Quantitative analysis of soil potassium by near-infrared (NIR) spectroscopy combined with a three-step progressive hybrid variable selection strategy.

Soil potassium is a crucial nutrient element necessary for crop growth, and its efficient measurement has become essential for developing rational fertilization plans and optimizing crop growth benefits. At present, data mining technology based on near-infrared (NIR) spectroscopy analysis has proven to be a powerful tool for real-time monitoring of soil potassium content. However, as technology and instruments improve, the curse of the dimensionality problem also increases accordingly. Therefore, it is urgent to develop efficient variable selection methods suitable for NIR spectroscopy analysis techniques. In this study, we proposed a three-step progressive hybrid variable selection strategy, which fully leveraged the respective strengths of several high-performance variable selection methods. By sequentially equipping synergy interval partial least squares (SiPLS), the random forest variable importance measurement (RF(VIM)), and the improved mean impact value algorithm (IMIV) into a fusion framework, a soil important potassium variable selection method was proposed, termed as SiPLS-RF(VIM)-IMIV. Finally, the optimized variables were fitted into a partial least squares (PLS) model. Experimental results demonstrated that the PLS model embedded with the hybrid strategy effectively improved the prediction performance while reducing the model complexity. The RMSET and RT on the test set were 0.01181% and 0.88246, respectively, better than the RMSET and RT of the full spectrum PLS, SiPLS, and SiPLS-RF(VIM) methods. This study demonstrated that the hybrid strategy established based on the combination of NIR spectroscopy data and the SiPLS-RF(VIM)-IMIV method could quantitatively analyze soil potassium content levels and potentially solve other issues of data-driven soil dynamic monitoring.

Interspecific association between two primatespecies in an urban park / Associação interespecífica entre duas espécies de primatas em um parque urbano

As with Amazonian primates, mixed associations between species in the Atlantic Forest are also influenced by ecological factors. However, Atlantic Forest primates may face additional challenges, such as isolation pressures and fragmentation of forest habitats, which may increase the frequency of these arrangements. The main of this work is to report a sympatry with possible interaction between individuals of two species of primates of the Pitheciidae and Callitrichidae families: Callicebus nigrifrons (Spix 1823) and Callithrix aurita (É. Geoffroy Saint-Hilaire 1812) in an urban park in the south of the state of Minas Gerais. Individuals were observed interacting during foraging and displacement. The association of individuals of the two species can be explained by the low quality of the forest fragment, as it can increases the chances of obtaining food resources and configures a dilution strategy against predator attacks.

Assim como ocorre com os primatas amazônicos, as associações mistas entre espécies na Mata Atlântica também são influenciadas por fatores ecológicos. No entanto, os primatas da Mata Atlântica podem enfrentar desafios adicionais, como pressões de isolamento e fragmentação de habitats florestais, que podem aumentar a frequência desses arranjos. O objetivo deste trabalho é apresentar um relato de simpatia com possível interação entre indivíduos de duas espécies de primatas das famílias Pitheciidae e Callitrichidae: Callicebus nigrifrons (Spix 1823) e Callithrix Resumo aurita (É. Geoffroy Saint-Hilaire 1812) em um parque urbano no sul do estado de Minas Gerais. Foram observados indivíduos interagindo durante o forrageio e deslocamento. A associação de indivíduos das duas espécies pode ser explicada devido à baixa qualidade do fragmento florestal, pois pode aumentar as chances de obter recursos alimentares e configura uma estratégia de diluição de contra-ataques de predadores.

Climate and topography control variation in the tropical dry forest-rainforest ecotone.

Ecotones are the transition zones between ecosystems and can exhibit steep gradients in ecosystem properties controlling flows of energy and organisms between them. Ecotones are understood to be sensitive to climate and environmental changes, but the potential for spatiotemporal dynamics of ecotones to act as indicators of such changes is limited by methodological and logistical constraints. Here, we use a novel combination of satellite remote sensing and analyses of spatial synchrony to identify the tropical dry forest-rainforest ecotone in Area de Conservación Guanacaste, Costa Rica. We further examine how climate and topography influence the spatiotemporal dynamics of the ecotone, showing that ecotone is most prevalent at mid-elevations where the topography leads to moisture accumulation and that climatic moisture availability influences up and downslope interannual variation in ecotone location. We found some evidence for long-term (22 year) trends toward upslope or downslope ecotone shifts, but stronger evidence that regional climate mediates topographic controls on ecotone properties. Our findings suggest the ecotone boundary on the dry forest side may be less resilient to future precipitation reductions and that if drought frequency increases, ecotone reductions are more likely to occur along the dry forest boundary.

Construction and evaluation of a liver cancer risk prediction model based on machine learning.

BACKGROUND: Liver cancer is one of the most prevalent malignant tumors worldwide, and its early detection and treatment are crucial for enhancing patient survival rates and quality of life. However, the early symptoms of liver cancer are often not obvious, resulting in a late-stage diagnosis in many patients, which significantly reduces the effectiveness of treatment. Developing a highly targeted, widely applicable, and practical risk prediction model for liver cancer is crucial for enhancing the early diagnosis and long-term survival rates among affected individuals. AIM: To develop a liver cancer risk prediction model by employing machine learning techniques, and subsequently assess its performance. METHODS: In this study, a total of 550 patients were enrolled, with 190 hepatocellular carcinoma (HCC) and 195 cirrhosis patients serving as the training cohort, and 83 HCC and 82 cirrhosis patients forming the validation cohort. Logistic regression (LR), support vector machine (SVM), random forest (RF), and least absolute shrinkage and selection operator (LASSO) regression models were developed in the training cohort. Model performance was assessed in the validation cohort. Additionally, this study conducted a comparative evaluation of the diagnostic efficacy between the ASAP model and the model developed in this study using receiver operating characteristic curve, calibration curve, and decision curve analysis (DCA) to determine the optimal predictive model for assessing liver cancer risk. RESULTS: Six variables including age, white blood cell, red blood cell, platelet counts, alpha-fetoprotein and protein induced by vitamin K absence or antagonist II levels were used to develop LR, SVM, RF, and LASSO regression models. The RF model exhibited superior discrimination, and the area under curve of the training and validation sets was 0.969 and 0.858, respectively. These values significantly surpassed those of the LR (0.850 and 0.827), SVM (0.860 and 0.803), LASSO regression (0.845 and 0.831), and ASAP (0.866 and 0.813) models. Furthermore, calibration and DCA indicated that the RF model exhibited robust calibration and clinical validity. CONCLUSION: The RF model demonstrated excellent prediction capabilities for HCC and can facilitate early diagnosis of HCC in clinical practice.

Spatial ecology, biodiversity, and abiotic determinants of Congo's bai ecosystem.

Canopy gaps are foundational features of rainforest biodiversity and successional processes. The bais of Central Africa are among the world's largest natural forest clearings and thought to be critically important islands of open-canopy habitat in an ocean of closed-canopy rainforest. However, while frequently denoted as a conservation priority, there are no published studies on the abundance or distribution of bais across the landscape, nor on their biodiversity patterns, limiting our understanding of their ecological contribution to Congolese rainforests. We combined remote sensing and field surveys to quantify the abundance, spatial distribution, shape, size, biodiversity, and soil properties of bais in Odzala-Kokoua National Park (OKNP), Republic of the Congo (hereafter, Congo). We related bai spatial distribution to variation in hydrology and topography, compared plant community composition and 3D structure between bais and other open ecosystems, quantified animal diversity from camera traps, and measured soil moisture content in different bai types. We found bais to be more numerous than previously thought (we mapped 2176 bais in OKNP), but their predominantly small size (80.7% of bais were <1 ha), highly clustered distribution, and restriction to areas of low topographic position make them a rare riparian habitat type. We documented low plant community and structural similarity between bai types and with other open ecosystems, and identified significant differences in soil moisture between bai and open ecosystem types. Our results demonstrate that two distinct bai types can be differentiated based on their plant and animal communities, soil properties, and vegetation structure. Taken together, our findings provide insights into how bais relate to other types of forest clearings and on their overall importance to Congolese rainforest ecosystems.

Nectriaceae species associated to root rot of nursery and young Eucalyptus smithii trees in Uruguay with Ilyonectria charruensis as novel species.

Forestry constitutes an important agronomical activity in Uruguay, involving the cultivation of exotic trees mainly for cellulose pulp production with Eucalyptus species. Over the last decade, E. smithii emerged as a species of interest for cellulose pulping. However, its rapid expansion has coincided with high mortality rates among young trees ranging from 5 to 85%, especially during the first and second summer after plantation. Disease surveys conducted on nine E. smithii commercial fields and three nurseries in southern and eastern Uruguay, yielded a collection of 25 isolates from E. smithii root rot belonging to the Nectriaceae family. In this study, we aimed to identify and characterize these isolates employing phenotypical and molecular studies and to assess their pathogenicity on E. smithii seedlings. Based on morphological features, the Nectriaceae isolates were subdivided into two groups, one resembling Calonectria (n=15) and another Cylindrocarpon-like (n=10). DNA sequences of the partial histone H3 (his3), actine, calmodulin, RNA polymerase II second largest subunit, translation elongation factor 1-alpha (tef1) and ß-tubulin (tub2) genes were amplified for Calonectria, as well as partial his3, tef1, tub2 and internal-transcribed spacer and intervening 5.8S (ITS) for the Cylindrocarpon-like group. Based on phylogenetic analysis and phenotypical features three species were identified and characterized; Calonectria pauciramosa (n=15), Dactylonectria novozelandica (n=2), and a novel taxon which we describe here as Ilyonectria charruensis sp. nov. (n=8). The pathogenicity trials revealed that isolates from the three species significantly reduced both shoot and root dry weights of inoculated E. smithii seedlings compared to control plants.

First Report of Botryosphaeria dothidea Causing Leaf Blight on Parrotia subaequalis in China.

Parrotia subaequalis is of great ornamental value due to its unique bark, featuring interesting textures and colors, and its large, striking galls. These characteristics make it a popular choice for bonsai cultivation. (Yan et al. 2022) . In July 2023, an outbreak of leaf blight was observed on 40, six-month-old P. subaequalis seedlings in Anqing, Anhui, China, with an incidence rate of 80%. In the early stages of infection, small brown spots appear on the leaf surface, which gradually become round or irregular and darken to a deep brown color. As the disease progresses, the affected areas expand from the leaf margins towards the center, causing the leaf surface to become concave, wilt, and necrotize. This resulted in restricted plant growth, and in severe cases, partial or complete plant death. For isolation, 30 tissue slices (5 × 5 mm) were taken from the leaves of 10 symptomatic seedlings and surface sterilized with 75% ethanol for 5 seconds, followed by five rinses with sterilized distilled water. After two days of dark incubation at 28°C, hyphal tips of fungi were transferred onto new potato dextrose agar (PDA) plates and incubated until conidia production. Six unidentified isolates with similar morphological characteristics were obtained. The colonies, initially white, darken to black after 7 to 10 days of incubation. They produced colorless, aseptate conidia that were oblong or fusiform, measuring 18-26 µm in length and 5-8 µm in width (n=50). The morphological characteristics of the isolates resembled those of Botryosphaeria (Udayanga et al. 2015) . Isolate IS2116-1 was further confirmed through molecular methods. The rDNA internal transcribed spacer (ITS) region, translation elongation factor 1-α (TEF1-α), and beta-tubulin (TUB2) genes were amplified and sequenced using the primers ITS1/ITS4 (White et al., 1990), EF1-728F/EF1-986R, and Bt2a/Bt2b (Ferreira et al., 2021; Carbone et al., 1999), respectively. BLAST analysis revealed that the ITS (OR958722) sequence was 100% similar to the B. dothidea isolate HZ5(MH329650.1), TEF1-a (PP214058) sequence was 100% similar to the B. dothidea strain JZB310220(ON890458.1), and strain TUB2 (PP214057) sequence was 99.78% similar to the B. dothidea strain L14 (KR260833.1). Maximum likelihood analyses were performed for the combined ITS、TUB2、TEF datasets using PhyloSuite v1.2.2, the resulting phylogenetic tree indicated that isolate IS2116-1 clustered together with Botryosphaeria dothidea in a clade with 97% bootstrap support(Zheng et al. 2020) . Pathogenicity tests were conducted on 3-6 month-old P. subaequalis seedlings (n = 5) grown in a greenhouse. A conidial suspension (106 spores/ml) collected from the isolates was sprayed onto P. subaequalis seedlings, while the control was treated with distilled water. All plants were maintained in a growth chamber at 28°C with a 12-h photoperiod. The experiment was conducted twice independently . After 20 days of inoculation, brownish lesions similar to those observed in the field appeared on the treated plants, while the noninoculated control plants remained symptomless. The pathogen was reisolated from the leaves of the obviously diseased seedlings and confirmed as B. dothidea through morphological and sequence analysis. No isolates were obtained from uninoculated control plants, thus fulfilling Koch's hypothesis. This report marks the first record of B. dothidea causing leaf blight in P. subaequalis. In light of the rarity of natural P. subaequalis populations, it is imperative to assess both the extent of disease spread and its economic impact. These insights are crucial for devising strategies to protect this endangered species from disease threats and to preserve its ecological significance.

Application of machine learning and deep learning techniques in modeling the associations between air pollution and meteorological parameters in urban areas of tehran metropolis.

Tehran, the most crowded city in Iran, suffers from severe air pollution, particularly during the cold months. This research endeavored to examine the statistical relationships between criteria air pollutants (CO, NO2, SO2, O3, PM10, and PM2.5) and meteorological elements (temperature, rainfall, wind speed, relative humidity, air pressure, sunshine hours, solar radiation, and cloudiness), as well as assess and compare the efficacy of six different algorithms (multiple linear regression (MLR), generalized additive model (GAM), classification and regression trees (CART), random forest (RF), gradient boosting machine (GBM), and deep learning (DL)) in modeling pollutants and climatic factors responsible for variations in Tehran's air pollution levels from 2001 to 2021 using R 4.3.2 software. The results of this study showed that O3 was strongly affected by weather conditions, while other pollutants were mainly influenced by each other than by meteorological parameters and more extensive research is required to pinpoint the precise impact of human activity on these pollutant levels in Tehran. Also based on the predictive model performance evaluation and concerning the principle of parsimony, in half of the cases, the MLR outperformed other models, despite its seeming simplicity and principal assumptions dependence. In other situations, the GAM was a good substitute.

Wind Shapes the Growth Strategies of Trees in a Tropical Forest.

In tropical forests, trees strategically balance growth patterns to optimise fitness amid multiple environmental stressors. Wind poses the primary risk to a tree's mechanical stability, prompting developments such as thicker trunks to withstand the bending forces. Therefore, a trade-off in resource allocation exists between diameter growth and vertical growth to compete for light. We explore this trade-off by measuring the relative wind mortality risk for 95 trees in a tropical forest in Panama and testing how it varies with tree size, species and wind exposure. Surprisingly, local wind exposure and tree size had minimal impact on wind mortality risk; instead, species wood density emerged as the crucial factor. Low wood density species exhibited a significantly greater wind mortality risk, suggesting a prioritisation of competition for light over biomechanical stability. Our study highlights the pivotal role of wind safety in shaping the life-history strategy of trees and structuring diverse tropical forests.

Landsat-based spatiotemporal estimation of subtropical forest aboveground carbon storage using machine learning algorithms with hyperparameter tuning.

Introduction: The aboveground carbon storage (AGC) in forests serves as a crucial metric for evaluating both the composition of the forest ecosystem and the quality of the forest. It also plays a significant role in assessing the quality of regional ecosystems. However, current technical limitations introduce a degree of uncertainty in estimating forest AGC at a regional scale. Despite these challenges, remote sensing technology provides an accurate means of monitoring forest AGC. Furthermore, the implementation of machine learning algorithms can enhance the precision of AGC estimates. Lishui City, with its rich forest resources and an approximate forest coverage rate of 80%, serves as a representative example of the typical subtropical forest distribution in Zhejiang Province. Methods: Therefore, this study uses Landsat remote sensing images, employing backpropagation neural network (BPNN), random forest (RF), and categorical boosting (CatBoost) to model the forest AGC of Lishui City, selecting the best model to estimate and analyze its forest AGC spatiotemporal dynamics over the past 30 years (1989-2019). Results: The study shows that: (1) The texture information calculated based on 9×9 and 11×11 windows is an important variable in constructing the remote sensing estimation model of the forest AGC in Lishui City; (2) All three machine learning techniques are capable of estimating forest AGC in Lishui City with high precision. Notably, the CatBoost algorithm outperforms the others in terms of accuracy, achieving a model training accuracy and testing accuracy R2 of 0.95 and 0.83, and RMSE of 2.98 Mg C ha-1 and 4.93 Mg C ha-1, respectively. (3) Spatially, the central and southwestern regions of Lishui City exhibit high levels of forest AGC, whereas the eastern and northeastern regions display comparatively lower levels. Over time, there has been a consistent increase in the total forest AGC in Lishui City over the past three decades, escalating from 1.36×107 Mg C in 1989 to 6.16×107 Mg C in 2019. Discussion: This study provided a set of effective hyperparameters and model of machine learning suitable for subtropical forests and a reference data for improving carbon sequestration capacity of subtropical forests in Lishui City.

Asymmetric responses of EVI and tree ring growth to extreme climate on the northeastern margin of the Tibetan Plateau.

Extreme climate events have increased in terms of their amplitudes, frequency and severity, greatly affecting ecosystem functions and the balance of the global carbon cycle. However, there are still uncertainties about how extreme climate change will affect tree growth. This study characterized the responses of tree growth to extreme climate on the northeastern Tibetan Plateau from 2000 to 2020. Meanwhile, a back propagation neural network was used to predict tree growth trends under two future emission scenarios from 2020 to 2050. This study revealed that: (1) the tree-ring width index (RWI) showed a decreasing trend (- 0.04/decade) in the eastern region, but the enhanced vegetation index (EVI) showed an increasing trend (0.05/decade) from 2000 to 2020. While both RWI and EVI in the middle and western regions showed increasing trends. (2) The responses of RWI and EVI to extreme climate were regionally asymmetric. In the eastern region, extreme precipitation inhibited tree radial growth, while extreme warm nights promoted tree canopy growth. In two other regions, both extreme precipitation and extreme warm nights promoted tree growth. (3) The model predicts that there was no significant change in RWI and EVI in the western region, but both RWI and EVI showed an increasing trend in the middle and eastern regions under the low emission scenario. Under the high emission scenario, the growth of tree stem and canopy in all three regions shows a general decreasing trend. The results of this study both improved the understanding of the differences in carbon allocation between tree stem (RWI) and canopy (EVI) and identified vulnerability thresholds for tree populations.

Elevation-dependent dynamics of soil properties in a hilly watershed: a landform-based approach.

Understanding the variation of soil physical properties in relation to land use and elevation is essential for modeling soil-landscape relationships and sustainable land management. Hence, this study investigates the spatio-temporal variability of soil physical properties in a lower Himalayan watershed, where agriculture, forest, and grasslands are dominant. Samples from 104 sites in a 422 km2 watershed were collected using a gridded sampling scheme (2 km × 2 km resolution) over 57 weeks. Spatial patterns were analyzed using the Kriging technique, and Spearman rank correlation was employed to identify landform-dependent correlations between soil properties and elevation. The interdependence of the properties was detected using principal component analysis (PCA), while the random forest (RF) approach explored the factors influencing electrical conductivity (EC), organic content (OC), soil temperature (ST), and soil moisture (SM). The results revealed that forest landforms have higher coarser fractions (40%) compared to other landforms, while grasslands have higher soil fines (66%). A positive correlation was observed for elevation with sand content (0.15*), organic content (0.42*), and specific gravity (0.03), while a negative correlation was observed for silt (0.10), clay (0.21*), bulk density (0.52*), electrical conductivity (0.41*), soil moisture (0.28*), and temperature (0.31*). Elevation, soil texture, and specific gravity were identified as critical controls for EC, OC, ST, and SM, emphasizing the importance of soil properties, especially elevation and texture, in shaping spatial distributions. These findings contribute to creating a high-resolution regional inventory for effective land use management, adaptation to climate change, and improved livelihood, specifically for mountain people.

Sex-specific Prediction of Cardiogenic Shock After Acute Coronary Syndromes: The SEX-SHOCK Score.

BACKGROUND: and aims: Cardiogenic shock (CS) remains the primary cause of in-hospital death after acute coronary syndromes (ACS), with its plateauing mortality rates approaching 50%. To test novel interventions, personalized risk prediction is essential. The ORBI (Observatoire Régional Breton sur l'Infarctus) score represents the first-of-its-kind risk score to predict in-hospital CS in ACS patients undergoing percutaneous coronary intervention (PCI). However, its sex-specific performance remains unknown, and refined risk prediction strategies are warranted. METHODS: This multinational study included a total of 53 537 ACS patients without CS on admission undergoing PCI. Following sex-specific evaluation of ORBI, regression and machine-learning models were used for variable selection and risk prediction. By combining best-performing models with highest-ranked predictors, SEX-SHOCK was developed, and internally and externally validated. RESULTS: The ORBI score showed lower discriminative performance for the prediction of CS in females than males in Swiss (AUC [95% CI]: 0.78 [0.76-0.81] vs. 0.81 [0.79-0.83]; p=0.048) and French ACS patients (0.77 [0.74-0.81] vs. 0.84 [0.81-0.86]; p=0.002). The newly developed SEX-SHOCK score, now incorporating ST-segment elevation, creatinine, C-reactive protein, and left ventricular ejection fraction, outperformed ORBI in both sexes (females: 0.81 [0.78-0.83]; males: 0.83 [0.82-0.85]; p<0.001), which prevailed following internal and external validation in RICO (females: 0.82 [0.79-0.85]; males: 0.88 [0.86-0.89]; p<0.001) and SPUM-ACS (females: 0.83 [0.77-0.90], p=0.004; males: 0.83 [0.80-0.87], p=0.001). CONCLUSIONS: The ORBI score showed modest sex-specific performance. The novel SEX-SHOCK score provides superior performance in females and males across the entire spectrum of ACS, thus providing a basis for future interventional trials and contemporary ACS management.

Improving ML-based landslide susceptibility using ensemble method for sample selection: a case study of Kangra district in Himachal Pradesh, India.

Developing effective strategies to predict areas susceptible to landslides and reducing risk is vital. This involves using ensemble methods to meet the precise prediction and addressing challenges like data limitation. Recent studies have highlighted the potential of using ensemble methods to enhance the prediction of landslide susceptibility maps (LSM). Ensemble methods present a sampling of landslides and non-landslide points from high and low susceptible areas, respectively. Extensive research has explored their application in machine learning processes, particularly in classification-related problems. This study delves into strategies of ensemble as a promising method in future landslide applications. The proposed method was tested considering Kangra district of Himachal Pradesh as study area where three datasets were prepared consisting of presence and absence points. Dataset 1 consisted of initial landslide and randomly generated non-landslide points. In dataset 2, additional landslide points obtained from the very high susceptibility of initial LSM were supplemented with initial landslide data, while the non-landslide points were generated randomly from the study area. Finally, dataset 3 was composed of the landslide points as in dataset 2, and the non-landslide points were obtained from the very low susceptible areas of initial LSM. These datasets are used with random forest (RF) and support vector machine (SVM), thereby preparing six landslide susceptibility maps. To analyze the applicability of the proposed method, we have used metrics such as AUC-ROC, precision, recall, F-score, accuracy and Mathew's correlation coefficient (MCC). The AUC for dataset 1 with SVM and RF is 0.89, which increased to 0.898 and 0.952 for datasets 2 and 3 with SVM and 0.937 and 0.954 with RF. Among all the methods, the precision and recall values were highest for dataset 3 with SVM as well as RF. Hence, based on several accuracy metrics, we conclude that when the landslides and non-landslides samples were sampled from very high and very low susceptible areas respectively, the LSM performed better than all the other methods. Sampling landslides from very high susceptible areas only (dataset 2) does not perform well thereby committing misclassification error. The study demonstrated that the landslide and non-landslide data were obtained from very high and very low susceptibility; the predictive capability of the LSM increased significantly. Thus, the results demonstrate the effectiveness of the proposed ensemble approach in providing precise delineation of landslide zones, facilitating informed decision-making for land and hazard management.

Application of random survival forest to establish a nomogram combining clinlabomics-score and clinical data for predicting brain metastasis in primary lung cancer.

PURPOSE: To establish a nomogram for predicting brain metastasis (BM) in primary lung cancer at 12, 18, and 24 months after initial diagnosis. METHODS: In this study, we included 428 patients who were diagnosed with primary lung cancer at Harbin Medical University Cancer Hospital between January 2020 and January 2022. The endpoint event was BM. The patients were randomly categorized into two groups in a 7:3 ratio: training (n = 299) and validation (n = 129) sets. Least absolute shrinkage and selection operator was utilized to analyze the laboratory test results in the training set. Furthermore, clinlabomics-score was determined using regression coefficients. Then, clinlabomics-score was combined with clinical data to construct a nomogram using random survival forest (RSF) and Cox multivariate regression. Then, various methods were used to evaluate the performance of the nomogram. RESULTS: Five independent predictive factors (pathological type, diameter, lymph node metastasis, non-lymph node metastasis and clinlabomics-score) were used to construct the nomogram. In the validation set, the bootstrap C-index was 0.7672 (95% CI 0.7092-0.8037), 12-month AUC was 0.787 (95% CI 0.708-0.865), 18-month AUC was 0.809 (95% CI 0.735-0.884), and 24-month AUC was 0.858 (95% CI 0.792-0.924). In addition, the calibration curve, decision curve analysis and Kaplan-Meier curves revealed a good performance of the nomogram. CONCLUSIONS: Finally, we constructed and validated a nomogram to predict BM risk in primary lung cancer. Our nomogram can identify patients at high risk of BM and provide a reference for clinical decision-making at different disease time points.

Widespread introduced species dominate the urban tree assemblage on the endemic-rich tropical island of São Tomé.

The Afrotropics are experiencing some of the fastest urbanisation rates on the planet but the impact of city growth on their rich and unique biodiversity remains understudied, especially compared to natural baselines. Little is also known about how introduced species influence ß-diversity in these contexts, and how patterns coincide with native ranges of species. Here we investigated how tree assemblages of the endemic-rich Afrotropical island of São Tomé differed between urban, rural and natural zones. These were primarily characterised by urban greenspaces, shade plantations, and old-growth forests, respectively. Based on 81 transects, we assessed biodiversity metrics of endemic, native and introduced species. Tree abundance and species richness were highest in the natural zone, where the composition was most different from the urban zone. The tree community of the rural zone was the most uneven and had the least variation among transects, representing the lowest ß-diversity. The urban zone was dominated by introduced species (57.7%), while the natural zone hosted almost exclusively native species (93.3%), including many endemics (26.1%). The biogeographic realms that species originated from were particularly diverse in the urban zone, with few species from the Afrotropics. In contrast to native and endemic trees, introduced trees were clearly associated with urban and rural expansion, as they were much more abundant and species-rich in these zones than in the natural zone, facilitating biotic homogenisation. These findings highlight how urban and rural environments are affecting the native tree flora of São Tomé, and the need for conservation measures geared towards globally threatened and endemic tree species. Importantly, these require the protection of natural forests, despite the rising land demands for settlements and agriculture. Ultimately, such action to conserve endemic trees will contribute to global efforts to prevent further biodiversity declines.

Identification of response regulation governing ozone formation based on influential factors using a random forest approach.

The pursuit of enhanced scientific, refined, and precise ozone and air quality control continues to pose significant challenges. Using data visualization techniques and random forest (RF) algorithms, the temporal distribution of atmospheric pollutants and the interrelationship between O3 concentration and its influential factors were investigated with one-year monitoring data in Deqing county in 2021. The local atmospheric conditions predominantly belonged to NOx-sensitive and transition zone. Extremely high O3 concentration were primarily observed when temperatures (T) exceeded 30 °C, with relative humidity (RH) ranging between 30 and 60 %. NO2, RH and T were identified as the top 3 important factors, and O3 concentration have stronger linearly relationship to RH and T, while stronger nonlinearly relationship to NO2. By employing an optimized RF model, controlling consistent mild and high reaction atmospheric conditions, the O3 concentration response to the change of individual influencing factors was acquired. The O3 concentration increased and then decreased in response to the increasing NO2 concentration, displaying a characteristic inflection point at 10 µg m-3. More reactive radicals produced at higher VOCs concentration and continuing NOx cycle at lower NO2 concentration, resulting in the acceleration in the direction of producing more O3. Therefore, the significant different O3 response to variation of VOCs and NOx concentration between mild and high reaction atmospheric conditions, as well as the existing of oxidant elevation should be considered in local air quality control. This study demonstrates the efficacy of ML methods in simulating nonlinear response of O3, supports the understanding of local O3 formation and quick guidance for precise local O3 pollution control and the related strategies.

Artificial intelligence algorithms permits rapid acute kidney injury risk classification of patients with acute myocardial infarction.

Objective: This study aimed to develop and validate several artificial intelligence (AI) models to identify acute myocardial infarction (AMI) patients at an increased risk of acute kidney injury (AKI) during hospitalization. Methods: Included were patients diagnosed with AMI from the Medical Information Mart for Intensive Care (MIMIC) III and IV databases. Two cohorts of AMI patients from Changzhou Second People's Hospital and Xuzhou Center Hospital were used for external validation of the models. Patients' demographics, vital signs, clinical characteristics, laboratory results, and therapeutic measures were extracted. Totally, 12 AI models were developed. The area under the receiver operating characteristic curve (AUC) were calculated and compared. Results: AKI occurred during hospitalization in 1098 (28.3 %) of the 3882 final enrolled patients, split into training (3105) and test (777) sets randomly. Among them, Random Forest (RF), C5.0 and Bagged CART models outperformed the other models in both the training and test sets. The AUCs for the test set were 0.754, 0.734 and 0.730, respectively. The incidence of AKI was 9.8 % and 9.5 % in 2202 patients in the Changzhou cohort and 807 patients in the Xuzhou cohort with AMI, respectively. The AUCs for patients in the Changzhou cohort were RF, 0.761; C5.0, 0.733; and bagged CART, 0.725, respectively, and Xuzhou cohort were RF, 0.799; C5.0, 0.808; and bagged CART, 0.784, respectively. Conclusion: Several machines learning-based prediction models for AKI after AMI were developed and validated. The RF, C5.0 and Bagged CART model performed robustly in identifying high-risk patients earlier. Clinical trial approval statement: This Trial was registered in the Chinese clinical trials registry: ChiCTR1800014583. Registered January 22, 2018 (http://www.chictr.org.cn/searchproj.aspx).

Prediction and interpretive of motor vehicle traffic crashes severity based on random forest optimized by meta-heuristic algorithm.

Providing accurate prediction of the severity of traffic collisions is vital to improve the efficiency of emergencies and reduce casualties, accordingly improving traffic safety and reducing traffic congestion. However, the issue of both the predictive accuracy of the model and the interpretability of predicted outcomes has remained a persistent challenge. We propose a Random Forest optimized by a Meta-heuristic algorithm prediction framework that integrates the spatiotemporal characteristics of crashes. Through predictive analysis of motor vehicle traffic crash data on interstate highways within the United States in 2020, we compared the accuracy of various ensemble models and single-classification prediction models. The results show that the Random Forest (RF) model optimized by the Crown Porcupine Optimizer (CPO) has the best prediction results, and the accuracy, recall, f1 score, and precision can reach more than 90 %. We found that factors such as Temperature and Weather are closely related to vehicle traffic crashes. Closely related indicators were analyzed interpretatively using a geographic information system (GIS) based on the characteristic importance ranking of the results. The framework enables more accurate prediction of motor vehicle traffic crashes and discovers the important factors leading to motor vehicle traffic crashes with an explanation. The study proposes that in some areas consideration should be given to adding measures such as nighttime lighting devices and nighttime fatigue driving alert devices to ensure safe driving. It offers references for policymakers to address traffic management and urban development issues.

Stochastic process drives the dissimilarity in biodiversity patterns between Pinus kwangtungensis coniferous forest and evergreen deciduous broad-leaved mixed forest in karst area.

Pinus kwangtungensis is an endangered evergreen conifer tree species, and its in situ conservation has been considered one of the most critical issues. However, relative protection is limited by the lack of understanding of its community structure and underlying assembly processes. To study how the species diversity and assembly processes of Pinus kwangtungensis coniferous forest (CF) differed with regional climax community, this study established a series forest dynamic plots both in CF and evergreen deciduous broadleaved mixed forest (EDBM). By performing comparison analysis and PER-SIMPER approaches, we quantified the differences in species diversity and community assembly rules. The results showed that the species α-diversity of CF differed greatly from the EDBM both in species richness and evenness. In addition, the stochastic process acted a more important role in determining species composition, indicating the uncertainty in presence of species. The soil phosphorus and changeable calcium content were the main factors driving the differences in biodiversity, which the importance of soil nutrient factors in driving species composition. Our study highlighted that we should consider the community structure and ecological process when conducting conservation of Pinus kwangtungensis.