The prediction of speed and incline in outdoor running in humans using accelerometry.

PURPOSE: To explore whether triaxial accelerometric measurements can be utilized to accurately assess speed and incline of running in free-living conditions. METHODS: Body accelerations during running were recorded at the lower back and at the heel by a portable data logger in 20 human subjects, 10 men, and 10 women. After parameterizing body accelerations, two neural networks were designed to recognize each running pattern and calculate speed and incline. Each subject ran 18 times on outdoor roads at various speeds and inclines; 12 runs were used to calibrate the neural networks whereas the 6 other runs were used to validate the model. RESULTS: A small difference between the estimated and the actual values was observed: the square root of the mean square error (RMSE) was 0.12 m x s(-1) for speed and 0.014 radiant (rad) (or 1.4% in absolute value) for incline. Multiple regression analysis allowed accurate prediction of speed (RMSE = 0.14 m x s(-1)) but not of incline (RMSE = 0.026 rad or 2.6% slope). CONCLUSION: Triaxial accelerometric measurements allows an accurate estimation of speed of running and incline of terrain (the latter with more uncertainty). This will permit the validation of the energetic results generated on the treadmill as applied to more physiological unconstrained running conditions.

Prediction of difficult intubation with advanced face recognition techniques: a preliminary study

Introduction: Difficult tracheal intubation remains a constant and significant source of morbidity and mortality in anaesthetic practice. Insufficient airway assessment in the preoperative period continues to be a major cause of unanticipated difficult intubation. Although many risk factors have already been identified, preoperative airway evaluation is not always regarded as a standard procedure and the respective weight of each risk factor remains unclear. Moreover the predictive scores available are not sensitive, moderately specific and often operator-dependant. In order to improve the preoperative detection of patients at risk for difficult intubation, we developed a system for automated and objective evaluation of morphologic criteria of the face and neck using video recordings and advanced techniques borrowed from face recognition. Method and results: Frontal video sequences were recorded in 5 healthy volunteers. During the video recording, subjects were requested to perform maximal flexion-extension of the neck and to open wide the mouth with tongue pulled out. A robust and real-time face tracking system was then applied, allowing to automatically identify and map a grid of 55 control points on the face, which were tracked during head motion. These points located important features of the face, such as the eyebrows, the nose, the contours of the eyes and mouth, and the external contours, including the chin. Moreover, based on this face tracking, the orientation of the head could also be estimated at each frame of the video sequence. Thus, we could infer for each frame the pitch angle of the head pose (related to the vertical rotation of the head) and obtain the degree of head extension. Morphological criteria used in the most frequent cited predictive scores were also extracted, such as mouth opening, degree of visibility of the uvula or thyreo-mental distance. Discussion and conclusion: Preliminary results suggest the high feasibility of the technique. The next step will be the application of the same automated and objective evaluation to patients who will undergo tracheal intubation. The difficulties related to intubation will be then correlated to the biometric characteristics of the patients. The objective in mind is to analyze the biometrics data with artificial intelligence algorithms to build a highly sensitive and specific predictive test.

Local and global error models to improve uncertainty quantification

In groundwater applications, Monte Carlo methods are employed to model the uncertainty on geological parameters. However, their brute-force application becomes computationally prohibitive for highly detailed geological descriptions, complex physical processes, and a large number of realizations. The Distance Kernel Method (DKM) overcomes this issue by clustering the realizations in a multidimensional space based on the flow responses obtained by means of an approximate (computationally cheaper) model; then, the uncertainty is estimated from the exact responses that are computed only for one representative realization per cluster (the medoid). Usually, DKM is employed to decrease the size of the sample of realizations that are considered to estimate the uncertainty. We propose to use the information from the approximate responses for uncertainty quantification. The subset of exact solutions provided by DKM is then employed to construct an error model and correct the potential bias of the approximate model. Two error models are devised that both employ the difference between approximate and exact medoid solutions, but differ in the way medoid errors are interpolated to correct the whole set of realizations. The Local Error Model rests upon the clustering defined by DKM and can be seen as a natural way to account for intra-cluster variability; the Global Error Model employs a linear interpolation of all medoid errors regardless of the cluster to which the single realization belongs. These error models are evaluated for an idealized pollution problem in which the uncertainty of the breakthrough curve needs to be estimated. For this numerical test case, we demonstrate that the error models improve the uncertainty quantification provided by the DKM algorithm and are effective in correcting the bias of the estimate computed solely from the MsFV results. The framework presented here is not specific to the methods considered and can be applied to other combinations of approximate models and techniques to select a subset of realizations

Prediction markets supporting technology assessment

In this thesis, we study the use of prediction markets for technology assessment. We particularly focus on their ability to assess complex issues, the design constraints required for such applications and their efficacy compared to traditional techniques. To achieve this, we followed a design science research paradigm, iteratively developing, instantiating, evaluating and refining the design of our artifacts. This allowed us to make multiple contributions, both practical and theoretical. We first showed that prediction markets are adequate for properly assessing complex issues. We also developed a typology of design factors and design propositions for using these markets in a technology assessment context. Then, we showed that they are able to solve some issues related to the R&D portfolio management process and we proposed a roadmap for their implementation. Finally, by comparing the instantiation and the results of a multi-criteria decision method and a prediction market, we showed that the latter are more efficient, while offering similar results. We also proposed a framework for comparing forecasting methods, to identify the constraints based on contingency factors. In conclusion, our research opens a new field of application of prediction markets and should help hasten their adoption by enterprises. Résumé français: Dans cette thèse, nous étudions l'utilisation de marchés de prédictions pour l'évaluation de nouvelles technologies. Nous nous intéressons plus particulièrement aux capacités des marchés de prédictions à évaluer des problématiques complexes, aux contraintes de conception pour une telle utilisation et à leur efficacité par rapport à des techniques traditionnelles. Pour ce faire, nous avons suivi une approche Design Science, développant itérativement plusieurs prototypes, les instanciant, puis les évaluant avant d'en raffiner la conception. Ceci nous a permis de faire de multiples contributions tant pratiques que théoriques. Nous avons tout d'abord montré que les marchés de prédictions étaient adaptés pour correctement apprécier des problématiques complexes. Nous avons également développé une typologie de facteurs de conception ainsi que des propositions de conception pour l'utilisation de ces marchés dans des contextes d'évaluation technologique. Ensuite, nous avons montré que ces marchés pouvaient résoudre une partie des problèmes liés à la gestion des portes-feuille de projets de recherche et développement et proposons une feuille de route pour leur mise en oeuvre. Finalement, en comparant la mise en oeuvre et les résultats d'une méthode de décision multi-critère et d'un marché de prédiction, nous avons montré que ces derniers étaient plus efficaces, tout en offrant des résultats semblables. Nous proposons également un cadre de comparaison des méthodes d'évaluation technologiques, permettant de cerner au mieux les besoins en fonction de facteurs de contingence. En conclusion, notre recherche ouvre un nouveau champ d'application des marchés de prédiction et devrait permettre d'accélérer leur adoption par les entreprises.

A new accelerometric method to assess the daily walking practice.

OBJECTIVE: To describe a method to obtain a profile of the duration and intensity (speed) of walking periods over 24 hours in women under free-living conditions. DESIGN: A new method based on accelerometry was designed for analyzing walking activity. In order to take into account inter-individual variability of acceleration, an individual calibration process was used. Different experiments were performed to highlight the variability of acceleration vs walking speed relationship, to analyze the speed prediction accuracy of the method, and to test the assessment of walking distance and duration over 24-h. SUBJECTS: Twenty-eight women were studied (mean+/-s.d.) age: 39.3+/-8.9 y; body mass: 79.7+/-11.1 kg; body height: 162.9+/-5.4 cm; and body mass index (BMI) 30.0+/-3.8 kg/m(2). RESULTS: Accelerometer output was significantly correlated with speed during treadmill walking (r=0.95, P<0.01), and short unconstrained walks (r=0.86, P<0.01), although with a large inter-individual variation of the regression parameters. By using individual calibration, it was possible to predict walking speed on a standard urban circuit (predicted vs measured r=0.93, P<0.01, s.e.e.=0.51 km/h). In the free-living experiment, women spent on average 79.9+/-36.0 (range: 31.7-168.2) min/day in displacement activities, from which discontinuous short walking activities represented about 2/3 and continuous ones 1/3. Total walking distance averaged 2.1+/-1.2 (range: 0.4-4.7) km/day. It was performed at an average speed of 5.0+/-0.5 (range: 4.1-6.0) km/h. CONCLUSION: An accelerometer measuring the anteroposterior acceleration of the body can estimate walking speed together with the pattern, intensity and duration of daily walking activity.

Accurate and efficient simulation of multiphase flow in a heterogeneous reservoir by using error estimate and control in the multiscale finite-volume framework

The multiscale finite-volume (MSFV) method is designed to reduce the computational cost of elliptic and parabolic problems with highly heterogeneous anisotropic coefficients. The reduction is achieved by splitting the original global problem into a set of local problems (with approximate local boundary conditions) coupled by a coarse global problem. It has been shown recently that the numerical errors in MSFV results can be reduced systematically with an iterative procedure that provides a conservative velocity field after any iteration step. The iterative MSFV (i-MSFV) method can be obtained with an improved (smoothed) multiscale solution to enhance the localization conditions, with a Krylov subspace method [e.g., the generalized-minimal-residual (GMRES) algorithm] preconditioned by the MSFV system, or with a combination of both. In a multiphase-flow system, a balance between accuracy and computational efficiency should be achieved by finding a minimum number of i-MSFV iterations (on pressure), which is necessary to achieve the desired accuracy in the saturation solution. In this work, we extend the i-MSFV method to sequential implicit simulation of time-dependent problems. To control the error of the coupled saturation/pressure system, we analyze the transport error caused by an approximate velocity field. We then propose an error-control strategy on the basis of the residual of the pressure equation. At the beginning of simulation, the pressure solution is iterated until a specified accuracy is achieved. To minimize the number of iterations in a multiphase-flow problem, the solution at the previous timestep is used to improve the localization assumption at the current timestep. Additional iterations are used only when the residual becomes larger than a specified threshold value. Numerical results show that only a few iterations on average are necessary to improve the MSFV results significantly, even for very challenging problems. Therefore, the proposed adaptive strategy yields efficient and accurate simulation of multiphase flow in heterogeneous porous media.

Outcome Prediction after Cardiac Arrest Treated with Hypothermia

Rationale: Clinical and electrophysiological prognostic markers of brain anoxia have been mostly evaluated in comatose survivors of out hospital cardiac arrest (OHCA) after standard resuscitation, but their predictive value in patients treated with mild induced hypothermia (IH) is unknown. The objective of this study was to identify a predictive score of independent clinical and electrophysiological variables in comatose OHCA survivors treated with IH, aiming at a maximal positive predictive value (PPV) and a high negative predictive value (NPV) for mortality. Methods: We prospectively studied consecutive adult comatose OHCA survivors from April 2006 to May 2009, treated with mild IH to 33-34_C for 24h at the intensive care unit of the Lausanne University Hospital, Switzerland. IH was applied using an external cooling method. As soon as subjects passively rewarmed (body temperature >35_C) they underwent EEG and SSEP recordings (off sedation), and were examined by experienced neurologists at least twice. Patients with status epilepticus were treated with AED for at least 24h. A multivariable logistic regression was performed to identify independent predictors of mortality at hospital discharge. These were used to formulate a predictive score. Results: 100 patients were studied; 61 died. Age, gender and OHCA etiology (cardiac vs. non-cardiac) did not differ among survivors and nonsurvivors. Cardiac arrest type (non-ventricular fibrillation vs. ventricular fibrillation), time to return of spontaneous circulation (ROSC) >25min, failure to recover all brainstem reflexes, extensor or no motor response to pain, myoclonus, presence of epileptiform discharges on EEG, EEG background unreactive to pain, and bilaterally absent N20 on SSEP, were all significantly associated with mortality. Absent N20 was the only variable showing no false positive results. Multivariable logistic regression identified four independent predictors (Table). These were used to construct the score, and its predictive values were calculated after a cut-off of 0-1 vs. 2-4 predictors. We found a PPV of 1.00 (95% CI: 0.93-1.00), a NPV of 0.81 (95% CI: 0.67-0.91) and an accuracy of 0.93 for mortality. Among 9 patients who were predicted to survive by the score but eventually died, only 1 had absent N20. Conclusions: Pending validation in a larger cohort, this simple score represents a promising tool to identify patients who will survive, and most subjects who will not, after OHCA and IH. Furthermore, while SSEP are 100% predictive of poor outcome but not available in most hospitals, this study identifies EEG background reactivity as an important predictor after OHCA. The score appears robust even without SSEP, suggesting that SSEP and other investigations (e.g., mismatch negativity, serum NSE) might be principally needed to enhance prognostication in the small subgroup of patients failing to improve despite a favorable score.

An adaptive multiscale method for density-driven instabilities

Accurate modeling of flow instabilities requires computational tools able to deal with several interacting scales, from the scale at which fingers are triggered up to the scale at which their effects need to be described. The Multiscale Finite Volume (MsFV) method offers a framework to couple fine-and coarse-scale features by solving a set of localized problems which are used both to define a coarse-scale problem and to reconstruct the fine-scale details of the flow. The MsFV method can be seen as an upscaling-downscaling technique, which is computationally more efficient than standard discretization schemes and more accurate than traditional upscaling techniques. We show that, although the method has proven accurate in modeling density-driven flow under stable conditions, the accuracy of the MsFV method deteriorates in case of unstable flow and an iterative scheme is required to control the localization error. To avoid large computational overhead due to the iterative scheme, we suggest several adaptive strategies both for flow and transport. In particular, the concentration gradient is used to identify a front region where instabilities are triggered and an accurate (iteratively improved) solution is required. Outside the front region the problem is upscaled and both flow and transport are solved only at the coarse scale. This adaptive strategy leads to very accurate solutions at roughly the same computational cost as the non-iterative MsFV method. In many circumstances, however, an accurate description of flow instabilities requires a refinement of the computational grid rather than a coarsening. For these problems, we propose a modified iterative MsFV, which can be used as downscaling method (DMsFV). Compared to other grid refinement techniques the DMsFV clearly separates the computational domain into refined and non-refined regions, which can be treated separately and matched later. This gives great flexibility to employ different physical descriptions in different regions, where different equations could be solved, offering an excellent framework to construct hybrid methods.

The systematic profiling of false identity documents: method validation and performance evaluation using seizures known to originate from common and different sources

False identity documents constitute a potential powerful source of forensic intelligence because they are essential elements of transnational crime and provide cover for organized crime. In previous work, a systematic profiling method using false documents' visual features has been built within a forensic intelligence model. In the current study, the comparison process and metrics lying at the heart of this profiling method are described and evaluated. This evaluation takes advantage of 347 false identity documents of four different types seized in two countries whose sources were known to be common or different (following police investigations and dismantling of counterfeit factories). Intra-source and inter-sources variations were evaluated through the computation of more than 7500 similarity scores. The profiling method could thus be validated and its performance assessed using two complementary approaches to measuring type I and type II error rates: a binary classification and the computation of likelihood ratios. Very low error rates were measured across the four document types, demonstrating the validity and robustness of the method to link documents to a common source or to differentiate them. These results pave the way for an operational implementation of a systematic profiling process integrated in a developed forensic intelligence model.

Ruling out coronary heart disease in primary care: external validation of a clinical prediction rule.

BACKGROUND: The Marburg Heart Score (MHS) aims to assist GPs in safely ruling out coronary heart disease (CHD) in patients presenting with chest pain, and to guide management decisions. AIM: To investigate the diagnostic accuracy of the MHS in an independent sample and to evaluate the generalisability to new patients. DESIGN AND SETTING: Cross-sectional diagnostic study with delayed-type reference standard in general practice in Hesse, Germany. METHOD: Fifty-six German GPs recruited 844 males and females aged ≥ 35 years, presenting between July 2009 and February 2010 with chest pain. Baseline data included the items of the MHS. Data on the subsequent course of chest pain, investigations, hospitalisations, and medication were collected over 6 months and were reviewed by an independent expert panel. CHD was the reference condition. Measures of diagnostic accuracy included the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, likelihood ratios, and predictive values. RESULTS: The AUC was 0.84 (95% confidence interval [CI] = 0.80 to 0.88). For a cut-off value of 3, the MHS showed a sensitivity of 89.1% (95% CI = 81.1% to 94.0%), a specificity of 63.5% (95% CI = 60.0% to 66.9%), a positive predictive value of 23.3% (95% CI = 19.2% to 28.0%), and a negative predictive value of 97.9% (95% CI = 96.2% to 98.9%). CONCLUSION: Considering the diagnostic accuracy of the MHS, its generalisability, and ease of application, its use in clinical practice is recommended.

Does the physical disector method provide an accurate estimation of sensory neuron number in rat dorsal root ganglia?

The physical disector is a method of choice for estimating unbiased neuron numbers; nevertheless, calibration is needed to evaluate each counting method. The validity of this method can be assessed by comparing the estimated cell number with the true number determined by a direct counting method in serial sections. We reconstructed a 1/5 of rat lumbar dorsal root ganglia taken from two experimental conditions. From each ganglion, images of 200 adjacent semi-thin sections were used to reconstruct a volumetric dataset (stack of voxels). On these stacks the number of sensory neurons was estimated and counted respectively by physical disector and direct counting methods. Also, using the coordinates of nuclei from the direct counting, we simulate, by a Matlab program, disector pairs separated by increasing distances in a ganglion model. The comparison between the results of these approaches clearly demonstrates that the physical disector method provides a valid and reliable estimate of the number of sensory neurons only when the distance between the consecutive disector pairs is 60 microm or smaller. In these conditions the size of error between the results of physical disector and direct counting does not exceed 6%. In contrast when the distance between two pairs is larger than 60 microm (70-200 microm) the size of error increases rapidly to 27%. We conclude that the physical dissector method provides a reliable estimate of the number of rat sensory neurons only when the separating distance between the consecutive dissector pairs is no larger than 60 microm.

Analysis and spatial modeling of the indoor radon Swiss data

The present research deals with an important public health threat, which is the pollution created by radon gas accumulation inside dwellings. The spatial modeling of indoor radon in Switzerland is particularly complex and challenging because of many influencing factors that should be taken into account. Indoor radon data analysis must be addressed from both a statistical and a spatial point of view. As a multivariate process, it was important at first to define the influence of each factor. In particular, it was important to define the influence of geology as being closely associated to indoor radon. This association was indeed observed for the Swiss data but not probed to be the sole determinant for the spatial modeling. The statistical analysis of data, both at univariate and multivariate level, was followed by an exploratory spatial analysis. Many tools proposed in the literature were tested and adapted, including fractality, declustering and moving windows methods. The use of Quan-tité Morisita Index (QMI) as a procedure to evaluate data clustering in function of the radon level was proposed. The existing methods of declustering were revised and applied in an attempt to approach the global histogram parameters. The exploratory phase comes along with the definition of multiple scales of interest for indoor radon mapping in Switzerland. The analysis was done with a top-to-down resolution approach, from regional to local lev¬els in order to find the appropriate scales for modeling. In this sense, data partition was optimized in order to cope with stationary conditions of geostatistical models. Common methods of spatial modeling such as Κ Nearest Neighbors (KNN), variography and General Regression Neural Networks (GRNN) were proposed as exploratory tools. In the following section, different spatial interpolation methods were applied for a par-ticular dataset. A bottom to top method complexity approach was adopted and the results were analyzed together in order to find common definitions of continuity and neighborhood parameters. Additionally, a data filter based on cross-validation was tested with the purpose of reducing noise at local scale (the CVMF). At the end of the chapter, a series of test for data consistency and methods robustness were performed. This lead to conclude about the importance of data splitting and the limitation of generalization methods for reproducing statistical distributions. The last section was dedicated to modeling methods with probabilistic interpretations. Data transformation and simulations thus allowed the use of multigaussian models and helped take the indoor radon pollution data uncertainty into consideration. The catego-rization transform was presented as a solution for extreme values modeling through clas-sification. Simulation scenarios were proposed, including an alternative proposal for the reproduction of the global histogram based on the sampling domain. The sequential Gaussian simulation (SGS) was presented as the method giving the most complete information, while classification performed in a more robust way. An error measure was defined in relation to the decision function for data classification hardening. Within the classification methods, probabilistic neural networks (PNN) show to be better adapted for modeling of high threshold categorization and for automation. Support vector machines (SVM) on the contrary performed well under balanced category conditions. In general, it was concluded that a particular prediction or estimation method is not better under all conditions of scale and neighborhood definitions. Simulations should be the basis, while other methods can provide complementary information to accomplish an efficient indoor radon decision making.

Individual prediction of cognitive decline in mild cognitive impairment using support vector machine-based analysis of diffusion tensor imaging data.

Although cross-sectional diffusion tensor imaging (DTI) studies revealed significant white matter changes in mild cognitive impairment (MCI), the utility of this technique in predicting further cognitive decline is debated. Thirty-five healthy controls (HC) and 67 MCI subjects with DTI baseline data were neuropsychologically assessed at one year. Among them, there were 40 stable (sMCI; 9 single domain amnestic, 7 single domain frontal, 24 multiple domain) and 27 were progressive (pMCI; 7 single domain amnestic, 4 single domain frontal, 16 multiple domain). Fractional anisotropy (FA) and longitudinal, radial, and mean diffusivity were measured using Tract-Based Spatial Statistics. Statistics included group comparisons and individual classification of MCI cases using support vector machines (SVM). FA was significantly higher in HC compared to MCI in a distributed network including the ventral part of the corpus callosum, right temporal and frontal pathways. There were no significant group-level differences between sMCI versus pMCI or between MCI subtypes after correction for multiple comparisons. However, SVM analysis allowed for an individual classification with accuracies up to 91.4% (HC versus MCI) and 98.4% (sMCI versus pMCI). When considering the MCI subgroups separately, the minimum SVM classification accuracy for stable versus progressive cognitive decline was 97.5% in the multiple domain MCI group. SVM analysis of DTI data provided highly accurate individual classification of stable versus progressive MCI regardless of MCI subtype, indicating that this method may become an easily applicable tool for early individual detection of MCI subjects evolving to dementia.

Experimental analysis and computer prediction of CTF/NFI transcription factor DNA binding sites.

Accurate prediction of transcription factor binding sites is needed to unravel the function and regulation of genes discovered in genome sequencing projects. To evaluate current computer prediction tools, we have begun a systematic study of the sequence-specific DNA-binding of a transcription factor belonging to the CTF/NFI family. Using a systematic collection of rationally designed oligonucleotides combined with an in vitro DNA binding assay, we found that the sequence specificity of this protein cannot be represented by a simple consensus sequence or weight matrix. For instance, CTF/NFI uses a flexible DNA binding mode that allows for variations of the binding site length. From the experimental data, we derived a novel prediction method using a generalised profile as a binding site predictor. Experimental evaluation of the generalised profile indicated that it accurately predicts the binding affinity of the transcription factor to natural or synthetic DNA sequences. Furthermore, the in vitro measured binding affinities of a subset of oligonucleotides were found to correlate with their transcriptional activities in transfected cells. The combined computational-experimental approach exemplified in this work thus resulted in an accurate prediction method for CTF/NFI binding sites potentially functioning as regulatory regions in vivo.

Prediction of Recanalization Trumps Prediction of Tissue Fate: The Penumbra: A Dual-edged Sword.

BACKGROUND AND PURPOSE: To determine whether infarct core or penumbra is the more significant predictor of outcome in acute ischemic stroke, and whether the results are affected by the statistical method used. METHODS: Clinical and imaging data were collected in 165 patients with acute ischemic stroke. We reviewed the noncontrast head computed tomography (CT) to determine the Alberta Score Program Early CT score and assess for hyperdense middle cerebral artery. We reviewed CT-angiogram for site of occlusion and collateral flow score. From perfusion-CT, we calculated the volumes of infarct core and ischemic penumbra. Recanalization status was assessed on early follow-up imaging. Clinical data included age, several time points, National Institutes of Health Stroke Scale at admission, treatment type, and modified Rankin score at 90 days. Two multivariate regression analyses were conducted to determine which variables predicted outcome best. In the first analysis, we did not include recanalization status among the potential predicting variables. In the second, we included recanalization status and its interaction between perfusion-CT variables. RESULTS: Among the 165 study patients, 76 had a good outcome (modified Rankin score ≤2) and 89 had a poor outcome (modified Rankin score >2). In our first analysis, the most important predictors were age (P<0.001) and National Institutes of Health Stroke Scale at admission (P=0.001). The imaging variables were not important predictors of outcome (P>0.05). In the second analysis, when the recanalization status and its interaction with perfusion-CT variables were included, recanalization status and perfusion-CT penumbra volume became the significant predictors (P<0.001). CONCLUSIONS: Imaging prediction of tissue fate, more specifically imaging of the ischemic penumbra, matters only if recanalization can also be predicted.