Search Results (552)

Agriforestry systems are essential for improving the quality of medicinal herbs and ensuring the sustainable management of forests. Forest soil acidification inhibits the growth of medicinal plants. The application of novel dolomite-loaded vermicompost (DOVC) is considered a potential method for promoting plants growth. However, the mechanisms by which it promotes the growth of medicinal plants are poorly understood. This study combined observational analysis and field experimentation, to first elucidate the correlation between under-forest soil pH and root dry weight of American ginseng (Panax quinquefolius L.). Subsequently, the mechanisms by which DOVC promotes the growth of P. quinquefolius were analyzed from the perspectives of plant physiology and soil microbiome. The results indicate: (1) Field survey results demonstrated when the pH was between 5.28 and 5.99, the root dry weight of P. quinquefolius gradually increased with increasing soil pH. (2) Compared with Control, DOVC increased the soil pH by 1.48 units and promoted the growth of P. quinquefolius, with a net photosynthetic rate increase of 60.26%, malondialdehyde content decrease of 71.07%, and root dry weight increase of 50.33%. (3) Compared with Control, DOVC enhanced bacterial community diversity, with Ace and Chao 1 indices increasing significantly by 33.88% and 25.18%, respectively; and increased the relative abundance of Chloroflexi and Basidiomycota. (4) Partial Least Squares Path Modeling revealed that DOVC positively influenced P. quinquefolius growth via the improvement of soil health index and microbial community diversity. The development of this novel soil amendment offers a new approach to improving soil health in agroforestry systems. Full article

Background/Objectives: Heart failure (HF) remains a major cause of global mortality and morbidity; it is, therefore, of paramount importance that diagnosis and prognostication are made timely in order to better improve outcomes and reduce healthcare expenditure. This research presents a novel predictive model of heart failure that combines clinical criteria with demographic factors in order to maximize predictive performance and act as a reliable tool for individualized healthcare intervention. Methods: Complex machine learning techniques, including decision trees, random forest, and deep learning, are applied in analyzing a large dataset of subjects with heart failure. We collected a diverse dataset comprising clinical indicators such as echocardiographic data, biomarkers, electrocardiogram (ECG) features, and demographic information. Data preprocessing techniques, such as feature normalization and handling of missing values, were applied to ensure the integrity and reliability of the dataset. Results: The results indicate that integrating both clinical indicators and demographic characteristics significantly improves the predictive power of the model, compared to models based on clinical indicators alone. Specifically, the hybrid model demonstrated a superior ability to predict short- and long-term outcomes in heart failure patients, offering enhanced accuracy in risk stratification and prognosis prediction. Conclusions: This research highlights the potential of artificial intelligence (AI) and machine learning in revolutionizing heart failure care by providing healthcare professionals with more accurate, data-driven decision support tools. The proposed model not only holds promise for clinical applications but also offers insights for future research into personalized medicine. Full article

Background/Objectives: First-trimester preeclampsia (PE) screening is most widely implemented using the Fetal Medicine Foundation (FMF) algorithm, which combines maternal factors with biophysical and biochemical markers via a competing-risks/Bayes framework to produce individualized risks and guide prophylaxis decisions. We aimed to compare commonly used machine-learning (ML) classifiers (logistic regression, random forest, XGBoost) against FMF a priori and a posteriori risk estimates in a Romanian screening cohort. Methods: We analyzed 1583 singleton pregnancies screened at 11–14 weeks’ gestation. Primary analyses excluded aspirin-treated women to reduce treatment-induced outcome modification. We evaluated two feature sets mirroring FMF structure: (1) a maternal-factor “a priori” set and (2) a “a posteriori” set additionally incorporating mean arterial pressure (MAP), uterine artery pulsatility index (UtA-PI), and Pregnancy-Associated Plasma Protein A (PAPP-A). Models were trained using stratified repeated cross-validation (5-fold × 10 repeats) and evaluated using AUC-ROC, DeLong tests, and sensitivity at 10% false-positive rate. Calibration of the model, sensitivity analyses and decision-curve analysis (DCA) were also assessed. Results: In the a priori comparison, the best ML model was logistic regression (AUC 0.796) versus FMF prior risk AUC 0.841 (DeLong p = 0.349). The sensitivity at 10% false positive rate (FPR) was 33.3% for the model versus 50.0% for FMF model. In the a posteriori comparison, the best ML model was random forest (AUC 0.844) versus FMF posterior risk AUC 0.929 (DeLong p = 0.087), with sensitivity at 10% FPR of 57.1% for ML and 71.4% for FMF. Random undersampling did not improve ML performance. Including aspirin-treated pregnancies did not significantly change our results. Conclusions: In this study, the FMF competing-risks outputs outperformed or matched ML classifiers in both maternal-only and biomarker-augmented screening, and DCA favored FMF particularly for the a posteriori model. Full article

Peppers from the Capsicum genus are highly valued worldwide for their culinary, medicinal, and nutritional uses. However, accurately classifying and developing new varieties to enhance these traits remains a challenge due to the limitations of traditional methods, which often lack precision and are time-consuming. This study aimed to overcome these limitations by applying advanced multivariate statistical techniques and machine learning models (KNN, RF, XGBoost) to characterize and classify Capsicum genotypes based on genetic and phenotypic features. Sixteen Capsicum genotypes were analyzed using methods such as MANOVA, PCA, and cluster analysis to explore their variabilities and similarities. Cluster analysis revealed the formation of distinct groups, indicating phenotypic similarity patterns among specific varieties. The machine learning models were evaluated using Leave-One-Out cross-validation to address the challenges posed by small datasets. The results indicated that Random Forest outperformed the other models, exhibiting superior class discrimination with an AUC of 0.96, while KNN and XGBoost achieved AUC values of 0.95 and 0.85, respectively. Despite the slightly superior performance of Random Forest relative to KNN, both models demonstrated strong predictive performance, whereas XGBoost exhibited moderate performance. In addition, key agronomic traits such as pericarp thickness, fruit diameter, seeds per fruit, and corolla color were identified as the most relevant variables for classification. Principal component analysis indicated that the first components explained a substantial proportion of the total variance, supporting efficient dimensionality reduction and pattern recognition. Furthermore, the Random Forest model achieved high overall performance, with accuracy, precision, recall, and F1-score values close to 0.93, reinforcing its robustness in multiclass classification. This study highlights the effectiveness of machine learning in overcoming the constraints of traditional classification methods, providing a robust approach for the accurate identification and improvement of pepper varieties. Full article

Background/Objectives: Recovery of upper limb function after stroke is highly heterogeneous, and accurate prediction of clinically meaningful functional transition remains a major challenge in rehabilitation medicine. We developed and temporally validated machine learning (ML)-based prognostic models for predicting transition from non-functional movement to functionally usable upper limb capacity in patients undergoing intensive inpatient rehabilitation during the early subacute phase of stroke. Methods: This retrospective cohort study included 960 patients with ischemic or hemorrhagic stroke admitted to a tertiary rehabilitation center between 2010 and 2025. Three functional recovery outcomes were defined: motor impairment recovery, defined as Fugl-Meyer Assessment for Upper Extremity score ≥ 32; gross manual dexterity recovery, defined as Box and Block Test score ≥ 2 blocks/min; and functional pinch strength recovery, defined as pinch strength ≥ 1.1 kgf. Multidimensional predictors spanning demographic, clinical, neurophysiological, neuroimaging, and rehabilitation-related domains were integrated. Four ML algorithms were evaluated using stratified 5-fold cross-validation and temporal validation in a chronologically independent cohort (2024–2025). Models were developed under two tracks: Track A, incorporating only baseline variables available at admission (primary prognostic model), and Track B, additionally incorporating cumulative rehabilitation-related variables (exploratory). Results: Random Forest demonstrated the best overall performance. During temporal validation, models achieved AUROC of 0.800 for motor impairment recovery, 0.958 for gross manual dexterity recovery, and 0.888 for functional strength recovery. Baseline motor severity and corticospinal tract integrity were the dominant biological determinants of recovery. Earlier rehabilitation initiation and greater upper-limb robot-assisted therapy exposure were also associated with improved outcomes; however, these findings should be interpreted as observational associations subject to treatment-selection bias rather than evidence of causal effects. Conclusions: Probabilistic ML prediction integrating neural reserve and rehabilitation-related exposure variables can support individualized precision rehabilitation planning and improve functional outcome stratification in early subacute stroke. Full article

A systematic survey of macrofungal diversity was conducted at the Jiulingshan National Nature Reserve, located in a subtropical monsoon climatic zone dominated by well-preserved evergreen broad-leaved forests, Jiangxi Province, China. From May 2020 to September 2025, fruiting bodies were collected along transects established in the experimental zone, covering major vegetation types across an elevation gradient of 50–850 m. Macrofungal specimens were initially identified using traditional morphological taxonomy. For taxonomically challenging species, identification was further supported by ITS sequence analysis. A total of 295 macrofungal species were identified, belonging to two phyla, six classes, 20 orders, 63 families, and 150 genera, along with one species of myxomycete. Boletaceae, Agaricaceae, Amanitaceae, and Polyporaceae were the most species-rich families, while Amanita, Russula, and Entoloma were the dominant genera. Floristic analysis revealed that cosmopolitan and North Temperate elements predominated in the macrofungal flora. Among the recorded species, 105 (35.6%) possess edible or medicinal value, whereas 26 (8.8%) are poisonous. This study provides the first comprehensive inventory of macrofungi in the Jiulingshan reserve, offering essential baseline data to support biodiversity conservation, sustainable resource utilization, and the understanding of fungal diversity in northwestern Jiangxi. Full article

During the drying of Fritillaria ussuriensis, complex nonlinear interactions occur between process parameters and quality attributes. Conventional approaches rely on empirical trial-and-error, limiting precise control and inverse optimization. This study proposes a hybrid optimization framework combining the whale optimization algorithm (WOA) and particle swarm optimization (PSO) to establish a bidirectional mapping between process variables and quality indicators. The WOA is applied for global optimization of the random forest (RF) hyperparameters, followed by PSO for local refinement. The resulting model enables both forward prediction (from temperature, heating air velocity, dehumidification air velocity, and infrared power to quality indicators) and inverse optimization (from target quality to process parameters). The model achieves high predictive performance, with mean R² values of 0.9739 (forward) and 0.9736 (inverse), outperforming WOA-RF, PSO-RF, and conventional RF models in accuracy, stability, and generalization. Industrial validation shows prediction errors below 10%, meeting engineering requirements. These results provide an effective approach for drying optimization and support intelligent modeling of rhizome-based medicinal materials. Full article

Sleep disorders, such as insomnia, obstructive sleep apnea (OSA), narcolepsy, REM sleep behavior disorder, and circadian rhythm disturbances, represent a rapidly expanding global health burden that is strongly associated with cardiovascular, metabolic, neurological, and psychiatric diseases. Advancements in wearable sensing technologies and Internet of Medical Things (IoMT) infrastructures have expanded the possibilities for continuous, home-based sleep assessment beyond conventional polysomnography laboratories. These Sleep Health Internet of Things (S-HIoT) systems combine multimodal physiological sensing (EEG, ECG, SpO₂, respiratory effort and actigraphy) with wireless communication and cloud-based analytics for automated sleep-stage classification and disorder detection. Nonetheless, the digitization of sleep medicine brings about significant cybersecurity concerns. The constant transmission of sensitive biomedical information makes S-HIoT networks open to anomalous traffic flows, signal manipulation, replay attacks, spoofing, and data integrity violation. Existing studies mostly focus on analyzing physiological signals and network intrusion detection independently, resulting in a systemic vulnerability of cyber–physical sleep monitoring ecosystems. With the aim of addressing this empirical deficiency, this review integrates emerging advances (2022–2026) in the AI-assisted categorization of sleep phases and IoMT anomaly detector designs on the finer analysis of CNN, LSTM/BiLSTM, Transformer-based systems, and a component part of federated schemes and the lightweight, edge-deployable intruder assessor models available. The aim of this study is to uncover a gap in the literature: integrated architectures to trade off audiences of faithfulness of physiological modeling with communication-layer security. To counter it, we present a single framework to include CNN-based spatial feature extraction, Bidirectional Long Short-Term Memory (BiLSTM)-based temporal models and Random Forest-based ensemble classification using a dual task-learning approach. We propose a multi-objective optimization framework to jointly optimize the performance of sleep-stage prediction and that of network anomaly detection. Performance on publicly available datasets (Sleep-EDF and CICIoMT2024) confirms that hybrid integration can be tailored to achieve high accuracy [99.8% sleep staging; 98.6% anomaly detection] whilst being characterized by low inference latency (<45 ms), which is promising for feasibility in real-time deployment in view of targeting edge devices. This work presents a comprehensive framework for developing secure, intelligent, and clinically robust digital sleep health ecosystems by bridging chronobiological signal modeling with cybersecurity mechanisms. Furthermore, it highlights future research directions, including explainable AI, federated secure learning, adversarial robustness, and energy-aware edge optimization. Full article

Background/Objectives: Hyperkalemia is common in patients with chronic kidney disease (CKD). However, its epidemiology may be evolving due to population aging, new therapeutic developments and novel estimated glomerular filtration rate (eGFR) equations. We have re-evaluated the epidemiology of hyperkalemia in a contemporary cohort in which eGFR was assessed using the EKFC equation recommended by the European Federation of Clinical Chemistry and Laboratory Medicine (EFLM). Methods: We analyzed 190,579 laboratory tests with serum potassium values corresponding to individual outpatients in Primary or Specialty Care from a single laboratory in 2023, representing 42% of the catchment area population. Results: Hypokalemia (<3.5 mmol/L) was present in 0.3% patients, hyperkalemia (≥5.0 mmol/L) in 10.5% (11.5% of men, 9.7% of women). Hyperkalemia was mostly mild (9.4%) but was severe in 0.1% overall and in 10.5% of CKD G5. One in four patients with hyperkalemia had CKD. Hyperkalemia was more common among patients with CKD G3–G5 defined using the CKD-EPI2009 equation than defined using the EKFC equation (20.5 vs. 18.6%, p < 0.0001). Using EKFC, hyperkalemia prevalence increased with decreasing eGFR from G1 (6.6%) to G2 (10.8%) and, especially in CKD G3–G5 (G3 17.2% to G5 47.5%). In multivariate logistic analysis, worse renal function, worse diabetes control, older age, and surrogates for release of intracellular potassium during sample processing (red blood cell counts or size, platelet counts, elevated calcium levels) were independently associated with hyperkalemia. This multivariate model yielded an area under the curve (AUC) of the Receiver Operating Characteristic (ROC) curve for hyperkalemia of 0.678 (95% CI 0.674–0.682). Random forest also identified GFR as the most important feature associated with hyperkalemia and generally concurred with logistic analysis findings. Conclusions: Hyperkalemia remains common, especially in CKD G5. While hyperkalemia is mainly associated with low eGFR, sample processing should be optimized. Full article

Empirical parameter settings in steam-based soil disinfestation for Panax notoginseng (a valuable medicinal plant) often hinder the simultaneous optimization of pathogen control and energy efficiency. To address this limitation, this study aims to develop a parameter regulation framework that integrates multi-output regression with scenario-oriented intelligent decision-making. Initially, a comprehensive dataset comprising critical parameters—steam pressure (P_steam), soil compaction (C_soil), and heating time (t_heat)—was established. A random search (RS) hyperparameter optimization scheme was employed to comparatively evaluate the multi-output predictive performance of Random Forest (RF), Support Vector Regression (SVR), and Multilayer Perceptron (MLP) for the joint estimation of soil temperature (T_soil) and root-rot pathogen kill rate (Kill_rate). Subsequently, by integrating total energy consumption (E_total) and operating electricity cost models, a constrained search algorithm was implemented to develop three objective-oriented decision modes: “maximize Kill_rate”, “minimize C_electricity”, and “maximize Efficiency”. Results demonstrate that the RS-optimized SVR yielded superior multi-output performance, achieving R² of 0.968 for T_soil (MAE = 2.44 °C) and 0.808 for Kill_rate (MAE = 7.85%). Compared to conventional empirical configurations, the proposed decision modes exhibited significant advantages across diverse scenarios. In the “maximize Kill_rate” mode, dynamic extensions of t_heat facilitated theoretical complete inactivation even under challenging heating conditions, effectively eliminating disinfection “blind spots” inherent in fixed-duration strategies. Under the “minimize C_electricity” mode, precise regulation of P_steam reduced operational electricity costs by 18.2% while satisfying the constraint of Kill_rate ≥ 95%. Furthermore, the “maximize Efficiency” mode identified an optimal operating point at C_soil = 64 kPa (P_steam = 0.4 MPa, t_heat = 13 min), thereby mitigating performance degradation associated with excessive tillage or high media rigidity and achieving an optimized cost–benefit ratio. By synthesizing high-fidelity multi-output regression with a flexible multi-mode decision-making framework, this study provides an intelligent solution for soil disinfestation in protected agriculture, facilitating the coordinated optimization of phytosanitary efficacy, energy expenditure, and economic viability. Full article

Sri Lanka provides a home for a significant number of fruit species, and yet most of them are underutilised due to a lack of awareness regarding their therapeutic potential. Different plant parts from these fruits have been used for centuries to cure various diseases in traditional medicine, as fodder and to overcome hunger. Despite having remarkable health benefits and being resistant to extreme environmental conditions, these fruits are still confined to home gardens and forests, while some commercially cultivated major fruits remain dominant in the market. Hence, gathering information on the nutritional and health benefits of these fruit species will enhance people’s awareness, ensure food security through value-added food product development, facilitate livelihoods for rural farmers and also establish long-term sustainability. The main objective of this review is to highlight the phytochemical potential of some underutilised fruit varieties in Sri Lanka while exploring their health-promoting aspects, including antioxidant, anti-cancer, anti-diabetic, cardioprotective, anti-inflammatory and cytoprotective properties. Many research studies have been conducted on commonly available major fruits. However, there is a notable gap in research that explores pharmacological aspects of these fruits. Further research is warranted in developing methods for sustainable harvesting and postharvest practices for underutilised fruits from Sri Lanka. Characterisation of health benefits associated with underutilised fruits will help to develop awareness about their potential and possibly foster commercial interest. Developing nutraceuticals or functional foods from these fruits will help us to focus on enhancing their sustainable production. Full article

Generally, forest trees with medicinal value present diverse chemotypes considered key determinants of efficacy, safety, and commercial valuation. Such heterogeneity varies among tissues, genotypes, and seasons, and stress exposure. This review summarizes how regulatory controls and genome architecture affect the stability and synthesis of secondary metabolites in woody medicinally important taxa. Detailed haplotypic and chromosomal analyses have recently identified diverse and repeatable architectural drivers. Among these, LTR/transposon-mediated revamping, neofunctionalization, biosynthetic gene clusters, and tandem duplication play a special role in reshaping pathway capacity. The enzymatic regulation of these drivers translates this “capacity” into harvest-pertinent chemistry by employing conserved TF modules, hormone crosstalk, and emergent chromatin/epigenetic layers. Nevertheless, major parameters pertaining to the tissue-specific storage, transport, and compartmentalization of these chemotypes are contextualized with certain limitations. In this review, the integration of GWAS/eQTL/TWAS with multi-tissue is explained in addition to the replacement of a single reference with pangenome/haplotype frameworks, and explicit modeling of G × E further strengthen genotype-to-chemotype mapping. Therefore, in this review we summarize practical workflows for chemotype discovery utilizing staged validation models of heterologous reconstitution, isotope/spatial evidence, and chemistry. These findings were supported by data on saponins, alkaloids, iridoids, and defense response. Such an integration links mechanistic understanding to authentication, standardization, and sustainable utilization strategies in woody medicinal trees. Full article

The urban trade in non-timber forest products (NTFPs) plays a key role in sustaining livelihoods in the Global South, while also suggesting potential pressure on resource supply systems. This study provides an integrated analysis of NTFP diversity, market structure, economic importance, and perceived drivers of resource decline in Kolwezi, a rapidly expanding mining city where such dynamics remain poorly documented. Data were collected through surveys conducted with 35 sellers across two major urban markets and 384 consumers from different neighbourhoods and analysed using descriptive and inferential statistics to examine patterns, associations, and socio-demographic influences. A total of 65 NTFP species were recorded, including 49 plant, 14 animal, and 2 fungal species, reflecting strong dependence on Miombo ecosystems. Medicinal (59.3%) and food uses dominate, with multifunctional species such as Bobgunnia madagascariensis (Desv.) J.H.Kirkbr. & Wiersama, Canarium schweinfurthii Engl., Terminalia mollis M.A.Lawson, Gardenia ternifolia subsp. jovis-tonantis (Welw.) Verdc., and Albizia antunesiana Harms, playing a central role in both household use and market supply. The trade is largely female-dominated (79.1%) and constitutes a major component of the informal urban economy, with monthly incomes ranging from USD 9 to 429.3, primarily driven by sales volume rather than unit price. However, the sector is constrained by structural and logistical limitations, including remoteness of supply areas, seasonality, and limited value addition. The perceived declining availability of high-use-value species, attributed by respondents to deforestation, mining expansion, and overexploitation, highlights perceived sustainability concerns. These pressures are perceived differently across socio-demographic groups, indicating heterogeneous understandings of environmental change. Overall, the results indicate a perceived mismatch between rising urban demand and declining resource availability, which may reflect an emerging socio-ecological imbalance between urban demand and perceived resource availability. Addressing these challenges requires integrated strategies that combine the domestication of priority species, the development of processing chains, improved infrastructure, and strengthened governance mechanisms. Such approaches are essential to reconcile livelihood support with the sustainable management of NTFPs in rapidly transforming urban landscapes. Full article

Traditional sensory evaluation of traditional Chinese medicine (TCM) and medicinal and food homologous products has long relied on human observation of appearance, color, aroma, and taste. However, this approach is highly subjective, difficult to quantify, and often lacks reproducibility across evaluators. Intelligent sensory systems, including the electronic nose, electronic tongue, and machine vision, provide objective and digitized sensory information for TCM quality evaluation. Nevertheless, these platforms generate high-dimensional and heterogeneous datasets, creating a strong demand for efficient artificial intelligence (AI)-based analytical tools. This review summarizes recent advances in the application of machine learning and deep learning methods, such as support vector machine, random forest, convolutional neural network, and long short-term memory networks, for intelligent sensory evaluation of TCM. Particular emphasis is placed on how AI supports feature extraction, pattern recognition, classification, regression, and multisource data fusion across electronic nose, electronic tongue, and machine vision systems. Representative applications in raw material authentication, geographical origin discrimination, processing monitoring, and quality grading are also discussed. In addition, the current challenges related to data standardization, sensor drift, model robustness, and interpretability are highlighted. Overall, this review provides an integrated overview of AI-enabled intelligent sensory technologies and clarifies their potential to advance TCM quality evaluation toward a more objective, efficient, and holistic framework. Full article

Brosimum alicastrum Swartz is a forest species with substantial potential for animal and human nutrition. However, its nutritional attributes and commercial applications are poorly disseminated and structurally underdeveloped. This study examines the relationship between scientific research and the commercialization of Brosimum alicastrum products in Mexico, integrating bibliometric analysis with a value network approach to identify market constraints and opportunities. Scientific publications indexed in Scopus from 1961 to 2024 were analyzed to characterize research trends, documented uses, and the geographic distribution of knowledge production. In parallel, companies commercializing Brosimum alicastrum-based products in Mexico were surveyed during 2024 using a value network approach (suppliers, customers, complementors, and competitors). A SWOT analysis was conducted to assess the structural strengths and vulnerabilities affecting market development. The results show that research in Mexico has primarily focused on the species’ properties as a functional food. At the same time, limited attention has been given to silviculture, commercialization strategies, and value-chain governance. Although Brosimum alicastrum products are currently positioned within premium market segments, business continuity is constrained by unstable supply systems that rely almost exclusively on seasonal wild collection from natural distribution areas. Both the value network and the SWOT analysis identified supply instability as the main factor limiting market expansion. Therefore, advancing research on the silviculture of Brosimum alicastrum is essential to support the establishment of managed production systems and commercial plantations capable of ensuring a stable, year-round supply of raw material. These developments would facilitate access to new market niches and enhance the biocultural and ethnobotanical value of Brosimum alicastrum as a functional and medicinal food resource within Mexico’s emerging bioeconomy. Full article