Daniel Koska
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Daniel Koska has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Christian Maiwald
Chemnitz University of Technology, Thüringer Weg 11, 09126 Chemnitz, Germany
6 shared publications Christian Maiwald
Institute of Human Movement Science and Health, Chemnitz University of Technology, 09126, Chemnitz, Germany
4 shared publications- Tobias A. Mayer
Department of Research Methodology and Data Analysis in Biomechanics, Institute of Human Movement Science and Health, Chemnitz University of Technology, Chemnitz, Germany
3 shared publications - Ann-Kathrin Harsch
Department of Research Methodology and Data Analysis in Biomechanics, Institute of Human Movement Science and Health, Chemnitz University of Technology, Chemnitz, Germany
2 shared publications Andresa Germano
Institute of Human Movement Science and Health, Chemnitz University of Technology, 09126, Chemnitz, Germany
1 shared publicationAnn-Kathrin Harsch
Institute of Human Movement Science and Health, Chemnitz University of Technology, 09126, Chemnitz, Germany
1 shared publication
Latest Publications
- Open Access
- 15 July 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Quantifying the added value of foot-controlled force variables in predicting mild cognitive impairment
Predicting early cognitive decline is important for timely interventions. However, existing approaches for early detection remain limited by cost, scalability, or concerns about their validity. This study evaluated the potential of lower-extremity force control capacities, a largely unexplored area, to improve prediction of cognitive status in older adults with and without Mild Cognitive Impairment (MCI). MCI refers to an early stage of cognitive decline that does not meet criteria for dementia. 224 participants aged 80–91 years completed a foot-pedal tracking task in which they continuously adjusted the force applied to a pedal to match a visual target curve presented at two different frequencies. The task was designed to capture ongoing visuomotor monitoring and fine motor control. Task performance was quantified using measures of tracking accuracy (Root Mean Square Error, RMSE) and signal complexity (Sample Entropy, SampEn). These reflect how precisely participants controlled force and how regular their output was over time. Participants with MCI showed lower accuracy and lower complexity than cognitively healthy individuals. Adding RMSE and SampEn to a baseline prediction model improved model performance, with the largest gains observed at the higher curve frequency: RMSE contributed 13% new predictive information, SampEn 17%, and both variables together 21%. These gains indicate that foot-controlled force measures added meaningful information beyond established predictors, although confirmation in independent samples is needed. Foot-controlled force tasks may therefore provide a quick-to-administer, objective complement for early detection of cognitive decline.
- 15 July 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Open AccessQuantifying the added value of foot-controlled force variables in predicting mild cognitive impairment
Predicting early cognitive decline is important for timely interventions. However, existing approaches for early detection remain limited by cost, scalability, or concerns about their validity. This study evaluated the potential of lower-extremity force control capacities, a largely unexplored area, to improve prediction of cognitive status in older adults with and without Mild Cognitive Impairment (MCI). MCI refers to an early stage of cognitive decline that does not meet criteria for dementia. 224 participants aged 80–91 years completed a foot-pedal tracking task in which they continuously adjusted the force applied to a pedal to match a visual target curve presented at two different frequencies. The task was designed to capture ongoing visuomotor monitoring and fine motor control. Task performance was quantified using measures of tracking accuracy (Root Mean Square Error, RMSE) and signal complexity (Sample Entropy, SampEn). These reflect how precisely participants controlled force and how regular their output was over time. Participants with MCI showed lower accuracy and lower complexity than cognitively healthy individuals. Adding RMSE and SampEn to a baseline prediction model improved model performance, with the largest gains observed at the higher curve frequency: RMSE contributed 13% new predictive information, SampEn 17%, and both variables together 21%. These gains indicate that foot-controlled force measures added meaningful information beyond established predictors, although confirmation in independent samples is needed. Foot-controlled force tasks may therefore provide a quick-to-administer, objective complement for early detection of cognitive decline.
- Open Access
- 1 April 2026
- Published by Elsevier in Journal of Biomechanics
- Vol. 201, 113280
Simulation-based analysis of rigid alignment bias in PCA of weight-bearing foot shapes
- 1 April 2026
- Published by Elsevier in Journal of Biomechanics
- Vol. 201, 113280
Open AccessSimulation-based analysis of rigid alignment bias in PCA of weight-bearing foot shapes
- 20 October 2025
- Published by The R Foundation
funbootband: Simultaneous Prediction and Confidence Bands for Functional Data
Provides methods to compute simultaneous prediction and confidence bands for dense time series data. The implementation builds on the functional bootstrap approach proposed by Lenhoff et al. (1999) and extended by Koska et al. (2023) to support both independent and clustered (hierarchical) data. Includes a simple API (see band()) and an 'Rcpp' backend for performance.
- 20 October 2025
- Published by The R Foundation
funbootband: Simultaneous Prediction and Confidence Bands for Functional Data
Provides methods to compute simultaneous prediction and confidence bands for dense time series data. The implementation builds on the functional bootstrap approach proposed by Lenhoff et al. (1999) and extended by Koska et al. (2023) to support both independent and clustered (hierarchical) data. Includes a simple API (see band()) and an 'Rcpp' backend for performance.
- Open Access
- 5 May 2025
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 27, e66463
Effectiveness of Self-Training With a Web-Based Digital Health Application Versus Physiotherapy in the Treatment of Disorders of the Patella: Randomized Controlled Trial
Background: Disorders of the patella are among the most prevalent knee injuries. While exercise therapy is widely accepted as an effective treatment strategy, the positive effects of conventional exercise therapy under the guidance of a physiotherapist may be offset by inherent limitations, such as difficulties in scheduling appointments or statutory policies restricting the number of training sessions. Home-based exercise interventions using digital health applications (DHAs) may help address some of these limitations. Objective: This study aimed to assess the efficacy of a 12-week exercise intervention using a web-based DHA for improving knee function and reducing pain in patients with disorders of the patella (International Classification of Diseases code M22). Methods: The outcomes of the DHA intervention group (IG) were compared to a control group (CG) that received conventional physiotherapy covered by statutory health insurance in Germany (SHI-PT). A total of 259 patients with diagnosed disorders of the patella were included in the trial and randomly allocated to IG DHA (n=136, 52.5%) and CG SHI-PT (n=123, 47.5%). Two primary end points were examined: “knee function” (Knee Injury and Osteoarthritis Outcome Score—Activities of Daily Living [KOOSADL] subscale, range 0-100 points) and “knee pain” (visual analog scale [VAS], range 0-100 points). Participants were asked to complete 2 surveys: one before the first therapy session (PRE) and one after completing the treatment period of 12 weeks (POST). Results: Training with the DHA resulted in a 4.5-fold greater improvement in “knee function” (PRE–POST differences in KOOSADL score; IG DHA: 15.7 points, 95% CI 13.7-17.6 vs CG SHI-PT: 3.5 points, 95% CI 1.5-5.5) and a 3.5-fold greater reduction in “knee pain” (PRE–POST differences in VAS pain score; IG DHA: –22.5 points, 95% CI –25.2 to –19.9 vs CG SHI-PT: –6.5 points, 95% CI –8.7 to –4.4) compared to SHI-PT. The improvements in IG DHA exceeded the limits of clinical relevance. The differences between the treatment groups (KOOSADL score –10.1 points, 95% CI –infinity to -8.0; VAS pain score 14.3 points 95% CI 11.7-infinity) were statistically significant (P<.001) for both end points in favor of IG DHA. No effect was found for age or sex. The reported use of pain medication decreased substantially in IG DHA, and showed almost no change in CG SHI-PT. Conclusions: Our findings indicated that the investigated DHA is superior to SHI-PT for treating disorders of the patella. Therefore, DHA has been approved by the German Federal Institute for Drugs and Medical Devices for treating disorders of the patella in persons of all sexes aged ≥12 years. Trial Registration: German Clinical Trials Register (DRKS) DRKS00023454; https://drks.de/search/en/trial/DRKS00023454
- 5 May 2025
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 27, e66463
Open AccessEffectiveness of Self-Training With a Web-Based Digital Health Application Versus Physiotherapy in the Treatment of Disorders of the Patella: Randomized Controlled Trial
Background: Disorders of the patella are among the most prevalent knee injuries. While exercise therapy is widely accepted as an effective treatment strategy, the positive effects of conventional exercise therapy under the guidance of a physiotherapist may be offset by inherent limitations, such as difficulties in scheduling appointments or statutory policies restricting the number of training sessions. Home-based exercise interventions using digital health applications (DHAs) may help address some of these limitations. Objective: This study aimed to assess the efficacy of a 12-week exercise intervention using a web-based DHA for improving knee function and reducing pain in patients with disorders of the patella (International Classification of Diseases code M22). Methods: The outcomes of the DHA intervention group (IG) were compared to a control group (CG) that received conventional physiotherapy covered by statutory health insurance in Germany (SHI-PT). A total of 259 patients with diagnosed disorders of the patella were included in the trial and randomly allocated to IG DHA (n=136, 52.5%) and CG SHI-PT (n=123, 47.5%). Two primary end points were examined: “knee function” (Knee Injury and Osteoarthritis Outcome Score—Activities of Daily Living [KOOSADL] subscale, range 0-100 points) and “knee pain” (visual analog scale [VAS], range 0-100 points). Participants were asked to complete 2 surveys: one before the first therapy session (PRE) and one after completing the treatment period of 12 weeks (POST). Results: Training with the DHA resulted in a 4.5-fold greater improvement in “knee function” (PRE–POST differences in KOOSADL score; IG DHA: 15.7 points, 95% CI 13.7-17.6 vs CG SHI-PT: 3.5 points, 95% CI 1.5-5.5) and a 3.5-fold greater reduction in “knee pain” (PRE–POST differences in VAS pain score; IG DHA: –22.5 points, 95% CI –25.2 to –19.9 vs CG SHI-PT: –6.5 points, 95% CI –8.7 to –4.4) compared to SHI-PT. The improvements in IG DHA exceeded the limits of clinical relevance. The differences between the treatment groups (KOOSADL score –10.1 points, 95% CI –infinity to -8.0; VAS pain score 14.3 points 95% CI 11.7-infinity) were statistically significant (P<.001) for both end points in favor of IG DHA. No effect was found for age or sex. The reported use of pain medication decreased substantially in IG DHA, and showed almost no change in CG SHI-PT. Conclusions: Our findings indicated that the investigated DHA is superior to SHI-PT for treating disorders of the patella. Therefore, DHA has been approved by the German Federal Institute for Drugs and Medical Devices for treating disorders of the patella in persons of all sexes aged ≥12 years. Trial Registration: German Clinical Trials Register (DRKS) DRKS00023454; https://drks.de/search/en/trial/DRKS00023454
- Open Access
Supervised vs. Self-Managed Exercise Therapy for Improving Shoulder Function After Traumatic Dislocation and Sprain: A Systematic Review and Meta-Analysis
Trauma-induced shoulder dislocations and sprains rank among the most common upper extremity injuries, with contact sports accounting for the majority of cases. These injuries often lead to substantial impairments in joint function and long recovery times, requiring targeted therapeutic interventions to restore mobility and prevent recurrent injuries. Given the pivotal role of exercise therapy in restoring shoulder function, this study systematically reviews the literature on the comparative effectiveness of supervised versus self-managed exercise therapy following acute shoulder trauma. PubMed, Cochrane CENTRAL, Embase, Web of Science, and Science Direct were searched up to 13 December 2024. Conservative and post-surgical treatment modes were analyzed separately. Five studies with a total 689 participants were included (conservative: n = 538 across two studies; post-surgical: n = 151 across three studies). Both treatment modes showed similar pooled effects (standardized mean difference, SMDconservative: , 95% CI [, 0.69]; SMDpost-surgical: , 95% CI [, 0.75]), with a marginal improvement in shoulder function favoring supervised therapy. Four studies had some risk of bias, and one had serious risk; GRADE certainty was low. Supervised exercise therapy may offer slightly greater functional improvements over self-managed training, but evidence is limited by heterogeneity and low certainty. Further high-quality trials with standardized protocols and improved adherence tracking are needed to establish more definitive conclusions and guide clinical decision-making.Open AccessSupervised vs. Self-Managed Exercise Therapy for Improving Shoulder Function After Traumatic Dislocation and Sprain: A Systematic Review and Meta-Analysis
Trauma-induced shoulder dislocations and sprains rank among the most common upper extremity injuries, with contact sports accounting for the majority of cases. These injuries often lead to substantial impairments in joint function and long recovery times, requiring targeted therapeutic interventions to restore mobility and prevent recurrent injuries. Given the pivotal role of exercise therapy in restoring shoulder function, this study systematically reviews the literature on the comparative effectiveness of supervised versus self-managed exercise therapy following acute shoulder trauma. PubMed, Cochrane CENTRAL, Embase, Web of Science, and Science Direct were searched up to 13 December 2024. Conservative and post-surgical treatment modes were analyzed separately. Five studies with a total 689 participants were included (conservative: n = 538 across two studies; post-surgical: n = 151 across three studies). Both treatment modes showed similar pooled effects (standardized mean difference, SMDconservative: , 95% CI [, 0.69]; SMDpost-surgical: , 95% CI [, 0.75]), with a marginal improvement in shoulder function favoring supervised therapy. Four studies had some risk of bias, and one had serious risk; GRADE certainty was low. Supervised exercise therapy may offer slightly greater functional improvements over self-managed training, but evidence is limited by heterogeneity and low certainty. Further high-quality trials with standardized protocols and improved adherence tracking are needed to establish more definitive conclusions and guide clinical decision-making. - Open Access
- 13 September 2024
- Published by JMIR Publications Inc. in JMIR Preprints
Effectiveness of Self-Training With a Web-Based Digital Health Application Versus Physiotherapy in the Treatment of Disorders of the Patella: Randomized Controlled Trial (Preprint)
BACKGROUND Disorders of the patella are among the most prevalent knee injuries. While exercise therapy is widely accepted as an effective treatment strategy, the positive effects of conventional exercise therapy under the guidance of a physiotherapist may be offset by inherent limitations, such as difficulties in scheduling appointments or statutory policies restricting the number of training sessions. Home-based exercise interventions using digital health applications (DHAs) may help address some of these limitations. OBJECTIVE This study aimed to assess the efficacy of a 12-week exercise intervention using a web-based DHA for improving knee function and reducing pain in patients with disorders of the patella (International Classification of Diseases code M22). METHODS The outcomes of the DHA intervention group (IG) were compared to a control group (CG) that received conventional physiotherapy covered by statutory health insurance in Germany (SHI-PT). A total of 259 patients with diagnosed disorders of the patella were included in the trial and randomly allocated to IG DHA (n=136, 52.5%) and CG SHI-PT (n=123, 47.5%). Two primary end points were examined: “knee function” (Knee Injury and Osteoarthritis Outcome Score—Activities of Daily Living [KOOSADL] subscale, range 0-100 points) and “knee pain” (visual analog scale [VAS], range 0-100 points). Participants were asked to complete 2 surveys: one before the first therapy session (PRE) and one after completing the treatment period of 12 weeks (POST). RESULTS Training with the DHA resulted in a 4.5-fold greater improvement in “knee function” (PRE–POST differences in KOOSADL score; IG DHA: 15.7 points, 95% CI 13.7-17.6 vs CG SHI-PT: 3.5 points, 95% CI 1.5-5.5) and a 3.5-fold greater reduction in “knee pain” (PRE–POST differences in VAS pain score; IG DHA: –22.5 points, 95% CI –25.2 to –19.9 vs CG SHI-PT: –6.5 points, 95% CI –8.7 to –4.4) compared to SHI-PT. The improvements in IG DHA exceeded the limits of clinical relevance. The differences between the treatment groups (KOOSADL score –10.1 points, 95% CI –infinity to -8.0; VAS pain score 14.3 points 95% CI 11.7-infinity) were statistically significant (P<.001) for both end points in favor of IG DHA. No effect was found for age or sex. The reported use of pain medication decreased substantially in IG DHA, and showed almost no change in CG SHI-PT. CONCLUSIONS Our findings indicated that the investigated DHA is superior to SHI-PT for treating disorders of the patella. Therefore, DHA has been approved by the German Federal Institute for Drugs and Medical Devices for treating disorders of the patella in persons of all sexes aged ≥12 years. CLINICALTRIAL German Clinical Trials Register (DRKS) DRKS00023454; https://drks.de/search/en/trial/DRKS00023454
- 13 September 2024
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessEffectiveness of Self-Training With a Web-Based Digital Health Application Versus Physiotherapy in the Treatment of Disorders of the Patella: Randomized Controlled Trial (Preprint)
BACKGROUND Disorders of the patella are among the most prevalent knee injuries. While exercise therapy is widely accepted as an effective treatment strategy, the positive effects of conventional exercise therapy under the guidance of a physiotherapist may be offset by inherent limitations, such as difficulties in scheduling appointments or statutory policies restricting the number of training sessions. Home-based exercise interventions using digital health applications (DHAs) may help address some of these limitations. OBJECTIVE This study aimed to assess the efficacy of a 12-week exercise intervention using a web-based DHA for improving knee function and reducing pain in patients with disorders of the patella (International Classification of Diseases code M22). METHODS The outcomes of the DHA intervention group (IG) were compared to a control group (CG) that received conventional physiotherapy covered by statutory health insurance in Germany (SHI-PT). A total of 259 patients with diagnosed disorders of the patella were included in the trial and randomly allocated to IG DHA (n=136, 52.5%) and CG SHI-PT (n=123, 47.5%). Two primary end points were examined: “knee function” (Knee Injury and Osteoarthritis Outcome Score—Activities of Daily Living [KOOSADL] subscale, range 0-100 points) and “knee pain” (visual analog scale [VAS], range 0-100 points). Participants were asked to complete 2 surveys: one before the first therapy session (PRE) and one after completing the treatment period of 12 weeks (POST). RESULTS Training with the DHA resulted in a 4.5-fold greater improvement in “knee function” (PRE–POST differences in KOOSADL score; IG DHA: 15.7 points, 95% CI 13.7-17.6 vs CG SHI-PT: 3.5 points, 95% CI 1.5-5.5) and a 3.5-fold greater reduction in “knee pain” (PRE–POST differences in VAS pain score; IG DHA: –22.5 points, 95% CI –25.2 to –19.9 vs CG SHI-PT: –6.5 points, 95% CI –8.7 to –4.4) compared to SHI-PT. The improvements in IG DHA exceeded the limits of clinical relevance. The differences between the treatment groups (KOOSADL score –10.1 points, 95% CI –infinity to -8.0; VAS pain score 14.3 points 95% CI 11.7-infinity) were statistically significant (P<.001) for both end points in favor of IG DHA. No effect was found for age or sex. The reported use of pain medication decreased substantially in IG DHA, and showed almost no change in CG SHI-PT. CONCLUSIONS Our findings indicated that the investigated DHA is superior to SHI-PT for treating disorders of the patella. Therefore, DHA has been approved by the German Federal Institute for Drugs and Medical Devices for treating disorders of the patella in persons of all sexes aged ≥12 years. CLINICALTRIAL German Clinical Trials Register (DRKS) DRKS00023454; https://drks.de/search/en/trial/DRKS00023454
- 15 February 2023
- Published by Elsevier in Journal of Biomechanics
- Vol. 149, 111506
Comparison of statistical models for characterizing continuous differences between two biomechanical measurement systems
- 15 February 2023
- Published by Elsevier in Journal of Biomechanics
- Vol. 149, 111506
Comparison of statistical models for characterizing continuous differences between two biomechanical measurement systems
- Open Access
- 2 August 2021
- Published by Association for Research in Vision and Ophthalmology (ARVO) in Journal of Vision
- Vol. 21 (8) , 11
Icy road ahead—rapid adjustments of gaze–gait interactions during perturbed naturalistic walking
Most humans can walk effortlessly across uniform terrain even when they do not pay much attention to it. However, most natural terrain is far from uniform, and we need visual information to maintain stable gait. Recent advances in mobile eye-tracking technology have made it possible to study, in natural environments, how terrain affects gaze and thus the sampling of visual information. However, natural environments provide only limited experimental control, and some conditions cannot safely be tested. Typical laboratory setups, in contrast, are far from natural settings for walking. We used a setup consisting of a dual-belt treadmill, 240 \(^\circ\) projection screen, floor projection, three-dimensional optical motion tracking, and mobile eye tracking to investigate eye, head, and body movements during perturbed and unperturbed walking in a controlled yet naturalistic environment. In two experiments (N = 22 each), we simulated terrain difficulty by repeatedly inducing slipping through accelerating either of the two belts rapidly and unpredictably (Experiment 1) or sometimes following visual cues (Experiment 2). We quantified the distinct roles of eye and head movements for adjusting gaze on different time scales. While motor perturbations mainly influenced head movements, eye movements were primarily affected by the presence of visual cues. This was true both immediately following slips and—to a lesser extent—over the course of entire 5-min blocks. We find adapted gaze parameters already after the first perturbation in each block, with little transfer between blocks. In conclusion, gaze–gait interactions in experimentally perturbed yet naturalistic walking are adaptive, flexible, and effector specific.- 2 August 2021
- Published by Association for Research in Vision and Ophthalmology (ARVO) in Journal of Vision
- Vol. 21 (8) , 11
Open AccessIcy road ahead—rapid adjustments of gaze–gait interactions during perturbed naturalistic walking
Most humans can walk effortlessly across uniform terrain even when they do not pay much attention to it. However, most natural terrain is far from uniform, and we need visual information to maintain stable gait. Recent advances in mobile eye-tracking technology have made it possible to study, in natural environments, how terrain affects gaze and thus the sampling of visual information. However, natural environments provide only limited experimental control, and some conditions cannot safely be tested. Typical laboratory setups, in contrast, are far from natural settings for walking. We used a setup consisting of a dual-belt treadmill, 240 \(^\circ\) projection screen, floor projection, three-dimensional optical motion tracking, and mobile eye tracking to investigate eye, head, and body movements during perturbed and unperturbed walking in a controlled yet naturalistic environment. In two experiments (N = 22 each), we simulated terrain difficulty by repeatedly inducing slipping through accelerating either of the two belts rapidly and unpredictably (Experiment 1) or sometimes following visual cues (Experiment 2). We quantified the distinct roles of eye and head movements for adjusting gaze on different time scales. While motor perturbations mainly influenced head movements, eye movements were primarily affected by the presence of visual cues. This was true both immediately following slips and—to a lesser extent—over the course of entire 5-min blocks. We find adapted gaze parameters already after the first perturbation in each block, with little transfer between blocks. In conclusion, gaze–gait interactions in experimentally perturbed yet naturalistic walking are adaptive, flexible, and effector specific. - 23 March 2020
- Published by Taylor & Francis in Footwear Science
- Vol. 12 (2) , 113-122
A time-series based framework for exploring the unknown effects of shoe comfort-induced biomechanical adaptations
Footwear Science struggles at identifying the unknown effects of footwear interventions on the biomechanics of running. Those struggles may partly be explained by methodological and statistical issues, such as using discrete parameters to reduce the dimensionality of time series data or testing against unspecific null hypotheses. This paper evaluates a method to address some of these deficits by applying a time series-based machine learning approach (k-nearest neighbour classification (kNN), Euclidean distance). As an example, we used a data set containing a largely unknown footwear effect: The relationship between subjective comfort and the rollover movement during running. For this purpose, we collected kinematic data and subjective ratings from 22 runners running two times each in both their most comfortable and uncomfortable shoe selected from a pool of different neutral running shoes. The kNN algorithm performed highly accurately in distinguishing between the kinematics of different shoes. We also found that larger differences in subjective comfort perception between two shoes were associated with higher classification rates. The kNN method, however, does not allow for conclusions to be drawn about the causality or quality of the observed changes within the kinematic trajectories. Accordingly, we see the main scope of the presented method primarily in exploring complex data sets in cases where no meaningful hypothesis about the presumed biomechanical effects can be derived a priori. The subsequently acquired knowledge may be used to design larger-scale studies in which these findings can be investigated more systematically by means of more specific hypotheses and better estimates of sample sizes, respectively.
- 23 March 2020
- Published by Taylor & Francis in Footwear Science
- Vol. 12 (2) , 113-122
A time-series based framework for exploring the unknown effects of shoe comfort-induced biomechanical adaptations
Footwear Science struggles at identifying the unknown effects of footwear interventions on the biomechanics of running. Those struggles may partly be explained by methodological and statistical issues, such as using discrete parameters to reduce the dimensionality of time series data or testing against unspecific null hypotheses. This paper evaluates a method to address some of these deficits by applying a time series-based machine learning approach (k-nearest neighbour classification (kNN), Euclidean distance). As an example, we used a data set containing a largely unknown footwear effect: The relationship between subjective comfort and the rollover movement during running. For this purpose, we collected kinematic data and subjective ratings from 22 runners running two times each in both their most comfortable and uncomfortable shoe selected from a pool of different neutral running shoes. The kNN algorithm performed highly accurately in distinguishing between the kinematics of different shoes. We also found that larger differences in subjective comfort perception between two shoes were associated with higher classification rates. The kNN method, however, does not allow for conclusions to be drawn about the causality or quality of the observed changes within the kinematic trajectories. Accordingly, we see the main scope of the presented method primarily in exploring complex data sets in cases where no meaningful hypothesis about the presumed biomechanical effects can be derived a priori. The subsequently acquired knowledge may be used to design larger-scale studies in which these findings can be investigated more systematically by means of more specific hypotheses and better estimates of sample sizes, respectively.
- 28 June 2019
- Published by Taylor & Francis in Footwear Science
- Vol. 11 (sup1) , S162-S163
A time-series based pattern recognition method to analyze rollover kinematics in running
Footwear science struggles at identifying effects of footwear interventions on the biomechanics of running with many studies affected or biased by small samples, small effect sizes and substantial ...
- 28 June 2019
- Published by Taylor & Francis in Footwear Science
- Vol. 11 (sup1) , S162-S163
A time-series based pattern recognition method to analyze rollover kinematics in running
Footwear science struggles at identifying effects of footwear interventions on the biomechanics of running with many studies affected or biased by small samples, small effect sizes and substantial ...