Uncertainty Quantification with Support Vector Regression Prediction Models

Uncertainty quantification of petroleum reservoir models is one of the present challenges, which is usually approached with a wide range of geostatistical tools linked with statistical optimisation or/and inference algorithms. The paper considers a data driven approach in modelling uncertainty in spatial predictions. Proposed semi-supervised Support Vector Regression (SVR) model has demonstrated its capability to represent realistic features and describe stochastic variability and non-uniqueness of spatial properties. It is able to capture and preserve key spatial dependencies such as connectivity, which is often difficult to achieve with two-point geostatistical models. Semi-supervised SVR is designed to integrate various kinds of conditioning data and learn dependences from them. A stochastic semi-supervised SVR model is integrated into a Bayesian framework to quantify uncertainty with multiple models fitted to dynamic observations. The developed approach is illustrated with a reservoir case study. The resulting probabilistic production forecasts are described by uncertainty envelopes.

Prognostic significance of deep vein thrombosis in patients presenting with acute symptomatic pulmonary embolism.

RATIONALE: Concomitant deep vein thrombosis (DVT) in patients with acute pulmonary embolism (PE) has an uncertain prognostic significance. OBJECTIVES: In a cohort of patients with PE, this study compared the risk of death in those with and those without concomitant DVT. METHODS: We conducted a prospective cohort study of outpatients diagnosed with a first episode of acute symptomatic PE. Patients underwent bilateral lower extremity venous compression ultrasonography to assess for concomitant DVT. MEASUREMENTS AND MAIN RESULTS: The primary study outcome, all-cause mortality, and the secondary outcome of PE-specific mortality were assessed during the 3 months of follow-up after PE diagnosis. Multivariate Cox proportional hazards regression was done to adjust for significant covariates. Of 707 patients diagnosed with PE, 51.2% (362 of 707) had concomitant DVT and 10.9% (77 of 707) died during follow-up. Patients with concomitant DVT had an increased all-cause mortality (adjusted hazard ratio [HR], 2.05; 95% confidence interval [CI], 1.24 to 3.38; P = 0.005) and PE-specific mortality (adjusted HR, 4.25; 95% CI, 1.61 to 11.25; P = 0.04) compared with those without concomitant DVT. In an external validation cohort of 4,476 patients with acute PE enrolled in the international multicenter RIETE Registry, concomitant DVT remained a significant predictor of all-cause (adjusted HR, 1.66; 95% CI, 1.28 to 2.15; P < 0.001) and PE-specific mortality (adjusted HR, 2.01; 95% CI, 1.18 to 3.44; P = 0.01). CONCLUSIONS: In patients with a first episode of acute symptomatic PE, the presence of concomitant DVT is an independent predictor of death in the ensuing 3 months after diagnosis. Assessment of the thrombotic burden should assist with risk stratification of patients with acute PE.

Cervical cancer: incidence and survival in migrants within Spain

This study examined the incidence of cervical cancer and survival rates according to migrant experience of women from different regions of Spain to Girona, Catalonia (Spain). DESIGN--Using data from the population based cancer registry of Girona for the period 1980-89, crude and age adjusted incidence rates were calculated for local-born and first generation migrants from other Spanish regions. The age standardised rate ratio (SRR) was calculated and Cox's regression model was used to adjust survival according to migrant status for age and stage at diagnosis. MAIN RESULTS--The incidence of cervical cancer was significantly higher in first generation Spanish migrants compared with locally born women (SRR: 2.02; 95% CI 1.40:2.92). The stage at diagnosis was more advanced among migrants. Survival probability was significantly associated with stage at diagnosis, but age and region of birth were not. CONCLUSIONS--Migrants from the southern Spanish regions show a twofold excess in the incidence of cervical cancer compared with the Girona-born female population. Cases of cervical cancer in migrants are diagnosed at a more advanced stage and as a consequence have a poorer prognosis.

Complete and long-lasting regression of disseminated multiple skin melanoma metastases under treatment with cyclooxygenase-2 inhibitor.

Experimental and clinical evidence indicates that non-steroidal anti-inflammatory drugs and cyclooxygenase-2 inhibitors may have anti-cancer activities. Here we report on a patient with a metastatic melanoma of the leg who experienced a complete and sustained regression of skin metastases upon continuous single treatment with the cyclooxygenase-2 inhibitor rofecoxib. Our observations indicate that the inhibition of cyclooxygenase-2 can lead to the regression of disseminated skin melanoma metastases, even after failure of chemotherapy.

What is the influence of vaccination's routes on the regression of tumors located at mucosal sites?

Tumor-regressions following tumor-associated-antigen vaccination in animal models contrast with the limited clinical outcomes in cancer patients. Most animal studies however used subcutaneous-tumor-models and questions arise as whether these are relevant for tumors growing in mucosae; whether specific mucosal-homing instructions are required; and how this may be influenced by the tumor.

Risk factors of stroke mortality in the African region: a cohort study

Background: Population-based cohort studies of risk factors of stroke are scarce in developing countries and none has been done in the African region. We conducted a longitudinal study in the Seychelles (Indian Ocean, east of Kenya), a middle-income island state where the majority of the population is of African descent. Such data in Africa are important for international comparison and for advocacy in the region. Methods: Three examination surveys of cardiovascular risk factors were performed in independent samples representative of the general population aged 25-64 in 1989, 1994 and 2004 (n=1081, 1067, and 1255, respectively). Baseline risk factors data were linked with cause-specific mortality from vital statistics up to May 2007 (all deaths are medically certified in the Seychelles and kept in an electronic database). We considered stroke (any type) as a cause of death if the diagnosis was reported in any of the 4 fields in the death certificates for underlying and concomitant causes of death. Results. Among the 2479 persons aged 35-64 at baseline, 280 died including 56 with stroke during follow up (maximum: 18.2 years; mean: 10.2 years). In this age range, age-adjusted mortality rates (/100'000/year) were 969 for all cause and 187 for stroke; age-adjusted prevalence of high blood pressure (≥140/90 mmHg) was 48%. In multivariate Cox survival time regression, stroke mortality was increased by 18% and 35% for a 10-mmHg increase in systolic, respectively diastolic BP (p<0.001). Stroke mortality was also associated with age, smoking ≥5 cigarettes vs. no smoking (HR: 2.4; 95% CI: 1.2-4.8) and diabetes (HR: 1.9; 1.02-3.6) but not with sex, LDL-cholesterol intake, alcohol intake and professional occupation. Conclusion. This first population-based cohort study in the African region demonstrates high mortality rates from stroke in middle-aged adults and confirms associations with high BP and other risk factors. This emphasizes the importance of reducing BP and other modifiable risk factors in high risk individuals and in the general population as a main strategy to reduce the burden of stroke.

Bootstrapping pairs in Distance-Based Regression

La regressió basada en distàncies és un mètode de predicció que consisteix en dos passos: a partir de les distàncies entre observacions obtenim les variables latents, les quals passen a ser els regressors en un model lineal de mínims quadrats ordinaris. Les distàncies les calculem a partir dels predictors originals fent us d'una funció de dissimilaritats adequada. Donat que, en general, els regressors estan relacionats de manera no lineal amb la resposta, la seva selecció amb el test F usual no és possible. En aquest treball proposem una solució a aquest problema de selecció de predictors definint tests estadístics generalitzats i adaptant un mètode de bootstrap no paramètric per a l'estimació dels p-valors. Incluim un exemple numèric amb dades de l'assegurança d'automòbils.

Geomodelling of a fluvial system with semi-supervised support vector regression

Fluvial deposits are a challenge for modelling flow in sub-surface reservoirs. Connectivity and continuity of permeable bodies have a major impact on fluid flow in porous media. Contemporary object-based and multipoint statistics methods face a problem of robust representation of connected structures. An alternative approach to model petrophysical properties is based on machine learning algorithm ? Support Vector Regression (SVR). Semi-supervised SVR is able to establish spatial connectivity taking into account the prior knowledge on natural similarities. SVR as a learning algorithm is robust to noise and captures dependencies from all available data. Semi-supervised SVR applied to a synthetic fluvial reservoir demonstrated robust results, which are well matched to the flow performance

Modelling non-industrial private forest landowners' strategic decision making by using logistic regression and neural networks: case of predicting the choice of forest taxation basis

Summary

Retrospective feasibility study of simultaneous integrated boost in cervical cancer using Tomotherapy: the impact of organ motion and tumor regression.

BACKGROUND: Whole pelvis intensity modulated radiotherapy (IMRT) is increasingly being used to treat cervical cancer aiming to reduce side effects. Encouraged by this, some groups have proposed the use of simultaneous integrated boost (SIB) to target the tumor, either to get a higher tumoricidal effect or to replace brachytherapy. Nevertheless, physiological organ movement and rapid tumor regression throughout treatment might substantially reduce any benefit of this approach. PURPOSE: To evaluate the clinical target volume - simultaneous integrated boost (CTV-SIB) regression and motion during chemo-radiotherapy (CRT) for cervical cancer, and to monitor treatment progress dosimetrically and volumetrically to ensure treatment goals are met. METHODS AND MATERIALS: Ten patients treated with standard doses of CRT and brachytherapy were retrospectively re-planned using a helical Tomotherapy - SIB technique for the hypothetical scenario of this feasibility study. Target and organs at risk (OAR) were contoured on deformable fused planning-computed tomography and megavoltage computed tomography images. The CTV-SIB volume regression was determined. The center of mass (CM) was used to evaluate the degree of motion. The Dice's similarity coefficient (DSC) was used to assess the spatial overlap of CTV-SIBs between scans. A cumulative dose-volume histogram modeled estimated delivered doses. RESULTS: The CTV-SIB relative reduction was between 31 and 70%. The mean maximum CM change was 12.5, 9, and 3 mm in the superior-inferior, antero-posterior, and right-left dimensions, respectively. The CTV-SIB-DSC approached 1 in the first week of treatment, indicating almost perfect overlap. CTV-SIB-DSC regressed linearly during therapy, and by the end of treatment was 0.5, indicating 50% discordance. Two patients received less than 95% of the prescribed dose. Much higher doses to the OAR were observed. A multiple regression analysis showed a significant interaction between CTV-SIB reduction and OAR dose increase. CONCLUSIONS: The CTV-SIB had important regression and motion during CRT, receiving lower therapeutic doses than expected. The OAR had unpredictable shifts and received higher doses. The use of SIB without frequent adaptation of the treatment plan exposes cervical cancer patients to an unpredictable risk of under-dosing the target and/or overdosing adjacent critical structures. In that scenario, brachytherapy continues to be the gold standard approach.

Regression analysis of spatial data.

Many of the most interesting questions ecologists ask lead to analyses of spatial data. Yet, perhaps confused by the large number of statistical models and fitting methods available, many ecologists seem to believe this is best left to specialists. Here, we describe the issues that need consideration when analysing spatial data and illustrate these using simulation studies. Our comparative analysis involves using methods including generalized least squares, spatial filters, wavelet revised models, conditional autoregressive models and generalized additive mixed models to estimate regression coefficients from synthetic but realistic data sets, including some which violate standard regression assumptions. We assess the performance of each method using two measures and using statistical error rates for model selection. Methods that performed well included generalized least squares family of models and a Bayesian implementation of the conditional auto-regressive model. Ordinary least squares also performed adequately in the absence of model selection, but had poorly controlled Type I error rates and so did not show the improvements in performance under model selection when using the above methods. Removing large-scale spatial trends in the response led to poor performance. These are empirical results; hence extrapolation of these findings to other situations should be performed cautiously. Nevertheless, our simulation-based approach provides much stronger evidence for comparative analysis than assessments based on single or small numbers of data sets, and should be considered a necessary foundation for statements of this type in future.

Bootstrapping pairs in Distance-Based Regression

La regressió basada en distàncies és un mètode de predicció que consisteix en dos passos: a partir de les distàncies entre observacions obtenim les variables latents, les quals passen a ser els regressors en un model lineal de mínims quadrats ordinaris. Les distàncies les calculem a partir dels predictors originals fent us d'una funció de dissimilaritats adequada. Donat que, en general, els regressors estan relacionats de manera no lineal amb la resposta, la seva selecció amb el test F usual no és possible. En aquest treball proposem una solució a aquest problema de selecció de predictors definint tests estadístics generalitzats i adaptant un mètode de bootstrap no paramètric per a l'estimació dels p-valors. Incluim un exemple numèric amb dades de l'assegurança d'automòbils.

Robust accelerated failure time regression

Robust estimators for accelerated failure time models with asymmetric (or symmetric) error distribution and censored observations are proposed. It is assumed that the error model belongs to a log-location-scale family of distributions and that the mean response is the parameter of interest. Since scale is a main component of mean, scale is not treated as a nuisance parameter. A three steps procedure is proposed. In the first step, an initial high breakdown point S estimate is computed. In the second step, observations that are unlikely under the estimated model are rejected or down weighted. Finally, a weighted maximum likelihood estimate is computed. To define the estimates, functions of censored residuals are replaced by their estimated conditional expectation given that the response is larger than the observed censored value. The rejection rule in the second step is based on an adaptive cut-off that, asymptotically, does not reject any observation when the data are generat ed according to the model. Therefore, the final estimate attains full efficiency at the model, with respect to the maximum likelihood estimate, while maintaining the breakdown point of the initial estimator. Asymptotic results are provided. The new procedure is evaluated with the help of Monte Carlo simulations. Two examples with real data are discussed.