Multivariate Regression Tree Research Articles

Taking Application Rates With a Grain of Salt: Uncovering the Impact of Road De‐Icing Salt on Freshwaters of a Mountain Catchment in the Italian Alps

ABSTRACTWhile application of salt for de‐icing purposes has been extensively studied in urban areas of North America, little attention has been paid to it in Europe, particularly in mountain areas. Here, after assessment of baseline salinity, and through applying different approaches (i.e., univariate statistical techniques, Multivariate Regression Trees, multivariate regressions), we investigated the potential changes in water chemistry and benthic macroinvertebrate community structure caused by the application of de‐icing salt over an entire winter season, in a mountain catchment located in the Italian Alps (N 46°, E 11°). Concurrently, we tested and compared the application of three different benthic macroinvertebrate indices used to assess salinisation impacts. Overall, we identified a constant level of baseline salinity across a 13‐year period, accompanied by a strong seasonality factor. Despite an application rate comparable to those of large North American cities, macroinvertebrate communities showed little evidence of change. However, chemical ions whose concentrations are known to be influenced by de‐icing salt (e.g., Na+, Cl−) were identified as the structuring drivers of the macroinvertebrate communities, thus suggesting that the studied riverine environment show a high potential for change in relation to salinity. In conclusion, we caution against the simple evaluation of application rates to assess the risk/level of salinisation within a catchment, and encourage further specific analysis and study of salinisation in mountain areas: they appear as sensitive habitats to potential variations in salinity, and stressors such as increased urbanisation and climate change will further exacerbate the risk of increasing salinisation in mountain freshwaters.

Clinical and laboratory predictors for bacteremia in critically ill calves.

Sepsis is a main contributor to calf mortality, but diagnosis is difficult. Develop and validate a predictive model for bacteremia in critically ill calves (CIC). A total of 334 CIC, sampled for blood culture. Cross-sectional study. Multivariable logistic regression and classification tree analysis on clinical, ultrasonographic, and laboratory variables were performed on a dataset including all animals. Model validation was done on 30% of the dataset. Similar statistics (except validation) were performed on a subset of the database (n = 143), in which presumed contaminants were excluded. The best performing model to predict bacteremia, taking all detected bacteria into account, included tachypnea, tachycardia, acidemia, hypoglycemia, venous hypoxemia, and hypoproteinemia. Sensitivity and specificity of this model were 70.6% and 98.0%, respectively, but decreased to 61.5% and 91.7% during model validation. The best-performing model, excluding presumed contaminants, included abnormal temperature, heart rate, absence of enteritis, hypocalcemia, and hyperlactatemia as risk factors for bacteremia. Sensitivity and specificity of this model were 71.4% and 93.9%, respectively. Both classification trees performed less well in comparison to logistic regression. The classification tree excluding presumed contaminants, featured hypoglycemia, absence of diarrhea, and hyperlactatemia as risk factors for bacteremia. Sensitivity and specificity were 39.4% and 92.7%, respectively. Hypoglycemia, hyperlactatemia, and hypoproteinemia seem relevant in assessing bacteremia in CIC. The performance of these models based on basic clinical and blood variables remains insufficient to predict bacteremia.

Enhancing diagnostic precision in EBV-related HLH: a multifaceted approach using 18F-FDG PET/CT and nomogram integration

BackgroundThe hyperinflammatory condition and lymphoproliferation due to Epstein-Barr virus (EBV)-associated hemophagocytic lymphohistiocytosis (HLH) affect the detection of lymphomas by 18F-FDG PET/CT. We aimed to improve the diagnostic capabilities of 18F-FDG PET/CT by combining laboratory parameters.MethodsThis retrospective study involved 46 patients diagnosed with EBV-positive HLH, who underwent 18F-FDG PET/CT before beginning chemotherapy within a 4-year timeframe. These patients were categorized into two groups: EBV-associated HLH (EBV-HLH) (n = 31) and EBV-positive lymphoma-associated HLH (EBV + LA-HLH) (n = 15). We employed multivariable logistic regression and regression tree analysis to develop diagnostic models and assessed their efficacy in diagnosis and prognosis.ResultsA nomogram combining the SUVmax ratio, copies of plasma EBV-DNA, and IFN-γ reached 100% sensitivity and 81.8% specificity, with an AUC of 0.926 (95%CI, 0.779–0.988). Importantly, this nomogram also demonstrated predictive power for mortality in EBV-HLH patients, with a hazard ratio of 4.2 (95%CI, 1.1–16.5). The high-risk EBV-HLH patients identified by the nomogram had a similarly unfavorable prognosis as patients with lymphoma.ConclusionsThe study found that while 18F-FDG PET/CT alone has limitations in differentiating between lymphoma and EBV-HLH in patients with active EBV infection, the integration of a nomogram significantly improves the diagnostic accuracy and also exhibits a strong association with prognostic outcomes.

Understanding healthy ageing in India: insights from multivariate regression trees

BackgroundPopulation ageing represents a significant global challenge, particularly pronounced in countries like India.AimsThis study aims to explore how factors such as socio-economic status, behaviour, and health influence healthy ageing across the Indian older population.MethodsIn this study, we utilized the Longitudinal Ageing Study in India – wave 1 dataset for analysis purposes. Scores were generated for five dimensions of healthy aging, including physical, functional, mental, cognitive, and social aspects and these scores were treated as the target variables. Multivariate Regression Trees analysis was employed to identify the behavioural and socio-demographic factors associated with each dimension of healthy ageing.ResultsYears of education emerge as crucial across all dimensions, positively impacting cognitive health and mitigating age-related decline in healthy ageing. Marital status, engagement in household activities, spiritual practices, and living arrangements impacts the scores of different aspects of healthy ageing. Gender disparities in healthy aging are noticeable in the 60–74 age group, with women generally having lower scores. Safety of the living environment is a crucial determinant of the mental health of the elderly across all age groups.These findings highlight the complex interplay of factors in healthy ageing outcomes.ConclusionOur study emphasizes the pivotal role of education in fostering healthy ageing in India. Factors such as environmental safety and social participation also influence well-being. Targeted interventions addressing education, gender equality, safety, and healthcare access are vital for enhancing the ageing experience and overall well-being of older adults.

Lesions hyper- to isointense to surrounding liver in the hepatobiliary phase of gadoxetic acid-enhanced MRI.

Hyper- or isointensity in the hepatobiliary phase (HBP) of gadoxetic acid-enhanced MRI has high specificity for focal nodular hyperplasia (FNH) but may be present in hepatocellular adenoma and carcinoma (HCA/HCC). This study aimed to identify imaging characteristics differentiating FNH and HCA/HCC. This multicenter retrospective cohort study included patients with pathology-proven FNH or HCA/HCC, hyper-/isointense in the HBP of gadoxetic acid-enhanced MRI between 2010 and 2020. Diagnostic performance of imaging characteristics for the differentiation between FNH and HCA/HCC were reported. Univariable analyses, multivariable logistic regression analyses, and classification and regression tree (CART) analyses were conducted. Sensitivity analyses evaluated imaging characteristics of B-catenin-activated HCA. In total, 124 patients (mean age 40 years, standard deviation 10 years, 108 female) with 128 hyper-/isointense lesions were included. Pathology diagnoses were FNH and HCA/HCC in 64 lesions (50%) and HCA/HCC in 64 lesions (50%). Imaging characteristics observed exclusively in HCA/HCC were raster and atoll fingerprint patterns in the HBP, sinusoidal dilatation on T2-w, hemosiderin, T1-w in-phase hyperintensity, venous washout, and nodule-in-nodule partification in the HBP and T2-w. Multivariable logistic regression and CART additionally found a T2-w scar indicating FNH, less than 50% fat, and a spherical contour indicating HCA/HCC. In our selected cohort, 14/48 (29%) of HCA were B-catenin activated, most (13/14) showed extensive hyper-/isointensity, and some had a T2-w scar (4/14, 29%). If the aforementioned characteristics typical for HCA/HCC are encountered in lesions extensively hyper- to isointense, further investigation may be warranted to exclude B-catenin-activated HCA. Hyper- or isointensity in the HBP of gadoxetic acid-enhanced MRI is specific for FNH, but HCA/HCC can also exhibit this feature. Therefore, we described imaging patterns to differentiate these entities. FNH and HCA/HCC have similar HBP intensities but have different malignant potentials. Six imaging patterns exclusive to HCA/HCC were identified in this lesion population. These features in liver lesions hyper- to isointense in the HBP warrant further evaluation.

Characteristics and Driving Mechanisms of Understory Vegetation Diversity Patterns in Central and Southern China

Large-scale forest restoration projects significantly reduce the net rates of forest loss. However, as a key component of forest restoration, planted forests have failed to restore biodiversity. China has implemented a large-scale afforestation program, which includes pure planted forests in particular, leading to various changes in ecosystem processes. Despite this, a comprehensive analysis of understory vegetation diversity patterns in these pure planted forests is still lacking. This study aimed to analyze the data on understory vegetation diversity from three typical pure and natural forest ecosystems of Hunan ecological forests to reveal their diversity patterns. The results revealed no significant difference in the understory diversity index between natural and pure forest types, although natural forests had a bigger species pool. The Zipf–Mandelbrot model was a better fit for species abundance distribution. The fitted results suggested that both environmental filtering and neutral processes affected the species abundance distribution and pure understory communities during restoration succession. Natural forests had the most stable understory diversity structure, whereas pure Phyllostachys heterocycla (Carr.) Mitford forests had the least stable structure. Multivariate regression tree analysis identified indicator species for each community. The gradient boosting model indicated that isothermality and slope direction were the most important factors affecting diversity. The β-diversity analysis showed that community establishment in the four forest types was affected via different mechanisms. The findings of this study have significant implications for understanding the impact of afforestation on the mechanisms for maintaining diversity.

Meta-regression of sulcal patterns, clinical and environmental factors on neurodevelopmental outcomes in participants with multiple CHD types.

Congenital heart disease affects 1% of infants and is associated with impaired neurodevelopment. Right- or left-sided sulcal features correlate with executive function among people with Tetralogy of Fallot or single ventricle congenital heart disease. Studies of multiple congenital heart disease types are needed to understand regional differences. Further, sulcal pattern has not been studied in people with d-transposition of the great arteries. Therefore, we assessed the relationship between sulcal pattern and executive function, general memory, and processing speed in a meta-regression of 247 participants with three congenital heart disease types (114 single ventricle, 92 d-transposition of the great arteries, and 41 Tetralogy of Fallot) and 94 participants without congenital heart disease. Higher right hemisphere sulcal pattern similarity was associated with improved executive function (Pearson r = 0.19, false discovery rate-adjusted P = 0.005), general memory (r = 0.15, false discovery rate P = 0.02), and processing speed (r = 0.17, false discovery rate P = 0.01) scores. These positive associations remained significant in for the d-transposition of the great arteries and Tetralogy of Fallot cohorts only in multivariable linear regression (estimated change β = 0.7, false discovery rate P = 0.004; β = 4.1, false discovery rate P = 0.03; and β = 5.4, false discovery rate P = 0.003, respectively). Duration of deep hypothermic circulatory arrest was also associated with outcomes in the multivariate model and regression tree analysis. This suggests that sulcal pattern may provide an early biomarker for prediction of later neurocognitive challenges among people with congenital heart disease.

Unraveling the environmental influence on inter-annual fishery yield in a small-scale gillnet fishery under Rio de la Plata influence, South America

The study focuses on understanding the influence of the environment on the relative yields of a gill net fishery operating in San Antonio Cape, Argentina. The research was conducted during five austral warm periods covering spring to summer from 2008 to 2013, aiming to assess the potential impacts of climate change on small-scale fisheries. The hierarchical species composition of 563 fishery landings encompasses 41 registered species. Among these species, Cynoscion guatucupa, Micropogonias furnieri, Mustelus schmitti, and Parona signata were found to be dominant. The species composition showed a similarity ranging from 36.22% to 57.59%, with significant differences observed among most of the warm seasons. The Multivariate Regression Tree analysis showed that the temperature was the variable with the greatest influence on the composition of the landings. During warmer conditions (>20.4 °C), the location of the draft became a significant factor, while variation in turbidity played a role in the northern zone. In colder warm conditions (<20.4 °C), the composition differed based on the volumes of Río de la Plata discharge. Specifically, the freshwater outflow was further differentiated by depth (∼9 m) at lower volumes (<20 649 m3/s) and by turbidity at intermediate values (20 649–22 908 m3/s). The vulnerability of the fishery was explained by a combination of specific ranges of various stressors. These stressors led to significant variations in the composition of fishery landings, ultimately affecting the economic income of the fishermen. By understanding the relationship between environmental factors and fishery yields, this study provides valuable insights into anticipating the potential impacts of climate change on small-scale, vulnerable fisheries.

Big data resolving using Apache Spark for load forecasting and demand response in smart grid: a case study of Low Carbon London Project

Using recent information and communication technologies for monitoring and management initiates a revolution in the smart grid. These technologies generate massive data that can only be processed using big data tools. This paper emphasizes the role of big data in resolving load forecasting, renewable energy sources integration, and demand response as significant aspects of smart grids. Meters data from the Low Carbon London Project is investigated as a case study. Because of the immense stream of meters' readings and exogenous data added to load forecasting models, addressing the problem is in the context of big data. Descriptive analytics are developed using Spark SQL to get insights regarding household energy consumption. Spark MLlib is utilized for predictive analytics by building scalable machine learning models accommodating meters' data streams. Multivariate polynomial regression and decision tree models are preferred here based on the big data point of view and the literature that ensures they are accurate and interpretable. The results confirmed the descriptive analytics and data visualization capabilities to provide valuable insights, guide the feature selection process, and enhance load forecasting models' accuracy. Accordingly, proper evaluation of demand response programs and integration of renewable energy resources is accomplished using achieved load forecasting results.

Comparison of Multivariate Adaptive Regression Splines and Classification Regression Tree for Prediction of Body Weight of Bapedi Sheep

Comparison of Multivariate Adaptive Regression Splines and Classification Regression Tree for Prediction of Body Weight of Bapedi Sheep

Pseudo-value regression trees

This paper presents a semi-parametric modeling technique for estimating the survival function from a set of right-censored time-to-event data. Our method, named pseudo-value regression trees (PRT), is based on the pseudo-value regression framework, modeling individual-specific survival probabilities by computing pseudo-values and relating them to a set of covariates. The standard approach to pseudo-value regression is to fit a main-effects model using generalized estimating equations (GEE). PRT extend this approach by building a multivariate regression tree with pseudo-value outcome and by successively fitting a set of regularized additive models to the data in the nodes of the tree. Due to the combination of tree learning and additive modeling, PRT are able to perform variable selection and to identify relevant interactions between the covariates, thereby addressing several limitations of the standard GEE approach. In addition, PRT include time-dependent effects in the node-wise models. Interpretability of the PRT fits is ensured by controlling the tree depth. Based on the results of two simulation studies, we investigate the properties of the PRT method and compare it to several alternative modeling techniques. Furthermore, we illustrate PRT by analyzing survival in 3,652 patients enrolled for a randomized study on primary invasive breast cancer.

Ecotypic variation in multiple traits of European beech: selection of suitable provenances based on performance and stability

Induced by climate change associated disturbances and further promoted by changes in forest management, the proportion of European beech, a highly competitive climax species, is increasing in Central Europe. However, its climatic stability is questioned by the recent loss of vitality. In this regard, the evaluation of seed sources used for reforestation receives great attention. Here, we present a multi-trait evaluation of height, basal area and stem quality assessed over 25 years for 85 provenances grown at three sites in northern, western and eastern Germany. Considerable provenance differentiation exists, explaining 21% (proportion of trees with acceptable stem form) to 45% (basal area) of the variance on single sites and 20 to 39% across sites, while provenance by environment interactions are absent. On the landscape level, this results in distinct patterns with spatially adjacent provenances showing a similar trait expression. These patterns are highly similar for height and basal area but divergent for stem form. They could be directly linked to geographic variables with multivariate regression tree analysis that captured 58% of the phenotypic variation, delineating eleven ‘ecotypes’ shaped by local adaptation. A selection based on two multi-trait indices gives highly concordant results. Particularly, the intermediate elevations of the central highlands in Western Germany host highly suitable provenances. Lower elevation provenances from continental climates in the south-east profit from the transfer to favorable growing conditions. Since the majority of provenances was already exposed to elevated temperatures compared to their origin during the observation period, this study gives a first indication for the potential benefits of assisted migration facing climate change.

Evaluation of meteorological drought effects on underground water level fluctuations using data mining methods (case study: semi-deep wells of Golestan province).

In most arid and semi-arid environments, groundwater is one of the precious resources threatened by water table decline and desiccation, thus it must be constantly monitored. Identifying the causes influencing the variations of the subsurface water level, such as meteorological drought, is one approach for monitoring these fluctuations. In the present study, the effect of two meteorological drought indices SPI and SPEI on the fluctuations of the underground water level was evaluated, as was their relationship with the drought index of the subsurface water level (SWI) using multivariate linear regression and M5 decision tree regression. After calculating climatic and hydrological drought indices in a 6-month time window for a long-term statistical period (1989-2018), the semi-deep aquifers of Golestan province, which is located in northern Iran, were considered as a research location for this purpose. The results demonstrated that the effect of meteorological drought does not immediately manifest in the changes of the subsurface water table and the hydrological drought index. By adding the meteorological drought index with a 6-month lag step, the average air temperature, and the total rainfall from the previous 6months as new variables, the correlation with the SWI index increases, so that in the best-case scenario, the M5 decision tree model provides the best result in predicting the SWI index. The second half of the year yielded a coefficient of determination of 0.92 and an error value of RMSE = 0.27 for the SPEI index. Among the meteorological drought indices, the SPEI index, which is based on precipitation and evapotranspiration, created a stronger link with the SWI index, which highlights the significance of potential evapotranspiration. It is a warning that, as a result of global warming, subsurface water tables in this region may fall in the future.

Development and external validation of a predictive model for prolonged length of hospital stay in elderly patients undergoing lumbar fusion surgery: comparison of three predictive models.

This study aimed to develop a predictive model for prolonged length of hospital stay (pLOS) in elderly patients undergoing lumbar fusion surgery, utilizing multivariate logistic regression, single classification and regression tree (hereafter, "classification tree") and random forest machine-learning algorithms. This study was a retrospective review of a prospective Geriatric Lumbar Disease Database. The primary outcome measure was pLOS, which was defined as the LOS greater than the 75th percentile. All patients were grouped as pLOS group and non-pLOS. Three models (including logistic regression, single-classification tree and random forest algorithms) for predicting pLOS were developed using training dataset and internal validation using testing dataset. Finally, online tool based on our model was developed to assess its validity in the clinical setting (external validation). The development set included 1025 patients (mean [SD] age, 72.8 [5.6] years; 632 [61.7%] female), and the external validation set included 175 patients (73.2 [5.9] years; 97[55.4%] female). Multivariate logistic analyses revealed that older age (odds ratio [OR] 1.06, p < 0.001), higher BMI (OR 1.08, p = 0.002), number of fused segments (OR 1.41, p < 0.001), longer operative time (OR 1.02, p < 0.001), and diabetes (OR 1.05, p = 0.046) were independent risk factors for pLOS in elderly patients undergoing lumbar fusion surgery. The single-classification tree revealed that operative time ≥ 232min, delayed ambulation, and BMI ≥ 30kg/m2 as particularly influential predictors for pLOS. A random forest model was developed using the remaining 14 variables. Intraoperative EBL, operative time, delayed ambulation, age, number of fused segments, BMI, and RBC count were the most significant variables in the final model. The predictive ability of our three models was comparable, with no significant differences in AUC (0.73 vs. 0.71 vs. 0.70, respectively). The logistic regression model had a higher net benefit for clinical intervention than the other models. The nomogram was developed, and the C-index of external validation for PLOS was 0.69 (95% CI, 0.65-0.76). This investigation produced three predictive models for pLOS in elderly patients undergoing lumbar fusion surgery. The predictive ability of our three models was comparable. Logistic regression model had a higher net benefit for clinical intervention than the other models. Our predictive model could inform physicians about elderly patients with a high risk of pLOS after surgery.

Incidence and risk factors of early onset VOD/SOS differ in younger vs older adults after stem cell transplantation

AbstractVeno-occlusive disease (VOD) is a rare but potentially life-threatening complication after allogeneic hematopoietic stem cell transplantation (allo-SCT). Although increasing awareness and modern transplant techniques have mitigated risk, the interaction of historic risk factors in the current era with posttransplant cyclophosphamide (PTCy) is unknown. We performed a retrospective single-center analysis of adult patients aged ≥18 years undergoing allo-SCT (N = 1561) using predominately PTCy as graft-versus-host disease (GVHD) prophylaxis (72%). We found a higher rate of VOD at 16.8% (20 of 119) in those aged ≤25 years compared with 3.8% (55 of 1442) in those aged >25 years, with unique predictors of VOD within each cohort. Multivariate classification and regression tree (CART) analysis confirmed age as the primary independent determinant of the rate of VOD. Among patients aged 18 to 25 years, disease risk index (DRI; 31% with high/very high DRI vs 12% low/intermediate DRI; P = .03) and prior lines of chemotherapy (24% with >1 vs 6% with ≤1; P = .03) were the strongest predictors of VOD. Incidence of VOD in patients aged >25 years of age consistently ranged between 3% and 5% across most risk factors evaluated, with only hepatic factors (baseline elevation of bilirubin, aspartate transferase, alanine aminotransferase) or gemtuzumab exposure associated with increased rates of VOD. There was no significant difference in rates of VOD in those receiving PTCy compared with those receiving alternate GVHD prophylaxis. Our data highlight the differences in incidence and predictors of VOD between younger (≤25) and older (>25) adults undergoing allo-SCT.

Nonlinearities in phytoplankton groups across temperate high mountain lakes

Abstract High mountain lakes are increasingly recognized as sentinel ecosystems of global change. Monitoring phytoplankton changes or reconstructing their composition from sedimentary records can help identify systemic changes in these lakes and their catchments. This study aimed to evaluate the distribution of the major phytoplankton groups in high mountain lakes across environmental gradients and identify tipping points in relative dominance. The phytoplankton groups were estimated using pigment‐based chemotaxonomy in 79 lakes in the Pyrenees selected to cover the bedrock and elevation gradients. Fifty‐four environment variables were considered, including in‐lake and catchment descriptors. Redundancy analyses showed that in‐lake descriptors override the explicative capacity of landscape variables. Generalized additive models and multivariate regression trees showed that water hardness, trophic state and food‐web descriptors were, in this order, the most influential factors determining phytoplankton group dominance. Calcium concentration of about 200 μeq L−1 defined the threshold between soft waters—with chrysophytes and chlorophytes showing a higher affinity for them—and harder waters that favour diatoms and cyanobacteria. Across the trophic gradient, there was a threshold at ~5 μg L−1 of total phosphorus (TP), chrysophytes being dominant below that TP value and cryptophytes above. The dominance of chlorophytes and cryptophytes increased with the density of macrozooplankton. Chrysophytes were significantly lower and diatoms higher in lakes with fish. Synthesis. The relative abundance of phytoplankton groups in temperate high mountain lakes responds in a nonlinear way to the hardness of the water in the range 20–1195 Ca2+ μeq L−1 and the trophic state in the range 0.94–19 TP μg L −1. The thresholds across water hardness and trophic state gradients coincide with studies based on other organisms, pointing to a robust typology for mountain lakes that should be considered when selecting global change sentinel lakes and anticipating abrupt transitions across these thresholds.

Development and external validation of a nomogram for predicting postoperative adverse events in elderly patients undergoing lumbar fusion surgery: comparison of three predictive models

BackgroundThe burden of lumbar degenerative diseases (LDD) has increased substantially with the unprecedented aging population. Identifying elderly patients with high risk of postoperative adverse events (AEs) and establishing individualized perioperative management is critical to mitigate added costs and optimize cost-effectiveness to the healthcare system. We aimed to develop a predictive tool for AEs in elderly patients with transforaminal lumbar interbody fusion (TLIF), utilizing multivariate logistic regression, single classification and regression tree (hereafter, “classification tree”), and random forest machine learning algorithms.MethodsThis study was a retrospective review of a prospective Geriatric Lumbar Disease Database (age ≥ 65). Our outcome measure was postoperative AEs, including prolonged hospital stays, postoperative complications, readmission, and reoperation within 90 days. Patients were grouped as either having at least one adverse event (AEs group) or not (No-AEs group). Three models for predicting postoperative AEs were developed using training dataset and internal validation using testing dataset. Finally, online tool was developed to assess its validity in the clinical setting (external validation).ResultsThe development set included 1025 patients (mean [SD] age, 72.8 [5.6] years; 632 [61.7%] female), and the external validation set included 175 patients (73.2 [5.9] years; 97 [55.4%] female). The predictive ability of our three models was comparable, with no significant differences in AUC (0.73 vs. 0.72 vs. 0.70, respectively). The logistic regression model had a higher net benefit for clinical intervention than the other models. A nomogram based on logistic regression was developed, and the C-index of external validation for AEs was 0.69 (95% CI 0.65–0.76).ConclusionThe predictive ability of our three models was comparable. Logistic regression model had a higher net benefit for clinical intervention than the other models. Our nomogram and online tool (https://xuanwumodel.shinyapps.io/Model_for_AEs/) could inform physicians about elderly patients with a high risk of AEs within the 90 days after TLIF surgery.

Application of Multivariate Logistic Regression and Decision Trees to Assess Factors Influencing Prevalence of Abortion and Stillbirth in Yankasa sheep

AbstractThis study was carried out to assess factors influencing prevalence of abortion and stillbirth in Yankasa sheep using multivariate logistic regression and decision trees. 191 kidding records of Ewes from a total of 50 traditional Yankasa sheep herders within Nasarawa South agro-ecological zone from the year 2020-2021 were utilized in the study. Sampling was restricted to only farmers that were able to give information on Lamb, Ram and Ewe identification as well as occurrence of abortion, stillbirth (defined as a kid born dead or dying within 24 hours after birth), kidding date or period, parity and number of foetuses. Three seasons of abortion or stillbirth were generated according to the month of the year: rainy season (from May to October), dry season (from February to April) and harmattan season (from November to January). The logit of the probability of an abortion or stillbirth was modelled using logistic regression assuming an asymptotic binomial distribution. The Chi-square goodness of fit test was performed to check if the multivariate logistic model fitted the data well (P&gt;0.05). Chi-square automatic interaction detection (CHAID) algorithm was also employed to model incidence of abortion or stillbirth. The chi-square analysis revealed that parity did not significantly (P&gt;0.05) affect the incidence of abortion. However, season of the year significantly (P&lt;0.05) affected prevalence of abortion, which was higher in the harmattan (38.5%) compared to the rainy (11.5%) and dry season (16.5%), respectively. Parity and season of the year did not affect significantly (P&gt;0.05) the prevalence of stillbirth. The binary logistic regression analysis showed that season affected significantly (P&lt;0.05) the prevalence of abortion, especially in the harmattan period with a high odds ratio (4.539). This was also confirmed by the result of the CHAID analysis. The present information could be exploited in management practices to reduce to the incidence of abortion in order to improve the production level of the sheep farmers.

Multivariate regression trees as an “explainable machine learning” approach to explore relationships between hydroclimatic characteristics and agricultural and hydrological drought severity: case of study Cesar River basin

Abstract. The typical drivers of drought events are lower than normal precipitation and/or higher than normal evaporation. The region's characteristics may enhance or alleviate the severity of these events. Evaluating the combined effect of the multiple factors influencing droughts requires innovative approaches. This study applies hydrological modelling and a machine learning tool to assess the relationship between hydroclimatic characteristics and the severity of agricultural and hydrological droughts. The Soil Water Assessment Tool (SWAT) is used for hydrological modelling. Model outputs, soil moisture and streamflow, are used to calculate two drought indices, namely the Soil Moisture Deficit Index and the Standardized Streamflow Index. Then, drought indices are utilised to identify the agricultural and hydrological drought events during the analysis period, and the index categories are employed to describe their severity. Finally, the multivariate regression tree technique is applied to assess the relationship between hydroclimatic characteristics and the severity of agricultural and hydrological droughts. Our research indicates that multiple parameters influence the severity of agricultural and hydrological droughts in the Cesar River basin. The upper part of the river valley is very susceptible to agricultural and hydrological drought. Precipitation shortfalls and high potential evapotranspiration drive severe agricultural drought, whereas limited precipitation influences severe hydrological drought. In the middle part of the river, inadequate rainfall partitioning and an unbalanced water cycle that favours water loss through evapotranspiration and limits percolation cause severe agricultural and hydrological drought conditions. Finally, droughts are moderate in the basin's southern part (Zapatosa marsh and the Serranía del Perijá foothills). Moderate sensitivity to agricultural and hydrological droughts is related to the capacity of the subbasins to retain water, which lowers evapotranspiration losses and promotes percolation. Results show that the presented methodology, combining hydrological modelling and a machine learning tool, provides valuable information about the interplay between the hydroclimatic factors that influence drought severity in the Cesar River basin.

Incidence and Risk Factors of Veno-Occlusive Disease Are Different in Younger Versus Older Adults Undergoing Allogeneic Hematopoietic Stem Cell Transplantation

Background: Veno-occlusive disease (VOD) is a rare but potentially life-threatening complication following allogeneic stem cell transplantation (allo-SCT). Improved transplant techniques and increased awareness of modifiable risk factors have reduced VOD incidence. However, the interaction of historic risk factors in the current era, particularly with the increasing use of calicheamicin-based therapies and post-transplant cyclophosphamide as GVHD prophylaxis, remains unclear. Methods: We conducted a retrospective, single center, chart-based study of consecutive adult patients (age ≥ 18 years) undergoing allo-SCT at MD Anderson Cancer Center between January 1 st, 2017 and December 31 st, 2021. VOD cases were defined using the classic VOD EBMT criteria or if patients received defibrotide treatment for VOD based on clinical judgment of the treating physician. Risk factors for VOD were evaluated in univariate analysis using Fine and Grey regression analysis. Multivariate analysis was performed using Classification and Regression Tree (CART) analysis to validate the findings of univariate analysis and evaluate independent effects accounting for potential interaction effects. Results: A total of 1561 patients were included in our analysis. Median age was 56 years and 60% were male. Patients primarily had acute myeloid leukemia/myelodysplastic syndrome (AML/MDS; 60%), acute lymphoblastic leukemia (ALL; 13%), or myeloproliferative neoplasms (13%). Most patients had matched related (28%) or unrelated donors (48%), and 21% underwent haploidentical transplantation. Forty-nine (3%) patients received inotuzumab ozogamicin (InO) containing regimens prior to allo-SCT, and 30 (2%) were exposed to gemtuzumab ozogamicin (GO). Post-transplant cyclophosphamide (PTCy) was used as GVHD prophylaxis in 72% of patients. Incidence of VOD in the entire study population was 4.8%. There was a significant difference in the median age of patients diagnosed with VOD compared to those without VOD (46 years vs 56 years, respectively, p=0.001). Further examination of the incidence of VOD within different age groups identified a VOD rate of 16.8% (20/119) in those aged ≤ 25 years compared to 3.8% (55/1442) in those &amp;gt; 25 years (Table 1). Multivariate classification and regression tree (CART) analysis confirmed age as the primary independent determinant of the rate of VOD (Figure 1). Given these findings, risk factor analysis was stratified according to age. In patients ≤25 years of age, disease risk index (DRI) (31% with high/very high DRI vs 12% low/intermediate DRI; p=0.03) and prior lines of chemotherapy (24% with &amp;gt;1 vs 6% with ≤1, p=0.03) were the strongest predictors of VOD. Within the younger cohort of patients with AML/MDS, 2 of 3 patients (67%) who received gemtuzumab ozogamicin (GO) developed VOD compared to 10% who did not receive GO (p=0.05). In patients aged &amp;gt;25 years, elevated baseline bilirubin, AST, ALT, and GO exposure were associated with increased VOD rates. VOD incidence based on baseline bilirubin levels (WNL, &amp;gt;ULN to 1.5x ULN, and &amp;gt;1.5x ULN) was 3%, 14%, and 16%, respectively (p&amp;lt;0.001). For baseline ALT levels (WNL, &amp;gt;ULN to 2.5x ULN, and &amp;gt;2.5x ULN), VOD rates were 4%, 3%, and 8%, respectively (p=0.02). Similarly, VOD rates with baseline AST levels (WNL, &amp;gt;ULN to 2.5x ULN, and &amp;gt;2.5x ULN) were 3%, 4%, and 27%, respectively (p≤0.001). In patients aged &amp;gt;25 years with AML/MDS, those receiving GO had a higher incidence of VOD compared to AML/MDS patients not exposed to GO (15% vs. 3%; p=0.01). There was no significant difference in VOD rates between those receiving PTCy and those receiving alternate GVHD prophylaxis in either age cohort. Conclusion: In summary, our data highlight that young adults (age 18 - 25 years) represent a distinct adult population with increased rates of VOD compared to their older counterparts, which are exacerbated by disease and treatment related factors (DRI and number lines of therapy). In contrast, patients &amp;gt; 25 years of age had low rates of VOD even in the presence of historical predictors, with only hepatic risk factors identified as increasing baseline VOD risk. There was no observed increased incidence of VOD among those receiving PTCy as GVHD prophylaxis.