Prediction de l'année 1649. sur l'emprisonnement du prince du sang, surnommé la Cuirasse

[Mazarinade. 1650]

Strategies for sequential prediction of stationary time series

We present simple procedures for the prediction of a real valued sequence. The algorithms are based on a combinationof several simple predictors. We show that if the sequence is a realization of a bounded stationary and ergodic random process then the average of squared errors converges, almost surely, to that of the optimum, given by the Bayes predictor. We offer an analog result for the prediction of stationary gaussian processes.

On prediction of individual sequences

Sequential randomized prediction of an arbitrary binary sequence isinvestigated. No assumption is made on the mechanism of generating the bit sequence. The goal of the predictor is to minimize its relative loss, i.e., to make (almost) as few mistakes as the best ``expert'' in a fixed, possibly infinite, set of experts. We point out a surprising connection between this prediction problem and empirical process theory. First, in the special case of static (memoryless) experts, we completely characterize the minimax relative loss in terms of the maximum of an associated Rademacher process. Then we show general upper and lower bounds on the minimaxrelative loss in terms of the geometry of the class of experts. As main examples, we determine the exact order of magnitude of the minimax relative loss for the class of autoregressive linear predictors and for the class of Markov experts.

Prediction of myocardial infarction size using the SYNTAX score in patients treated with primary percutaneous coronary intervention for acute ST- segment elevation myocardial infarction

Objectives The relevance of the SYNTAX score for the particular case of patients with acute ST- segment elevation myocardial infarction (STEMI) undergoing primary percutaneous coronary intervention (PPCI)  has previously only been studied in the setting of post hoc analysis of large prospective randomized clinical trials. A "real-life" population approach has never been explored before. The aim of this study was to evaluate the impact of the SYNTAX score for the prediction of the myocardial infarction size, estimated by the creatin-kinase (CK) peak value, using the SYNTAX score in patients treated with primary coronary intervention for acute ST-segment elevation myocardial infarction. Methods The primary endpoint of the study was myocardial infarction size as measured by the CK peak value. The SYNTAX score was calculated retrospectively in 253 consecutive patients with acute ST-segment elevation myocardial infarction (STEMI) undergoing primary percutaneous coronary intervention (PPCI) in a large tertiary referral center in Switzerland, between January 2009 and June 2010. Linear regression analysis was performed to compare myocardial infarction size with the SYNTAX score. This same endpoint was then stratified according to SYNTAX score tertiles: low <22 (n=178), intermediate [22-32] (n=60), and high >=33 (n=15). Results There were no significant differences in terms of clinical characteristics between the three groups. When stratified according to the SYNTAX score tertiles, average CK peak values of 1985 (low<22), 3336 (intermediate [22-32]) and 3684 (high>=33) were obtained with a p-value <0.0001. Bartlett's test for equal variances between the three groups was 9.999 (p-value <0.0067). A moderate Pearson product-moment correlation coefficient (r=0.4074) with a high statistical significance level (p-value <0.0001) was found. The coefficient of determination (R^2=0.1660) showed that approximately 17% of the variation of CK peak value (myocardial infarction size) could be explained by the SYNTAX score, i.e. by the coronary disease complexity. Conclusion In an all-comers population, the SYNTAX score is an additional tool in predicting myocardial infarction size in patients treated with primary percutaneous coronary intervention (PPCI). The stratification of patients in different risk groups according to SYNTAX enables to identify a high-risk population that may warrant particular patient care.

Implementation study of a clinical prediction score to rule out cardiogenic chest pain in community: Cluster randomized trial

1.1 Fundamentals Chest pain is a common complaint in primary care patients (1 to 3% of all consultations) (1) and its aetiology can be miscellaneous, from harmless to potentially life threatening conditions. In primary care practice, the most prevalent aetiologies are: chest wall syndrome (43%), coronary heart disease (12%) and anxiety (7%) (2). In up to 20% of cases, potentially serious conditions as cardiac, respiratory or neoplasic diseases underlie chest pain. In this context, a large number of laboratory tests are run (42%) and over 16% of patients are referred to a specialist or hospitalized (2).¦A cardiovascular origin to chest pain can threaten patient's life and investigations run to exclude a serious condition can be expensive and involve a large number of exams or referral to specialist -­‐ often without real clinical need. In emergency settings, up to 80% of chest pains in patients are due to cardiovascular events (3) and scoring methods have been developed to identify conditions such as coronary heart disease (HD) quickly and efficiently (4-­‐6). In primary care, a cardiovascular origin is present in only about 12% of patients with chest pain (2) and general practitioners (GPs) need to exclude as safely as possible a potential serious condition underlying chest pain. A simple clinical prediction rule (CPR) like those available in emergency settings may therefore help GPs and spare time and extra investigations in ruling out CHD in primary care patients. Such a tool may also help GPs reassure patients with more common origin to chest pain.

Markers of atherosclerosis and inflammation for prediction of coronary heart disease in older adults.

Although both inflammatory and atherosclerosis markers have been associated with coronary heart disease (CHD) risk, data directly comparing their predictive value are limited. The authors compared the value of 2 atherosclerosis markers (ankle-arm index (AAI) and aortic pulse wave velocity (aPWV)) and 3 inflammatory markers (C-reactive protein (CRP), interleukin-6 (IL-6), and tumor necrosis factor-alpha (TNF-alpha)) in predicting CHD events. Among 2,191 adults aged 70-79 years at baseline (1997-1998) from the Health, Aging, and Body Composition Study cohort, the authors examined adjudicated incident myocardial infarction or CHD death ("hard" events) and "hard" events plus hospitalization for angina or coronary revascularization (total CHD events). During 8 years of follow-up between 1997-1998 and June 2007, 351 participants developed total CHD events (197 "hard" events). IL-6 (highest quartile vs. lowest: hazard ratio = 1.82, 95% confidence interval: 1.33, 2.49; P-trend < 0.001) and AAI (AAI </= 0.9 vs. AAI 1.01-1.30: hazard ratio = 1.57, 95% confidence interval: 1.14, 2.18) predicted CHD events above traditional risk factors and modestly improved global measures of predictive accuracy. CRP, TNF-alpha, and aPWV had weaker associations. IL-6 and AAI accurately reclassified 6.6% and 3.3% of participants, respectively (P's </= 0.05). Results were similar for "hard" CHD, with higher reclassification rates for AAI. IL-6 and AAI are associated with future CHD events beyond traditional risk factors and modestly improve risk prediction in older adults.

Robust response transformations based on optimal prediction

Nonlinear regression problems can often be reduced to linearity by transforming the response variable (e.g., using the Box-Cox family of transformations). The classic estimates of the parameter defining the transformation as well as of the regression coefficients are based on the maximum likelihood criterion, assuming homoscedastic normal errors for the transformed response. These estimates are nonrobust in the presence of outliers and can be inconsistent when the errors are nonnormal or heteroscedastic. This article proposes new robust estimates that are consistent and asymptotically normal for any unimodal and homoscedastic error distribution. For this purpose, a robust version of conditional expectation is introduced for which the prediction mean squared error is replaced with an M scale. This concept is then used to develop a nonparametric criterion to estimate the transformation parameter as well as the regression coefficients. A finite sample estimate of this criterion based on a robust version of smearing is also proposed. Monte Carlo experiments show that the new estimates compare favorably with respect to the available competitors.

Accounting information and the prediction of farm viability

Until recently farm management made little use of accounting and agriculture has been largely excluded from the scope of accounting standards. This article examines the current use of accounting in agriculture and points theneed to establish accounting standards for agriculture. Empirical evidence shows that accounting can make a significant contribution to agricultural management and farm viability and could also be important for other agents involved in agricultural decision making. Existing literature on failureprediction models and farm viability prediction studies provide the starting point for our research, in which two dichotomous logit models were applied to subsamples of viable and unviable farms in Catalonia, Spain. The firstmodel considered only non-financial variables, while the other also considered financial ones. When accounting variables were added to the model, a significant reduction in deviance was observed.

Improving generalized regression analysis for the spatial prediction of forest communities

Aim This study used data from temperate forest communities to assess: (1) five different stepwise selection methods with generalized additive models, (2) the effect of weighting absences to ensure a prevalence of 0.5, (3) the effect of limiting absences beyond the environmental envelope defined by presences, (4) four different methods for incorporating spatial autocorrelation, and (5) the effect of integrating an interaction factor defined by a regression tree on the residuals of an initial environmental model. Location State of Vaud, western Switzerland. Methods Generalized additive models (GAMs) were fitted using the grasp package (generalized regression analysis and spatial predictions, http://www.cscf.ch/grasp). Results Model selection based on cross-validation appeared to be the best compromise between model stability and performance (parsimony) among the five methods tested. Weighting absences returned models that perform better than models fitted with the original sample prevalence. This appeared to be mainly due to the impact of very low prevalence values on evaluation statistics. Removing zeroes beyond the range of presences on main environmental gradients changed the set of selected predictors, and potentially their response curve shape. Moreover, removing zeroes slightly improved model performance and stability when compared with the baseline model on the same data set. Incorporating a spatial trend predictor improved model performance and stability significantly. Even better models were obtained when including local spatial autocorrelation. A novel approach to include interactions proved to be an efficient way to account for interactions between all predictors at once. Main conclusions Models and spatial predictions of 18 forest communities were significantly improved by using either: (1) cross-validation as a model selection method, (2) weighted absences, (3) limited absences, (4) predictors accounting for spatial autocorrelation, or (5) a factor variable accounting for interactions between all predictors. The final choice of model strategy should depend on the nature of the available data and the specific study aims. Statistical evaluation is useful in searching for the best modelling practice. However, one should not neglect to consider the shapes and interpretability of response curves, as well as the resulting spatial predictions in the final assessment.

Prediction of postnatal outcome in fetuses with pulmonary hypoplasia by fetal-MRI: Comparison between lung volumetry and pulmonary signal intensity values

Purpose: Pulmonary hypoplasia is a determinant parameter for extra-uterine life. In the last years, MRI appears as a complement to US in order to evaluate the degree of pulmonary hypoplasia in foetuses with congenital anomalies, by using different methods - fetal lung volumetry (FLV), lung-to-liver signal intensity ratio (LLSIR)-. But until now, information about the correlation between the MRI prediction and the real postnatal outcome is limited. Methods and materials: We retrospectively reviewed the fetal MRI performed at our Institution in the last 8 years and selected the cases with suspicion of fetal pulmonary hypoplasia (n = 30). The pulmonary volumetry data of these foetuses were collected and the lung-to-liver signal intensity ratio (LLSIR) measures performed. These data were compared with those obtained from a control group of 25 foetuses considered as normal at MRI. The data of the study group were also correlated with the autopsy records or the post-natal clinical information of the patients. Results: As expected, the control group showed higher FLV and LLSIR values than the problem group at all gestational ages. Higher values of FLV and LLSIR were associated with a better post-natal outcome. Sensitivity, specificity, positive and negative predictive values and accuracy for the relative LLSIR and the relative FLV showed no significant differences. Conclusion: Our data show that not only the FLV but also the relative LLSIR inform about the degree of fetal lung development. This information may help to predict the fetal outcome and to evaluate the need for neonatal intensive care.

Genome-Wide Prediction Methods in Highly Diverse and Heterozygous Species: Proof-of-Concept through Simulation in Grapevine.

Nowadays, genome-wide association studies (GWAS) and genomic selection (GS) methods which use genome-wide marker data for phenotype prediction are of much potential interest in plant breeding. However, to our knowledge, no studies have been performed yet on the predictive ability of these methods for structured traits when using training populations with high levels of genetic diversity. Such an example of a highly heterozygous, perennial species is grapevine. The present study compares the accuracy of models based on GWAS or GS alone, or in combination, for predicting simple or complex traits, linked or not with population structure. In order to explore the relevance of these methods in this context, we performed simulations using approx 90,000 SNPs on a population of 3,000 individuals structured into three groups and corresponding to published diversity grapevine data. To estimate the parameters of the prediction models, we defined four training populations of 1,000 individuals, corresponding to these three groups and a core collection. Finally, to estimate the accuracy of the models, we also simulated four breeding populations of 200 individuals. Although prediction accuracy was low when breeding populations were too distant from the training populations, high accuracy levels were obtained using the sole core-collection as training population. The highest prediction accuracy was obtained (up to 0.9) using the combined GWAS-GS model. We thus recommend using the combined prediction model and a core-collection as training population for grapevine breeding or for other important economic crops with the same characteristics.

A simple randomized algorithm for consistent sequential prediction of ergodic time series

We present a simple randomized procedure for the prediction of a binary sequence. The algorithm uses ideas from recent developments of the theory of the prediction of individual sequences. We show that if thesequence is a realization of a stationary and ergodic random process then the average number of mistakes converges, almost surely, to that of the optimum, given by the Bayes predictor.

The predictive value of trabecular bone score (TBS) on whole lumbar vertebrae mechanics: an ex vivo study.

We investigated the association of trabecular bone score (TBS) with microarchitecture and mechanical behavior of human lumbar vertebrae. We found that TBS reflects vertebral trabecular microarchitecture and is an independent predictor of vertebral mechanics. However, the addition of TBS to areal BMD (aBMD) did not significantly improve prediction of vertebral strength. INTRODUCTION: The trabecular bone score (TBS) is a gray-level measure of texture using a modified experimental variogram which can be extracted from dual-energy X-ray absorptiometry (DXA) images. The current study aimed to confirm whether TBS is associated with trabecular microarchitecture and mechanics of human lumbar vertebrae, and if its combination with BMD improves prediction of fracture risk. METHODS: Lumbar vertebrae (L3) were harvested fresh from 16 donors. The anteroposterior and lateral bone mineral content (BMC) and areal BMD (aBMD) of the vertebral body were measured using DXA; then, the TBS was extracted using TBS iNsight software (Medimaps SA, France). The trabecular bone volume (Tb.BV/tissue volume, TV), trabecular thickness (Tb.Th), degree of anisotropy, and structure model index (SMI) were measured using microcomputed tomography. Quasi-static uniaxial compressive testing was performed on L3 vertebral bodies to assess failure load and stiffness. RESULTS: The TBS was significantly correlated to Tb.BV/TV and SMI (râeuro0/00=âeuro0/000.58 and -0.62; pâeuro0/00=âeuro0/000.02, 0.01), but not related to BMC and BMD. TBS was significantly correlated with stiffness (râeuro0/00=âeuro0/000.64; pâeuro0/00=âeuro0/000.007), independently of bone mass. Using stepwise multiple regression models, we failed to demonstrate that the combination of BMD and TBS was better at explaining mechanical behavior than either variable alone. However, the combination TBS, Tb.Th, and BMC did perform better than each parameter alone, explaining 79 % of the variability in stiffness. CONCLUSIONS: In our study, TBS was associated with microarchitecture parameters and with vertebral mechanical behavior, but TBS did not improve prediction of vertebral biomechanical properties in addition to aBMD.

Prediction of functional outcome 18 months after a first psychotic episode: a proton magnetic resonance spectroscopy study.

CONTEXT: Recent magnetic resonance imaging studies have attempted to relate volumetric brain measurements in early schizophrenia to clinical and functional outcome some years later. These studies have generally been negative, perhaps because gray and white matter volumes inaccurately assess the underlying dysfunction that might be predictive of outcome. OBJECTIVE: To investigate the predictive value of frontal and temporal spectroscopy measures for outcome in patients with first-episode psychoses. DESIGN: Left prefrontal cortex and left mediotemporal lobe voxels were assessed using proton magnetic resonance spectroscopy to provide the ratio of N-acetylaspartate (NAA) and choline-containing compounds to creatine and phosphocreatine (Cr) (NAA/Cr ratio). These data were used to predict outcome at 18 months after admission, as assessed by a systematic medical record audit. SETTING: Early psychosis clinic. PARTICIPANTS: Forty-six patients with first-episode psychosis. MAIN OUTCOME MEASURES: We used regression models that included age at imaging and duration of untreated psychosis to predict outcome scores on the Global Assessment of Functioning Scale, Clinical Global Impression scales, and Social and Occupational Functional Assessment Scale, as well as the number of admissions during the treatment period. We then further considered the contributions of premorbid function and baseline level of negative symptoms. RESULTS: The only spectroscopic predictor of outcome was the NAA/Cr ratio in the prefrontal cortex. Low scores on this variable were related to poorer outcome on all measures. In addition, the frontal NAA/Cr ratio explained 17% to 30% of the variance in outcome. CONCLUSIONS: Prefrontal neuronal dysfunction is an inconsistent feature of early psychosis; rather, it is an early marker of poor prognosis across the first years of illness. The extent to which this can be used to guide treatment and whether it predicts outcome some years after first presentation are questions for further research.

Prediction of subcutaneous fatty acid composition from ham of CLA fed boars and gilts using a NIRS fiber optic probe

The aim of this work was the use of NIR technology by direct application of a fiber optic probe on back fat to analyze the fatty acid composition of CLA fed boars and gilts. 265 animals were fed 3 different diets and the fatty acid profile of back fat from Gluteus medius was analyzed using gas chromatography and FT-NIR. Spectra were acquired using a Bruker Optics Matrix-F duplex spectrometer equipped with a fiber optic probe (IN-268-2). Oleic and stearic fatty acids were predicted accurately; myristic, vaccenic and linoleic fatty acids were predicted with lower accuracy, while palmitic and α-linolenic fatty acids were poorly predicted. The relative percentage of fatty acids and NIR spectra showed differences in fatty acid composition of back fat from pigs fed CLA which increased the relative percentage of SFA and PUFA while MUFA decreased. Results suggest that a NIR fiber optic probe can be used to predict total saturated and unsaturated fatty acid composition, as well as the percentage of stearic and oleic. NIR showed potential as a rapid and easily implemented method to discriminate carcasses from animals fed different diets.