Predicting Outcome on Admission and Post-Admission for Acetaminophen-Induced Acute Liver Failure Using Classification and Regression Tree Models

Background/Aim

Assessing prognosis for acetaminophen-induced acute liver failure (APAP-ALF) patients often presents significant challenges. King’s College (KCC) has been validated on hospital admission, but little has been published on later phases of illness. We aimed to improve determinations of prognosis both at the time of and following admission for APAP-ALF using Classification and Regression Tree (CART) models.

Methods

CART models were applied to US ALFSG registry data to predict 21-day death or liver transplant early (on admission) and post-admission (days 3-7) for 803 APAP-ALF patients enrolled 01/1998–09/2013. Accuracy in prediction of outcome (AC), sensitivity (SN), specificity (SP), and area under receiver-operating curve (AUROC) were compared between 3 models: KCC (INR, creatinine, coma grade, pH), CART analysis using only KCC variables (KCC-CART) and a CART model using new variables (NEW-CART).

Results

Traditional KCC yielded 69% AC, 90% SP, 27% SN, and 0.58 AUROC on admission, with similar performance post-admission. KCC-CART at admission offered predictive 66% AC, 65% SP, 67% SN, and 0.74 AUROC. Post-admission, KCC-CART had predictive 82% AC, 86% SP, 46% SN and 0.81 AUROC. NEW-CART models using MELD (Model for end stage liver disease), lactate and mechanical ventilation on admission yielded predictive 72% AC, 71% SP, 77% SN and AUROC 0.79. For later stages, NEW-CART (MELD, lactate, coma grade) offered predictive AC 86%, SP 91%, SN 46%, AUROC 0.73.

Conclusion

CARTs offer simple prognostic models for APAP-ALF patients, which have higher AUROC and SN than KCC, with similar AC and negligibly worse SP. Admission and post-admission predictions were developed.

Key Points

• Prognostication in acetaminophen-induced acute liver failure (APAP-ALF) is challenging beyond admission• Little has been published regarding the use of King’s College Criteria (KCC) beyond admission and KCC has shown limited sensitivity in subsequent studies• Classification and Regression Tree (CART) methodology allows the development of predictive models using binary splits and offers an intuitive method for predicting outcome, using processes familiar to clinicians• Data from the ALFSG registry suggested that CART prognosis models for the APAP population offer improved sensitivity and model performance over traditional regression-based KCC, while maintaining similar accuracy and negligibly worse specificity• KCC-CART models offered modest improvement over traditional KCC, with NEW-CART models performing better than KCC-CART particularly at late time points     

橡胶树栽培种质农艺性状的相关性和聚类分析

以我国国家橡胶树种质资源圃保存的119份橡胶树栽培种为材料,对叶蓬形状、叶面绿色程度等21个农艺性状进行比较分析。结果表明,遗传多样性指数平均值为0.83,叶痕形状最高为1.20,蜜腺表面形态为0.27,且性状数据分布集中;各性状中变异系数最大的大叶柄形状为60.03,蜜腺表面形态最小为9.08,平均值为33.88;叶面绿色程度和叶面光泽度、叶片形状与叶片基部形状等7对性状相关性极显著;21个性状可聚为2大类,119份供试材料中,同一品种来源地、亲本和子代、具有类似品种特性(抗寒性)等类型的品种聚为一类。分析结果可供橡胶树种质资源鉴定和杂交亲本选配参考。     

模糊聚类分析法及其在群落聚类分析中的应用

以不同种类蔬菜菜地节肢动物群落作为研究对象,介绍模糊聚类分析法在群落相似性分析中的应用。得到如下的结果：在建立模糊等价关系的基础上,根据不同的需要,当λ取０．８９９时,聚合成３个类群,当λ为０．８５２时,聚合成２个类群。而Ｆ－ＰＦＳ聚类分析法则根据群落在聚类类群之间或其中的散布情况,从所有的聚类结果中,选择最佳的聚类方案。本文材料的最佳的聚类结果为：把群落聚合成２类。类群１包括：菜心、小白菜、奶白菜、芥菜、芥兰、通菜、豇豆、四季豆上的节肢动物群落;类群２包括：藤菜与苋菜上节肢动物群落。     

Hierarchical Gene Selection and Genetic Fuzzy System for Cancer Microarray Data Classification

This paper introduces a novel approach to gene selection based on a substantial modification of analytic hierarchy process (AHP). The modified AHP systematically integrates outcomes of individual filter methods to select the most informative genes for microarray classification. Five individual ranking methods including t-test, entropy, receiver operating characteristic (ROC) curve, Wilcoxon and signal to noise ratio are employed to rank genes. These ranked genes are then considered as inputs for the modified AHP. Additionally, a method that uses fuzzy standard additive model (FSAM) for cancer classification based on genes selected by AHP is also proposed in this paper. Traditional FSAM learning is a hybrid process comprising unsupervised structure learning and supervised parameter tuning. Genetic algorithm (GA) is incorporated in-between unsupervised and supervised training to optimize the number of fuzzy rules. The integration of GA enables FSAM to deal with the high-dimensional-low-sample nature of microarray data and thus enhance the efficiency of the classification. Experiments are carried out on numerous microarray datasets. Results demonstrate the performance dominance of the AHP-based gene selection against the single ranking methods. Furthermore, the combination of AHP-FSAM shows a great accuracy in microarray data classification compared to various competing classifiers. The proposed approach therefore is useful for medical practitioners and clinicians as a decision support system that can be implemented in the real medical practice.     

A Comparative Assessment of the Influences of Human Impacts on Soil Cd Concentrations Based on Stepwise Linear Regression,Classification and Regression Tree,and Random Forest Models

Soil cadmium (Cd) contamination has attracted a great deal of attention because of its detrimental effects on animals and humans. This study aimed to develop and compare the performances of stepwise linear regression (SLR), classification and regression tree (CART) and random forest (RF) models in the prediction and mapping of the spatial distribution of soil Cd and to identify likely sources of Cd accumulation in Fuyang County, eastern China. Soil Cd data from 276 topsoil (0–20 cm) samples were collected and randomly divided into calibration (222 samples) and validation datasets (54 samples). Auxiliary data, including detailed land use information, soil organic matter, soil pH, and topographic data, were incorporated into the models to simulate the soil Cd concentrations and further identify the main factors influencing soil Cd variation. The predictive models for soil Cd concentration exhibited acceptable overall accuracies (72.22% for SLR, 70.37% for CART, and 75.93% for RF). The SLR model exhibited the largest predicted deviation, with a mean error (ME) of 0.074 mg/kg, a mean absolute error (MAE) of 0.160 mg/kg, and a root mean squared error (RMSE) of 0.274 mg/kg, and the RF model produced the results closest to the observed values, with an ME of 0.002 mg/kg, an MAE of 0.132 mg/kg, and an RMSE of 0.198 mg/kg. The RF model also exhibited the greatest R² value (0.772). The CART model predictions closely followed, with ME, MAE, RMSE, and R² values of 0.013 mg/kg, 0.154 mg/kg, 0.230 mg/kg and 0.644, respectively. The three prediction maps generally exhibited similar and realistic spatial patterns of soil Cd contamination. The heavily Cd-affected areas were primarily located in the alluvial valley plain of the Fuchun River and its tributaries because of the dramatic industrialization and urbanization processes that have occurred there. The most important variable for explaining high levels of soil Cd accumulation was the presence of metal smelting industries. The good performance of the RF model was attributable to its ability to handle the non-linear and hierarchical relationships between soil Cd and environmental variables. These results confirm that the RF approach is promising for the prediction and spatial distribution mapping of soil Cd at the regional scale.     

Superiority of insulin analogues versus human insulin in the treatment of diabetes mellitus

The modern goals of insulin replacement in Type 1 and Type 2 diabetes mellitus (T1, T2DM) are A1C <6.5% long-term, and prevention of hypoglycaemia (blood glucose, BG <70 mg/dl). In addition to appropriate education and motivation of diabetic subjects, the use of rapid- and long-acting insulin analogues, is critical to achieve these goals. The benefits of rapid-acting analogues (lispro, aspart and glulisine have similar pharmacodynamic effects) compared with non-modified human regular insulin, are: (a) lower 1- and 2-h post-prandial blood glucose; (b) lower risk of late post-prandial hypoglycaemia (and therefore lower BG variability); (c) better quality of life (greater flexibility in timing and dosing of insulin). In T1DM, rapid-acting analogues improve A1C only by the extent to which replacement of basal insulin is optimized at the same time, either by multiple daily NPH administrations, or continuous subcutaneous insulin infusion (CSII), or use of the long-acting insulin analogues glargine or detemir. In T2DM, rapid-acting analogues reduce post-prandial hyperglycaemia more than human regular insulin, but systematic studies are needed to examine the effects on A1C. The benefits of long-acting insulin analogues glargine and detemir vs. NPH, are: (1) lower fasting BG combined with lower risk of hypoglycaemia in the interprandial state (night); (2) lower variability of BG. Glargine and detemir differ in terms of potency and duration of action. Detemir should be given twice daily in the large majority of people with T1DM, and in a large percentage of subjects with T2DM as well, usually at doses greater vs those of the once daily glargine. However, when used appropriately for individual pharmacokinetics and pharmacodynamics, glargine and detemir result into similar effects on BG, risk of hypoglycaemia and A1C. Rapid- and long-acting insulin analogues should always be combined in the treatment of T1 and T2DM.     

安徽苹果生态区划的模糊聚类分析

本文根据苹果对生态条件的要求,选择了影响苹果生长发育的四个重要气象因子,采用模糊聚类方法,对安徽省栽培苹果的生态气候条件进行研究,初步划出了安徽苹果经济栽培的南线．作者认为,宿县、泗县以北地区是乔化苹果栽培的次适宜区,阜阳、寿县和定远一线为矮化苹果栽培的南线．     

Glioma 2021 WHO Classification: The Superiority of NGS Over IHC in Routine Diagnostics

Molecular Diagnosis & Therapy - The accurate detection of genetic variants such as single substitutions (IDH1/2, TERT), chromosomal abnormalities (CDKN2A, 1p/19q deletions, and EGFR...     

Wearable-Sensor-Based Classification Models of Faller Status in Older Adults

Wearable sensors have potential for quantitative, gait-based, point-of-care fall risk assessment that can be easily and quickly implemented in clinical-care and older-adult living environments. This investigation generated models for wearable-sensor based fall-risk classification in older adults and identified the optimal sensor type, location, combination, and modelling method; for walking with and without a cognitive load task. A convenience sample of 100 older individuals (75.5 ± 6.7 years; 76 non-fallers, 24 fallers based on 6 month retrospective fall occurrence) walked 7.62 m under single-task and dual-task conditions while wearing pressure-sensing insoles and tri-axial accelerometers at the head, pelvis, and left and right shanks. Participants also completed the Activities-specific Balance Confidence scale, Community Health Activities Model Program for Seniors questionnaire, six minute walk test, and ranked their fear of falling. Fall risk classification models were assessed for all sensor combinations and three model types: multi-layer perceptron neural network, naïve Bayesian, and support vector machine. The best performing model was a multi-layer perceptron neural network with input parameters from pressure-sensing insoles and head, pelvis, and left shank accelerometers (accuracy = 84%, F1 score = 0.600, MCC score = 0.521). Head sensor-based models had the best performance of the single-sensor models for single-task gait assessment. Single-task gait assessment models outperformed models based on dual-task walking or clinical assessment data. Support vector machines and neural networks were the best modelling technique for fall risk classification. Fall risk classification models developed for point-of-care environments should be developed using support vector machines and neural networks, with a multi-sensor single-task gait assessment.     

因子分析和聚类分析在玉米品种资源分类上的应用

本研究对201份湖北省玉米品种资源的28个性状进行了因子分析,结果前7个公因子对变异的累计方差贡献率达79.4％,前7个独立的公因子真实地反了所控制的28个性状及其相互关系．以前7个公因子为综合指标进行系统聚类,201份玉米品种聚成12类,其中A,B,H,K类综合性状较好．     

A Model of a Segmental Oscillator in the Leech Heartbeat Neuronal Network

We modeled a segmental oscillator of the timing network that paces the heartbeat of the leech. This model represents a network of six heart interneurons that comprise the basic rhythm-generating network within a single ganglion. This model builds on a previous two cell model (Nadim et al., 1995) by incorporating modifications of intrinsic and synaptic currents based on the results of a realistic waveform voltage-clamp study (Olsen and Calabrese, 1996). Due to these modifications, the new model behaves more similarly to the biological system than the previous model. For example, the slow-wave oscillation of membrane potential that underlies bursting is similar in form and amplitude to that of the biological system. Furthermore, the new model with its expanded architecture demonstrates how coordinating interneurons contribute to the oscillations within a single ganglion, in addition to their role of intersegmental coordination.     

Allometric Models for Tree Volume and Total Aboveground Biomass in a Tropical Humid Forest in Costa Rica1

Allometric equations for the estimation of tree volume and aboveground biomass in a tropical humid forest were developed based on direct measurements of 19 individuals of seven tree species in Northern Costa Rica. The volume and the biomass of the stems represented about two‐thirds of the total volume and total aboveground biomass, respectively. The average stem volume varied between 4 and 11 Mg/tree and the average total aboveground biomass ranged from 4 to 10 mg/tree. The mean specific gravity of the sampled trees was 0.62 ± 0.06 (g/cm³). The average biomass expansion factor was 1.6 ± 0.2. The best‐fit equations for stem and total volume were of logarithmic form, with diameter at breast height (R²= 0.66 ? 0.81) as an independent variable. The best‐fit equations for total aboveground biomass that were based on combinations of diameter at breast height, and total and commercial height as independent variables had R² values between 0.77 and 0.87. Models recommended for estimating total aboveground biomass are based on diameter at breast height, because the simplicity of these models is advantageous. This variable is easy to measure accurately in the field and is the most common variable recorded in forest inventories. Two widely used models in literature tend to underestimate aboveground biomass in large trees. In contrast, the models developed in this study accurately estimate the total aboveground biomass in these trees.     

Hierarchical Description and Extensive Classification of Protein Structural Changes by Motion Tree

The structures of the same protein, determined under different conditions, provide clues toward understanding the role of structural changes in the protein's function. Structural changes are usually identified as rigid-body motions, which are defined using a particular threshold of rigidity, such as domain motions. However, each protein actually undergoes motions with various size and magnitude ranges. In this study, to describe protein structural changes more comprehensively, we propose a method based on hierarchical clustering. This method enables the illustration of a wide range of protein motions in a single tree diagram, named the “Motion Tree”. We applied the method to 432 proteins exhibiting large structural changes and classified their Motion Trees in terms of the characteristic indices of the trees. This classification of the Motion Trees revealed clear relationships to their protein functions. Especially, complex structural changes are significantly correlated with multi-step protein functions.     

Large-Scale Phylogenetic Classification of Fungal Chitin Synthases and Identification of a Putative Cell-Wall Metabolism Gene Cluster in Aspergillus Genomes

The cell wall is a protective and versatile structure distributed in all fungi. The component responsible for its rigidity is chitin, a product of chitin synthase (Chsp) enzymes. There are seven classes of chitin synthase genes (CHS) and the amount and type encoded in fungal genomes varies considerably from one species to another. Previous Chsp sequence analyses focused on their study as individual units, regardless of genomic context. The identification of blocks of conserved genes between genomes can provide important clues about the interactions and localization of chitin synthases. On the present study, we carried out an in silico search of all putative Chsp encoded in 54 full fungal genomes, encompassing 21 orders from five phyla. Phylogenetic studies of these Chsp were able to confidently classify 347 out of the 369 Chsp identified (94%). Patterns in the distribution of Chsp related to taxonomy were identified, the most prominent being related to the type of fungal growth. More importantly, a synteny analysis for genomic blocks centered on class IV Chsp (the most abundant and widely distributed Chsp class) identified a putative cell wall metabolism gene cluster in members of the genus Aspergillus, the first such association reported for any fungal genome.     

Simulation of behavioral profiles in the plus-maze: A Classification and Regression Tree approach

This article introduces a simulation model of rat behavior in the elevated plus-maze, designed through a Decision trees approach using Classification and Regression algorithms. Starting from the analysis of the behavior performed by a sample of 18 Sprague-Dawley male rats, probabilistic rules describing behavioral patterns of the animals were extracted, and were used as the basis of the model computations. The model adequacy was tested by contrasting a simulated sample against an independent sample of real animals. Statistical tests showed that the simulated sample exhibits similar behaviors to those displayed by the real animals, both in terms of the number of entries to open and close arms as well as in terms of the time spent by the animals in those arms. However, the performance of the model in parameters related to the behavioral patterns was partially satisfactory. Given that previous attempts in the literature have neither include this kind of patterns nor the time as a crucial model parameter, the present model offers a suitable alternative for the computational simulation of this paradigm. Compared with antecedent models, the present simulation produced similar or better results in all the considered parameters. Beyond the goal of establish an appropriate simulational model, extracted rules also reveal important regularities associated to the rat behavior previously ignored by other models, i.e. that specific rat behaviors in the elevated plus-maze are time dependent. These and other important considerations to improve the model performance are discussed.     

基于聚类分析的广东省乡土阔叶树种分布研究

利用《中国植物志》、《广东植物志》等资料并结合实地野外踏查记录数据,获取了广东省1152个乡土阔叶树种的分布信息,在对其进行聚类分析的基础上采用多响应置换过程、指示种分析和Kruskal-Wallis检验,研究广东省乡土阔叶树种的分布特征。结果表明,乡土阔叶树种在广东省的分布具有较明显的纬度地带性,且可划分为3个分布区:Ⅰ区主要出现在广东省北部山区的中亚热带,树种丰富度的均值最大(376.5),缺萼枫香(Liquidambar acalycina)、椿叶花椒(Zanthoxylum ailanthoides)、伞花木(Eurycorymbus cavaleriei)等为主要指示种;Ⅱ区主要出现在广东省中部的南亚热带,树种丰富度的均值为339.8,肉桂(Cinnamomum cassia)、狭叶山黄麻(Trema angustifolia)、黄叶树(Xanthophyllum hainanense)等为主要指示种;Ⅲ区主要出现在广东省南部沿海的热带北缘,树种丰富度的均值最小(206.5),秋茄树(Kandelia candel)和山油柑(Acronychia pedunculata)等为主要指示种。