Quantitative Assessment of the Arm/Hand Movements in Parkinson's Disease Using a Wireless Armband Device.

We present an approach for quantitative assessment of the arm/hand movements in patients with Parkinson's disease (PD), from sensor data acquired with a wearable, wireless armband device (Myo sensor). We propose new Movement Performance Indicators that can be adopted by practitioners for the quantitative evaluation of motor performance and support their clinical evaluations. In addition, specific Movement Performance Indicators can indicate the presence of the bradykinesia symptom. The study includes seventeen PD patients and sixteen age-matched controls. A set of representative arm/hand movements is defined under the supervision of movement disorder specialist. In order to assist the evaluations, and for progress monitoring purposes, as well as for assessing the amount of bradykinesia in PD, a total set of 84 Movement Performance Indicators are computed from the sensor readings. Subsequently, we investigate whether wireless armband device, with the use of the proposed Movement Performance Indicators can be utilized: (1) for objective and precise quantitative evaluation of the arm/hand movements of Parkinson's patients, (2) for assessment of the bradykinesia motor symptom, and (3) as an adequate low-cost alternative for the sensor glove. We conducted extensive analysis of proposed Movement Performance Indicators and results are indicating following clinically relevant characteristics: (i) adequate reliability as measured by ICC; (ii) high accuracy in discrimination between the patients and controls, and between the disease stages (support to disease diagnosis and progress monitoring, respectively); (iii) substantial difference in comparison between the left-hand and the right-hand movements across controls and patients, as well as between disease stage groups; (iv) statistically significant correlation with clinical scales (tapping test and UPDRS-III Motor Score); and (v) quantitative evaluation of bradykinesia symptom. Results suggest that the proposed approach has a potential to be adopted by physicians, to afford them with quantitative, objective and precise methods and data during clinical evaluations and support the assessment of bradykinesia.

A robust data scaling algorithm to improve classification accuracies in biomedical data.

BACKGROUND: Machine learning models have been adapted in biomedical research and practice for knowledge discovery and decision support. While mainstream biomedical informatics research focuses on developing more accurate models, the importance of data preprocessing draws less attention. We propose the Generalized Logistic (GL) algorithm that scales data uniformly to an appropriate interval by learning a generalized logistic function to fit the empirical cumulative distribution function of the data. The GL algorithm is simple yet effective; it is intrinsically robust to outliers, so it is particularly suitable for diagnostic/classification models in clinical/medical applications where the number of samples is usually small; it scales the data in a nonlinear fashion, which leads to potential improvement in accuracy. RESULTS: To evaluate the effectiveness of the proposed algorithm, we conducted experiments on 16 binary classification tasks with different variable types and cover a wide range of applications. The resultant performance in terms of area under the receiver operation characteristic curve (AUROC) and percentage of correct classification showed that models learned using data scaled by the GL algorithm outperform the ones using data scaled by the Min-max and the Z-score algorithm, which are the most commonly used data scaling algorithms. CONCLUSION: The proposed GL algorithm is simple and effective. It is robust to outliers, so no additional denoising or outlier detection step is needed in data preprocessing. Empirical results also show models learned from data scaled by the GL algorithm have higher accuracy compared to the commonly used data scaling algorithms.

Structured feature selection using coordinate descent optimization.

BACKGROUND: Existing feature selection methods typically do not consider prior knowledge in the form of structural relationships among features. In this study, the features are structured based on prior knowledge into groups. The problem addressed in this article is how to select one representative feature from each group such that the selected features are jointly discriminating the classes. The problem is formulated as a binary constrained optimization and the combinatorial optimization is relaxed as a convex-concave problem, which is then transformed into a sequence of convex optimization problems so that the problem can be solved by any standard optimization algorithm. Moreover, a block coordinate gradient descent optimization algorithm is proposed for high dimensional feature selection, which in our experiments was four times faster than using a standard optimization algorithm. RESULTS: In order to test the effectiveness of the proposed formulation, we used microarray analysis as a case study, where genes with similar expressions or similar molecular functions were grouped together. In particular, the proposed block coordinate gradient descent feature selection method is evaluated on five benchmark microarray gene expression datasets and evidence is provided that the proposed method gives more accurate results than the state-of-the-art gene selection methods. Out of 25 experiments, the proposed method achieved the highest average AUC in 13 experiments while the other methods achieved higher average AUC in no more than 6 experiments. CONCLUSION: A method is developed to select a feature from each group. When the features are grouped based on similarity in gene expression, we showed that the proposed algorithm is more accurate than state-of-the-art gene selection methods that are particularly developed to select highly discriminative and less redundant genes. In addition, the proposed method can exploit any grouping structure among features, while alternative methods are restricted to using similarity based grouping.

Effectiveness of Multiple Blood-Cleansing Interventions in Sepsis, Characterized in Rats.

Sepsis is a serious, life-threatening condition that presents a growing problem in medicine, but there is still no satisfying solution for treating it. Several blood cleansing approaches recently gained attention as promising interventions that target the main site of problem development-the blood. The focus of this study is an evaluation of the theoretical effectiveness of hemoadsorption therapy and pathogen reduction therapy. This is evaluated using the mathematical model of Murine sepsis, and the results of over 2,200 configurations of single and multiple intervention therapies simulated on 5,000 virtual subjects suggest the advantage of pathogen reduction over hemoadsorption therapy. However, a combination of two approaches is found to take advantage of their complementary effects and outperform either therapy alone. The conducted computational experiments provide unprecedented evidence that the combination of two therapies synergistically enhances the positive effects beyond the simple superposition of the benefits of two approaches. Such a characteristic could have a profound influence on the way sepsis treatment is conducted.