Search for: All records

Background and Objectives: Sepsis is a leading cause of mortality in intensive care units (ICUs). The development of a robust prognostic model utilizing patients’ clinical data could significantly enhance clinicians’ ability to make informed treatment decisions, potentially improving outcomes for septic patients. This study aims to create a novel machine-learning framework for constructing prognostic tools capable of predicting patient survival or mortality outcome. Methods: A novel dataset is created using concatenated triples of static data, temporal data, and clinical outcomes to expand data size. This structured input trains five machine learning classifiers (KNN, Logistic Regression, SVM, RF, and XGBoost) with advanced feature engineering. Models are evaluated on an independent cohort using AUROC and a new metric, 𝛾, which incorporates the F1 score, to assess discriminative power and generalizability. Results: We developed five prognostic models using the concatenated triple dataset with 10 dynamic features from patient medical records. Our analysis shows that the Extreme Gradient Boosting (XGBoost) model (AUROC = 0.777, F1 score = 0.694) and the Random Forest (RF) model (AUROC = 0.769, F1 score = 0.647), when paired with an ensemble under-sampling strategy, outperform other models. The RF model improves AUROC by 6.66% and reduces overfitting by 54.96%, while the XGBoost model shows a 0.52% increase in AUROC and a 77.72% reduction in overfitting. These results highlight our framework’s ability to enhance predictive accuracy and generalizability, particularly in sepsis prognosis. Conclusion: This study presents a novel modeling framework for predicting treatment outcomes in septic patients, designed for small, imbalanced, and high-dimensional datasets. By using temporal feature encoding, advanced sampling, and dimension reduction techniques, our approach enhances standard classifier performance. The resulting models show improved accuracy with limited data, offering valuable prognostic tools for sepsis management. This framework demonstrates the potential of machine learning in small medical datasets. 

Atmospheric frontal passage is a common meteorological event that can significantly affect hydrodynamics in coastal environments, including the hydrological connectivity between channels and floodplains that regulates material transport in river deltas. This study is focused on the influence of atmospheric cold fronts on the hydrological connectivity between channels and floodplains within the Wax Lake Delta using the Delft3D FM model. The results demonstrate a substantial effect of passing cold fronts on the exchange of water and transport fraction between the primary channels and floodplains. This impact is intricately connected to the morphodynamical characteristics of the floodplains, the intensity of cold fronts, river discharge, Coriolis force, and tidal currents. The passing cold fronts can enhance or reverse the direction of water exchange between channels and floodplains. For floodplains, the passage of cold fronts can lead to an increase in the rate of water exchange by as much as five times. In the WLD, a substantial fraction of water, 39-58%, is flowing through the floodplains to the bay at the delta front influenced by the prevailing discharge, although there is a significant spatial heterogeneity. Passing cold fronts can alter the transport distribution, depending on the phase of the front. An increase in river discharge tends to bolster floodplain connectivity and lessen the effects of cold fronts. Conversely, decreased river discharge results in reduced connectivity and exacerbates the fluctuations induced by cold fronts. Moreover, the findings indicate that from the apex to downstream, the contribution of channels decreases as they become shallower, while the role of the floodplains increases, leading to a less distinct demarcation between channels and floodplains. It has also been noted that an increase in river discharge correlates with an increased contribution from floodplains to transfer water to the bay. 

The effects of passing atmospheric cold fronts with different orientations and moving directions on the hydrodynamics of the Wax Lake Delta (WLD) were analyzed by considering the influence of river discharge, cold front moving direction, wind magnitude, and Coriolis effect. The study employs numerical simulations using the Delft-3D model and an analytical model to explore water volume transport, water level variations, water circulation, and particle trajectories during nine cold front events. Results indicate that cold fronts cause a decrease in the average contribution of the water transport through western channels and an increase of that in central and eastern channels. A westerly cold front with an average wind speed of ~12 m/s can increase water transport through eastern channels by about 35%. During the passage of a cold front, the intertidal islands between the main channels and East Bay experience the largest fluctuations in subtidal water levels, which can be attributed to the influence of local wind stress. For example, a westerly cold front can result in a water level variation of approximately 0.45 m over some of the intertidal Islands and 0.65 m in the East Bay. Results also show that the subtidal water circulation in the WLD is correlated with the Wax Lake Outlet (WLO) discharge and wind magnitude. The findings illustrate that when WLO discharge is low, the impact of cold fronts is more pronounced, and cold fronts from the west have a greater impact compared to those from the northwest and north. This study identifies the significance of WLO discharge and Coriolis force by the trajectories of particles in the water column. The results of the simulations indicate that under low WLO discharge (less than 2000 m3/s), the majority of particles are found to exit through Campground Pass instead of Gadwall because of the dominance of Coriolis force. To summarize, this study assesses the impact of cold fronts on the hydrodynamics of the Wax Lake Delta, underscoring the contributions of multiple factors, including the cold front moving direction, river discharge, wind strength, and Coriolis force. 

Atmospheric cold fronts can periodically generate storm surges and affect sediment transport in the Northern Gulf of Mexico (NGOM). In this paper, we evaluate water circulation spatiotemporal patterns induced by six atmospheric cold front events in the Wax Lake Delta (WLD) in coastal Louisiana using the 3-D hydrodynamic model ECOM-si. Model simulations show that channelized and inter-distributary water flow is significantly impacted by cold fronts. Water volume transport throughout the deltaic channel network is not just constrained to the main channels but also occurs laterally across channels accounting for about a quarter of the total flow. Results show that a significant landward flow occurs across the delta prior to the frontal passage, resulting in a positive storm surge on the coast. The along-channel current velocity dominates while cross-channel water transport occurs at the southwest lobe during the post-frontal stage. Depending on local weather conditions, the cold-front-induced flushing event lasts for 1.7 to 7 days and can flush 32–76% of the total water mass out of the system, a greater range of variability than previous reports. The magnitude of water flushed out of the system is not necessarily dependent on the duration of the frontal events. An energy partitioning analysis shows that the relative importance of subtidal energy (10–45% of the total) and tidal energy (20–70%) varies substantially from station to station and is linked to the weather impact. It is important to note that within the WLD region, the weather-induced subtidal energy (46–66% of the total) is much greater than the diurnal tidal energy (13–25% of the total). The wind associated with cold fronts in winter is the main factor controlling water circulation in the WLD and is a major driver in the spatial configuration of the channel network and delta progradation rates. 

Environmental temperature is a widely used variable to describe weather and climate conditions. The use of temperature anomalies to identify variations in climate and weather systems makes temperature a key variable to evaluate not only climate variability but also shifts in ecosystem structural and functional properties. In contrast to terrestrial ecosystems, the assessment of regional temperature anomalies in coastal wetlands is more complex since the local temperature is modulated by hydrology and weather. Thus, it is unknown how the regional free-air temperature (T Free ) is coupled to local temperature anomalies, which can vary across interfaces among vegetation canopy, water, and soil that modify the wetland microclimate regime. Here, we investigated the temperature differences (offsets) at those three interfaces in mangrove-saltmarsh ecotones in coastal Louisiana and South Florida in the northern Gulf of Mexico (2017–2019). We found that the canopy offset (range: 0.2–1.6°C) between T Free and below-canopy temperature (T Canopy ) was caused by the canopy buffering effect. The similar offset values in both Louisiana and Florida underscore the role of vegetation in regulating near-ground energy fluxes. Overall, the inundation depth did not influence soil temperature (T Soil ). The interaction between frequency and duration of inundation, however, significantly modulated T Soil given the presence of water on the wetland soil surface, thus attenuating any short- or long-term changes in the T Canopy and T Free . Extreme weather events—including cold fronts and tropical cyclones—induced high defoliation and weakened canopy buffering, resulting in long-term changes in canopy or soil offsets. These results highlight the need to measure simultaneously the interaction between ecological and climatic processes to reduce uncertainty when modeling macro- and microclimate in coastal areas under a changing climate, especially given the current local temperature anomalies data scarcity. This work advances the coupling of Earth system models to climate models to forecast regional and global climate change and variability along coastal areas. 

In this paper, subtidal responses of Barataria Bay to an atmospheric cold front in 2014 and Hurricane Barry of 2019 are studied. The cold fronts had shorter influencing periods (1 to 3 days), while Hurricane Barry had a much longer influencing period (about 1 week). Wind direction usually changes from southern quadrants to northern quadrants before and after a cold front’s passage. For a hurricane making its landfall at the norther Gulf of Mexico coast, wind variation is dependent on the location relative to the location of landfall. Consequently, water level usually reaches a trough after the maximum cold front wind usually; while after the maximum wind during a hurricane, water level mostly has a surge, especially on the right-hand side of the hurricane. Water level variation induced by Hurricane Barry is about 3 times of that induced by a cold front event. Water volume flux also shows differences under these two weather types: the volume transport during Hurricane Barry was 4 times of that during a cold front. On the other hand, cold front events are much more frequent (30–40 times a year), and they lead to more frequent exchange between Barataria Bay and the coastal ocean.