health profile (Neal et al., 2024). health but also to act as a preventive tool by providing ac-
In this study, we focus on a cohort of 80 physical culture tionable insights.
students, utilizing wearable technology to collect and ana- The integration of data analytics with wearable technol-
lyze data relevant to sports injury prevention. This ap- ogy has further enhanced the ability to predict sports inju-
proach not only aids in understanding the specific injury ries. Rahlf et al. (2022) applied machine learning algorithms
mechanisms but also in developing targeted interventions to data collected from wearables to identify athletes at high
that can significantly reduce the incidence of injuries. The risk of ligament injuries. Their approach allowed for real-
findings from this study are expected to contribute to the time risk assessment and the implementation of preventa-
growing body of literature on the effectiveness of wearable tive measures. This predictive capability was extended by
technology in sports, specifically in relation to injury pre- Ren et al. (2024), who used a combination of artificial in-
vention and management. telligence and wearable data to develop models that forecast
The integration of wearable technology into sports injuries based on training load data and physiological re-
practices offers a dynamic and effective strategy to en- sponses.
hance athlete safety and performance. Through continu- Mechanical load monitoring, particularly through de-
ous monitoring and data-driven insights, it is possible to vices that measure force and torque, has been identified as
create more tailored and effective training programs that crucial for injury prevention. Scott et al. (2023) found a
reduce injury risks while optimizing performance (Rebelo correlation between mechanical overload and the occur-
et al., 2023; Ribeiro Neto et al., 2023). The current study rence of overuse injuries in runners. Wearables that meas-
aims to expand on these themes, providing empirical evi- ure these loads help coaches and therapists design training
dence to support the use of wearable technology in fore- regimens that optimize performance while minimizing in-
casting sports-related injuries. jury risks (Altayeva et al., 2016; Wells et al., 2023).
In this paper, we will explore how wearable technolo- The influence of body composition on injury risk has
gies can be effectively implemented to monitor, predict, been extensively explored, highlighting nuanced outcomes
and prevent sports injuries, thus enhancing the health out- based on body type. Hardaker et al. (2024) noted that ath-
comes and athletic performance of athletes across various letes with a higher BMI are generally more susceptible to
sports disciplines. This research contributes to the field by joint injuries due to increased mechanical stress. However,
offering a comprehensive analysis of how data gathered it is crucial to differentiate between BMI contributions from
from wearable devices can be utilized to make significant fat and muscle mass. Athletes with greater muscle mass
advancements in sports injury management. might not experience the same injury risk, as their enhanced
musculature could actually mitigate certain mechanical
Related Works stresses. Anam et al. (2024) utilized wearables to monitor
changes in athletes' body composition, tailoring training
The intersection of sports science and technology has programs to ensure that mechanical loads were adapted to
grown substantially over the past decade, driven by ad- each athlete’s specific physical condition, thus reducing in-
vancements in sensor technology, data analytics, and the jury rates.
increasing need for personalized athlete care. This section Recent shifts in monitoring practices have favored a ho-

-1126- Retos, número 58, 2024 (septiembre)

2024, Retos, 58, 1125-1133
© Copyright: Federación Española de Asociaciones de Docentes de Educación Física (FEADEF) ISSN: Edición impresa: 1579-1726. Edición Web: 1988-2041 (https://recyt.fecyt.es/index.php/retos/index)

listic approach where multiple variables are analyzed con- gender, was thoroughly documented to ensure a compre-
currently to provide a comprehensive assessment of injury hensive evaluation of the impact of wearable technology on
risk. Keogh et al. (2023) integrated data from various sen- injury prevention across different physical profiles and
sors to examine the effects of fatigue, biomechanical sporting activities. This specification aims to enhance the
stresses, and physiological factors. Their multidimensional understanding of the study's context and the applicability of
approach not only enhances the prediction of injury likeli- its findings. This study was approved by the University’s
hood but also deepens the understanding of how diverse fac- Ethics Committee, and all participants provided written in-
tors, including muscle mass, interact to influence injury formed consent.
risk. This approach acknowledges the complexity of inter-
preting high BMI in athletes, emphasizing the importance of Wearable Technology and Data Collection
context-specific evaluations to accurately assess injury vul- Participants were equipped with advanced wearable de-
nerabilities. vices capable of recording data at a high resolution of 1 kHz,
The role of wearables in rehabilitation and return-to- translating to measurements at millisecond intervals. These
play decisions has also been a focus of recent research. devices were selected for their ability to comprehensively
Cheng and Bergmann (2022) utilized wearable sensors to monitor a broad spectrum of physiological and biomechan-
monitor athletes' recovery from injuries, providing data ical metrics. The recorded parameters included electrocar-
that helped tailor rehabilitation exercises and reduce the diograms (ECG), respiratory rate, accelerometry, as well
risk of re-injury. This application is crucial in ensuring ath- as time-stamped geographical location data.
letes do not return to play prematurely, which is a common The software integrated within these devices pro-
cause of injury relapse (Nassis et al., 2023). cessed and interpreted additional biometric data such as
Despite these advancements, challenges remain in the heart rate variability (HRV), heart rate (HR), estimated
widespread adoption of wearable technology in sports. Is- core body temperature, total caloric expenditure, pos-
sues such as data privacy, sensor accuracy, and the integra- ture, activity levels, and various other physiological and
tion of data into actionable strategies are areas that require mechanical loads. This included data on jumps, sprints,
further research and development (Finkenzeller et al., mechanical impacts, peak forces, and GPS-based metrics
2022; Darbandi et al., 2023; Omarov et al., 2024). More- such as speed, distance, and altitude.
over, the economic aspects of implementing these technol-
ogies at different levels of sport—from amateur to profes- Data Analysis Tools
sional—must be considered (Doskarayev et al., 2023). For the analysis of the collected data, we utilized a cus-
The literature demonstrates substantial progress in the tom-developed Python-based tool. This tool facilitated
use of wearable technology for injury prediction and pre- the parsing, visualization, and statistical analysis of the
vention in sports. As sensor technology improves and be- data. It was specifically designed to handle large datasets
comes more cost-effective, and as data analytics techniques generated by the wearable devices, allowing for real-time
become more sophisticated, the potential of wearables to data processing and reporting.
enhance athlete care and performance is vast (Kazanskiy et
al., 2024; Stessens et al., 2024). However, for these tech- Statistical Methods
nologies to be fully effective, they must be integrated into a Descriptive statistics were used to summarize the de-
holistic approach that considers the physical, psychological, mographic and baseline characteristics of the participants.
and tactical aspects of sports performance (Zhang et al., Inferential statistical methods, including multivariate re-
2023). Future research should continue to address these gression analysis, were employed to identify the relation-
challenges, focusing on the integration of multidimensional ships between various recorded parameters and the inci-
data and the development of predictive models that are tai- dence of sports-related injuries. The significance level was
lored to individual athlete needs and sports disciplines. set at p < 0.05.

Materials and Methods Data Collection Strategy

In this study, data collection spanned a period of 20
Study Design and Participants weeks, from January 8, 2024, to May 26, 2024. During
Thank you for your insightful feedback regarding the de- this time, participants were scheduled to engage in orga-
mographic specifics of our study cohort. We have clarified nized physical exercise sessions three times per week,
that the study involved 80 physical culture students from with each session designed to last 120 minutes. To ensure
International Kazakh-Turkish University, comprising 50 the reliability of the data regarding physical activity levels,
boys and 30 girls, aged between 18 and 25. These students participants were also monitored for any additional physi-
participated in a variety of sports, including track and field, cal activity outside of these structured sessions. This mon-
basketball, soccer, and gymnastics, reflecting a diverse mix itoring was achieved through the continuous use of wear-
of disciplines that enrich our analysis. The detailed demo- able devices, which tracked their overall daily activity lev-
graphic information, including age, weight, height, and els and ensured that no significant unreported physical ac-

-1127- Retos, número 58, 2024 (septiembre)

2024, Retos, 58, 1125-1133
© Copyright: Federación Española de Asociaciones de Docentes de Educación Física (FEADEF) ISSN: Edición impresa: 1579-1726. Edición Web: 1988-2041 (https://recyt.fecyt.es/index.php/retos/index)

tivities were conducted that could skew the study's out- were based on standard practices that did not incorporate
comes. real-time data or personalized adjustments. This group
To monitor and analyze physiological and biomechan- served as a baseline to assess the effectiveness of using wear-
ical parameters, each participant was assigned a designated able technology in reducing injuries.
wearable device. These devices were individually num- The comparison between these two groups provided a
bered and attached to their respective participants for the clear framework to evaluate the hypothesis that wearable
duration of the study. Data from each device were automat- devices significantly contribute to the reduction of injury
ically recorded in separate files after every exercise session, incidence among athletes by allowing for data-driven ad-
ensuring the integrity and accuracy of the information col- justments to their physical training.
lected.
This systematic approach to data collection ensured that Data Analysis Results
information on each participant was organized and readily In this study, we utilized a BMI threshold of 26.5 as the
accessible for analysis, which is critical for achieving the ob- demarcation for pre-obesity. The chart depicted in Figure 1
jective results of the research. illustrates the relationship between mechanical load and
Body Mass Index (BMI) in predicting the risk of concussion.
Data Security and Privacy It highlights two distinct groups based on BMI: participants
Given the sensitive nature of the biometric data col- with a BMI of less than 26.5, and those with a BMI of 26.5
lected, stringent data security measures were implemented. or greater, according to the World Health Organization's
All participant data were anonymized and encrypted to en- classification standards (World Health Organization,
sure confidentiality. Access to the data was restricted to au- 2010).
thorized personnel only, and all data analyses were per- The data shows a clear interaction between BMI and me-
formed on secure, university-maintained servers. chanical load in terms of injury risk, as evidenced by the
In summary, this section outlines the comprehensive non-parallel nature of the lines on the graph. For partici-
methodology employed in this study to evaluate the effec- pants with a BMI ≥ 26.5, the probability of sustaining a con-
tiveness of wearable technology in predicting and prevent- cussion increases significantly with higher mechanical loads.
ing sports-related injuries among university athletes. By Specifically, at a mechanical load of less than 100.09, the
combining high-resolution data collection with advanced percentage of concussed participants is 0.0%, which esca-
analytical techniques, the study aims to contribute valuable lates dramatically to 54.5% when the mechanical load ex-
insights into the dynamics of sports injuries and their pre- ceeds 100.09.
vention.

Results

In the study, two groups were employed to rigorously

test the impact of wearable devices on injury prevention
among athletes during physical activities. The experimental
group and the control group were structured as follows:
Experimental Group: Participants in this group were
equipped with wearable devices throughout the duration of
the study. These devices collected real-time data on various
physiological metrics such as heart rate, biomechanical
load, muscle activity, and more. Based on the data col-
lected, participants received tailored recommendations to Figure 1. Impact of Mechanical Load and BMI on Concussion Risk in Athletes
adjust their training regimens. This adaptive approach al-
lowed for personalized adjustments to exercises, aiming to Conversely, for participants with a BMI < 26.5, the in-
optimize performance and minimize injury risk. crease in concussion risk with greater mechanical load is less
The allocation of participants to the experimental and pronounced. The chart shows a more moderate increase
control groups was conducted through a randomized pro- from 0.0% at lower mechanical loads to 16.7% at higher
cess to ensure the validity and integrity of the study out- loads. This suggests that while higher mechanical loads do
comes. Randomization was achieved using a computer-gen- increase the risk of concussion, the effect is substantially
erated random number sequence, thereby minimizing se- amplified by a higher BMI.
lection bias and ensuring that any differences observed be- The interaction between these two predictors—BMI
tween the groups could be attributed solely to the interven- and mechanical load—highlights the importance of consid-
tion. ering multiple factors when assessing injury risk. Partici-
Control Group: Participants in the control group ad- pants with higher BMI are more than three times more
hered to traditional training methods, without the aid of likely to sustain injuries under high mechanical load condi-
wearable technology. Their training and exercise regimens tions compared to those with lower BMI, emphasizing the

-1128- Retos, número 58, 2024 (septiembre)

2024, Retos, 58, 1125-1133
© Copyright: Federación Española de Asociaciones de Docentes de Educación Física (FEADEF) ISSN: Edición impresa: 1579-1726. Edición Web: 1988-2041 (https://recyt.fecyt.es/index.php/retos/index)

compounded risk factors. In light of your comment, we The hypothesis testing involves a systematic examina-
have further analyzed the athletic background of the partic- tion of the collected data to determine if the use of wearable
ipants to assess whether their BMI might reflect higher mus- technology can be statistically linked to a decrease in the
cle mass rather than excess body fat. This distinction is crit- frequency and severity of sports-related injuries. This anal-
ical, as muscular athletes might present with a higher BMI ysis will help in substantiating or refuting the proposed ben-
without necessarily experiencing the associated increased efits of wearable devices in sports settings.
risk of injury typical of higher fat mass. This clarification
helps refine our understanding of BMI as a risk factor, en- Table 1.
Group Statistics for testing the Hypothesis I to test Micro Injury Rate
suring that our conclusions more accurately reflect the nu- Std. Std.
F Group N Mean
ances of physical composition among athletes. Deviation Error Mean
In summary, the analysis from this chart reveals that 2.243 Experimental Group 40 30.63 16.423 2.597
Control Group 40 48.68 23.685 3.745
both BMI and mechanical load are crucial predictors of con-
cussion risk, but their impact is not uniform across all lev-
Table 1 provides a statistical summary for each group
els. This interaction suggests the need for targeted preven-
involved in the study—the Experimental Group and the
tion strategies that account for both mechanical load and Control Group. The groups consisted of 40 participants
BMI to effectively reduce the risk of sports-related injuries.
each. The mean micro injury rate for the Experimental
Group, which used wearable devices, was significantly
Hypothesis Testing
lower at 30.63 compared to 48.68 in the Control Group,
In the pedagogical experiments conducted within the which followed traditional training methods. The standard
scope of this study, we explore the efficacy of wearable de- deviation, which measures the amount of variation or dis-
vices in mitigating injury risks among athletes engaged in persion from the mean, was also lower in the Experimental
physical activities. The central hypothesis tested is as fol-
Group (16.423) than in the Control Group (23.685). The
lows: standard error mean, which indicates the accuracy of the
Hypothesis (H1): The utilization of wearable devices
sample mean as an estimate of the population mean, was
significantly contributes to the reduction of injury incidence also lower in the Experimental Group (2.597) compared to
among athletes during physical activities.
the Control Group (3.745). These statistics suggest that the
To rigorously test this hypothesis, the following null hy-
use of wearable devices might be associated with a reduced
pothesis is posited: rate of micro injuries compared to traditional training
Null Hypothesis (H0): The utilization of wearable de-
methods.
vices does not contribute to the reduction of injury inci-
dence among athletes during physical activities.

Table 2.
Independent Samples Test Results to Test Micro Injury Rate
Levene’s Test for
Equality of t-test for Equality of Means
Variances
95% Confidence Interval
Sig. Mean Std. Error
F Sig. t df of the Difference
(2-tailed) Difference Difference
Lower Upper
Micro Injury Equal variances 9.42
.003 -3.961 78 .000 -18.050 4.557 -27.123 -8.977
Rate assumed 6
Equal variances
-3.961 69.461 .000 -18.050 4.557 -27.140 -8.960
not assumed

Table 2 outlines the results of the statistical tests per- standard error of this difference is 4.557, which further
formed to compare the micro injury rates between the two supports the robustness of the observed difference.
groups. The Levene’s Test for Equality of Variances re- The 95% confidence interval for the mean difference
sulted in an F value of 9.426 with a significance level of ranges from -27.140 to -8.960, confirming that the differ-
.003, indicating that the variances of the micro injury rates ence is not only statistically significant but also practically
for the two groups are not equal. Consequently, the appro- significant. This interval does not straddle zero, reinforcing
priate results to consider are those under the "Equal vari- that the mean injury rate for the Experimental Group is
ances not assumed" row. lower than that for the Control Group, and the use of wear-
The t-test for Equality of Means under this condition able technology contributes significantly to reducing the in-
shows a t-statistic of -3.961 with 69.461 degrees of free- jury rates among athletes.
dom and a p-value of .000. This highly significant result The data from Tables 1 and 2 provide robust statistical
strongly suggests that there is a statistically significant dif- evidence supporting the hypothesis that the use of wearable
ference in the mean micro injury rates between the two devices in athletic training significantly reduces the inci-
groups, with the Experimental Group showing lower injury dence of micro injuries compared to traditional training
rates as indicated by a mean difference of -18.050. The methods. Table 3 presents the statistics for the big injury

-1129- Retos, número 58, 2024 (septiembre)

2024, Retos, 58, 1125-1133
© Copyright: Federación Española de Asociaciones de Docentes de Educación Física (FEADEF) ISSN: Edición impresa: 1579-1726. Edición Web: 1988-2041 (https://recyt.fecyt.es/index.php/retos/index)

rates between the Experimental Group, which utilized

Table 3.
wearable devices, and the Control Group, which followed Group Statistics for testing the Hypothesis I to test Big Injury Rate
traditional training methods. Both groups consisted of 40 F Group n Mean
Std. Std. Error
participants each. The mean big injury rate for the Experi- Deviation Mean
2.243 Experimental Group 40 3.58 2.374 .375
mental Group was 3.58, lower than the mean of 4.65 ob- Control Group 40 4.65 2.486 .393
served in the Control Group. The standard deviations, in-
dicating the variability of injury rates within each group,
were relatively similar, with the Experimental Group at
2.374 and the Control Group at 2.486. The standard error
mean, reflecting the precision of the group means as esti-
mates of the population means, was also comparable across
groups (0.375 for the Experimental Group and 0.393 for
the Control Group).

Table 4.
Independent Samples Test Results to Test Big Injury Rate
Levene’s Test for
Equality of t-test for Equality of Means
Variances
95% Confidence Interval
Mean Std. Error
F Sig. t df Sig. (2-tailed) of the Difference
Difference Difference
Lower Upper
Micro Injury Equal variances
.011 .916 -1.978 78 .051 -1.075 .544 -2.157 .007
Rate assumed
Equal variances
-1.978 77.833 .051 -1.075 .544 -2.157 .007
not assumed

The analysis in Table 4 includes the results from the Discussion

Levene’s Test for Equality of Variances and the t-test for
Equality of Means. The Levene’s Test resulted in an F The primary objective of this research was to evaluate
value of 0.011 with a significance (Sig.) value of 0.916, the impact of wearable technology on reducing injury rates
suggesting that the variances of big injury rates between among athletes. The findings from this study offer crucial
the two groups are equal, thus, the analysis assumes equal insights into the potential benefits of integrating advanced
variances. monitoring tools into athletic training routines. Here, we
The t-test for Equality of Means under the assumption discuss the implications of these results, compare them
of equal variances shows a t-value of -1.978 with 78 de- with existing literature, and explore the practical applica-
grees of freedom and a p-value (Sig. 2-tailed) of 0.051. tions and limitations of our findings.
This p-value is marginally above the conventional thresh-
old of 0.05, suggesting that the difference in mean big in- Interpretation of Findings
jury rates between the groups approaches but does not Our study demonstrated a statistically significant re-
reach statistical significance. The mean difference be- duction in micro injury rates in athletes using wearable
tween the groups is -1.075, with a standard error of the devices compared to those who adhered to traditional
difference at 0.544. training methods. The experimental group, which utilized
The 95% confidence interval for the mean difference wearable technology, showed a notable decrease in injury
of big injury rates ranges from -2.157 to 0.007. The con- incidence, confirming our hypothesis that wearable de-
fidence interval includes zero, which implies that while vices can play a critical role in injury prevention.
the mean big injury rate for the Experimental Group is However, the results concerning big injury rates did
lower, the difference is not statistically significant at the not reach statistical significance, though they did indicate
5% level. However, the interval being very close to zero a trend towards injury reduction in the experimental
suggests a potential practical significance, warranting fur- group. This suggests that while wearable technology can
ther investigation or a larger sample size to confirm these significantly impact certain types of injuries (specifically
findings. micro injuries), its effectiveness in preventing more se-
The analysis from Tables 3 and 4 indicates a trend vere injuries remains less certain. This finding echoes the
where the Experimental Group has a lower average big work of Caulfield et al. (2023), who noted that severe in-
injury rate compared to the Control Group, although this juries often result from acute, unpredictable incidents that
difference did not achieve statistical significance. The find- may not be easily mitigated through monitoring alone.
ings suggest that while the use of wearable technology may
contribute to reducing major injuries, more robust evi- Comparison with Existing Literature
dence or additional studies might be required to defini- The findings of our investigation corroborate existing
tively establish its effectiveness.

-1130- Retos, número 58, 2024 (septiembre)

2024, Retos, 58, 1125-1133
© Copyright: Federación Española de Asociaciones de Docentes de Educación Física (FEADEF) ISSN: Edición impresa: 1579-1726. Edición Web: 1988-2041 (https://recyt.fecyt.es/index.php/retos/index)

literature which suggests that wearable technology can ef- monitor a wider range of physiological and biomechanical
fectively decrease the occurrence of minor injuries in ath- indicators are also recommended. Such studies will fur-
letes through real-time monitoring and data-driven inter- ther elucidate the capabilities and limitations of wearable
ventions (Tileubay et al., 2024; Kaldarova et al., 2023; technology in enhancing athletic training and reducing in-
Omarov et al., 2023). Nonetheless, the diminished influ- jury incidence effectively.
ence on severe injuries reinforces the challenges identified
by Hawryluk and Ghajar (2021), which emphasize the in- Conclusion
herent unpredictability of acute, severe injuries that are
not as amenable to preventative strategies based on moni- In conclusion, this research has substantiated the hy-
toring. This study enriches the discourse in sports science pothesis that the implementation of wearable technology
by underscoring the differential effectiveness of wearable significantlreduces the incidence of micro injuries among
devices across various injury types. While the technology athletes by enabling real-time monitoring and personalized
shows promise in continuous health monitoring and pre- adjustments to training regimens. The statistical analysis
ventive care, its efficacy varies with the nature and sever- presented compelling evidence physical culture students
ity of potential injuries, highlighting an area ripe for fur- equipped with wearable devices experienced fewer minor
ther exploration and technological enhancement in the injuries compared to those who followed traditional train-
realm of sports medicine. ing methods. However, the impact on preventing severe in-
juries was less definitive, suggesting that while wearable
Practical Applications technology is beneficial for monitoring and potentially mit-
igating some risks, it does not entirely eliminate the occur-
The results of this study have significant practical im- rence of acute, severe injuries. These findings contribute to
plications for the field of sports medicine and athletic a nuanced understanding within the sports science commu-
training. The utilization of wearable technology, as nity about the capacities and limitations of current wearable
demonstrated, can lead to a measurable reduction in mi- technologies. The practical implications of this research are
cro injuries among athletes by facilitating the customiza- significant, offering a pathway for sports professionals to in-
tion of training regimens based on real-time physiological tegrate advanced technological tools into their training pro-
data. This capability enables sports professionals to imple- tocols to enhance athlete safety and performance. Future
ment more dynamic and responsive training strategies, research should expand on these findings by incorporating
which can be adjusted to optimize athlete health and per- a broader participant pool across varied sports disciplines
formance while minimizing injury risk. Specifically, these and employing longitudinal study designs to capture long-
devices can help in monitoring workload and recovery, term effects and further validate the effectiveness of weara-
thereby preventing overtraining and under-recovery— ble devices in a comprehensive sports setting. By continuing
common causes of injuries in sports. Furthermore, the to explore and innovate in the application of wearable tech-
data provided by wearables can also enhance injury reha- nology, the sports industry can better protect its athletes
bilitation processes by offering precise monitoring, thus and optimize their performance through data-driven in-
ensuring that athletes only return to full activity when they sights and interventions.
are truly ready. These applications underscore the trans-
formative potential of wearable technologies in advancing References
athlete care and training methodologies.
Reid, H., Ridout, A. J., Tomaz, S. A., Kelly, P., & Jones, N.
Future Directions (2022). Benefits outweigh the risks: a consensus statement on
the risks of physical activity for people living with long-term
Future research should aim to broaden the scope and conditions. British journal of sports medicine, 56(8), 427-
depth of the current study to enhance the robustness and 438.
Davies, M., Lawrence, T., Edwards, A., McKay, C., Lecky, F.
applicability of the findings. Expanding the participant
E., Stokes, K. A., & Williams, S. (2024). Sport-related major
base to include a diverse array of athletes from various trauma incidence in young people and adults in England and
sports and competitive levels would help generalize the Wales: a national registry-based study. Injury prevention,
results and ascertain the effectiveness of wearable technol- 30(1), 1-8.
ogy across different athletic disciplines. Longitudinal stud- Omarov, B., Batyrbekov, A., Suliman, A., Omarov, B., Sab-
ies extending over multiple seasons could provide more denbekov, Y., & Aknazarov, S. (2020, November). Elec-
comprehensive insights into the long-term impacts of tronic stethoscope for detecting heart abnormalities in ath-
wearable devices on injury prevention and athlete perfor- letes. In 2020 21st International Arab Conference on Infor-
mance. Additionally, integrating advanced analytical tech- mation Technology (ACIT) (pp. 1-5). IEEE.
niques, such as machine learning and predictive analytics, Kárason, H., Ritrovato, P., Maffulli, N., Boccaccini, A. R., &
Tortorella, F. (2024). Wearable approaches for non-invasive
could improve the precision of injury risk assessments de-
monitoring of tendons: A scoping review. Internet of Things,
rived from wearable data. Investigations into the develop- 101199.
ment and utilization of next-generation wearables that

-1131- Retos, número 58, 2024 (septiembre)

2024, Retos, 58, 1125-1133
© Copyright: Federación Española de Asociaciones de Docentes de Educación Física (FEADEF) ISSN: Edición impresa: 1579-1726. Edición Web: 1988-2041 (https://recyt.fecyt.es/index.php/retos/index)

Tursynova, A., Omarov, B., Tukenova, N., Salgozha, I., Khaa- Raj, R., Arias-Gonzáles, J. L., ... & Mia, M. S. (2024). Inter-
val, O., Ramazanov, R., & Ospanov, B. (2023). Deep learn- net of things sensors and support vector machine integrated
ing-enabled brain stroke classification on computed tomogra- intelligent irrigation system for agriculture industry. Dis-
phy images. Comput. Mater. Contin, 75(1), 1431-1446. cover Sustainability, 5(1), 6.
Sprouse, B., Chandran, A., Rao, N., Boltz, A. J., Johnson, M., Neal, B. S., Bramah, C., McCarthy-Ryan, M. F., Moore, I. S.,
Hennis, P., & Varley, I. (2024). Injury and illness surveillance Napier, C., Paquette, M. R., & Gruber, A. H. (2024). Using
monitoring in team sports: a framework for all. Injury epide- wearable technology data to explain recreational running in-
miology, 11(1), 23. jury: A prospective longitudinal feasibility study. Physical
Tursynova, A., Omarov, B., Sakhipov, A., & Tukenova, N. Therapy in Sport, 65, 130-136.
(2022). Brain Stroke Lesion Segmentation Using Computed Rebelo, A., Martinho, D. V., Valente-dos-Santos, J., Coelho-e-
Tomography Images based on Modified U-Net Model with Silva, M. J., & Teixeira, D. S. (2023). From data to action: a
ResNet Blocks. International Journal of Online & Biomedical scoping review of wearable technologies and biomechanical
Engineering, 18(13). assessments informing injury prevention strategies in sport.
Kim, J., Porciuncula, F., Yang, H. D., Wendel, N., Baker, T., BMC sports science, medicine and rehabilitation, 15(1), 169.
Chin, A., ... & Walsh, C. J. (2024). Soft robotic apparel to Ribeiro Neto, A., Ferreira Magalhães, L. ., Gotti Alves, R. R. .,
avert freezing of gait in Parkinson’s disease. Nature medicine, Flor Bertolini, G. R. ., Moreira Lobato, D. F. ., & Berton-
30(1), 177-185. cello, D. . (2023). Análisis de vídeo bidimensional de senta-
Thomas, C. (2023). Assessment of Physical Qualities Associated dilla sobre la cabeza: un estudio preliminar (Two-dimensional
with Multidirectional Speed. Multidirectional Speed in Sport, video analysis of the overhead squat: a preliminary study). Re-
144-167. tos, 50, 50–56. https://doi.org/10.47197/retos.v50.99340
Okilanda, A. ., Ihsan, N. ., Arnando, M., Hasan, B., Ishak, M., Del-Valle-Soto, C., Briseño, R. A., Valdivia, L. J., & Nolazco-
Mohamed Shapie, M. N. ., Tulyakul, S. ., Duwarah, T., Ah- Flores, J. A. (2024). Unveiling wearables: exploring the
med, M., & Syaputri, W. (2024). Acelerar el rendimiento: el global landscape of biometric applications and vital signs and
impacto del entrenamiento interválico con resistencia ponde- behavioral impact. BioData Mining, 17(1), 15.
rada en la mejora de la velocidad en estudiantes universitarios Yang, G., Hong, J., & Park, S. B. (2024). Wearable device for
(Revving up performance: the impact of interval training with continuous sweat lactate monitoring in sports: a narrative re-
weighted resistance on speed enhancement in university stu- view. Frontiers in Physiology, 15, 1376801.
dents). Retos, 58, 469–476. https://doi.org/10.47197/re- Tan, T., Gatti, A. A., Fan, B., Shea, K. G., Sherman, S. L.,
tos.v58.106752 Uhlrich, S. D., ... & Chaudhari, A. S. (2023). A scoping re-
Qi, Y., Sajadi, S. M., Baghaei, S., Rezaei, R., & Li, W. (2024). view of portable sensing for out-of-lab anterior cruciate liga-
Digital technologies in sports: Opportunities, challenges, and ment injury prevention and rehabilitation. NPJ Digital Medi-
strategies for safeguarding athlete wellbeing and competitive cine, 6(1), 46.
integrity in the digital era. Technology in Society, 102496. Chang, P., Wang, C., Chen, Y., Wang, G., & Lu, A. (2023).
Marco, M. K. D., Goods, D. P., Baldwin, D. K., Hiscock, D. Identification of runner fatigue stages based on inertial sensors
D., & Scott, A. P. B. (2024). Resistance Training Prescrip- and deep learning. Frontiers in Bioengineering and Biotech-
tion For Athletes During Periods Of Planned De-Loading: A nology, 11, 1302911.
Survey Of Strength And Conditioning Coaches. Journal of Hannay, W. M., Sliepka, J. M., Parker, K., Sammons, K., Gee,
Clinical Exercise Physiology, 13(s2), 355-355. A. O., Kweon, C. Y., & Hagen, M. S. (2024). Limited Re-
Kusmiyati, K., Setiawati, H., Setijono, H., Soedjatmiko, S., Kris- turn to Preinjury Performance in NCAA Division I American
tiyanto, A., & Suryadi, D. (2024). Autoeficacia de los profe- Football Players With Hamstring Injuries. Orthopaedic Jour-
sores de educación física: ¿cómo contribuye a la consecución nal of Sports Medicine, 12(5), 23259671241243345.
de los objetivos generales del deporte nacional? (Self-efficacy Rahlf, A. L., Hoenig, T., Stürznickel, J., Cremans, K.,
of physical education teachers: how does it contribute to Fohrmann, D., Sanchez-Alvarado, A., ... & Hollander, K.
achieving the overarching objectives of national sport?). Re- (2022). A machine learning approach to identify risk factors
tos, 58, 546–551. https://doi.org/10.47197/re- for running-related injuries: study protocol for a prospective
tos.v58.108159 longitudinal cohort trial. BMC sports science, medicine and
Nagorna, V., Mytko, A., Borysova, O., Potop, V., Petrenko, H., rehabilitation, 14(1), 75.
Zhyhailova, L., ... & Lorenzetti, S. (2024). Innovative tech- Ren, L., Wang, Y., & Li, K. (2024). Real-time sports injury
nologies in sports games: A comprehensive investigation of monitoring system based on the deep learning algorithm.
theory and practice. Journal of Physical Education and Sport, BMC medical imaging, 24(1), 122.
585-596. Scott, R., James, R., Barnett, C. T., Sale, C., & Varley, I.
Moral Moreno, L., Flores Ferro, E. ., & Maureira Cid, F. . (2023). Perspectives from research and practice: A survey on
(2024). Nivel de actividad física en estudiantes universitarios: external load monitoring and bone in sport. Frontiers in
un estudio comparativo España-Chile (Physical activity level Sports and Active Living, 5, 1150052.
in university students: a Spain-Chile comparative study). Re- Altayeva, A., Omarov, B., Jeong, H. C., & Cho, Y. I. (2016).
tos, 56, 188–199. https://doi.org/10.47197/re- Multi-step face recognition for improving face detection and
tos.v56.102969 recognition rate. Far East Journal of Electronics and Commu-
Cleary Jr, C. J. (2024). Evaluation of Body Composition, Skeletal nications 16(3), pp. 471-491.
Muscle Size, and Musculoskeletal Performance in Individuals Wells, L., Konoval, T., & Bruce, L. (2023). An examination of
With and Without a Previous Anterior Cruciate Ligament how and why triathlon coaches use a suite of technologies in
Reconstruction Surgery (Doctoral dissertation, University of their practice. International Journal of Sports Science &
Kansas). Coaching, 18(3), 687-694.
Kumar, G. K., Bangare, M. L., Bangare, P. M., Kumar, C. R., Hardaker, N. J., Hume, P. A., & Sims, S. T. (2024). Differences

-1132- Retos, número 58, 2024 (septiembre)

2024, Retos, 58, 1125-1133
© Copyright: Federación Española de Asociaciones de Docentes de Educación Física (FEADEF) ISSN: Edición impresa: 1579-1726. Edición Web: 1988-2041 (https://recyt.fecyt.es/index.php/retos/index)

in injury profiles between female and male athletes across the Games to Increase Motivation for Sports. International Jour-
participant classification framework: a systematic review and nal of Advanced Computer Science and Applications, 14(4).
meta-analysis. Sports medicine, 1-71. Kazanskiy, N. L., Khonina, S. N., & Butt, M. A. (2024). A re-
Anam, K., Setiowati, A., Indardi, N., Irawan, F. A., Pavlović, view on flexible wearables-Recent developments in non-in-
R., Susanto, N., ... & Setyawan, H. (2024). Functional vasive continuous health monitoring. Sensors and Actuators
movement screen score to predict injury risk of sports stu- A: Physical, 114993.
dents: a review of foot shape and body mass index. Pedagogy Stessens, L., Gielen, J., Meeusen, R., & Aerts, J. M. (2024).
of Physical Culture and Sports, 28(2), 124-131. Physical performance estimation in practice: A systematic re-
Keogh, J. A., Waddington, E. E., Masood, Z., Mahmood, S., view of advancements in performance prediction and model-
Palanisamy, A. C., Ruder, M. C., ... & Kobsar, D. (2023). ing in cycling. International Journal of Sports Science &
Monitoring lower limb biomechanical asymmetry and psy- Coaching, 17479541241262385.
chological measures in athletic populations—A scoping re- Zhang, Y., Hu, Y., Jiang, N., & Yetisen, A. K. (2023). Wearable
view. Scandinavian Journal of Medicine & Science in Sports, artificial intelligence biosensor networks. Biosensors and Bi-
33(11), 2125-2148. oelectronics, 219, 114825.
Cheng, R., & Bergmann, J. H. (2022). Impact and workload are World Health Organization. (2010, May 6). A healthy lifestyle -
dominating on-field data monitoring techniques to track WHO recommendations. World Health Organisation.
health and well-being of team-sports athletes. Physiological https://www.who.int/europe/news-room/fact-
Measurement, 43(3), 03TR01. sheets/item/a-healthy-lifestyle---who-recommendations.
Nassis, G., Verhagen, E., Brito, J., Figueiredo, P., & Krustrup, Caulfield, R., Wiseman, T., Gullick, J., & Ogilvie, R. (2023).
P. (2023). A review of machine learning applications in soc- Factors preceding occupational distress in emergency nurses:
cer with an emphasis on injury risk. Biology of sport, 40(1), An integrative review. Journal of clinical nursing, 32(13-14),
233-239. 3341-3360.
Darbandi, H., Munsters, C., Parmentier, J., & Havinga, P. Tileubay, S., Yerekeshova, M., Baiganova, A., Janyssova, D.,
(2023). Detecting fatigue of sport horses with biomechanical Omarov, N., Omarov, B., & Baiekeyeva, Z. (2024). Devel-
gait features using inertial sensors. PloS one, 18(4), opment of Deep Learning Enabled Augmented Reality
e0284554. Framework for Monitoring the Physical Quality Training of
Finkenzeller, T., Burberg, T., Kranzinger, S., Harbour, E., Future Trainers-Teachers. International Journal of Advanced
Snyder, C., Würth, S., & Amesberger, G. (2022). Effects of Computer Science & Applications, 15(3).
physical stress in Alpine skiing on psychological, physiologi- Kaldarova, B., Omarov, B., Zhaidakbayeva, L., Tursynbayev, A.,
cal, and biomechanical parameters: an individual approach. Beissenova, G., Kurmanbayev, B., & Anarbayev, A. (2023,
Frontiers in Sports and Active Living, 4, 971137. February). Applying game-based learning to a primary school
Omarov, B., Omarov, N., Mamutov, Q., Kissebaev, Z., Anarba- class in computer science terminology learning. In Frontiers
yev, A., Tastanov, A., & Yessirkepov, Z. (2024). Examina- in Education (Vol. 8, p. 1100275). Frontiers Media SA.
tion of the augmented reality exercise monitoring system as Omarov, B., Narynov, S., & Zhumanov, Z. (2023). Artificial In-
an adjunct tool for prospective teacher trainers. Retos: nuevas telligence-Enabled Chatbots in Mental Health: A Systematic
tendencias en educación física, deporte y recreación, (58), Review. Computers, Materials & Continua, 74(3).
85-94. Hawryluk, G. W., & Ghajar, J. (2021). Evolution and impact of
Doskarayev, B., Omarov, N., Omarov, B., Ismagulova, Z., Koz- the Brain Trauma Foundation guidelines. Neurosurgery,
hamkulova, Z., Nurlybaeva, E., & Kasimova, G. (2023). De- 89(6), 1148-1156.
velopment of Computer Vision-enabled Augmented Reality

Datos de los/as autores/as y traductor/a:

Moldir Kizdarbekova [email protected] Autor/a

Balnur Kenjayeva [email protected] Autor/a
Mirambek Murzabekov [email protected] Autor/a
Balnur Kenjayeva [email protected] Traductor/a

-1133- Retos, número 58, 2024 (septiembre)