A lightweight network based on multi-feature pseudo-color mapping for arrhythmia recognition.

Heartbeats classification is a crucial tool for arrhythmia diagnosis. In this study, a multi-feature pseudo-color mapping (MfPc Mapping) was proposed, and a lightweight FlexShuffleNet was designed to classify heartbeats. MfPc Mapping converts one-dimensional (1-D) electrocardiogram (ECG) recordings into corresponding two-dimensional (2-D) multi-feature RGB graphs, and it offers good excellent interpretability and data visualization. FlexShuffleNet is a lightweight network that can be adapted to classification tasks of varying complexity by tuning hyperparameters. The method has three steps. The first step is data preprocessing, which includes de-noising the raw ECG recordings, removing baseline drift, extracting heartbeats, and performing data balancing, the second step is transforming the heartbeats using MfPc Mapping. Finally, the FlexShuffleNet is employed to classify heartbeats into 14 categories. This study was evaluated on the test set of the MIT-BIH arrhythmia database (MIT/BIH DB), and it yielded the results i.e., accuracy of 99.77%, sensitivity of 94.60%, precision of 89.83% and specificity of 99.85% and F1-score of 0.9125 in 14-category classification task. Additionally, validation on Shandong Province Hospital database (SPH DB) yielded the results i.e., accuracy of 92.08%, sensitivity of 93.63%, precision of 91.25% and specificity of 99.85% and F1-score of 0.9315. The results show the satisfied performance of the proposed method.

Boosted Intracavity Aperture in Macrocyclic Amines Enabling Finely Regulated Microporous Membranes.

Finely tuning the pore structure of traditional nanofiltration (NF) membranes is challenging but highly effective for achieving efficient separations. Herein, we propose a concept of using macrocyclic amines (1,4,7-triazacyclononane, 3A; 1,4,7,10-tetraazacyclododecane, 4A1; and 1,4,8,11-tetraazacyclotetradecane, 4A2) with different intra-annular apertures to finely modulate the pore structure of microporous membranes via interfacial polymerization (IP). The boost in the intracavity size of the building blocks results in heightened steric hindrance of these amine monomers, leading to a controlled increase in membrane pore size, as demonstrated by both film characterizations and multiscale simulations. In conjunction with the increased intracavity size, the water permeability follows an augmented trend of 3A-TMC, 4A1-TMC, and 4A2-TMC (TMC: trimesoyl chloride) while exhibiting increased molecular weight cut-offs due to larger free-volume elements and stronger pore interconnectivity. Our proposed macrocyclic amine design strategy provides a guideline for finely regulated microporous membranes with high potential in NF-related applications.

Recent Advances of Metal-Organic Framework for Heavy Metal Ions Adsorption.

Heavy metal ion wastewater is a pressing and inescapable issue that is closely related to human health and ecological security due to its toxicity, carcinogenicity, and the unmanageable property of this type of wastewater. Metal-Organic Frameworks (MOFs) are a class of crystalline nanoporous materials with flexible designability and controllability, showing great potential in the field of adsorption and purification of heavy metals in wastewater. In this Perspective, we first discuss the harm of different heavy metal ions and briefly expound virtues of MOFs for pollutant adsorption. Then, we mainly summarize the recent advances in the construction of different metal-based MOFs (Zr-based, Zn-based, Co-based, Al-based, etc.) and their research progress in heavy metal ions adsorption. Furthermore, various types of MOF additives can often be effectively applied for heavy metal ion adsorption by functional modification or with other materials composition. Additionally, several commonly used adsorption kinetics and isotherm models are also detailed to help an in-depth understanding of the adsorption mechanism. Finally, the challenges and opportunities of MOFs for heavy metal ion adsorption are additionally discussed, and this review may provide new insight for other potential water purification applications.

A Novel Multi-modal Population-graph based Framework for Patients of Esophageal Squamous Cell Cancer Prognostic Risk Prediction.

Prognostic risk prediction is pivotal for clinicians to appraise the patient's esophageal squamous cell cancer (ESCC) progression status precisely and tailor individualized therapy treatment plans. Currently, CT-based multi-modal prognostic risk prediction methods have gradually attracted the attention of researchers for their universality, which is also able to be applied in scenarios of preoperative prognostic risk assessment in the early stages of cancer. However, much of the current work focuses only on CT images of the primary tumor, ignoring the important role that CT images of lymph nodes play in prognostic risk prediction. Additionally, it is important to consider and explore the inter-patient feature similarity in prognosis when developing models. To solve these problems, we proposed a novel multi-modal population-graph based framework leveraging CT images including primary tumor and lymph nodes combined with clinical, hematology, and radiomics data for ESCC prognostic risk prediction. A patient population graph was constructed to excavate the homogeneity and heterogeneity of inter-patient feature embedding. Moreover, a novel node-level multi-task joint loss was proposed for graph model optimization through a supervised-based task and an unsupervised-based task. Sufficient experimental results show that our model achieved state-of-the-art performance compared with other baseline models as well as the gold standard on discriminative ability, risk stratification, and clinical utility. The core code is available at https://github.com/wuchengyu123/MPGSurv.

Visualized Lead Selection for Arrhythmia Classification Based on a Lead Activation Heatmap Using Multi-Lead ECGs.

Visualizing the decision-making process is a key aspect of research regarding explainable arrhythmia recognition. This study proposed a visualized lead selection method to classify arrhythmia for multi-lead ECG signals. The proposed method has several advantages, as it uses a visualized approach to select effective leads, avoiding redundant leads and invalid information. It also captures the temporal dependencies of ECG signals and the complementary information between leads. The method deployed a lead activation heatmap (LA heatmap) based on a lead-wise network to select the proper 5 leads from 12-lead ECG heartbeats extracted from the public 2018 Chinese Physiological Signal Challenge database (CPSC 2018 DB), which were then fed into a ResBiTime network combining bidirectional long short-term memory (Bi-LSTM) networks and residual connections for a classification task of nine heartbeat categories (i.e., N, AF, I-AVB, RBBB, PAC, PVC, STD, LBBB, and STE). The results indicate an average precision of 93.25%, an average recall of 93.03%, an average F1-score of 0.9313, and that the proposed method can effectively extract additional information from ECG heartbeat data.

Polymer carbon nitride nanosheet-based lamellar membranes inspired by "couple hardness with softness" for ultrafast molecular separation in organic solvents.

Membranes with ultrafast molecular separation ability in organic solvents can offer unprecedented opportunities for efficient and low-cost solvent recovery in industry. Herein, a graphene-like polymer carbon nitride nanosheet (PCNN) with a low-friction surface was applied as the main membrane building block to boost the ultrafast transport of the solvent. Meanwhile, inspired by the concept of "couple hardness with softness", soft and flexible graphene oxide (GO) was chosen to fix the random stack of the rigid PCNN and tailor the lamellar structure of the PCNN membrane. The optimal PCNN/GO lamellar membrane shows a remarkable methanol permeance of 435.5 L m-2 h-1 bar-1 (four times higher than that of the GO membrane) while maintaining a high rejection for reactive black (RB, 98.9% in ethanol). Molecular dynamics simulations were conducted to elucidate the ultrafast transport mechanism of the PCNN/GO membrane. This study reveals that PCNN is a promising building block for lamellar membranes and may open up new avenues for high-performance molecular separation membranes.

Construction of Hydration Layer for Proton Transport by Implanting the Hydrophilic Center Ag0 in Nickel Metal-Organic Frameworks.

The directional arrangement of H2O molecules can effectively regulate the ordered protons transfer to improve transport efficiency, which can be controlled by the interaction between materials and H2O. Herein, a strategy to build a stable hydration layer in metal-organic framework (MOF) platforms, in which hydrophilic centers that can manipulate H2O molecules are implanted into MOF cavities is presented. The rigid grid-Ni-MOF is selected as the supporting material due to the uniformly distributed cavities and rigid structures. The Ag0 possesses potential combination ability with the hydrophilic substances, so it is introduced into the MOF as hydration layer centers. Relying on the strong interaction between Ag0 and H2O, the H2O molecules can rearrange around Ag0 in the cavity, which is intuitively verified by DFT calculation and molecular dynamics simulation. The establishment of a hydration layer in Ag@Ni-MOF regulates the chemical properties of the material and gives the material excellent proton conduction performance, with a proton conductivity of 4.86 × 10-2 S cm-1.

Uniformly Distributed Mixed Matrix Membranes via a Solution Processable Strategy for Propylene/Propane Separation.

Aggregation of filler particles during the formation of mixed matrix membranes is difficult to avoid when filler loadings exceed a 10-15 wt %. Such agglomeration usually leads to poor membrane performance. In this work, using a ZIF-67 metal-organic framework (MOF) as filler along with surface modification of Ag4 tz4 to improve processability and selective olefin adsorption, we demonstrate that highly loaded with a very low agglomeration degree membranes can be synthesized displaying unmatched separation selectivity (39) for C3 H6 /C3 H8 mixtures and high permeability rates (99 Barrer), far surpassing previous reports in the literature. Through molecular dynamics simulation, the enhanced compatibility between ZIF-67 and polymer matrix with adding Ag4 tz4 was proven and the tendency in gas permeability and C3 H6 selectivity in the mixed matrix membranes (MMMs) were well explained. More importantly, the membrane showed a wide range of pressure and temperature resistance, together with remarkable long-term stability (>900 h). The modification method might help solve interface issues in MMMs and can be extended to the fabrication of other fillers to achieve high performance MMMs for gas separation.

Chemically Asymmetric Polymers Manipulate the Crystallization of Two-Dimensional Covalent Organic Frameworks to Synthesize Processable Nanosheets.

Nanosheets derived from two-dimensional covalent organic frameworks (2D COFs) are increasingly desirable in various fields. While breakthroughs in the chemical and physical delamination of 2D COFs are rising, precisely regulating the growth of the COF nanosheets has not been realized yet. Herein, we report an effective strategy of polymer-manipulated crystallization to accurately control the growth of COF nanosheets. Chemically asymmetric polyvinylpyrrolidone (PVP) is developed as the manipulator that selectively interacts with the aldehydes and (100) facet to induce anisotropic growth of COFs. The number of PVP constitutional units determines this specific interaction, leading to molecularly thin but thickness-controllable nanosheets with excellent dispersity. We process these nanosheets into robust A4-sized membranes for ultraselective molecular separation. The membrane intercalated with long-chain PVP demonstrates largely improved performance, surpassing the reported COF membranes. This work reports a strategy for anisotropically crystallizing 2D COFs to yield processable nanosheets toward practical applications.

The telomere-to-telomere gap-free reference genome of wild blueberry (Vaccinium duclouxii) provides its high soluble sugar and anthocyanin accumulation.

Vaccinium duclouxii, endemic to southwestern China, is a berry-producing shrub or small tree belonging to the Ericaceae family, with high nutritive, medicinal, and ornamental value, abundant germplasm resources, and good edible properties. In addition, V. duclouxii exhibits strong tolerance to adverse environmental conditions, making it a promising candidate for research and offering wide-ranging possibilities for utilization. However, the lack of V. duclouxii genome sequence has hampered its development and utilization. Here, a high-quality telomere-to-telomere genome sequence of V. duclouxii was de novo assembled and annotated. All of 12 chromosomes were assembled into gap-free single contigs, providing the highest integrity and quality assembly reported so far for blueberry. The V. duclouxii genome is 573.67 Mb, which encodes 41 953 protein-coding genes. Combining transcriptomics and metabolomics analyses, we have uncovered the molecular mechanisms involved in sugar and acid accumulation and anthocyanin biosynthesis in V. duclouxii. This provides essential molecular information for further research on the quality of V. duclouxii. Moreover, the high-quality telomere-to-telomere assembly of the V. duclouxii genome will provide insights into the genomic evolution of Vaccinium and support advancements in blueberry genetics and molecular breeding.