Forecasting Treatment Outcomes Over Time Using Alternating Deep Sequential Models.

Medical decision making often relies on accurately forecasting future patient trajectories. Conventional approaches for patient progression modeling often do not explicitly model treatments when predicting patient trajectories and outcomes. In this paper, we propose Alternating Transformer (AL-Transformer) to jointly model treatment and clinical outcomes over time as alternating sequential models. We leverage causal convolution in the self-attention mechanism of AL-Transformer to incorporate local spatial information in the sequence, thus enhancing the model's ability to capture local contextual information of the sequence. Additionally, to predict the sparse treatment, a constraint learned by a convolutional neural network (CNN) is used to constrain the sparse treatment output. Experimental results on two datasets from patients with sepsis and respiratory failure extracted from the Medical Information Mart for Intensive Care (MIMIC) database demonstrate the effectiveness of the proposed approach, outperforming existing state-of-the-art methods.

Investigating the impact of the quantity of wet and dry cycles on the mechanical characteristics and fracture variations of sandstones.

The sandstone is in a state of dry-wet cycle under the repeated action of rainfall, and its mechanical properties are deteriorated to varying degrees, which causes cracks in the sandstone. Therefore, it is of great significance to study the mechanical properties and fracture propagation of sandstone under the action of dry-wet cycles. Currently, there are limited studies using numerical simulation methods to study the fracture extension of rocks under various dry and wet cycling conditions.Therefore, in this paper, the effects of different amounts of dry and wet cycling on the mechanical properties and fracture behavior of sandstone are investigated through uniaxial compression tests and numerical simulations of fracture extension. The findings indicate that the deformation stage of sandstone remains unchanged by the dry-wet cycle. The uniaxial compressive potency and coefficient of restitution gradually diminish as the quantity of cycles rises, while the Poisson's ratio exhibits the opposite trend, and the impact on the mechanical performance of sandstone wanes with cycle increments, and the correlation coefficient surpasses 0.93, signifying a substantial influence of the dry-wet cycle on sandstone's mechanical performances. The discrepancy between the numerical simulation and experimental results is minimal, with a maximum error of only 3.1%, demonstrating the congruence of the simulation and experimental outcomes.The mesoscopic examination of the simulations indicates that the quantity of fractures in the sandstone specimens rises with the escalation of dry-wet cycles, and the steps of analysis linked to crack inception and fracture propagation are accelerated, and the analysis steps from fracture initiation to penetration are also reduced.

Application of machine learning in the study of cobalt-based oxide catalysts for antibiotic degradation: An innovative reverse synthesis strategy.

This study addresses antibiotic pollution in global water bodies by integrating machine learning and optimization algorithms to develop a novel reverse synthesis strategy for inorganic catalysts. We meticulously analyzed data from 96 studies, ensuring quality through preprocessing steps. Employing the AdaBoost model, we achieved 90.57% accuracy in classification and an R²value of 0.93 in regression, showcasing strong predictive power. A key innovation is the Sparrow Search Algorithm (SSA), which optimizes catalyst selection and experimental setup tailored to specific antibiotics. Empirical experiments validated SSA's efficacy, with degradation rates of 94% for Levofloxacin and 97% for Norfloxacin, aligning closely with predictions within a 2% margin of error. This research advances theoretical understanding and offers practical applications in material science and environmental engineering, significantly enhancing catalyst design efficiency and accuracy through the fusion of advanced machine learning techniques and optimization algorithms.

Activation of sulfite by micron-scale iron-carbon composite for metronidazole degradation: Theoretical and experimental studies.

In recent years, sulfite (S(Ⅳ)), as an alternative to persulfates, has played a crucial role in eliminating antibiotics in wastewater, so there is an urgent need to develop a cheap, environmentally friendly, and effective catalyst. Zero-valent iron (ZVI) has great potential for activated S(Ⅳ) removal of organic pollutants, but its reactivity in water is reduced due to passivation. In this study, a micron-scale iron-carbon composite(mZVI@C-800) prepared via high-temperature calcination was coupled with S(Ⅳ) to degrade metronidazole (MNZ). Under the optimized reaction conditions of mZVI@C-800 dosage of 0.2 g/L and S(Ⅳ) concentration of 0.1 g/L, the MNZ removal rate was up to 81.5 % in acidic and neutral environments. The surface chemical properties of the catalysts were characterized by different analytical techniques, and the corresponding catalytic mechanism was analyzed based on these analytical results. As a result, Fe2+ is the main active site, and ·OH and SO4·- were the dominant active species. The increase in efficiency was attributed to the introduction of carbon to enhance the corrosion of mZVI further releasing more Fe2+. Additionally proposed were the potential response mechanism, the degradation path, and the toxicity change rule. These results demonstrate that the catalytic breakdown of antibiotics in wastewater treatment can be accelerated by the use of the outstanding catalytic material mZVI@C-800.

A contrastive learning approach for ICU false arrhythmia alarm reduction.

The high rate of false arrhythmia alarms in Intensive Care Units (ICUs) can lead to disruption of care, negatively impacting patients' health through noise disturbances, and slow staff response time due to alarm fatigue. Prior false-alarm reduction approaches are often rule-based and require hand-crafted features from physiological waveforms as inputs to machine learning classifiers. Despite considerable prior efforts to address the problem, false alarms are a continuing problem in the ICUs. In this work, we present a deep learning framework to automatically learn feature representations of physiological waveforms using convolutional neural networks (CNNs) to discriminate between true vs. false arrhythmia alarms. We use Contrastive Learning to simultaneously minimize a binary cross entropy classification loss and a proposed similarity loss from pair-wise comparisons of waveform segments over time as a discriminative constraint. Furthermore, we augment our deep models with learned embeddings from a rule-based method to leverage prior domain knowledge for each alarm type. We evaluate our method using the dataset from the 2015 PhysioNet Computing in Cardiology Challenge. Ablation analysis demonstrates that Contrastive Learning significantly improves the performance of a combined deep learning and rule-based-embedding approach. Our results indicate that the final proposed deep learning framework achieves superior performance in comparison to the winning entries of the Challenge.

Python program for spatial reduction and reconstruction method in flood inundation modelling.

Fast and accurate modelling of flood inundation has gained increasing attention in recent years. One approach gaining popularity recently is the development of emulation models using data driven methods, such as artificial neural networks. These emulation models are often developed to model flood depth for each grid cell in the modelling domain in order to maintain accurate spatial representation of the flood inundation surface. This leads to redundancy in modelling, as well as difficulties in achieving good model performance across floodplains where there are limited data available. In this paper, a spatial reduction and reconstruction (SRR) method is developed to (1) identify representative locations within the model domain where water levels can be used to represent flood inundation surface using deep learning models; and (2) reconstruct the flood inundation surface based on water levels simulated at these representative locations. The SRR method is part of the SRR-Deep-Learning framework for flood inundation modelling and therefore, it needs to be used together with data driven models. The SRR method is programmed using the Python programming language and is freely available from https://github.com/yuerongz/SRR-method.•The SRR method identifies locations which are representative of flood inundation behavior in surrounding areas.•The representative locations selected following the SRR method have sufficient flood data for developing emulation models.•Flood inundation surfaces can be reconstructed using the SRR method with a detection rate of above 99%.

Single-particle analysis of urea amidolyase reveals its molecular mechanism.

Urea amidolyase (UA), a bifunctional enzyme that is widely distributed in bacteria, fungi, algae, and plants, plays a pivotal role in the recycling of nitrogen in the biosphere. Its substrate urea is ultimately converted to ammonium, via successive catalysis at the C-terminal urea carboxylase (UC) domain and followed by the N-terminal allophanate hydrolyse (AH) domain. Although our previous studies have shown that Kluyveromyces lactis UA (KlUA) functions efficiently as a homodimer, the architecture of the full-length enzyme remains unresolved. Thus how the biotin carboxyl carrier protein (BCCP) domain is transferred within the UC domain remains unclear. Here we report the structures of full-length KlUA in its homodimer form in three different functional states by negatively-stained single-particle electron microscopy. We report here that the ADP-bound structure with or without urea shows two possible locations of BCCP with preferred asymmetry, and that when BCCP is attached to the carboxyl transferase domain of one monomer, it is attached to the biotin carboxylase domain in the second domain. Based on this observation, we propose a BCCP-swinging model for biotin-dependent carboxylation mechanism of this enzyme.

High-resolution global urban growth projection based on multiple applications of the SLEUTH urban growth model.

As urban population is forecast to exceed 60% of the world's population by 2050, urban growth can be expected. However, research on spatial projections of urban growth at a global scale are limited. We constructed a framework to project global urban growth based on the SLEUTH urban growth model and a database with a resolution of 30 arc-seconds containing urban growth probabilities from 2020 to 2050. Using the historical distribution of the global population from LandScanTM as a proxy for urban land cover, the SLEUTH model was calibrated for the period from 2000 to 2013. This model simulates urban growth using two layers of 50 arc-minutes grids encompassing global urban regions. While varying growth rates are observed in each urban area, the global urban cover is forecast to reach 1.7 × 106 km2 by 2050, which is approximately 1.4 times that of the year 2012. A global urban growth database is essential for future environmental planning and assessments, as well as numerical investigations of future urban climates.