•  
  •  
 

Delta University Scientific Journal

Delta University Scientific Journal

Abstract

X-Ray or video raster stereography are used for the progress control of the FED therapy but applied only at intervals of months. A short-term evaluation would allow to adjust the therapy parameters based on the individual therapy progression and could also provide a direct feedback for patient. Therefore, this study aims to isolate parameters for a short-term progression monitoring by applying machine learning algorithms on a set of 130 posture characteristics. A measuring procedure using the DIERS formetric 4D optical measuring system was developed and validated on six patients. The measuring procedure was repeated eight times (four days, each morning and afternoon). Eight parameters were evaluated. The Wilcoxon signed rank test and the Friedman test were used to verify the statistical significance. In order to identify small changes in posture correlating with the applied treatment a hierarchical cluster analysis was performed. The evaluation shows that the parameters pelvic tilt, kyphosis angle and lordosis angle changed significantly between the individual measuring points, but not across all eight parameters. The data is highly dependent on the daily form and cooperation of the patient. The cluster classification is not determined on the basis of the four measurement points, but on the basis of patient individuality. Hierarchical clustering can classify new patients to match them with successful treatment plans of similar cases. By further optimizing the setting parameters a better cluster result should be achieved. More measurements will be made to expand the database. In order to obtain a short-term patient monitoring, other methods of artificial intelligence especially neural networks will be considered.

Download

Included in

Life Sciences Commons

Share

COinS