Data-driven healthcare: from patterns to actions

The era of big data opens up new opportunities in personalised medicine, preventive care, chronic disease management and in telemonitoring and managing of patients with implanted devices. The rich data accumulating within online services and internet companies provide a microscope to study human behaviour at scale, and to ask completely new questions about the interplay between behavioural patterns and health. In this paper, we shed light on a particular aspect of data-driven healthcare: autonomous decision-making. We first look at three examples where we can expect data-driven decisions to be taken autonomously by technology, with no or limited human intervention. We then discuss some of the technical and practical challenges that can be expected, and sketch the research agenda to address them.

Distinct characteristics of e13a2 versus e14a2 BCR-ABL1 driven chronic myeloid leukemia under first-line therapy with imatinib

The vast majority of chronic myeloid leukemia patients express a BCR-ABL1 fusion gene mRNA encoding a 210 kDa tyrosine kinase which promotes leukemic transformation. A possible differential impact of the corresponding BCR-ABL1 transcript variants e13a2 ("b2a2") and e14a2 ("b3a2") on disease phenotype and outcome is still a subject of debate. A total of 1105 newly diagnosed imatinib-treated patients were analyzed according to transcript type at diagnosis (e13a2, n=451; e14a2, n=496; e13a2+e14a2, n=158). No differences regarding age, sex, or Euro risk score were observed. A significant difference was found between e13a2 and e14a2 when comparing white blood cells (88 vs. 65 × 10(9)/L, respectively; P<0.001) and platelets (296 vs. 430 × 10(9)/L, respectively; P<0.001) at diagnosis, indicating a distinct disease phenotype. No significant difference was observed regarding other hematologic features, including spleen size and hematologic adverse events, during imatinib-based therapies. Cumulative molecular response was inferior in e13a2 patients (P=0.002 for major molecular response; P<0.001 for MR4). No difference was observed with regard to cytogenetic response and overall survival. In conclusion, e13a2 and e14a2 chronic myeloid leukemia seem to represent distinct biological entities. However, clinical outcome under imatinib treatment was comparable and no risk prediction can be made according to e13a2 versus e14a2 BCR-ABL1 transcript type at diagnosis. (clinicaltrials.gov identifier:00055874).

The role of climate-driven chemical weathering on soil production

Climate plays an important role in controlling rates of weathering and weathered regolith production. Regolith production functions, however, seldom take climate parameters into account. Based on a climate-dependent weathered regolith production model, at low denudation rates, relative regolith thicknesses are less sensitive to changes in precipitation rates, while at high denudation rates, small changes in climatic parameters can result in complete stripping of hillslopes. This pattern is compounded by the long residence times and system response times associated with low denudation rates, and vice versa. As others have shown, the transition between regolith-mantled and bedrock slopes is dependent on the ratio of denudation to production. Here, we further suggest that this is itself a function of precipitation rate and temperature. We suggest that climatic parameters can be easily incorporated into existing soil production models and that such additions improve the predictive power of soil production models. (C) 2013 Elsevier B.V. All rights reserved.

3D Intervertebral Disc Localization and Segmentation from MR Images by Data-Driven Regression and Classification

In this paper we propose a new fully-automatic method for localizing and segmenting 3D intervertebral discs from MR images, where the two problems are solved in a unified data-driven regression and classification framework. We estimate the output (image displacements for localization, or fg/bg labels for segmentation) of image points by exploiting both training data and geometric constraints simultaneously. The problem is formulated in a unified objective function which is then solved globally and efficiently. We validate our method on MR images of 25 patients. Taking manually labeled data as the ground truth, our method achieves a mean localization error of 1.3 mm, a mean Dice metric of 87%, and a mean surface distance of 1.3 mm. Our method can be applied to other localization and segmentation tasks.

Automatic X-ray landmark detection and shape segmentation via data-driven joint estimation of image displacements

In this paper, we propose a new method for fully-automatic landmark detection and shape segmentation in X-ray images. To detect landmarks, we estimate the displacements from some randomly sampled image patches to the (unknown) landmark positions, and then we integrate these predictions via a voting scheme. Our key contribution is a new algorithm for estimating these displacements. Different from other methods where each image patch independently predicts its displacement, we jointly estimate the displacements from all patches together in a data driven way, by considering not only the training data but also geometric constraints on the test image. The displacements estimation is formulated as a convex optimization problem that can be solved efficiently. Finally, we use the sparse shape composition model as the a priori information to regularize the landmark positions and thus generate the segmented shape contour. We validate our method on X-ray image datasets of three different anatomical structures: complete femur, proximal femur and pelvis. Experiments show that our method is accurate and robust in landmark detection, and, combined with the shape model, gives a better or comparable performance in shape segmentation compared to state-of-the art methods. Finally, a preliminary study using CT data shows the extensibility of our method to 3D data.

Localization and Segmentation of 3D Intervertebral Discs in MR Images by Data Driven Estimation

This paper addresses the problem of fully-automatic localization and segmentation of 3D intervertebral discs (IVDs) from MR images. Our method contains two steps, where we first localize the center of each IVD, and then segment IVDs by classifying image pixels around each disc center as foreground (disc) or background. The disc localization is done by estimating the image displacements from a set of randomly sampled 3D image patches to the disc center. The image displacements are estimated by jointly optimizing the training and test displacement values in a data-driven way, where we take into consideration both the training data and the geometric constraint on the test image. After the disc centers are localized, we segment the discs by classifying image pixels around disc centers as background or foreground. The classification is done in a similar data-driven approach as we used for localization, but in this segmentation case we are aiming to estimate the foreground/background probability of each pixel instead of the image displacements. In addition, an extra neighborhood smooth constraint is introduced to enforce the local smoothness of the label field. Our method is validated on 3D T2-weighted turbo spin echo MR images of 35 patients from two different studies. Experiments show that compared to state of the art, our method achieves better or comparable results. Specifically, we achieve for localization a mean error of 1.6-2.0 mm, and for segmentation a mean Dice metric of 85%-88% and a mean surface distance of 1.3-1.4 mm.

Service Level Agreements-Driven Management of Distributed Applications in Cloud Computing Environments

Cloud Computing enables provisioning and distribution of highly scalable services in a reliable, on-demand and sustainable manner. However, objectives of managing enterprise distributed applications in cloud environments under Service Level Agreement (SLA) constraints lead to challenges for maintaining optimal resource control. Furthermore, conflicting objectives in management of cloud infrastructure and distributed applications might lead to violations of SLAs and inefficient use of hardware and software resources. This dissertation focusses on how SLAs can be used as an input to the cloud management system, increasing the efficiency of allocating resources, as well as that of infrastructure scaling. First, we present an extended SLA semantic model for modelling complex service-dependencies in distributed applications, and for enabling automated cloud infrastructure management operations. Second, we describe a multi-objective VM allocation algorithm for optimised resource allocation in infrastructure clouds. Third, we describe a method of discovering relations between the performance indicators of services belonging to distributed applications and then using these relations for building scaling rules that a CMS can use for automated management of VMs. Fourth, we introduce two novel VM-scaling algorithms, which optimally scale systems composed of VMs, based on given SLA performance constraints. All presented research works were implemented and tested using enterprise distributed applications.

North Atlantic Eddy-Driven Jet in interglacial and glacial winter climates

The atmospheric westerly flow in the North Atlantic (NA) sector is dominated by atmospheric waves or eddies generating via momentum flux convergence, the so-called eddy-driven jet. The position of this jet is variable and shows for the present-day winter climate three preferred latitudinal states: a northern, central, and southernposition in the NA. Here, the authors analyze the behavior of the eddy-driven jet under different glacial and interglacial boundary conditions using atmosphere–land-only simulations with the CCSM4 climate model. As state-of-the-art climate models tend to underestimate the trimodality of the jet latitude, the authors apply a bias correction and successfully extract the trimodal behavior of the jet within CCSM4. The analysis shows that during interglacial times (i.e., the early Holocene and the Eemian) the preferred jet positions are rather stable and the observed multimodality is the typical interglacial character of the jet. During glacial times, the jet is strongly enhanced, its position is shifted southward, and the trimodal behavior vanishes. This is mainly due to the presence of the Laurentide ice sheet (LIS). The LIS enhances stationary waves downstream, thereby accelerating and displacing the NA eddy-driven jet by anomalous stationary momentum flux convergence. Additionally, changes in the transient eddy activity caused by topography changes as well as other glacial boundary conditions lead to an acceleration of the westerly winds over the southern NA at the expenseof more northernareas. Consequently, bothstationaryand transient eddiesfoster the southward shift of the NA eddy-driven jet during glacial winter times.

Strengthening the Reporting of Observational Studies in Epidemiology for respondent-driven sampling studies: "STROBE-RDS" statement.

OBJECTIVES Respondent-driven sampling (RDS) is a new data collection methodology used to estimate characteristics of hard-to-reach groups, such as the HIV prevalence in drug users. Many national public health systems and international organizations rely on RDS data. However, RDS reporting quality and available reporting guidelines are inadequate. We carried out a systematic review of RDS studies and present Strengthening the Reporting of Observational Studies in Epidemiology for RDS Studies (STROBE-RDS), a checklist of essential items to present in RDS publications, justified by an explanation and elaboration document. STUDY DESIGN AND SETTING We searched the MEDLINE (1970-2013), EMBASE (1974-2013), and Global Health (1910-2013) databases to assess the number and geographical distribution of published RDS studies. STROBE-RDS was developed based on STROBE guidelines, following Guidance for Developers of Health Research Reporting Guidelines. RESULTS RDS has been used in over 460 studies from 69 countries, including the USA (151 studies), China (70), and India (32). STROBE-RDS includes modifications to 12 of the 22 items on the STROBE checklist. The two key areas that required modification concerned the selection of participants and statistical analysis of the sample. CONCLUSION STROBE-RDS seeks to enhance the transparency and utility of research using RDS. If widely adopted, STROBE-RDS should improve global infectious diseases public health decision making.

Appraisal-driven somatovisceral response patterning: effects of intrinsic pleasantness and goal conduciveness.

Several componential emotion theories suggest that appraisal outcomes trigger characteristic somatovisceral changes that facilitate information processing and prepare the organism for adaptive behavior. The current study tested predictions derived from Scherer's Component Process Model. Participants viewed unpleasant and pleasant pictures (intrinsic pleasantness appraisal) and were asked to concurrently perform either an arm extension or an arm flexion, leading to an increase or a decrease in picture size. Increasing pleasant stimuli and decreasing unpleasant stimuli were considered goal conducive; decreasing pleasant stimuli and increasing unpleasant stimuli were considered goal obstructive (goal conduciveness appraisal). Both appraisals were marked by several somatovisceral changes (facial electromyogram, heart rate (HR)). As predicted, the changes induced by the two appraisals showed similar patterns. Furthermore, HR results, compared with data of earlier studies, suggest that the adaptive consequences of both appraisals may be mediated by stimulus proximity.