The aim of the present study was to develop and validate an objective index for nociception level (NoL) of patients under general anesthesia, based on a combination of multiple physiological parameters. Twenty-five patients scheduled for elective surgery were enrolled. For clinical reference of NoL, the combined index of stimulus and analgesia was defined as a composite of the surgical stimulus level and a scaled effect-site concentration of opioid. The physiological parameters heart rate, heart rate variability (0.15-0.4 Hz band power), plethysmograph wave amplitude, skin conductance level, number of skin conductance fluctuations, and their time derivatives, were extracted. Two techniques to incorporate these parameters into a single index representing the NoL have been proposed: NoLlinear, based on an ordinary linear regression, and NoLnon-linear, based on a non-linear Random Forest regression. NoLlinear and NoLnon-linear significantly increased after moderate to severe noxious stimuli (Wilcoxon rank test, p < 0.01), while the individual parameters only partially responded. Receiver operating curve analysis showed that NoL index based on both techniques better discriminated noxious and non-noxious surgical events [area under curve (AUC) = 0.97] compared with individual parameters (AUC = 0.56-0.74). NoLnon-linear better ranked the level of nociception compared with NoLlinear (R = 0.88 vs. 0.77, p < 0.01). These results demonstrate the superiority of multi-parametric approach over any individual parameter in the evaluation of nociceptive response. In addition, advanced non-linear technique may have an advantage over ordinary linear regression for computing NoL index. Further research will define the usability of the NoL index as a clinical tool to assess the level of nociception during general anesthesia.

No abstract

In many practical applications of clustering, the objects to be clustered evolve over time, and a clustering result is desired at each time step. In such applications, evolutionary clustering typically outperforms traditional static clustering by producing clustering results that reflect long-term trends while being robust to short-term variations. Several evolutionary clustering algorithms have recently been proposed, often by adding a temporal smoothness penalty to the cost function of a static clustering method. In this paper, we introduce a different approach to evolutionary clustering by accurately tracking the time-varying proximities between objects followed by static clustering. We present an evolutionary clustering framework that adaptively estimates the optimal smoothing parameter using shrinkage estimation, a statistical approach that improves a naïve estimate using additional information. The proposed framework can be used to extend a variety of static clustering algorithms, including hierarchical, k-means, and spectral clustering, into evolutionary clustering algorithms. Experiments on synthetic and real data sets indicate that the proposed framework outperforms static clustering and existing evolutionary clustering algorithms in many scenarios.

No abstract

39 pagesInternational audienceThis paper introduces a novel distance measure for clustering high dimensional data based on the hitting time of two Minimal Spanning Trees (MST) grown sequentially from a pair of points by Prim's algorithm. When the proposed measure is used in conjunction with spectral clustering, we obtain a powerful clustering algorithm that is able to separate neighboring non-convex shaped clusters and to account for local as well as global geometric features of the data set. Remarkably, the new distance measure is a true metric even if the Prim algorithm uses a non-metric dissimilarity measure to compute the edges of the MST. This metric property brings added flexibility to the proposed method. In particular, the method is applied to clustering non Euclidean quantities, such as probability distributions or spectra, using the Kullback-Liebler divergence as a base measure. We reduce computational complexity by applying consensus clustering to a small ensemble of dual rooted MSTs. We show that the resultant consensus spectral clustering with dual rooted MST is competitive with other clustering methods, both in terms of clustering performance and computational complexity. We illustrate the proposed clustering algorithm on public domain benchmark data for which the ground truth is known, on one hand, and on real-world astrophysical data on the other hand