4046405

Development of a worldwide network for the purpose of hypothesis-driven research through data mining

(Entwicklung eines weltweiten Netzwerks mit dem Ziel der hypothesenbasierten Forschung mittels Datenerhebung)

A significant limitation with biomechanical gait research is that most laboratories function in isolation and have access to a limited number of subjects. Therefore, in order to overcome this limitation we have developed a worldwide network of clinical and research partners all linked to a common research database. This network represents a world.s-first in biomedical engineering and clinical health research. As examples, our most recent data-mining efforts have yielded new kinematic methods to predict the timing of foot strike, independent of striking technique and also novel methods to evaluate error in anatomical marker placement and thereby improve between-center reliability of kinematic data. Our most recent work identified differences in running gait kinematics for large cohorts of competitive and recreational male and female runners across a wide spectrum of age. This study improves upon prior literature by increasing the sample size by 4-44 times and the results suggest that the discrimination of running kinematics between male and female runners is a complex classification problem, reflecting relationships amongst many kinematic variables. Therefore, simplistic approaches, such as analyzing several discrete variables and the use inferential statistics, are not sufficient. Our data-mining efforts have also revealed that when higher-order mathematical techniques are used, differences and/or binomial classification accuracy using biomechanical data can often reach 95% simply as a result of the large volumes of data and the mathematical technique employed. Thus, we strongly believe that researchers must first develop hypothesis-driven research questions and also combine clinical and biomechanical data in order to develop meaningful and applicable context to the results. We also know that this goal of extracting and analysing big data via high-performance computing is only possible through a collaborative and international community: one we continue to build.
© Copyright 2014 International Calgary Running Symposium, August 14-17, 2014. Alle Rechte vorbehalten.

Bibliographische Detailangaben
Schlagworte:
Notationen:Ausdauersportarten Naturwissenschaften und Technik
Veröffentlicht in:International Calgary Running Symposium, August 14-17, 2014
Sprache:Englisch
Veröffentlicht: 2014
Online-Zugang:https://fis.dshs-koeln.de/portal/files/217822/upload.pdf
Seiten:44
Dokumentenarten:Kongressband, Tagungsbericht
Level:hoch