Quantifying drug induced dyskinesia in Parkinson's disease patients using standardized videos
ABSTRACT This paper presents a video based method to quantify drug induced dyskinesias in Parkinson's disease (PD) patients. Dyskinetic movement in standard clinical videos of patients is analyzed by tracking landmark points on the video frames using non-rigid image registration. The novel application of Point Distribution Models (PDM) allows geometric variations and covariations of the landmark points to be captured from each video sequence. The PDM parameters represent quantifiable information that can be used to rate dyskinesia effectively, analogously to a neurologist's strategy of assessing the movement of multiple body parts simultaneously to effectively rate dyskinesia. A heuristic decision function is then developed using the PDM parameters to quantify the severity of the dyskinesia. The severity score using our decision function showed a high correlation to the dyskinesia rating of a neurologist on the corresponding patient videos.
[show abstract] [hide abstract]
ABSTRACT: There has been a lot of interest in recent years in using inertial sensors (accelerometers and gyroscopes) to monitor movement disorder motion and monitor the efficacy of treatment options. Two of the most prominent movement disorders, which are under evaluation in this research paper, are essential tremor (ET) and Parkinson's disease (PD). These movement disorders are first evaluated to show that ET and PD motion often depict more (tremor) motion content in the 3-12 Hz frequency band of interest than control data and that such tremor motion can be characterized using inertial sensors. As well, coherence analysis is used to compare between pairs of many of the six degrees-of-freedom of motions under evaluation, to determine the similarity in tremor motion for the various degrees-of-freedom at different frequency bands of interest. It was quite surprising that this coherence analysis depicts that there is a statistically significant relationship using coherence analysis when differentiating between control and effectively medicated PD motion. The statistical analysis uncovers the novel finding that PD medication induced dyskinesia is depicted within coherence data from inertial signals. Dyskinesia is involuntary motion or the absence of intended motion, and it is a common side effect among medicated PD patients. The results show that inertial sensors can be used to differentiate between effectively medicated PD motion and control motion; such a differentiation can often be difficult to perform with the human eye because effectively medicated PD patients tend to not produce much tremor. As well, the finding that PD motion, when well medicated, does still differ significantly from control motion allows for researchers to quantify potential deficiencies in the use of medication. By using inertial sensors to spot such deficiencies, as outlined in this research paper, it is hoped that medications with even a larger degree of efficacy can be created in the future.Sensors 01/2012; 12(3):3512-27. · 1.74 Impact Factor