This paper presents the results of a pilot study to assess the feasibility of using accelerometer data to estimate the severity of symptoms and motor complications in patients with Parkinson’s disease. A Support Vector Machine (SVM) classifier was implemented to estimate the severity of tremor, bradykinesia and dyskinesia from accelerometer data features. SVM-based estimates were compared with clinical scores derived via visual inspection of video recordings taken while patients performed a series of standardized motor tasks. The analysis of the video recordings was performed by clinicians trained in the use of scales for the assessment of the severity of Parkinsonian symptoms and motor complications. Results derived from the accelerometer time series were analyzed to assess the effect on the estimation of clinical scores of the duration of the window utilized to derive segments (to eventually compute data features) from the accelerometer data, the use of different support vector machine kernels and misclassification cost values, and the use of data features derived from different motor tasks. Results were also analyzed to assess which combinations of data features carried enough information to reliably assess the severity of symptoms and motor complications. Combinations of data features were compared taking into consideration the computational cost associated with estimating each data feature on the nodes of a body sensor network and the effect of using such data features on the reliability of SVM-based estimates of the severity of Parkinsonian symptoms and motor complications.

In this paper, we attempted to classify the acceleration signals for walking along a corridor and on stairs by using the wavelet-based fractal analysis method. In addition, the wavelet-based fractal analysis method was used to evaluate the gait of elderly subjects and patients with Parkinson's disease. The triaxial acceleration signals were measured close to the center of gravity of the body while the subject walked along a corridor and up and down stairs continuously. Signal measurements were recorded from 10 healthy young subjects and 11 elderly subjects. For comparison, two patients with Parkinson's disease participated in the level walking. The acceleration signal in each direction was decomposed to seven detailed signals at different wavelet scales by using the discrete wavelet transform. The variances of detailed signals at scales 7 to 1 were calculated. The fractal dimension of the acceleration signal was then estimated from the slope of the variance progression. The fractal dimensions were significantly different among the three types of walking for individual subjects (p< 0.01) and showed a high reproducibility. Our results suggest that the fractal dimensions are effective for classifying the walking types. Moreover, the fractal dimensions were significantly higher for the elderly subjects than for the young subjects (p < 0.01). For the patients with Parkinson's disease, the fractal dimensions tended to be higher than those of healthy subjects. These results suggest that the acceleration signals change into a more complex pattern with aging and with Parkinson's disease, and the fractal dimension can be used to evaluate the gait of elderly subjects and patients with Parkinson's disease.

Accelerometer data is being used to evaluate the success of rehabilitation efforts on movements, from shoulder to finger tips, for patients who have suffered strokes.

Glioblastoma multiforme (GBM) is the most common and malignant of all human primary brain cancers, in which drug treatment is still one of the most effective treatments. However, existing drug discovery and development methods rely on the use of conventional two-dimensional (2D) cell cultures, which have been proven to be poor representatives of native physiology. Here, we developed a novel three-dimensional (3D) brain cancer chip composed of photo-polymerizable poly(ethylene) glycol diacrylate (PEGDA) hydrogel for drug screening. This chip can be produced after a few seconds of photolithography and requires no silicon wafer, replica molding, and plasma bonding like microfluidic devices made of poly(dimethylsiloxane) (PDMS). We then cultured glioblastoma cells (U87), which formed 3D brain cancer tissues on the chip, and used the GBM chip to perform combinatorial treatment of Pitavastatin and Irinotecan. The results indicate that this chip is capable of high-throughput GBM cancer spheroids formation, multiple-simultaneous drug administration, and a massive parallel testing of drug response. Our approach is easily reproducible, and this chip has the potential to be a powerful platform in cases such as high-throughput drug screening and prolonged drug release. The chip is also commercially promising for other clinical applications, including 3D cell culture and micro-scale tissue engineering.

No abstract