55 research outputs found
State space modelling of extreme values with particle filters
No full textState space models are a flexible class of Bayesian model that can be used to smoothly capture non-stationarity. Observations are assumed independent given a latent state process so that their distribution can change gradually over time. Sequential Monte Carlo methods known as particle filters provide an approach to inference for such models whereby observations are added to the fit sequentially. Though originally developed for on-line inference, particle filters, along with related particle smoothers, often provide the best approach for off-line inference. This thesis develops new results for particle filtering and in particular develops a new particle smoother that has a computational complexity that is linear in the number of Monte Carlo samples. This compares favourably with the quadratic complexity of most of its competitors resulting in greater accuracy within a given time frame. The statistical analysis of extremes is important in many fields where the largest or smallest values have the biggest effect. Accurate assessments of the likelihood of extreme events are crucial to judging how severe they could be. While the extreme values of a stationary time series are well understood, datasets of extremes often contain varying degrees of non-stationarity. How best to extend standard extreme value models to account for non-stationary series is a topic of ongoing research. The thesis develops inference methods for extreme values of univariate and multivariate non-stationary processes using state space models fitted using particle methods. Though this approach has been considered previously in the univariate case, we identify problems with the existing method and provide solutions and extensions to it. The application of the methodology is illustrated through the analysis of a series of world class athletics running times, extreme temperatures at a site in the Antarctic, and sea-level extremes on the east coast of England
Spatial analysis and simulation of extreme coastal flooding scenarios for national-scale emergency planning
No full textThe UK has a long history of coastal flooding, driven by large-scale low-pressure weather systems which can result in flooding over large spatial areas. Traditional coastal flood risk analysis is, however, often undertaken at local scales and hence does not consider the likelihood of simultaneous flooding over larger areas. The flooding within the UK over the Winter of 2013/2014 was notable both for its long duration, lasting over two months, and its spatial extent, affecting many different areas of England and Wales. It is thus apparent that to plan and prepare for these types of extreme event it is necessary to consider the likelihood of flood events arising at different locations simultaneously (i.e. to consider the spatial dependence of extreme flood events). This paper describes the application of a state-of-the-art multivariate extreme value methodology to extreme sea levels and wave conditions around the coast of England and Wales. The output of the analysis comprises a synthetic set of extreme but plausible events that explicitly captures the dependence between sea conditions at different spatial locations around the coast. These simulated extreme events can be used for emergency management and advanced flood risk analysis
A sequential smoothing algorithm with linear computational cost.
No full textIn this paper we propose a new particle smoother that has a computational complexity of O(N), where N is the number of particles. This compares favourably with the O(N2) computational cost of most smoothers. The new method also overcomes some degeneracy problems in existing algorithms. Through simulation studies we show that substantial gains in efficiency are obtained for practical amounts of computational cost. It is shown both through these simulation studies, and by the analysis of an athletics dataset, that our new method also substantially outperforms the simple filter-smoother, the only other smoother with computational cost that is O(N)
The challenges of including historical events using Bayesian methods to improve flood flow estimates in the United Kingdom: A practitioner's point of view
No full textEstimates of design flood flows; are important for the design of a wide variety of civil engineering structures. In the United Kingdom, the Flood Estimation Handbook (FEH) methodologies are used by practitioners to estimate flood flows. Until recently it was challenging for practitioners to include additional non‐continuous flood information, such as historical flood descriptions from historical archives, in their analyses, to reduce the uncertainty within the FEH approaches. This paper shows how Bayesian statistical methods can be applied to historical data which have degrees of uncertainty associated with then to improve design flood flows. The paper uses the River Avon at Evesham in the United Kingdom as a case study to illustrate the advantages of the method. The inclusion of historical information at this site improves the estimates of the one in 100 year flood flow compared to the values generated by the FEH pooling group method. The paper makes recommendations as to how practitioners could be encouraged to use historical flood water levels in their analysis of floods more regularly
Serial measurement of pancreatic stone protein for the early detection of sepsis in intensive care unit patients: a prospective multicentric study.
No full textBACKGROUND
The early recognition and management of sepsis improves outcomes. Biomarkers may help in identifying earlier sub-clinical signs of sepsis. We explored the potential of serial measurements of C-reactive protein (CRP), procalcitonin (PCT) and pancreatic stone protein (PSP) for the early recognition of sepsis in patients hospitalized in the intensive care unit (ICU).
METHODS
This was a multicentric international prospective observational clinical study conducted in 14 ICUs in France, Switzerland, Italy, and the United Kingdom. Adult ICU patients at risk of nosocomial sepsis were included. A biomarker-blinded adjudication committee identified sepsis events and the days on which they began. The association of clinical sepsis diagnoses with the trajectories of PSP, CRP, and PCT in the 3 days preceding these diagnoses of sepsis were tested for markers of early sepsis detection. The performance of the biomarkers in sepsis diagnosis was assessed by receiver operating characteristic (ROC) analysis.
RESULTS
Of the 243 patients included, 53 developed nosocomial sepsis after a median of 6 days (interquartile range, 3-8 days). Clinical sepsis diagnosis was associated with an increase in biomarkers value over the 3 days preceding this diagnosis [PSP (p = 0.003), PCT (p = 0.025) and CRP (p = 0.009)]. PSP started to increase 5 days before the clinical diagnosis of sepsis, PCT 3 and CRP 2 days, respectively. The area under the ROC curve at the time of clinical sepsis was similar for all markers (PSP, 0.75; CRP, 0.77; PCT, 0.75).
CONCLUSIONS
While the diagnostic accuracy of PSP, CRP and PCT for sepsis were similar in this cohort, serial PSP measurement demonstrated an increase of this marker the days preceding the onset of signs necessary to clinical diagnose sepsis. This observation justifies further evaluation of the potential clinical benefit of serial PSP measurement in the management of critically ill patients developing nosocomial sepsis. Trial registration The study has been registered at ClinicalTrials.gov (no. NCT03474809), on March 16, 2018. https://www.clinicaltrials.gov/ct2/show/NCT03474809?term=NCT03474809&draw=2&rank=1
Is Drotrecogin alfa (activated) for adults with severe sepsis, cost-effective in routine clinical practice?
No full textINTRODUCTION: Previous cost-effectiveness analyses (CEA) reported that Drotrecogin alfa (DrotAA) is cost-effective based on a Phase III clinical trial (PROWESS). There is little evidence on whether DrotAA is cost-effective in routine clinical practice. We assessed whether DrotAA is cost-effective in routine practice for adult patients with severe sepsis and multiple organ systems failing. METHODS: This CEA used data from a prospective cohort study that compared DrotAA versus no DrotAA (control) for severe sepsis patients with multiple organ systems failing admitted to critical care units in England, Wales, and Northern Ireland. The cohort study used case-mix and mortality data from a national audit, linked with a separate audit of DrotAA infusions. Re-admissions to critical care and corresponding mortality were recorded for four years. Patients receiving DrotAA (n = 1,076) were matched to controls (n = 1,650) with a propensity score (Pscore), and Genetic Matching (GenMatch). The CEA projected long-term survival to report lifetime incremental costs per quality-adjusted life year (QALY) overall, and for subgroups with two or three to five organ systems failing at baseline. RESULTS: The incremental costs per QALY for DrotAA were £30,000 overall, and £16,000 for the subgroups with three to five organ systems failing. For patients with two organ systems failing, DrotAA resulted in an average loss of one QALY at an incremental cost of £15,000. When the subgroup with two organ systems was restricted to patients receiving DrotAA within 24 hours, DrotAA led to a gain of 1.2 QALYs at a cost per QALY of £11,000. The results were robust to other assumptions including the approach taken to projecting long-term outcomes. CONCLUSIONS: DrotAA is cost-effective in routine practice for severe sepsis patients with three to five organ systems failing. For patients with two organ systems failing, this study could not provide unequivocal evidence on the cost-effectiveness of DrotAA
Prophylactic heparin in patients with severe sepsis treated with drotrecogin alfa (activated)
No full textRATIONALE: Patients with severe sepsis frequently receive prophylactic heparin during drotrecogin alfa (activated) (DrotAA) treatment due to risk of venous thromboembolic events (VTEs). Biological plausibility exists for heparin to reduce DrotAA efficacy and/or increase bleeding. OBJECTIVES: Primary: demonstrate in adult patients with severe sepsis receiving DrotAA treatment that 28-day mortality was equivalent for patients treated with concomitant prophylactic heparin compared with placebo; secondary: safety and VTE incidence. METHODS: International, randomized, double-blind, phase 4, equivalence-design trial (n = 1994). Patients were eligible if indicated for and receiving DrotAA treatment under the country's approved label. Study drug (low molecular weight/unfractionated heparin) or placebo (saline) was administered every 12 hours during DrotAA infusion (24 ug/kg/hr for 96 hr). In patients on baseline heparin and randomized to placebo, heparin was stopped. MEASUREMENTS AND MAIN RESULTS: Twenty-eight-day mortality was not equivalent between treatment groups. Heparin mortality was numerically lower (28.3 vs. 31.9%; p = 0.08). In the prospectively defined subgroup of patients exposed to heparin at baseline, patients receiving placebo experienced higher mortality (35.6 vs. 26.9%; p = 0.005). For safety, significant differences were observed during Days 0-6 for any bleeding event (placebo, n = 78; heparin, n = 105; p = 0.049) and ischemic stroke during Days 0-6 (placebo, n = 12; heparin, n = 3; p = 0.02) and Days 0-28 (placebo, n = 17; heparin, n = 5; p = 0.009). The VTE rate was low, with no statistical difference between groups (0-6 d, p = 0.60; 0-28 d, p = 0.26). CONCLUSIONS: Compared with placebo, concomitant prophylactic heparin was not equivalent, did not increase 28-day mortality, and had an acceptable safety profile in patients with severe sepsis receiving DrotAA. Heparin discontinuation should be carefully weighed in patients considered for DrotAA treatment. XPRESS clinical trial registered with www.clinicaltrials.gov (NCT 00049777). The study ID numbers are 6743; F1K-MC-EVB
Mortality from PROWESS and ENHANCE based on end-of-infusion PC levels by categories
No full textThe protein C (PC) categories were normal (> 80%), deficient (41% to 80%), and severely deficient (< 40%). The number in each column is the total number of patients in each category. Patients were included if they had a baseline PC measure. Day 4 PC was classified as end of infusion. If day 4 measurement was not available, last observation carried forward values were used for classification. These data were reported by Vangerow and coworkers [42]. ENHANCE, Extended Evaluation of Recombinant Activated Protein C; PROWESS, Recombinant Human Activated Protein C Worldwide Evaluation in Severe Sepsis.<p><b>Copyright information:</b></p><p>Taken from "Protein C: a potential biomarker in severe sepsis and a possible tool for monitoring treatment with drotrecogin alfa (activated)"</p><p>http://ccforum.com/content/12/2/R45</p><p>Critical Care 2008;12(2):R45-R45.</p><p>Published online 4 Apr 2008</p><p>PMCID:PMC2447591.</p><p></p
- …
