In this paper, we address scheduling methods for queue stabilization and appropriate power allocation techniques in downlink dense user-centric scalable cell-free multiple-input multiple-output (CF-MIMO) networks. Scheduling is performed by the central processing unit (CPU) scheduler using Lyapunov optimization for queue stabilization. In this process, the drift-plus-penalty is utilized, and the control parameter V serves as the weighting factor for the penalty term. The control parameter V is fixed to achieve queue stabilization. We introduce the dynamic V method, which adaptively selects the control parameter V considering the current queue backlog, arrival rate, and effective rate. The dynamic V method allows flexible scheduling based on traffic conditions, demonstrating its advantages over fixed V scheduling methods. In cases where UEs scheduled with dynamic V exceed the number of antennas at the access point (AP), the semi-orthogonal user selection (SUS) algorithm is employed to reschedule UEs with favorable channel conditions and orthogonality. Dynamic V shows the best queue stabilization performance across all traffic conditions. It shows a 10% degraded throughput performance compared to V = 10,000. Max-min fairness (MMF), sum SE maximization, and fractional power allocation (FPA) are widely considered power allocation methods. However, the power allocation method proposed in this paper, combining FPA and queue-based FPA, achieves up to 60% better queue stabilization performance compared to MMF. It is suitable for systems requiring low latency. Full article

Considering the negative effects of wetland degradation, various measures have been implemented to restore wetland habitats for aquatic organisms, and their effectiveness levels must be assessed. To reduce the effects of aquaculture on aquatic communities, pen culture facilities, which are widely distributed in Yangtze-connected lakes, were removed in 2018. We surveyed and compared waterbird communities in Caizi Lake during the four months before (2017–2018) and after net pen removal (2021–2022) to evaluate their effect on the diversity and species composition of wintering waterbirds. After net pen removal, the richness and number of individual waterbird species increased, whereas the Shannon–Wiener diversity index did not change because the increase in the bird number throughout the year was mostly associated with a few species. The response of individual numbers of different guilds to the removal of net pens differed. The number of deep-water fish eaters, seed eaters, and tuber feeders increased, whereas that of invertebrate eaters decreased. The species composition also changed, particularly in the northeastern and southwestern parts of the lake. Differences in waterbird communities between the winters of 2017–2018 and 2021–2022 indicated that net pen removal had a positive impact on waterbird communities. Full article

Background: Peroxynitrite (ONOO⁻) is an oxidant linked with several human pathologies. Apigenin, a natural flavonoid known for its health benefits, remains unexplored in relation to ONOO⁻ effects. This study investigated the potential of apigenin to structurally protect fibrinogen, an essential blood clotting factor, from ONOO⁻-induced damage. Methods: Multi-approach analyses were carried out where fibrinogen was exposed to ONOO⁻ generation while testing the efficacy of apigenin. The role of apigenin against ONOO⁻-induced modifications in fibrinogen was investigated using UV spectroscopy, tryptophan or tyrosine fluorescence, protein hydrophobicity, carbonylation, and electrophoretic analyses. Results: The findings demonstrate that apigenin significantly inhibits ONOO⁻-induced oxidative damage in fibrinogen. ONOO⁻ caused reduced UV absorption, which was reversed by apigenin treatment. Moreover, ONOO⁻ diminished tryptophan and tyrosine fluorescence, which was effectively restored by apigenin treatment. Apigenin also reduced the hydrophobicity of ONOO⁻-damaged fibrinogen. Moreover, apigenin exhibited protective effects against ONOO⁻-induced protein carbonylation. SDS-PAGE analyses revealed that ONOO⁻treatment eliminated bands corresponding to fibrinogen polypeptide chains Aα and γ, while apigenin preserved these changes. Conclusions: This study highlights, for the first time, the role of apigenin in structural protection of human fibrinogen against peroxynitrite-induced nitrosative damage. Our data indicate that apigenin offers structural protection to all three polypeptide chains (Aα, Bβ, and γ) of human fibrinogen. Specifically, apigenin prevents the dislocation or breakdown of the amino acids tryptophan, tyrosine, lysine, arginine, proline, and threonine and also prevents the exposure of hydrophobic sites in fibrinogen induced by ONOO⁻. Full article

This study developed an innovative active vibration canceling (AVC) system designed to mitigate non-periodic vibrations during road driving to enhance passenger comfort. The macro-fiber composite (MFC) used in the system is a smart material that is flexible, soft, lightweight, and applicable in many fields as a dual-purpose sensor and actuator. The target vibrations are road vibration data that were collected while driving on standard urban (Seoul) and highway roads at 40 km/s. To predict and cancel the target vibration accurately before passing it, we modeled the vibration prediction algorithm using a long short-term memory recurrent neural network (LSTM RNN). We regenerated vibrations on Seoul and highway roads at 40 km/s using MFCs and measured the displacements of the measured, predicted, and AVC vibrations of each road condition. To evaluate the vibration, we computed the root mean squared error (RMSE) and compared standard deviation (SD) values. The accuracies of LSTM RNN vibration prediction algorithms are 97.27% and 96.36% on Seoul roads and highway roads, respectively, at 40 km/s. Although the vibration ratio compared with the AVC results are different, there was no difference between the values of the AVC vibrations. According to a previous study and the principle of the AVC system, the target vibrations decrease by canceling the inverse vibration of the MFC actuator. Full article

The advancements in deep learning have significantly enhanced the capability of image generation models to produce images aligned with human intentions. However, training and adapting these models to new data and tasks remain challenging because of their complexity and the risk of catastrophic forgetting. This study proposes a method for addressing these challenges involving the application of class-replacement techniques within a continual learning framework. This method utilizes selective amnesia (SA) to efficiently replace existing classes with new ones while retaining crucial information. This approach improves the model’s adaptability to evolving data environments while preventing the loss of past information. We conducted a detailed evaluation of class-replacement techniques, examining their impact on the “class incremental learning” performance of models and exploring their applicability in various scenarios. The experimental results demonstrated that our proposed method could enhance the learning efficiency and long-term performance of image generation models. This study broadens the application scope of image generation technology and supports the continual improvement and adaptability of corresponding models. Full article

This narrative review aims to examine the therapeutic potential and mechanism of action of plant extracts in preventing and treating alopecia (baldness). We searched and selected research papers on plant extracts related to hair loss, hair growth, or hair regrowth, and comprehensively compared the therapeutic efficacies, phytochemical components, and modulatory targets of plant extracts. These studies showed that various plant extracts increased the survival and proliferation of dermal papilla cells in vitro, enhanced cell proliferation and hair growth in hair follicles ex vivo, and promoted hair growth or regrowth in animal models in vivo. The hair growth-promoting efficacy of several plant extracts was verified in clinical trials. Some phenolic compounds, terpenes and terpenoids, sulfur-containing compounds, and fatty acids were identified as active compounds contained in plant extracts. The pharmacological effects of plant extracts and their active compounds were associated with the promotion of cell survival, cell proliferation, or cell cycle progression, and the upregulation of several growth factors, such as IGF-1, VEGF, HGF, and KGF (FGF-7), leading to the induction and extension of the anagen phase in the hair cycle. Those effects were also associated with the alleviation of oxidative stress, inflammatory response, cellular senescence, or apoptosis, and the downregulation of male hormones and their receptors, preventing the entry into the telogen phase in the hair cycle. Several active plant extracts and phytochemicals stimulated the signaling pathways mediated by protein kinase B (PKB, also called AKT), extracellular signal-regulated kinases (ERK), Wingless and Int-1 (WNT), or sonic hedgehog (SHH), while suppressing other cell signaling pathways mediated by transforming growth factor (TGF)-β or bone morphogenetic protein (BMP). Thus, well-selected plant extracts and their active compounds can have beneficial effects on hair health. It is proposed that the discovery of phytochemicals targeting the aforementioned cellular events and cell signaling pathways will facilitate the development of new targeted therapies for alopecia. Full article

In the dynamic landscape of modern education, characterized by an increasingly active involvement of IT technologies in learning, the imperative to transfer to university students the skills necessary to integrate Artificial Intelligence (AI) into the process represents an important goal. This paper presents a novel framework for knowledge transfer, diverging from traditional programming language-centric approaches by integrating PSoC 6 microcontroller technology. This framework proposes a cyclical learning cycle encompassing theoretical fundamentals and practical experimentation, fostering AI literacy at the edge. Through a structured combination of theoretical instruction and hands-on experimentation, students develop proficiency in understanding and harnessing AI capabilities. Emphasizing critical thinking, problem-solving, and creativity, this approach equips students with the tools to navigate the complexities of real-world AI applications effectively. By leveraging PSoC 6 as an educational tool, a new generation of individuals is efficiently cultivated with essential AI skills. These individuals are adept at leveraging AI technologies to address societal challenges and drive innovation, thereby contributing to long-term sustainability initiatives. Specific strategies for experiential learning, curriculum recommendations, and the results of knowledge application are presented, aimed at preparing university students to excel in a future where AI will be omnipresent and indispensable. Full article

Wood-decaying fungi are important study subjects for their ecological role as well as for their biotechnological applications. They break down lignin, cellulose, and hemicelluloses using enzymes that modify the chemical structure of these complex macromolecules. Due to their ability to degrade wood, these fungi can create structural damage to wooden structures and to trees, especially those with very low level of fitness. Previous studies on wood decay fungi in the Maltese Islands are limited to records and checklists described by a handful of authors. The aim of this study was to provide a comprehensive description of wood decay fungal diversity in the Maltese Islands including an updated checklist based on DNA barcoding, as well as to establish the first wood-decay fungal culture collection at the Biology Department Seed Bank of the University of Malta. Several surveys were carried out during the rainy season along wooded areas of the Maltese Islands as well as in historical gardens. Isolates were identified using macro- and micro-morphological features, dichotomous keys, as well as molecular data. Basidiomes were recorded growing on 14 different host plant species, 11 axenic cultures have been made and 9 species of wood decay fungi have been conclusively identified by DNA barcoding. The collection of the axenic isolates includes one of Aurificaria cf. euphoria, three of Ganoderma resinaceum sl., two of Laetiporus sulphureus, one of Inonotus sp., one of Inonotus rickii anamorph, one of Inocutis tamaricis, one of Stereum hirsutum, and one of Pleurotus eryngii. However, the mycelium of Coriolopsis gallica, though collected and identified, could not be isolated. Full article

Revealing the biogeography and community assembly mechanisms of soil microorganisms is crucial in comprehending the diversity and maintenance of Pinus sylvestris var. mongolica forests. Here, we used high-throughput sequencing techniques and null model analysis to explore the distribution patterns and assembly processes of abundant, rare, and total fungal communities in P. sylvestris var. mongolica forests based on a large-scale soil survey across northern China. Compared to the abundant and total taxa, the diversity and composition of rare taxa were found to be more strongly influenced by regional changes and environmental factors. At the level of class, abundant and total taxa were dominated by Agaricomycetes and Leotiomycetes, while Agaricomycetes and Sordariomycetes were dominant in the rare taxa. In the functional guilds, symbiotrophic fungi were advantaged in the abundant and total taxa, and saprotrophic fungi were advantaged in the rare taxa. The null model revealed that the abundant, rare, and total taxa were mainly governed by stochastic processes. However, rare taxa were more influenced by deterministic processes. Precipitation and temperature were the key drivers in regulating the balance between stochastic and deterministic processes. This study provides new insights into both the biogeographical patterns and assembly processes of soil fungi in P. sylvestris var. mongolica forests. Full article

Melioidosis is an endemic infectious disease caused by Burkholderia pseudomallei bacteria, which contaminates soil and water. To better understand the environmental changes that have contributed to melioidosis outbreaks, this study used spatiotemporal analyses to clarify the distribution pattern of melioidosis and the relationship between melioidosis morbidity rate and local environmental indicators (land surface temperature, normalised difference vegetation index, normalised difference water index) and rainfall. A retrospective study was conducted from January 2013 to December 2022, covering data from 219 sub-districts in Northeast Thailand, with each exhibiting a varying morbidity rate of melioidosis on a monthly basis. Spatial autocorrelation was determined using local Moran’s I, and the relationship between the melioidosis morbidity rate and the environmental indicators was evaluated using a geographically weighted Poisson regression. The results revealed clustered spatiotemporal patterns of melioidosis morbidity rate across sub-districts, with hotspots predominantly observed in the northern region. Furthermore, we observed a range of coefficients for the environmental indicators, varying from negative to positive, which provided insights into their relative contributions to melioidosis in each local area and month. These findings highlight the presence of spatial heterogeneity driven by environmental indicators and underscore the importance of public health offices implementing targeted monitoring and surveillance strategies for melioidosis in different locations. Full article

Background: Several screening strategies for identifying congenital CMV (cCMV) have been proposed; however, the optimal solution has yet to be determined. We aimed to determine the prevalence of cCMV by universal screening with saliva pool testing and to identify the clinical variables associated with a higher risk of cCMV to optimize an expanded screening strategy. Methods: We carried out a prospective universal cCMV screening (September/2022 to August/2023) of 2186 newborns, analyzing saliva samples in pools of five (Alethia-LAMP-CMV^®) and then performed confirmatory urine CMV RT-PCR. Infants with risk factors (small for gestational age, failed hearing screening, HIV-exposed, born to immunosuppressed mothers, or <1000 g birth weight) underwent expanded screening. Multivariate analyses were used to assess the association with maternal/neonatal variables. Results: We identified 10 infants with cCMV (prevalence: 0.46%, 95% CI 0.22–0.84), with significantly higher rates (2.1%, 95% CI 0.58–5.3) in the high-risk group (p = 0.04). False positives occurred in 0.09% of cases. No significant differences in maternal/neonatal characteristics were observed, except for a higher prevalence among infants born to non-Chilean mothers (p = 0.034), notably those born to Haitian mothers (1.5%, 95% CI 0.31–4.34), who had higher odds of cCMV (OR 6.82, 95% CI 1.23–37.9, p = 0.04). Incorporating maternal nationality improved predictive accuracy (AUC: 0.65 to 0.83). Conclusions: For low-prevalence diseases such as cCMV, universal screening with pool testing in saliva represents an optimal and cost-effective approach to enhance diagnosis in asymptomatic patients. An expanded screening strategy considering maternal nationality could be beneficial in resource-limited settings. Full article

Buprenorphine is a semi-synthetic long-acting partial µ-opioid receptor (MOR) agonist that can be used for chronic pain as a sublingual tablet, transdermal patch (Butrans^®), or a buccal film (Belbuca^®). Buprenorphine’s unique high receptor binding affinity and slow dissociation at the MOR allow for effective analgesia while offering less adverse effects compared to a full agonist opioid, in particular, less concern for respiratory depression and constipation. It is underused in chronic pain and palliative care due to misconceptions and stigma from its use in opioid use disorder (OUD). This case report discusses the unique pharmacology of buprenorphine, including its advantages, disadvantages, available formulations, drug–drug interactions, initiation and conversion strategies, and identifies ideal populations for use, especially within the palliative care patient population. Full article

(1) Background: Niemann–Pick type C1 (NP-C1) is a lysosomal storage disorder that results in the defective trafficking of cholesterol and other cellular lipids in the endosomal–lysosomal pathway. This rare autosomal recessive disorder presents in three forms based on the age of onset. The adult form presents in patients greater than 15 years of age but is rarely seen after the age of 30. Common symptoms of the late adult-onset category of NP-C1 include progressive cognitive impairment and ataxia, with psychiatric and movement disorders presenting less frequently than in other forms of NP-C1. Dystonic movement disorders present most frequently, along with chorea, myoclonus, and parkinsonism. Herein, we present a rare case of NP-C1, diagnosed at age 35 with an initial symptom of supranuclear palsy. The goal of the presented case is to highlight the importance of the neurological examination and an inclusive differential diagnosis in patients with new-onset supranuclear palsy. (2) Methods: A single case report. (3) Results: A 46-year-old male with a past medical history of NP-C1 was admitted to the hospital for respiratory distress. He was noted to have a supranuclear gaze palsy with partially preserved voluntary saccades to the right. His mother revealed that he first had difficulty moving his eyes at the age of 34. After multiple consultations and genetic testing one year later, he was diagnosed with NP-C1. (4) Conclusions: Because NP-C1 affects many regions of the brain responsible for eye movements, neurological eye assessments can be a useful tool in diagnoses. Furthermore, eye movement abnormalities may be the initial presenting symptom of NP-C1, predisposing patients to misdiagnosis with progressive supranuclear palsy and other conditions that may mimic early-stage NP-C1. Definitive diagnosis is achieved through genetic testing. Filipin staining test was the gold standard in the past. The NP-C Suspicion Index was developed to assist in diagnoses, but its efficacy is unclear with late adult-onset NP-C1. Although no cure exists, early identification can facilitate an improved symptom management course for patients. Miglustat, a glucosylceramide synthase (GCS) inhibitor, is the approved therapy in Europe specific to NP-C1 for slowing and preventing the neurological manifestations of NP-C1. Delays between symptom onset and treatment initiation are likely to result in poorer outcomes and a progression of neurological symptoms. High doses may present tolerance concerns, especially in cases of delayed treatment and advanced neurological deficit. Full article

Research Highlights: This study examined the emotional and cognitive health benefits of nature in comparison with working memory training. It considered the long-term effects, the application of mobile terminal technology, and routine-based approaches with the aim of integrating nature’s health benefits into people’s daily lives. Background and Objectives: Infectious diseases and aging may limit people’s activities indoors; the recovery effect of nature has been widely recognized, and terminal technology is developing rapidly. In this context, we want to explore the emotional and cognitive effects of viewing nature (VR) videos on mobile devices for a long time. Materials and Methods: The experiment employed a between-subjects design, with participants being randomly assigned to one of four groups: a forest VR video group, a water VR group, a working memory training group, and a control group. The participants watched the video three times a week for 20 min each for four weeks. The number of valid participants for compliance, preference, and willingness was 136, and the number of valid participants for the study of emotional and cognitive effects was 62. Brief Profile of Mood States (BPOMS) scales, running memory accuracy, shifting cost, etc., were used as indicators to reflect emotions and cognition. A repeated measures analysis of variance was performed on these indicators at four groups × two time points (pretest/post-test). Results: ① There were no significant differences in the participants’ adherence, preferences, and willingness to watch different natural videos and perform working memory training. ② Long-term home training (e.g., watching VR nature videos or working memory training) may have had a minimal effect on emotional responses to mobile terminals. However, home training may be more conducive to the stabilization of anger. ③ Watching forest VR videos had a positive effect on the updating function of the brain; watching water VR videos was beneficial for the shifting function and automatic processing speed; and working memory training had a positive effect on the updating and shifting functions. Conclusions: There were no significant differences in adherence, preference, willingness, and effects on emotion and cognition between long-term forest VR video viewing, water VR video viewing, and working memory training on mobile terminals. All three types of home training may be beneficial for the stabilization of emotion (especially anger), and all can have some positive effects on cognition. Full article

Radiation treatment of cancers like prostate or cervix cancer requires considering nearby bone structures like vertebrae. In this work, we present and validate a novel automated method for the 3D segmentation of individual lumbar and thoracic vertebra in computed tomography (CT) scans. It is based on a single, low-complexity convolutional neural network (CNN) architecture which works well even if little application-specific training data are available. It is based on volume patch-based processing, enabling the handling of arbitrary scan sizes. For each patch, it performs segmentation and an estimation of up to three vertebrae center locations in one step, which enables utilizing an advanced post-processing scheme to achieve high segmentation accuracy, as required for clinical use. Overall, 1763 vertebrae were used for the performance assessment. On 26 CT scans acquired for standard radiation treatment planning, a Dice coefficient of 0.921 ± 0.047 (mean ± standard deviation) and a signed distance error of 0.271 ± 0.748 mm was achieved. On the large-sized publicly available VerSe2020 data set with 129 CT scans depicting lumbar and thoracic vertebrae, the overall Dice coefficient was 0.940 ± 0.065 and the signed distance error was 0.109 ± 0.301 mm. A comparison to other methods that have been validated on VerSe data showed that our approach achieved a better overall segmentation performance. Full article

The electrochemical splitting of seawater is promising but also challenging for sustainable hydrogen gas production. Herein, ZIF-67 nanosheets are grown on nickel foam and then etched by Ni²⁺ in situ to obtain a hierarchical hollow nanosheets structure, which demonstrates outstanding OER performance in alkaline seawater (355 mV at 100 mA cm⁻²). Diven by a silicon solar panel, an overall electrolysis energy efficiency of 62% is achieved at a high current of 100 mA cm⁻² in seawater electrolytes. This work provides a new design route for improving the catalytic activity of metal organic framework materials. Full article

Timely and accurate information on tree species is of great importance for the sustainable management of natural resources, forest inventory, biodiversity detection, and carbon stock calculation. The advancement of remote sensing technology and artificial intelligence has facilitated the acquisition and analysis of remote sensing data, resulting in more precise and effective classification of tree species. A review of the remote sensing data and deep learning tree species classification methods is lacking in its analysis of unimodal and multimodal remote sensing data and classification methods in this field. To address this gap, we search for major trends in remote sensing data and tree species classification methods, provide a detailed overview of classic deep learning-based methods for tree species classification, and discuss some limitations of tree species classification. Full article

(1) Background: Bowel management contributes throughout the pathway of care for children with Hirschsprung. Preoperative bowel management prepares the child and family for the pull-through surgery. Perioperative bowel management supports early recovery and tailored bowel management in the follow-up supports the achievement of social continence. (2) Methods: We conducted a cross-sectional assessment of our institutional bowel management program to illustrate the pre-, peri- and postoperative bowel management strategies. (3) Results: A total of 31 children underwent primary pull-through, 23 without a stoma and 8 with a stoma, at a median age of 9 months. All children without a stoma were prepared for surgery by using rectal irrigations. Children with a stoma were prepared for surgery with a transfer of stoma effluent. Transanal irrigation supported early recovery. (4) Conclusions: Bowel management is a key pillar of the management of children with Hirschsprung disease. Incorporating bowel management in the pathway of care facilitates primary pull-through and supports perioperative recovery. Full article

Two new Mn(II) and Zn(II) metal–organic compounds of 1,10-phenanthroline and methyl benzoates viz. [Mn(phen)₂Cl₂]2-ClBzH (1) and [Zn(4-MeBz)₂(2-AmPy)₂] (2) (where 4-MeBz = 4-methylbenzoate, 2-AmPy = 2-aminopyridine, phen = 1,10-phenanthroline, 2-ClBzH = 2-chlorobenzoic acid) were synthesized and characterized using elemental analysis, TGA, spectroscopic (FTIR, electronic) and single crystal X-ray diffraction techniques. The crystal structure analysis of the compounds revealed the presence of various non-covalent interactions, which provides stability to the crystal structures. The crystal structure analysis of compound 1 revealed the formation of a supramolecular dimer of 2-ClBzH enclathrate within the hexameric host cavity formed by the neighboring monomeric units. Compound 2 is a mononuclear compound of Zn(II) where flexible binding topologies of 4-CH₃Bz are observed with the metal center. Moreover, various non-covalent interactions, such as lp(O)-π, lp(Cl)-π, C–H∙∙∙Cl, π-stacking interactions as well as N–H∙∙∙O, C–H∙∙∙O and C–H∙∙∙π hydrogen bonding interactions, are found to be involved in plateauing the molecular self-association of the compounds. The remarkable enclathration of the H-bonded 2-ClBzH dimer into a supramolecular cavity formed by two [Mn(phen)₂Cl₂] complexes were further studied theoretically using density functional theory (DFT) calculations, the non-covalent interaction (NCI) plot index and quantum theory of atoms in molecules (QTAIM) computational tools. Synergistic effects were also analyzed using molecular electrostatic potential (MEP) surface analysis. Full article

Autonomous driving, as a pivotal technology in modern transportation, is progressively transforming the modalities of human mobility. In this domain, vehicle detection is a significant research direction that involves the intersection of multiple disciplines, including sensor technology and computer vision. In recent years, many excellent vehicle detection methods have been reported, but few studies have focused on summarizing and analyzing these algorithms. This work provides a comprehensive review of existing vehicle detection algorithms and discusses their practical applications in the field of autonomous driving. First, we provide a brief description of the tasks, evaluation metrics, and datasets for vehicle detection. Second, more than 200 classical and latest vehicle detection algorithms are summarized in detail, including those based on machine vision, LiDAR, millimeter-wave radar, and sensor fusion. Finally, this article discusses the strengths and limitations of different algorithms and sensors, and proposes future trends. Full article

Background: Centrifugal-flow left ventricular assist devices (CF-LVADs) have improved morbidity and mortality for their recipients. Hospital readmissions remain common, negatively impacting quality of life and survival. We sought to identify risk factors associated with hospital readmissions among patients with CF-LVADs. Methods: Consecutive patients receiving a CF-LVAD between February 2011 and March 2021 were retrospectively evaluated using prospectively maintained institutional databases. Hospital readmissions within three years post-LVAD implantation were dichotomized into heart failure (HF)/LVAD-related or non-HF/LVAD-related readmissions. Multivariable Cox regression models augmented using a machine learning algorithm, the least absolute shrinkage and selection operator (LASSO) method, for variable selection were used to estimate associations between HF/LVAD-related readmissions and pre-, intra- and post-operative clinical variables. Results: A total of 204 CF-LVAD recipients were included, of which 138 (67.7%) had at least one HF/LVAD-related readmission. HF/LVAD-related readmissions accounted for 74.4% (436/586) of total readmissions. The main reasons for HF/LVAD-related readmissions were major bleeding, major infection, HF exacerbation, and neurological dysfunction. Using pre-LVAD variables, HF/LVAD-related readmissions were associated with substance use, previous cardiac surgery, HF duration, pre-LVAD inotrope dependence, percutaneous LVAD/VA-ECMO support, LVAD type, and the left ventricular ejection fraction in multivariable analysis (Harrell’s concordance c-statistic; 0.629). After adding intra- and post-operative variables in the multivariable model, LVAD implant hospitalization length of stay was an additional predictor of readmission. Conclusions: Using machine learning-based techniques, we generated models identifying pre-, intra-, and post-operative variables associated with a higher likelihood of rehospitalizations among patients on CF-LVAD support. These models could provide guidance in identifying patients with increased readmission risk for whom clinical strategies to mitigate this risk may further improve LVAD recipient outcomes. Full article

(1) Background: The effective selection of hyperspectral feature bands is pivotal in monitoring the nutritional status of intricate alpine grasslands on the Qinghai–Tibet Plateau. The traditional methods often employ hierarchical screening of multiple feature indicators, but their universal applicability suffers due to the use of a consistent methodology across diverse environmental contexts. To remedy this, a backward feature elimination (BFE) selection method has been proposed to assess indicator importance and stability. (2) Methods: As research indicators, the crude protein (CP) and chlorophyll (Chl) contents in degraded grasslands on the Qinghai–Tibet Plateau were selected. The BFE method was integrated with partial least squares regression (PLS), random forest (RF) regression, and tree-based regression (TBR) to develop CP and Chl inversion models. The study delved into the significance and consistency of the forage quality indicator bands. Subsequently, a path analysis framework (PLS-PM) was constructed to analyze the influence of grassland community indicators on Spec_Chl and Spec_CP. (3) Results: The implementation of the BFE method notably enhanced the prediction accuracy, with ΔR²_RF-Chl = 56% and ΔR²_RF-CP = 57%. Notably, spectral bands at 535 nm and 2091 nm emerged as pivotal for CP prediction, while vegetation indices like the PRI and mNDVI were critical for Chl estimation. The goodness of fit for the PLS-PM stood at 0.70, indicating the positive impact of environmental factors such as grassland cover on Spec_Chl and Spec_CP prediction (r_Chl = 0.73, r_CP = 0.39). Spec_Chl reflected information pertaining to photosynthetic nitrogen associated with photosynthesis (r = 0.80). (4) Disscusion: Among the applied model methods, the BFE+RF method is excellent in periodically discarding variables with the smallest absolute coefficient values. This variable screening method not only significantly reduces data dimensionality, but also gives the best balance between model accuracy and variables, making it possible to significantly improve model prediction accuracy. In the PLS-PM analysis, it was shown that different coverage and different community structures and functions affect the estimation of Spec_CP and Spec_Chl. In addition, Spec_Chl has a positive effect on the estimation of Spec_CP (r = 0.80), indicating that chlorophyll does reflect photosynthetic nitrogen information related to photosynthesis, but it is still difficult to obtain non-photosynthetic and compound nitrogen information. (5) Conclusions: The application of the BFE + RF method to monitoring the nutritional status of complex alpine grasslands demonstrates feasibility. The BFE filtration process, focusing on importance and stability, bolsters the system’s generalizability, resilience, and versatility. A key research avenue for enhancing the precision of CP monitoring lies in extracting non-photosynthetic nitrogen information. Full article