Invisible Monitoring for Athlete Health and Performance: A Call for a Better Conceptualization and Practical Recommendations

Click name to view affiliation

Cedric Leduc Center for Human Performance, Carnegie School of Sport, Leeds Beckett University, Leeds, United Kingdom

Search for other papers by Cedric Leduc in
Current site
Google Scholar
PubMed
Close
https://orcid.org/0000-0002-8054-546X *
and
Daniel Weaving Department of Sport and Physical Activity, Faculty of Arts and Sciences, Edge Hill University, Ormskirk, United Kingdom
Applied Sports Science and Exercise Testing Laboratory, University of Newcastle, Ourimbah, NSW, Australia

Search for other papers by Daniel Weaving in
Current site
Google Scholar
PubMed
Close
https://orcid.org/0000-0002-4348-9681
Free access

Background: Practices to routinely monitor athletes are rapidly changing. With the concurrent exponential rise in wearable technologies and advanced data analysis, tracking training exposures and responses is widespread and more frequent in the athlete–coach decision-making process. Within this scenario, the concept of invisible monitoring emerged, which was initially vaguely defined as testing athletes without testing them. Despite sound practical applications and benefits (eg, reduced burden on player staff and more frequent measurement), a clear lack of constitutive definition has led to multiple cleavages in both research and practice, including ethical concerns. Purpose: The purpose of this study is to (1) extend the current conceptualization of invisible monitoring by considering subdimensions of the concept and (2) its data-related and ethical challenges and (3) provide practical considerations to implement invisible monitoring. Monitoring burden (degree of obtrusion and frequency of measurement) and the number of constructs a single measurement tool can assess have been proposed as subdimensions of the concept of invisible monitoring. Challenges include the governance and analysis of data required to make estimates, validity and reliability of an invisible monitoring measure, and communication to athletes. Conclusions: This commentary presents a first attempt to conceptualize invisible monitoring in the context of elite sport and provide subdimensions of the concept that can be used to classify choices of measurement tools. A consensus is required from both researchers and practitioners regarding its definition and operationalization to optimize current monitoring services to elite athletes.

In elite sport performance, developments in technology including hardware (eg, miniaturization) and software (eg, data analysis techniques) have opened appealing possibilities to monitor athletes over time. Their application has primarily focused on 3 key constructs: training exposure (both external and internal) and the acute and chronic effects of training (both positive and negative).1 Yet, despite technological advancements, practitioners still face numerous challenges, such as logistical constraints (eg, fixture scheduling), a lack of buy-in (from players and coaches), and evidence of efficacy toward improving training prescription or performance.2 While monitoring training exposure is generally accepted to be practically feasible, numerous studies have discussed the challenges with estimating training effects regularly.2,3 These barriers might restrict our understanding of the training process. To mitigate these limitations, an emerging concept termed “invisible monitoring” was proposed and is gaining popularity.4

Initially, invisible monitoring was described in a blog post as “gathering as much information about the athlete, their performance, and their current training status without them even knowing you’re doing it.”4 Recently, Weakley et al5 expanded this description as “testing athletes as they train and perform without specific intervention.” This has since received significant attention on social media6 and now within peer-reviewed publications (Supplementary Material S1 [available online]713). Developing invisible monitoring methods are attractive to practitioners to minimize burden on players (eg, performing a maximal effort or repeatedly completing the same questionnaire) and staff (eg, time-consuming collection and analysis of data). By minimizing assessment interventions and using data observed during training and matches, it could also help to increase the frequency of assessment thereby increasing individual player observations within observational designs and better facilitating statistical analyses (eg, n-of-1 trials study design, regression discontinuity, and real world causal inference) that allow a greater understanding of the dose–response relationship within the training process.

However, there are concerns regarding athletes’ perceptions of invisible monitoring, and their role within this generating process, and the overall use and management of the data.13 Given the advancement in technology across fields, the concept of invisible monitoring is not unique to sport and has been discussed in other fields such as healthcare where other concepts (ie, unobtrusive monitoring) have been developed and could be useful for our field.14,15 However, despite its increasing popularity in sport, this concept requires further conceptualization and consideration of the ethical and data management/analysis challenges associated with “invisibly” monitoring athletes.

Therefore, the aim is to (1) extend the current conceptualization of invisible monitoring by considering subdimensions of the concept, (2) discuss its data-related and ethical challenges, and finally, (3) provide practical considerations to implement invisible monitoring in elite sport organizations. It is hoped that this can assist practitioners to evaluate the extent that a measurement tool can be used to “invisibly” monitor athletes and for practitioners to critically consider their role within this generative process.

Conceptualization of Invisible Monitoring

It is possible that the lack of an elaboration of the concept of invisible monitoring has led to some cleavages (Supplementary Material S1 [available online]). As a conceptual framework aims to inform future research and act as a reference guide in practical settings,13 it is likely an elaboration would enhance current invisible monitoring practices and avoid future misconceptions.

Our attempt to improve the initial conceptualization and operationalization of invisible monitoring from the available body of knowledge16 is summarized in Table 1 and Figure 1. While an initial conceptualization of the concept has been proposed, such dimensions require a consensus and further investigation (ie, Delphi Study). This conceptualization includes the main subdimensions of monitoring burden (the interaction between frequency and degree of obtrusion of a measurement) and the number of constructs a measurement tool can measure.

Table 1

Definitions of Label Constructs

Label of the construct or conceptDefinitions
Invisible monitoringConstitutive definition: Invisible monitoring is a set of techniques and associated data analysis allowing the measurement of a single or multiple training effects using a single or combination of measurement tool with a minimal degree of burden to athlete and staff.
Operational definition: Collecting and assessing athlete status-related data by minimizing inconveniences to practice and potentially everyday life while optimizing data analysis by evaluating multiple constructs from a single measurement tool.
Monitoring burdenConstitutive definition: Monitoring burden represent the temporal and logistical constraints induced when using a monitoring techniques.
Operational definition: Monitoring burden is equal to the frequency of measurement and the degree of obtrusion induced by the monitoring technique used.
Degree of obtrusionConstitutive definition: Extent to what a measurement tool might disrupt daily operations such as training.
Operational definition: The degree of obtrusion can be assessed by the amount of time a measurement tool disrupt training practice or could be rated arbitrarily from low to high by practitioners for example.
Frequency of measurementConstitutive definition: Capacity of a measurement tool to be used recurrently by a practitioner to assess athlete status.
Operational definition: The frequency of a measurement tool can be assessed either objectively by the number of times a tool is used a week or rated arbitrarily by practitioners from low to high for example.
Number of constructs measurableConstitutive definition: Constitutive definition: Capacity of a single measurement tool to capture multiple dimensions of the training performance process.
Operational definition: The number of constructs represents those that have been defined previously within existing training performance framework including exposure to training (external and internal load) and training effects (acute, chronic and positive, negative subdimensions).

Note: A constitutive definition aims to define a concept or term by explaining its essential characteristics or nature. An operational definition aims to defines a concept or term by specifying the procedures or operations used to assess it.

Figure 1
Figure 1

Conceptualization of invisible monitoring.

Citation: International Journal of Sports Physiology and Performance 2025; 10.1123/ijspp.2024-0292

Monitoring Burden

It is clear that invisible monitoring approaches aim to elicit less disruption to practice and daily operations therefore the extent of monitoring burden placed onto both athletes and staff by a measurement tool is clearly a fundamental subdimension.10 The initial definition proposed by Delaney4 suggested that invisible monitoring strategies aim to maximize the data collected routinely with the athlete suggesting an increased frequency of observations than traditional approaches. Burden is often composed of 2 subdimensions related to the probability an event can occur (ie, frequency) and the associated consequences of the measured event (eg, magnitude, severity).17 The term “invisible” has likely elicited a conceptualization of a false dichotomy, whereby invisible monitoring approaches are an opposite entity to more traditional methods of monitoring. However, when considering the burden of a measurement tool, this should be considered as a continuum rather than dichotomous terms of “visible” or “invisible,” moving from an invasive method to fully unobtrusive. While the label invasive is well understood, the term unobtrusive has been introduced due to its previous use in the context of healthcare.14,15 Unobtrusive health monitoring has been suggested to be focused on obtaining and monitoring health information from participants without introducing inconveniences to everyday life. Such an objective can be achieved by avoiding the constraints of classical approaches requiring wired connections and complex monitoring procedures.14 In the context of sport, the degree of obtrusion of a measurement tool refers to the amount of disruption and additional resource induced to daily operations for both athletes and staff (eg, training, tactical meeting, and gym session).

Considering frequency and obtrusion of a measurement tool in the context of measuring acute training effects (ie, fatigue), a submaximal running test requires a specific task3 but imposes less obtrusion than a countermovement jump due to its easier on field integration (eg, multiple players tested simultaneously) and nonmaximal nature. However, it is not fully unobtrusive to the athlete as a specific intervention is required. Also, despite less obtrusion for athletes, data processing may place a greater burden on staff due to complex analysis requirements. In contrast, wearables sensors aiming to measure key physiological parameters (eg, glucose, hydration, inflammation, and sleep) could be worn theoretically every day in and outside training hours, enabling an improved frequency of measurement. However, while this approach might reduce the severity of the measurement (eg, vs maximal test), the increased frequency of measurement could provide similar burden overall. This challenge highlights the importance of considering obtrusion and frequency of measurement (and therefore burden) as a continuum when considering measurement tools within an invisible monitoring approach.

Number of Constructs

Another consideration within invisible monitoring approaches is the number of constructs that can be assessed through a single measurement within a given observational area (eg, during specific training drills/sessions or matches). For example, can a measurement tool used during a training drill (eg, small sided games) assess both training exposure (eg, intensity of training) and training responses (eg, fitness or fatigue) at a high frequency without additional burden to the athlete? Over the past decade, different approaches have emerged to monitor athlete training responses and physiological capacity that do not require specific intervention and instead are gathered from observational data during training. Recent methods compared predicted (ie, from a multivariate regression model) and actual heart rate responses during soccer training to determine player’s fitness status.7,18 Alternatively, estimating neuromuscular status using a Random Forest method (ie, predicted vs actual Player Load) reported an ability to detect clear seasonal and daily fluctuations.19 In a similar vein, computing a linear regression to acceleration and speed data has been proposed to estimate maximal neuromuscular qualities.20

While there is nothing new about fitting data to create estimations, such methods are advantageous by providing highly frequent (daily basis) estimates of player responses (fitness or fatigue) without additional disruption to training practices or burden onto players. In these cases, the primary use of the collected data (monitoring training exposure) using wearable technology (in this case GPS) is diverted to a secondary aim (monitoring acute and chronic training effects). Therefore, the data currently collected are not only used to monitor training exposure, but also the training effects indirectly and clearly represents a distinctive dimension of the invisible monitoring concept. Indeed, when considering the number of constructs a wearable sensor could potentially assess using a single type of signal, it becomes obvious that such a dimension needs to be considered when evaluating the integration of measurement tools.

Challenges and Practical Recommendations

With the different examples provided earlier, there are a variety of considerations that make invisible monitoring difficult to implement in practice. Such a complexity arises from data management (eg, high sampling frequency, format discrepancies, storage, and analytical methods) and ethical challenges (ie, athlete’s awareness). Hence, it is important to provide clear guidance on the integration of technology, data storage, access, and analysis to facilitate translation of such methods efficiently in practice. Such challenges led us to the dimensions proposed in the current commentary and highlight the benefits of further conceptualizing invisible monitoring.

The proposed dimensions can assist sport organizations to classify measurements and directly assess their capacities to integrate a deemed invisible methodology within their respective context (Figure 2 and Table 2). However, the specific classification requires consensus (eg, survey, Delphi) to create standardized guidelines.

Figure 2
Figure 2

Schematic example demonstrating the process of considering measurement tools for athlete monitoring. This considers the dimensions of extent of monitoring burden and capability to measure multiple constructs (y-axis). The actual position of measurements requires further consensus. Additionally, the different measurements are a nonexhaustive list, which could be further complemented. Bottom left zone represents high burden, limited number of constructs; bottom middle zone, medium burden, limited number of constructs; top middle zone, medium burden, several constructs; bottom right zone, low burden, limited number of constructs; top right zone, low burden, several constructs. EMG indicates electromyography; GPS, global positioning systems; HR, heart rate; iEMG, intramuscular EMG.

Citation: International Journal of Sports Physiology and Performance 2025; 10.1123/ijspp.2024-0292

Table 2

Practical Examples and Associated Recommendations to Implement Invisible Monitoring Strategies

ClassificationExample of methodsData collectionData storageAdditional data processing
Medium burden,

limited number of constructs
Current monitoring strategies such as countermovement jump or sprintAdditional setup required outside training.No additional data storage.Performed by the provider.
Medium burden,

several constructs
Standardized running tests using GPS and embedded accelerometerNeed to accommodate a minimal time during on-pitch warm-up.Data can be temporally stored locally.

Application programming interface can be used if available.
Filtering and patterns recognition.

Calculation of new variables.
Low burden,

limited number of constructs
Usual wearables sensors (eg, sleep actigraphy and glucose monitoring)Need to be worn continuously.

No burden.
Raw data can be stored if there is a need, but it requires a cloud-based solution.Performed by the provider.

Possibility to perform in-house analysis.
Low burden,

several constructs
Predictive model from well-integrated wearables sensorsNo additional burden to collect data.Cloud-based solution might be required.Feature selection for model construction.

Model training.

Calculation of new variables.

Monitoring strategies that elicit the least obtrusion and highest frequency of measurement are beneficial in facilitating analysis of observational data to understand the effects of interventions or performance/health related outcomes. However, such approaches require appropriate decision support systems (eg, data management and governance) and additional statistical analysis expertise within a sporting organization to add value.21,22 Therefore, while minimizing the burden on the athlete, this could shift the burden to the staff/organization and requires consideration when deciding approaches. As those methods heavily involve strong data-related skills (eg, databasing and automation), practitioners need to be aware of these inherent challenges.23 Hence, it will be critical to assess if the organization has the capabilities required to integrate such methods (eg, local server vs cloud-based solution), as this will be critical for the effectiveness of the process and security and privacy of the outcome measures gathered. Moreover, it is important to be aware that some methods require important data transformation (signal processing statistical modeling and artificial intelligence) and involve important expert knowledge to develop and interpret outputs.23

As mentioned previously, invisible monitoring aims to reduce burden on the player and staff regarding data collection.4 Although, while this is obviously attractive from an operational standpoint, practitioners need to be aware that using surrogate measures of a construct likely leads to an inherent deviation from the grand truth (ie, the true training exposure or response) until further advancements in measurement tools occur.1 Therefore, careful consideration is needed (including evaluation of construct validity and reliability) before engaging in such data collection processes.

While minimizing the burden on staff is always advocated, the athlete who is a central part of this process needs to be considered.13 Recently, McCall et al13 considered limitations of invisible monitoring by stating that “with this approach the consequence could be amassing unnecessary data that does not even reflect how the athlete actually feels, thus, increasing the likelihood of making ill-informed decisions about the athlete’s full spectrum of health and performance capabilities.” This position was further reinforced by world-class team sport athletes’ concerns gathered during semistructured interviews.13 Such fair apprehension arose from ethical considerations primarily due to the lack of communication (eg, “Human interaction is so important”) to players on how the data are used (eg, “I’m not a f**king science experiment”) by practitioners to athletes. They further advocated that a more “visible” method to monitor an athlete should be employed. To achieve that, it is important for practitioners to inform and communicate in a very transparent way to the athlete how and why the data collected on the day to day are used and its limitations. It is vital that we communicate, both formally (eg, information sheet) and informally (eg, discussion), to bring athletes on the data journey and make them informed about the different strategies put in place to optimize their health and performance. These requirements also include transparency in communicating the uncertainty of our approaches (that we do not have all the answers) and increasing scientific literacy as well as innovation mindsets in our athletes and staff. Such a transparency should lead to a more cooperative relationship between staff members and athletes.

Conclusions

The expansion of technology and advanced analysis techniques led to the concept of invisible monitoring to minimize the burden of measurement onto athletes but still improving the understanding of the athlete training process. Yet, the process of invisible monitoring has not been clearly conceptualized, limiting the current use of such approaches in practice and rather than improving athlete performance has led to a reluctance to such procedures. This commentary discussed key subdimensions of the invisible monitoring concepts, which includes monitoring burden (frequency and degree of obtrusion of a measurement) and the number of constructs that a single measurement tool can assess. Such a conceptualization facilitates a critical consideration for the adoption and choice of invisible monitoring approaches in practice, alongside their data-related and ethical considerations. Finally, while we have discussed specific subdimensions of invisible monitoring and its implications for practice, it is also important to consider other dimensions (eg, validity, reliability, and safety) within the overall evaluation and integration of a measurement tool. It is an exciting time for sports science, but a global effort from researcher and practitioners is required to make this invisible monitoring concept more widespread, operational, and visible to athletes.

Acknowledgments

We would like to express our gratitude to Dr Kelly Vaughan and Professor Paul Laursen for their constructive feedback during the writing process. Author Contributions: Conceptualization: Leduc, Weaving. Writing—original draft: Leduc. Writing—review and editing: Leduc, Weaving. Visualization: Leduc. Supervision: Weaving.

References

  • 1.

    Impellizzeri FM, Shrier I, McLaren SJ, et al. Understanding training load as exposure and dose. Sports Med. 2023;53(9):16671679. doi:

  • 2.

    Carling C, Lacome M, Mccall A, Simpson B, Buchheit M. Monitoring of post-match fatigue in professional soccer: welcome to the real world. Sports Med. 2018;48(12):26952702. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 3.

    Leduc, C, Tee, J, Lacome, M, Weakley, J, Cheradame, J, Ramirez, C, Jones B. Convergent validity, reliability and sensitivity of a running test to monitor neuromuscular fatigue. Int J Sports Physiol Perform. 2020;15(8):10671073. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 4.

    Delaney J. The paradox of “invisible” monitoring: the less you do, the more you do! 2023. Accessed September 3, 2023. https://hiitscience.com/the-paradox-of-invisible-monitoring-the-less-you-do-the-more-you-do/

    • Search Google Scholar
    • Export Citation
  • 5.

    Weakley J, Mclaren S, Scantlebury S, et al. Testing and profiling athletes: recommendations for test selection, implementation, and maximizing information. Strength Cond J. 2023;10:784. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 6.

    Jo Clubb. What is invisible monitoring in sports science? 2023. Accessed May 26, 2024. https://www.globalperformanceinsights.com/post/what-is-invisible-monitoring-in-sports-science

    • Search Google Scholar
    • Export Citation
  • 7.

    Mandorino M, Clubb J, Lacome M. Predicting soccer players’ fitness status through a machine-learning approach. Int J Sports Physiol Perform. 2024;10:444. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 8.

    Fernández D, Moya D, Cadefau JA, Carmona G. Integrating external and internal load for monitoring fitness and fatigue status in standard microcycles in elite rink hockey. Front Physiol. 2021;12:463. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 9.

    Cormier P, Tsai MC, Meylan C, Klimstra M. Comparison of acceleration-speed profiles from training and competition to individual maximal sprint efforts. J Biomech. 2023;157:724. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 10.

    West SW, Clubb J, Torres-Ronda L, et al. More than a metric: how training load is used in elite sport for athlete management. Int J Sports Med. 2021;42(4):300306. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 11.

    Weldon A, Duncan MJ, Turner A, et al. Contemporary practices of strength and conditioning coaches in professional soccer. Biol Sport. 2021;38(3):377390. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 12.

    Windt J, MacDonald K, Taylor D, Zumbo BD, Sporer BC, Martin DT. “To tech or not to tech?” A critical decision-making framework for implementing technology in sport. J Athl Train. 2020;55(9):902910. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 13.

    McCall A, Wolfberg A, Ivarsson A, Dupont G, Larocque A, Bilsborough J. A qualitative study of 11 world-class team-sport athletes’ experiences answering subjective questionnaires: a key ingredient for ‘visible’ health and performance monitoring? Sports Med. 2023;53(5):10851100. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 14.

    Wang J, Spicher N, Warnecke JM, Haghi M, Schwartze J, Deserno TM. Unobtrusive health monitoring in private spaces: the smart home. Sensors. 2021;21(3):123. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 15.

    Guo Y, Liu X, Peng S, et al. A review of wearable and unobtrusive sensing technologies for chronic disease management. Comput Biol Med. 2021;129:163. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 16.

    Jeffries AC, Marcora SM, Coutts AJ, Wallace L, McCall A, Impellizzeri FM. Development of a revised conceptual framework of physical training for use in research and practice. Sports Med. 2022;52(4):709724. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 17.

    Fuller CW. Injury risk (burden), risk matrices and risk contours in team sports: a review of principles, practices and problems. Sports Med. 2018;48(7):15971606. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 18.

    Lacome M, Simpson B, Broad N, Buchheit M. Monitoring players’ readiness using predicted heart-rate responses to soccer drills. Int J Sports Physiol Perform. 2018;13(10):12731280. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 19.

    Mandorino M, Tessitore A, Leduc C, Persichetti V, Morabito M, Lacome M. A new approach to quantify soccer players’ readiness through machine learning techniques. Appl Sci. 2023;13(15):808. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 20.

    Clavel P, Leduc C, Morin JB, Buchheit M, Lacome M. Reliability of individual acceleration-speed profile in-situ in elite youth soccer players. J Biomech. 2023;153:602. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 21.

    Robertson PS. Man & machine: adaptive tools for the contemporary performance analyst. J Sports Sci. 2020;38(18):21182126. doi:

  • 22.

    Lolli L, Bauer P, Irving C, et al. Data analytics in the football industry: a survey investigating operational frameworks and practices in professional clubs and national federations from around the world. Sci Med Footb. 2024;10:837. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 23.

    Richter C, O’Reilly M, Delahunt E. Machine learning in sports science: challenges and opportunities. Sports Biomech. 2021;23(8):961967. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation

Supplementary Materials

  • Collapse
  • Expand
  • Figure 1

    Conceptualization of invisible monitoring.

  • Figure 2

    Schematic example demonstrating the process of considering measurement tools for athlete monitoring. This considers the dimensions of extent of monitoring burden and capability to measure multiple constructs (y-axis). The actual position of measurements requires further consensus. Additionally, the different measurements are a nonexhaustive list, which could be further complemented. Bottom left zone represents high burden, limited number of constructs; bottom middle zone, medium burden, limited number of constructs; top middle zone, medium burden, several constructs; bottom right zone, low burden, limited number of constructs; top right zone, low burden, several constructs. EMG indicates electromyography; GPS, global positioning systems; HR, heart rate; iEMG, intramuscular EMG.

  • 1.

    Impellizzeri FM, Shrier I, McLaren SJ, et al. Understanding training load as exposure and dose. Sports Med. 2023;53(9):16671679. doi:

  • 2.

    Carling C, Lacome M, Mccall A, Simpson B, Buchheit M. Monitoring of post-match fatigue in professional soccer: welcome to the real world. Sports Med. 2018;48(12):26952702. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 3.

    Leduc, C, Tee, J, Lacome, M, Weakley, J, Cheradame, J, Ramirez, C, Jones B. Convergent validity, reliability and sensitivity of a running test to monitor neuromuscular fatigue. Int J Sports Physiol Perform. 2020;15(8):10671073. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 4.

    Delaney J. The paradox of “invisible” monitoring: the less you do, the more you do! 2023. Accessed September 3, 2023. https://hiitscience.com/the-paradox-of-invisible-monitoring-the-less-you-do-the-more-you-do/

    • Search Google Scholar
    • Export Citation
  • 5.

    Weakley J, Mclaren S, Scantlebury S, et al. Testing and profiling athletes: recommendations for test selection, implementation, and maximizing information. Strength Cond J. 2023;10:784. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 6.

    Jo Clubb. What is invisible monitoring in sports science? 2023. Accessed May 26, 2024. https://www.globalperformanceinsights.com/post/what-is-invisible-monitoring-in-sports-science

    • Search Google Scholar
    • Export Citation
  • 7.

    Mandorino M, Clubb J, Lacome M. Predicting soccer players’ fitness status through a machine-learning approach. Int J Sports Physiol Perform. 2024;10:444. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 8.

    Fernández D, Moya D, Cadefau JA, Carmona G. Integrating external and internal load for monitoring fitness and fatigue status in standard microcycles in elite rink hockey. Front Physiol. 2021;12:463. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 9.

    Cormier P, Tsai MC, Meylan C, Klimstra M. Comparison of acceleration-speed profiles from training and competition to individual maximal sprint efforts. J Biomech. 2023;157:724. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 10.

    West SW, Clubb J, Torres-Ronda L, et al. More than a metric: how training load is used in elite sport for athlete management. Int J Sports Med. 2021;42(4):300306. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 11.

    Weldon A, Duncan MJ, Turner A, et al. Contemporary practices of strength and conditioning coaches in professional soccer. Biol Sport. 2021;38(3):377390. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 12.

    Windt J, MacDonald K, Taylor D, Zumbo BD, Sporer BC, Martin DT. “To tech or not to tech?” A critical decision-making framework for implementing technology in sport. J Athl Train. 2020;55(9):902910. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 13.

    McCall A, Wolfberg A, Ivarsson A, Dupont G, Larocque A, Bilsborough J. A qualitative study of 11 world-class team-sport athletes’ experiences answering subjective questionnaires: a key ingredient for ‘visible’ health and performance monitoring? Sports Med. 2023;53(5):10851100. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 14.

    Wang J, Spicher N, Warnecke JM, Haghi M, Schwartze J, Deserno TM. Unobtrusive health monitoring in private spaces: the smart home. Sensors. 2021;21(3):123. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 15.

    Guo Y, Liu X, Peng S, et al. A review of wearable and unobtrusive sensing technologies for chronic disease management. Comput Biol Med. 2021;129:163. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 16.

    Jeffries AC, Marcora SM, Coutts AJ, Wallace L, McCall A, Impellizzeri FM. Development of a revised conceptual framework of physical training for use in research and practice. Sports Med. 2022;52(4):709724. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 17.

    Fuller CW. Injury risk (burden), risk matrices and risk contours in team sports: a review of principles, practices and problems. Sports Med. 2018;48(7):15971606. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 18.

    Lacome M, Simpson B, Broad N, Buchheit M. Monitoring players’ readiness using predicted heart-rate responses to soccer drills. Int J Sports Physiol Perform. 2018;13(10):12731280. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 19.

    Mandorino M, Tessitore A, Leduc C, Persichetti V, Morabito M, Lacome M. A new approach to quantify soccer players’ readiness through machine learning techniques. Appl Sci. 2023;13(15):808. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 20.

    Clavel P, Leduc C, Morin JB, Buchheit M, Lacome M. Reliability of individual acceleration-speed profile in-situ in elite youth soccer players. J Biomech. 2023;153:602. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 21.

    Robertson PS. Man & machine: adaptive tools for the contemporary performance analyst. J Sports Sci. 2020;38(18):21182126. doi:

  • 22.

    Lolli L, Bauer P, Irving C, et al. Data analytics in the football industry: a survey investigating operational frameworks and practices in professional clubs and national federations from around the world. Sci Med Footb. 2024;10:837. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 23.

    Richter C, O’Reilly M, Delahunt E. Machine learning in sports science: challenges and opportunities. Sports Biomech. 2021;23(8):961967. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
All Time Past Year Past 30 Days
Abstract Views 0 0 0
Full Text Views 1622 1622 1622
PDF Downloads 1665 1665 1665