Advanced machine learning algorithms have the potential to be successfully applied to many areas of system modelling. In the present study, the capability of ten machine learning algorithms to ...predict the structural damage of an 8-storey reinforced concrete frame building subjected to single and successive ground motions is examined. From this point of view, the initial damage state of the structural system, as well as 16 well-known ground motion intensity measures, are adopted as the features of the machine-learning algorithms that aim to predict the structural damage after each seismic event. The structural analyses are performed considering both real and artificial ground motion sequences, while the structural damage is expressed in terms of two overall damage indices. The comparative study results in the most efficient damage index, as well as the most promising machine learning algorithm in predicting the structural response of a reinforced concrete building under single or multiple seismic events. Finally, the configured methodology is deployed in a user-friendly web application.
The effect of carotid artery stenting (CAS) and carotid endarterectomy (CEA) on cognitive function is unclear. Both cognitive improvement and decline have been reported after CAS and CEA. We aimed to ...compare the changes in postprocedural cognitive function after CAS versus CEA. A systematic qualitative review of the literature was conducted according to the recommendations of the Preferred Reporting Items for Systematic Reviews and Meta-analysis statement for studies evaluating the changes in cognitive function after CAS compared with CEA. Thirteen studies (403 CEAs; 368 CAS procedures) comparing the changes in cognitive function after CEA versus CAS were identified. Most studies did not show significant differences in overall cognitive function or only showed a difference in a single cognitive test between the two procedures. A definitive conclusion regarding the effect of CAS versus CEA on cognitive function was not possible owing to heterogeneity in definition, method, timing of assessment, and type of cognitive tests. For the same reasons, performing a meta-analysis was not feasible. The lack of standardization of specific cognitive tests and timing of assessment of cognitive function after CAS and CEA do not allow for definite conclusions to be drawn. Larger, adequately-powered and appropriately designed studies are required to accurately evaluate the effect of CAS versus CEA on postprocedural cognitive function.
•COVID-19 disease is associated with stroke•All strokes subtypes are seen in association with COVID-19, with ischemic stroke being most prevalent•The most common etiology for ischemic stroke in ...SARS-CoV2 infection is cryptogenic•Sex plays an important role in stroke outcomes in patients with COVID-19 disease•Males have higher rates of ICU admission, in-hospital complications and more likely to have worse outcome at hospital discharge compare with females
Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) infection is associated with stroke. The role of sex on stroke outcome has not been investigated. To objective of this paper is to describe the characteristics of a diverse cohort of acute stroke patients with COVID-19 disease and determine the role of sex on outcome.
This is a retrospective study of patients with acute stroke and SARS-CoV-2 infection admitted between March 15 to May 15, 2020 to one of the six participating comprehensive stroke centers. Baseline characteristics, stroke subtype, workup, treatment and outcome are presented as total number and percentage or median and interquartile range. Outcome at discharge was determined by the modified Rankin Scale Score (mRS). Variables and outcomes were compared for males and females using univariate and multivariate analysis.
The study included 83 patients, 47% of which were Black, 28% Hispanics/Latinos, and 16% whites. Median age was 64 years. Approximately 89% had at least one preexisting vascular risk factor (VRF). The most common complications were respiratory failure (59%) and septic shock (34%). Compared with females, a higher proportion of males experienced severe SARS-CoV-2 symptoms requiring ICU hospitalization (73% vs. 49%; p = 0.04). When divided by stroke subtype, there were 77% ischemic, 19% intracerebral hemorrhage and 3% subarachnoid hemorrhage. The most common ischemic stroke etiologies were cryptogenic (39%) and cardioembolic (27%). Compared with females, males had higher mortality (38% vs. 13%; p = 0.02) and were less likely to be discharged home (12% vs. 33%; p = 0.04). After adjustment for age, race/ethnicity, and number of VRFs, mRS was higher in males than in females (OR = 1.47, 95% CI = 1.03–2.09).
In this cohort of SARS-CoV-2 stroke patients, most had clinical evidence of coronavirus infection on admission and preexisting VRFs. Severe in-hospital complications and worse outcomes after ischemic strokes were higher in males, than females.
Recently developed Machine Learning (ML) interpretability techniques have the potential to explain how predictors influence the dependent variable in high-dimensional and non-linear problems. This ...study investigates the application of the above methods to damage prediction during a sequence of earthquakes, emphasizing the use of techniques such as SHapley Additive exPlanations (SHAP), Partial Dependence Plots (PDPs), Local Interpretable Model-agnostic Explanations (LIME), Accumulated Local Effects (ALE), permutation and impurity-based techniques. Following previous investigations that examine the interdependence between predictors and the cumulative damage caused by a seismic sequence using classic statistical methods, the present study deploy ML interpretation techniques to deal with this multi-parametric and complex problem. The research explores the cumulative damage during seismic sequences, aiming to identify critical predictors and assess their influence on the cumulative damage. Moreover, the predictors contribution with respect to the range of final damage is evaluated. Non-linear time history analyses are applied to extract the seismic response of an eight-story Reinforced Concrete (RC) frame. The regression problem’s input variables are divided into two distinct physical classes: pre-existing damage from the initial seismic event and seismic parameters representing the intensity of the subsequent earthquake, expressed by the Park and Ang damage index (DIPA) and Intensity Measures (IMs), respectively. In addition to the interpretability analysis, the study offers also a comprehensive review of ML methods, hyperparameter tuning, and ML method comparisons. A LightGBM model emerges as the most efficient, among 15 different ML methods examined. Among the 17 examined predictors, the initial damage, caused by the first shock, and the IMs of the subsequent shock—IFVF and SIH—emerged as the most important ones. The novel results of this study provide useful insights in seismic design and assessment taking into account the structural performance under multiple moderate to strong earthquake events.
Constructing models can be complicated when the available fitting data are highly correlated and of high dimension. However, the complications depend on whether the goal is prediction instead of ...estimation. We focus on predicting tree mortality (measured as the number of dead trees) from change metrics derived from moderate-resolution imaging spectroradiometer satellite images. The high dimensionality and multicollinearity inherent in such data are of particular concern. Standard regression techniques perform poorly for such data, so we examine shrinkage regression techniques such as ridge regression, the LASSO, and partial least squares, which yield more robust predictions. We also suggest efficient strategies that can be used to select optimal models such as 0.632+ bootstrap and generalized cross validation. The techniques are compared using simulations. The techniques are then used to predict insect-induced tree mortality severity for a Pinus radiata D. Don plantation in southern New South Wales, Australia, and their prediction performances are compared. We find that shrinkage regression techniques outperform the standard methods, with ridge regression and the LASSO performing particularly well.
Celotno besedilo
Dostopno za:
BF, DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Patient-specific epidemiologic intracranial pressure (ICP) thresholds in adult traumatic brain injury (TBI) have emerged, using the relationship between pressure reactivity index (PRx) and ICP, ...displaying stronger association with outcome over existing guideline thresholds. The goal of this study was to explore this relationship in a multi-center cohort in order to confirm the previous finding.
Using the Collaborative European Neuro Trauma Effectiveness Research in TBI (CENTER-TBI) high-resolution intensive care unit cohort, we derived individualized epidemiologic ICP thresholds for each patient using the relationship between PRx and ICP. Mean hourly dose of ICP was calculated for every patient for the following thresholds: 20, 22 mm Hg and the patient's individual ICP threshold. Univariate logistic regression models were created comparing mean hourly dose of ICP above thresholds to dichotomized outcome at 6 to 12 months, based on Glasgow Outcome Score-Extended (GOSE) (alive/dead-GOSE≥2/GOSE=1; favorable/unfavorable-GOSE 5 to 8/GOSE 1 to 4, respectively).
Individual thresholds were identified in 65.3% of patients (n=128), in keeping with previous results (23.0±11.8 mm Hg interquartile range: 14.9 to 29.8 mm Hg). Mean hourly dose of ICP above individual threshold provides superior discrimination (area under the receiver operating curve AUC=0.678, P=0.029) over mean hourly dose above 20 mm Hg (AUC=0.509, P=0.03) or above 22 mm Hg (AUC=0.492, P=0.035) on univariate analysis for alive/dead outcome at 6 to 12 months. The AUC for mean hourly dose above individual threshold trends to higher values for favorable/unfavorable outcome, but fails to reach statistical significance (AUC=0.610, P=0.060). This was maintained when controlling for baseline admission characteristics.
Mean hourly dose of ICP above individual epidemiologic ICP threshold has stronger associations with mortality compared with the dose above Brain Trauma Foundation defined thresholds of 20 or 22 mm Hg, confirming prior findings. Further studies on patient-specific epidemiologic ICP thresholds are required.
...we may be misled targeting what we can measure, not necessarily what matters. ...heuristics are strategies that ignore part of the information in order to make decisions faster, more frugally, or ...more accurately (a less-is-more effect) than more complex methods. ...this work utilized the entire recording period, and average ICP, for determination of epidemiologic thresholds. ...the methodology followed is vulnerable to an ecological fallacy, i.e., inferences about the nature of individuals are deduced from inferences about the group to which those individuals belong.
Abstract
Introduction
Atrial fibrillation (AF) is the most common arrhythmia and is associated with high risk of morbidity and mortality. In many patients, AF is of episodic character (paroxysmal AF ...– PAF), which makes the identification of these patients during sinus rhythm (SR) challenging.
Purpose
The aim of the present study is to compare the performance of beat-to-beat P-wave analysis with P-wave indices used as predictors of PAF, such as P-wave duration, area, voltage, axis, terminal force in V1, inter-atrial block or orthogonal type, in identifying patients with history of PAF during sinus rhythm.
Methods
Standard 12-lead ECG and 10-minute orthogonal ECG recordings were obtained from 40 consecutive patients with short history of PAF under no antiarrhythmic medication and 60 age- and sex- matched healthy controls. The P-waves on the 10-minute recordings were analyzed on a beat-to-beat basis and classified as belonging to a primary or secondary morphology according to previous study. Wavelet transform used to further analyze P-wave orthogonal signals of main morphology on a beat-to-beat basis.
Results
38 out of 327 studied features were found to differ significantly among the two groups. These features were tested for their diagnostic ability and receiver operating characteristic curves were ploted. Only 3 of them performed adequetly, with an area under curve (AUC) above 0.65; Two of them came from morphology analysis (percentage of beats following main morphology in axis X and Y) and one from wavelet analysis (max energy in high frequency zone -Y axis). Among standard P-wave indices, P-wave area in lead II was the one with the highest AUC (0.64).
Conclusion
Novel indices derived from beat-to-beat analysis outperform stadard P-wave markers in identifying patients with PAF history during sinus rhythm.
Funding Acknowledgement
Type of funding sources: None. ROC curves of most significant featuresAUC characteristics of P-wave indices
Purpose
The purpose of this experimental study is to investigate the effects of iloprost on colonic anastomotic healing in rats, after intraperitoneal administration.
Methods
Forty male Albino-Wistar ...rats were randomized into two groups of twenty animals each. They all underwent colonic resection followed by an inverted anastomosis. The rats of Group A (control) received 3 ml of NaCl intraperitoneally, while those of Group B (iloprost) received iloprost (2 μg/kg body weight), immediately postoperatively and daily until killed. Each group was further divided into two equal subgroups, depending on the day of killing. The animals of subgroups 1 were killed on the fourth postoperative day, while those of subgroups 2 on the eighth. Macroscopical and histological assessments were performed. Besides, anastomotic bursting pressures and the tissue concentrations in hydroxyproline and collagenase I were also evaluated.
Results
No anastomotic dehiscence was noted. The mean bursting pressure was higher in the iloprost group compared with the control group, but a significant difference was revealed only on the fourth postoperative day. Furthermore, iloprost significantly increased the new vessel formation on the fourth, as well as on the eighth postoperative day.
Conclusion
Iloprost enhances the early phase of colonic anastomotic healing in rats.
PDF
