Evaluating Methods for Imputing Missing Data from Longitudinal Monitoring of Athlete Workload

Benson, Lauren C.; Stilling, Carlyn; Owoeye, Oluwatoyosi; Emery, Carolyn A.

doi:10.52082/jssm.2021.188

Cited by 9 publications

(18 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Missing data have to be handled (Benson et al, 2021 ). In this study, we used the simplest imputation form, which replaces the missing data with the most recent measurement.…”

Section: Discussionmentioning

confidence: 99%

“…The monitoring process implies inevitable missing values (Benson et al, 2021 ). We observed three causes for missing values in the dataset: (1) the athletes did not train on a given day; (2) some variables were not measured daily; and (3) the athletes omitted to report data.…”

Section: Methodsmentioning

confidence: 99%

“…Although not perfect, the imputation strategy is easy to implement, avoids information leakage (Van Eetvelde et al, 2021 ), and provides indicators of the stress response variables over a short time frame. It is the most simplistic single imputation technique described by Benson et al ( 2021 ).…”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Monitoring Variables Influence on Random Forest Models to Forecast Injuries in Short-Track Speed Skating

Briand¹,

Deguire²,

Gaudet³

et al. 2022

Front. Sports Act. Living

View full text Add to dashboard Cite

Injuries limit the athletes' ability to participate fully in their training and competitive process. They are detrimental to performance, affecting the athletes psychologically while limiting physiological adaptations and long-term development. This study aims to present a framework for developing random forest classifier models, forecasting injuries in the upcoming 1 to 7 days, to assist the performance support staff in reducing injuries and maximizing performance within the Canadian National Female Short-Track Speed Skating Program. Forty different variables monitored daily over two seasons (2018–2019 and 2019–2020) were used to develop two sets of forecasting models. One includes only training load variables (TL), and a second (ALL) combines a wide array of monitored variables (neuromuscular function, heart rate variability, training load, psychological wellbeing, past injury type, and location). The sensitivity (ALL: 0.35 ± 0.19, TL: 0.23 ± 0.03), specificity (ALL: 0.81 ± 0.05, TL: 0.74 ± 0.03) and Matthews Correlation Coefficients (MCC) (ALL: 0.13 ± 0.05, TL: −0.02 ± 0.02) were computed. Paired T-test on the MCC revealed statistically significant (p < 0.01) and large positive effects (Cohen d > 1) for the ALL forecasting models' MCC over every forecasting window (1 to 7 days). These models were highly determined by the athletes' training completion, lower limb and trunk/lumbar injury history, as well as sFatigue, a training load marker. The TL forecasting models' MCC suggests they do not bring any added value to forecast injuries. Combining a wide array of monitored variables and quantifying the injury etiology conceptual components significantly improve the injury forecasting performance of random forest models. The ALL forecasting models' performances are promising, especially on one time windows of one or two days, with sensitivities and specificities being respectively above 0.5 and 0.7. They could add value to the decision-making process for the support staff in order to assist the Canadian National Female Team Short-Track Speed Skating program in reducing the number of incomplete training days, which could potentially increase performance. On longer forecasting time windows, ALL forecasting models' sensitivity and MCC decrease gradually. Further work is needed to determine if such models could be useful for forecasting injuries over three days or longer.

show abstract

“…Missing data have to be handled (Benson et al, 2021 ). In this study, we used the simplest imputation form, which replaces the missing data with the most recent measurement.…”

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Monitoring Variables Influence on Random Forest Models to Forecast Injuries in Short-Track Speed Skating

Briand¹,

Deguire²,

Gaudet³

et al. 2022

Front. Sports Act. Living

View full text Add to dashboard Cite

show abstract

“…We consider that the sentiment value of trust is a dependent variable, while the sentiment values of other service features are independent variables. According to the research of Little and Rubin (2002) and Benson et al (2021), the missing value was filled with the average sentiment value of other doctors in this service feature. According to this part's research purpose, the independent variable was adjusted based on the following points: (1) When we first regress all the service features and trust, we find that the collinear coefficient variance inflation factor (VIF) of "phraseology" and "overall service experience" are both greater than 10 (Appendix 1).…”

Section: The Effect Of Service Features On Trustmentioning

confidence: 99%

Influencing factors and mechanism of doctor consultation volume on online medical consultation platforms based on physician review analysis

Wan

Peng

Wang

et al. 2021

INTR

View full text Add to dashboard Cite

PurposeThis paper aims to reveal the factors patients consider when choosing a doctor for consultation on an online medical consultation (OMC) platform and how these factors influence doctors' consultation volumes.Design/methodology/approachIn Study 1, influencing factors reflected as service features were identified by applying a feature extraction method to physician reviews, and the importance of each feature was determined based on word frequencies and the PageRank algorithm. Sentiment analysis was used to analyze patient satisfaction with each service feature. In Study 2, regression models were used to analyze the relationships between the service features obtained from Study 1 and the doctor's consultation volume.FindingsThe study identified 14 service features of patients' concerns and found that patients mostly care about features such as trust, phraseology, overall service experience, word of mouth and personality traits, all of which describe a doctor's soft skills. These service features affect patients' trust in doctors, which, in turn, affects doctors' consultation volumes.Originality/valueThis research is important as it informs doctors about the features they should improve, to increase their consultation volume on OMC platforms. Furthermore, it not only enriches current trust-related research in the field of OMC, which has a certain reference significance for subsequent research on establishing trust in online doctor–patient relationships, but it also provides a reference for research concerning the antecedents of trust in general.

show abstract

“…When workload data were missing for any reason (e.g., no data recorded that session, equipment malfunction, individual did not wear jump counter and/or report RPE, etc. ), the missing workload variables for that session were imputed according to the following steps (Benson et al, 2021). For each workload variable, the workload for all non-missing participant-sessions was expressed relative to the duration of the session in hours.…”

Section: Workload Data Processingmentioning

confidence: 99%

Magnitude, Frequency, and Accumulation: Workload Among Injured and Uninjured Youth Basketball Players

Benson

Owoeye

Räisänen

et al. 2021

Front. Sports Act. Living

Self Cite

View full text Add to dashboard Cite

Overuse injuries are common in basketball. Wearable technology enables the workload to be monitored in sport settings. However, workload–injury models lack a biological basis both in the metrics recorded and how workload is accumulated. We introduce a new metric for monitoring workload: weighted jump height, where each jump height is weighted to represent the expected effect of the jump magnitude on damage to the tendon. The objectives of this study were to use principal components analysis to identify distinct modes of variation in all workload metrics accumulated over 1, 2, 3, and 4 weeks and to examine differences among the modes of variation in workload metrics between participants before the injury and uninjured participants. Forty-nine youth basketball players participated in their typical basketball practices and games, and lower extremity injuries were classified as patellar or Achilles tendinopathy, other overuse, or acute. An inertial measurement unit recorded the number and height of all jumps, and session rating of perceived exertion was recorded. The previous 1-, 2-, 3-, and 4-week workloads of jump count, jump height, weighted jump height, and session rating of perceived exertion were summed for each participant-week. Principal components analysis explained the variance in the accumulated workload variables. Using the retained principal components, the difference between the workload of injured participants in the week before the injury and the mean workload of uninjured participants was described for patellar or Achilles tendinopathy, overuse lower extremity injury, and any lower extremity injury. Participants with patellar or Achilles tendinopathy and overuse lower extremity injuries had a low workload magnitude for all variables in the 1, 2, 3, and 4 weeks before injury compared with the weeks before no injury. Participants with overuse lower extremity injuries and any lower extremity injury had a high previous 1-week workload for all variables along with a low previous 3- and 4-week jump count, jump height, and weighted jump height before injury compared with the weeks before no injury. Weighted jump height represents the cumulative damage experienced by tissues due to repetitive loads. Injured youth basketball athletes had a low previous 3- and 4-week workloads coupled with a high previous 1-week workload.

show abstract

Evaluating Methods for Imputing Missing Data from Longitudinal Monitoring of Athlete Workload

Cited by 9 publications

References 39 publications

Monitoring Variables Influence on Random Forest Models to Forecast Injuries in Short-Track Speed Skating

Monitoring Variables Influence on Random Forest Models to Forecast Injuries in Short-Track Speed Skating

Influencing factors and mechanism of doctor consultation volume on online medical consultation platforms based on physician review analysis

Magnitude, Frequency, and Accumulation: Workload Among Injured and Uninjured Youth Basketball Players

Contact Info

Product

Resources

About