Bayesian hierarchical classification and information sharing for clinical trials with subgroups and binary outcomes

Bayesian hierarchical models have been applied in clinical trials to allow for information sharing across subgroups. Traditional Bayesian hierarchical models do not have subgroup classifications; thus, information is shared across all subgroups. When the difference between subgroups is large, it suggests that the subgroups belong to different clusters. In that case, placing all subgroups in one pool and borrowing information across all subgroups can result in substantial bias for the subgroups with strong borrowing, or a lack of efficiency gain with weak borrowing. To resolve this difficulty, we propose a hierarchical Bayesian classification and information sharing (BaCIS) model for the design of multigroup phase II clinical trials with binary outcomes. We introduce subgroup classification into the hierarchical model. Subgroups are classified into two clusters on the basis of their outcomes mimicking the hypothesis testing framework. Subsequently, information sharing takes place within subgroups in the same cluster, rather than across all subgroups. This method can be applied to the design and analysis of multigroup clinical trials with binary outcomes. Compared to the traditional hierarchical models, better operating characteristics are obtained with the BaCIS model under various scenarios.     

Efficient statistical inference procedures for partially nonlinear models and their applications

Summary .   Motivated by an analysis of a real data set in ecology, we consider a class of partially nonlinear models where both a nonparametric component and a parametric component are present. We develop two new estimation procedures to estimate the parameters in the parametric component. Consistency and asymptotic normality of the resulting estimators are established. We further propose an estimation procedure and a generalized F -test procedure for the nonparametric component in the partially nonlinear models. Asymptotic properties of the newly proposed estimation procedure and the test statistic are derived. Finite sample performance of the proposed inference procedures are assessed by Monte Carlo simulation studies. An application in ecology is used to illustrate the proposed methods.     

Airborne hyperspectral imaging for estimating acorn yield based on the PLS B-matrix calibration technique

Alternate bearing of acorn is a well-marked yield variability phenomenon in forest production. In Japan, this phenomenon is also related to wildlife management (e.g. of animals such as wild pigs, that rely on acorn as their major feed source). Effective management of animals dependent on acorn will require accurate estimation of acorn yield at an early stage. In this paper, we proposed a way to estimate acorn yield from the canopy reflectance values of individual trees. Using an Airborne Imaging Spectrometer for Application (AISA) Eagle System, hyperspectral images in 72 visible and near-infrared wavelengths (407–898 nm) were acquired over an acorn forest in Japan 10 times over three consecutive years (2003–2005) during the early acorn growing season. The canopy spectral reflectance values for individual trees at each wavelength were extracted from the images, and important wavelengths were determined as estimating factors by the B-matrix technique based on partial least squares (PLS) analysis. Yield-estimating models were then developed by multiple linear regression (MLR). Three models obtained from images acquired on June 27 in 2003, July 13 in 2004 and June 21 in 2005 estimated acorn yield well in comparison with ground truth, indicating that the procedure has considerable potential. The study also demonstrated the B-matrix technique based on PLS analysis to be reliable and efficient in identifying important wavelengths for determining suitable estimating factors that best contribute to the estimation model.     

喷雾方式及喷液量对吡蚜酮和啶虫脒在棉田的沉积分布及棉蚜防治效果的影响

为探明防治棉田棉蚜Aphis gossypii (Glover)的最佳喷雾方式及喷液量, 提高棉田的农药利用率, 作者于2011-2012年在山东省棉花苗期和成株期分别使用背负式手动喷雾器和背负式机动弥雾机以常规大容量和低容量喷雾, 比较杀虫剂25%吡蚜酮可湿性粉剂和3%啶虫脒乳油的喷雾雾滴在棉花田的沉积分布及棉蚜防治效果。结果表明： 在棉花苗期, 3%啶虫脒乳油用量450 mL/ha时, 使用机动弥雾机以75, 150和225 L/ha喷液量喷雾, 药剂在地面的流失率分别为24.4%, 28.9%和26.7%; 使用手动喷雾器以300, 450和600 L/ha喷液量喷雾, 杀虫剂在地面的流失率分别为35.6%, 37.8%和46.7%; 啶虫脒不同喷雾处理对棉蚜的防效无显著性差异（P>0.05）。在棉花成株期, 25%吡蚜酮可湿性粉剂用量为300 g/ha时, 使用手动喷雾器以600 L/ha喷液量喷雾, 药剂地面流失率为13.3%; 使用机动弥雾机以喷液量150 L/ha喷雾时, 药剂地面流失率为3.3%; 25%吡蚜酮可湿性粉剂用量减少至225 g/ha, 使用机动弥雾机以喷液量150和300 L/ha喷雾, 对棉蚜的防效与吡蚜酮用量300 g/ha、 使用手动喷雾器在喷液量600 L/ha条件下喷雾相比没有显著差异（P>0.05）。使用机动弥雾机喷雾可以减少田间用药量和喷液量, 降低药液的流失率, 减轻对环境的污染。     

食块茎水鸟及水位对沙湖沉水植物冬芽分布的影响

分别于2012—2013、2013—2014年度越冬期候鸟越冬前(10月份)与越冬后(4月份)采用样方法调查沙湖沉水植物冬芽的种类、密度及生物量,分析不同水位条件的2个年度鄱阳湖碟形子湖沉水植物冬芽的分布及其对食块茎水鸟食物贡献的差异性,探讨越冬水鸟取食与水位变化对沉水植物冬芽分布的影响。结果表明:刺苦草(Vallisneria spinulosa)和罗氏轮叶黑藻(Hydrilla verticillata var.rosburghii)2种沉水植物的冬芽同域分布。2013年10月2种植物冬芽的密度与生物量均显著低于2012年同期,主要原因是鄱阳湖水位年际间变化剧烈,并对水质有显著影响:与2012年相比,2013年丰水期(4—9月)沙湖与主湖区连通的时间和日平均水深显著减小,但水体浊度显著增加,不利于沉水植物生长发育。2012—2013年度越冬水鸟迁出后2种冬芽的密度和生物量均明显下降,而2013—2014年度越冬期水鸟迁出后与迁入前相比两种植物冬芽的密度和生物量均无显著变化,很可能与食块茎水鸟的取食活动和高水位对食物可利用性的负面影响有密切关系。湖泊剧烈的水位变化导致越冬水鸟的食源具有年际波动的特征,而食块茎水鸟对鄱阳湖子湖的食物利用率受越冬季冬芽丰富度和食物可及性(accessibility)的共同影响。研究结果对鄱阳湖乃至长江中下游流域沉水植被恢复、越冬水鸟保护以及生态系统功能评估具有指导意义。     

An exploration of fixed and random effects selection for longitudinal binary outcomes in the presence of nonignorable dropout

We explore a Bayesian approach to selection of variables that represent fixed and random effects in modeling of longitudinal binary outcomes with missing data caused by dropouts. We show via analytic results for a simple example that nonignorable missing data lead to biased parameter estimates. This bias results in selection of wrong effects asymptotically, which we can confirm via simulations for more complex settings. By jointly modeling the longitudinal binary data with the dropout process that possibly leads to nonignorable missing data, we are able to correct the bias in estimation and selection. Mixture priors with a point mass at zero are used to facilitate variable selection. We illustrate the proposed approach using a clinical trial for acute ischemic stroke.     

Modulation of dragon's blood on tetrodotoxin-resistant sodium currents in dorsal root ganglion neurons and identification of its material basis for efficacy

To clarify the modulation of dragon's blood on the tetrodotoxin-resistant (TTX-R) sodium currents in dorsal root ganglion (DRG) neurons and explore its corresponding material basis for the efficacy, using whole-cell patch clamp technique, the effects of dragon's blood and the combined effects of three components (cochinchinenin A, cochinchinenin B, and loureirin B) extracted from dragon's blood on the TTX-R sodium currents in acute-isolated DRG neurons of rats were observed. According to the operational definition of material basis for the efficacy of TCM established, the material basis of the modulation on the TTX-R sodium currents in DRG neurons of dragon's blood was judged from the experimental results. The drug interaction equation of Greco et al. was used to assess the interaction of the three components extracted from dragon's blood. This investigation demonstrated that dragon's blood suppressed the peak TTX-R sodium currents in a dose-dependent way and affected the activations of TTX-R sodium currents. The effects of the combination of cochinchinenin A, cochinchinenin B, and loureirin B were in good agreement with those of dragon's blood. Although the three components used alone could modulate TTX-R sodium currents, the concentrations of the three components used alone were respectively higher than those used in combination when the inhibition rates on the TTX-R sodium currents of them used alone and in combination were the same. The combined effects of the three components were synergistic. These results suggested that the interference with pain messages caused by the modulation of dragon's blood on TTX-R sodium currents in DRG neurons may explain some of the analgesic effect of dragon's blood and the corresponding material basis for the efficacy is the combination of cochinchinenin A, cochinchinenin B, and loureirin B.     

Modulation of dragon’s blood on tetrodotoxin-resistant sodium currents in dorsal root ganglion neurons and identification of its material basis for efficacy

To clarify the modulation of dragon’s blood on the tetrodotoxin-resistant (TTX-R) sodium currents in dorsal root ganglion (DRG) neurons and explore its corresponding material basis for the efficacy, using whole-cell patch clamp technique, the effects of dragon’s blood and the combined effects of three components (cochinchinenin A, cochinchinenin B, and loureirin B) extracted from dragon’s blood on the TTX-R sodium currents in acute-isolated DRG neurons of rats were observed. According to the operational definition of material basis for the efficacy of TCM established, the material basis of the modulation on the TTX-R sodium currents in DRG neurons of dragon’s blood was judged from the experimental results. The drug interaction equation of Greco et al. was used to assess the interaction of the three components extracted from dragon’s blood. This investigation demonstrated that dragon’s blood suppressed the peak TTX-R sodium currents in a dose-dependent way and affected the activations of TTX-R sodium currents. The effects of the combination of cochinchinenin A, cochinchinenin B, and loureirin B were in good agreement with those of dragon’s blood. Although the three components used alone could modulate TTX-R sodium currents, the concentrations of the three components used alone were respectively higher than those used in combination when the inhibition rates on the TTX-R sodium currents of them used alone and in combination were the same. The combined effects of the three components were synergistic. These results suggested that the interference with pain messages caused by the modulation of dragon’s blood on TTX-R sodium currents in DRG neurons may explain some of the analgesic effect of dragon’s blood and the corresponding material basis for the efficacy is the combination of cochinchinenin A, cochinchinenin B, and loureirin B.     

Epidemiological evaluations of the efficacy of slow-released praziquantel-medicated bars for dogs in the prevention and control of cystic echinococcosis in man and animals

To assess the epidemiological efficacy of type SRP III slow-released praziquantel-medicated bars for dogs in the prevention and control of cystic echinococcosis in man and livestock, praziquantel-medicated bars were implanted subcutaneously in over 90% of dogs in villages in north Xinjiang, China, where cystic echinococcosis is highly endemic. After implantation, infection rate of Echinococcus granulosus in dogs, specific antibodies in children and prevalence of echinococcosis in one-year-old lambs were observed for 3 years. Coproantigen of E. granulosus was positive in 41.2% of the dogs at the start of experiment. In the second and third year after medicated-bar implantation, coproantigen was undetectable in any dogs examined, while 3.0% of dogs were positive at the end of the fourth year. The antibody positive rate in 7-year-old pupils, that was 41.2% before the experiment, declined gradually and it was 5.4% in the fourth year, while children in the non-intervention control area showed 30.6% seropositivity. The prevalence of hydatid disease in children aged 7–16 years also declined significantly. The prevalence of hydatidosis in lambs one year of age was 44.8% in the first year, dropping to 10.7% in the fourth year, while in the non-intervention control area the level of infection was 46.4%. These results demonstrated not only that the slow released praziquantel-medicated bars efficiently blocked reinfection in dogs at least for 2 years, but also the measure was effective in preventing transmission of cystic echinococcosis to both man and livestock.     

奇异数据筛选法在玉米籽粒蛋白质近红外光谱检测中的应用

相对于传统生化测定方法,基于近红外光谱(Near infrared spectroscopy,NIRS)玉米籽粒蛋白质含量检测是一种快速、非破坏、且适用于多组分同时检测的新方法。但在建模过程中,由于奇异数据(异常值)的存在会影响近红外光谱模型的预测精度和稳定性,我们采用奇异数据筛选法剔除了玉米籽粒近红外光谱中的奇异数据并建立了玉米籽粒蛋白质含量的偏最小二乘支持向量机(Least squares support vector machine,LS-SVM)模型。本文分别采用杠杆值法(Leverage)、半数重采样法(Resampling by Half-Mean,RHM)和蒙特卡洛采样法(Monte-Carlo Sampling,MCS)剔除了玉米籽粒蛋白质光谱数据中的奇异数据并对模型结果进行比较。在剔除奇异数据的基础上,采用偏最小二乘回归法(Partial least squares regression,PLSR)提取主成分,并基于小生境蚁群算法(Niche ant colony algorithm,NACA)优化偏最小二乘支持向量机(LS-SVM)模型参数(γ和σ2),建立基于LS-SVM的玉米籽粒蛋白质定量分析模型。结果表明,采用3种奇异数据筛选法剔除奇异数据后所建LS-SVM模型的预测结果都优于采用原光谱数据所建模型,相比较而言,蒙特卡洛采样法为基于近红外光谱检测玉米籽粒蛋白质的最佳奇异数据筛选法。     

UV protectants for the biopesticide based on Bacillus sphaericus Neide and their role in protecting the binary toxins from UV radiation

The UV protectant properties of 26 natural and synthetic compounds were investigated for a biopesticide based on an indigenously isolated strain (ISPC-8) of Bacillus sphaericus Neide. In initial screening, spores of ISPC-8 with 0.1% (w/w for solid and v/w for liquid materials) concentration of different compounds were exposed to UV-B radiation (4.9 × 10⁵ J/m²) for 6 h and their spore viability and larvicidal activity were studied. The larvicidal activity was evaluated against third-instar larvae of Culex quinquefasciatus Say. There was a complete loss of spore viability (1.4% viable spores) and partial reduction in larvicidal activity (57.7% of original activity) after exposure of spores to UV-B for 6 h. However, spore viability as well as larvicidal activity protected significantly when spores were mixed with different compounds before exposing them to UV-B. Among the different compounds tested benzaldehyde, congo red, para-aminobenzoic acid (PABA) and cinnamaldehyde were found to be promising in protecting the spores from UV-B radiation. The presence of binary toxins (41.9 kDa and 51.4 kDa) in protected and unprotected samples were examined by SDS–PAGE. The binary toxin bands disappeared in unprotected spores after 24 h of exposure to UV-B, whereas toxin bands were distinctly visible when spores with benzaldehyde and cinnamaldehyde were exposed to UV-B for 96 h and 120 h, respectively. Congo red and PABA were found to be most effective in protecting binary toxins even after 168 h of exposure to UV-B. Incorporation of these promising UV protectant compounds in biopesticides would help in protecting the spores from the adverse effects of UV radiation and prolong the persistence of biopesticides under field conditions.     

孟鲁司特联合舒利迭对哮喘急性发作期患者疗效及免疫功能的影响

目的探讨孟鲁司特联合舒利迭对哮喘急性发作期患者疗效及免疫功能的影响。方法 2012年1月至2014年1月选取在本院收治的120例哮喘急性发作期患者为研究对象,根据随机数字表将患者分为观察组及对照组各60例,对照组给予舒利迭雾化吸入治疗,50 mg/250 mg,2次/d,观察组在对照组基础上口服孟鲁司特,10 mg/次,1次/d,疗程为2周。对比分析两组患者治疗效果及治疗前后肺功能及免疫功能的变化。结果观察组总有效率为96.67%,对照组总有效率为76.67%,差异有统计学意义(P0.05)。观察组患者治疗后第1秒呼吸气体的容积(FEV1)、用力呼吸的肺活量(FVC)及FVC占预计值百分比(FVC%)改善优于对照组(P0.05)。观察组治疗后白细胞介素4(IL-4)、免疫球蛋白(Ig E)水平、IL-4/INF-γ显著低于对照组,而干扰素(IFN-γ)与对照组相比差异无统计学意义。结论孟鲁司特联合舒利迭能有效改善哮喘急性发作期患者肺功能及免疫功能,提高哮喘患者治疗效果。     

Comparative efficacy of Beauveria bassiana, Bacillus thuringiensis, and aldicarb for control of Colorado potato beetle in an irrigated desert agroecosystem and their effects on biodiversity

Five weekly applications of Beauveria bassiana (Balsamo) Vuillemin, a genetically engineered isolate of Bacillus thuringiensis Berliner (Raven^®), and aldicarb (Temik^®) were compared for control of Colorado potato beetle, Leptinotarsa decemlineata (Say) in an irrigated desert cropping system. B. thuringiensis was applied using low and high label rates (1.17 and 7.0 l ha^–1). B. bassiana was applied at 5×10¹³ spores ha^–1. Aldicarb (Rh^one-Poulenc), applied at 3.37 kg a.i. ha^–1 provided the greatest beetle control and potato yields (45 metric tons ha^–1), but overall lowest biodiversity in nontarget organisms, particularly predatory Heteroptera. Low and high rates of B. thuringiensis produced fair to excellent beetle control, yielded 33 and 40 metric tons ha^–1 and enabled good survival in predatory Heteroptera and other nontargets. Plots treated with B. bassiana resulted in poor control of beetles prior to row closure after which fair to good control was achieved. Yield in the Beauveria-treated plots was 33 metric tons ha^–1 and effect on biodiversity was comparable to the Bt-treated plots. The lowest number of overwintering adult L. decemlineata was found in the plots treated with bacteria and fungi (0.68–0.84 adults/0.03 m^–3 of soil) and the highest was found in control and aldicarb plots (3.44 and 1.84 adults/0.03 m³ of soil). Aphids and leafhoppers showed higher densities in plots treated with microbial control agents, but were eliminated from plots treated with aldicarb.     

Adaptive seamless clinical trials using early outcomes for treatment or subgroup selection: Methods,simulation model and their implementation in R

Adaptive seamless designs combine confirmatory testing, a domain of phase III trials, with features such as treatment or subgroup selection, typically associated with phase II trials. They promise to increase the efficiency of development programmes of new drugs, for example, in terms of sample size and/or development time. It is well acknowledged that adaptive designs are more involved from a logistical perspective and require more upfront planning, often in the form of extensive simulation studies, than conventional approaches. Here, we present a framework for adaptive treatment and subgroup selection using the same notation, which links the somewhat disparate literature on treatment selection on one side and on subgroup selection on the other. Furthermore, we introduce a flexible and efficient simulation model that serves both designs. As primary endpoints often take a long time to observe, interim analyses are frequently informed by early outcomes. Therefore, all methods presented accommodate interim analyses informed by either the primary outcome or an early outcome. The R package asd , previously developed to simulate designs with treatment selection, was extended to include subgroup selection (so-called adaptive enrichment designs). Here, we describe the functionality of the R package asd and use it to present some worked-up examples motivated by clinical trials in chronic obstructive pulmonary disease and oncology. The examples both illustrate various features of the R package and provide insights into the operating characteristics of adaptive seamless studies.     

Genetic markers on BTA14 predictive for residual feed intake in beef steers and their effects on carcass and meat quality traits

With the high cost of feed for animal production, genetic selection for animals that metabolize feed more efficiently could result in substantial cost savings for cattle producers. The purpose of this study was to identify DNA markers predictive for differences among cattle for traits associated with feed efficiency. Crossbred steers were fed a high‐corn diet for 140 days and average daily feed intake (ADFI), average daily gain (ADG), and residual feed intake (RFI) phenotypes were obtained. A region on chromosome 14 was previously associated with RFI in this population of animals. To develop markers with the highest utility for predicting an animal's genetic potential for RFI, we genotyped additional markers within this chromosomal region. These polymorphisms were genotyped on the same animals (n = 1066) and tested for association with ADFI, ADG and RFI. Six markers within this region were associated with RFI (P ≤ 0.05). After conservative correction for multiple testing, one marker at 25.09 Mb remained significant (P = 0.02) and is responsible for 3.6% of the RFI phenotypic variation in this population of animals. Several of these markers were also significant for ADG, although none were significant after correction. Marker alleles with positive effects on ADG corresponded to lower RFI, suggesting an effect increasing growth without increasing feed intake. All markers were also assessed for their effects on meat quality and carcass traits. All of the markers associated with RFI were associated with adjusted fat thickness (AFT, P ≤ 0.009) and three were also associated with hot carcass weight (HCW, P ≤ 0.003). Marker alleles associated with lower RFI were also associated with reduced AFT, and if they were associated for HCW, the effect was an increase in weight. These markers may be useful as prediction tools for animals that utilize feed more efficiently; however, validation with additional populations of cattle is required.     

Evaluating outcomes of restoration ecology projects on limited budgets: assessment of variation in sampling intensity and sampling frequency for four habitat types

While best practices for evaluating restoration ecology projects are emerging rapidly, budget constraints often limit postrestoration monitoring, which emphasizes the need for practical and efficient monitoring strategies. We examined the postrestoration outcome for an ENGO (Nature Conservancy of Canada) project, to assess retroactively how variation in intensity and frequency of sampling would have affected estimates of plant species composition, diversity, and richness over time. The project restored four habitat types (mesic forest, oak woodland, wet meadow, and sand barren) using sculptured seeding of tallgrass prairie and woody species. Species‐level plant cover was monitored annually for 10 years in 168 2 × 2–m quadrats. We performed randomization tests to examine estimates of species diversity and richness as a function of the number of quadrats sampled, and assessed the necessity of annual sampling for describing changes in species composition and successional trajectories. The randomization tests revealed that sampling 10–17 quadrats, depending on habitat type, was sufficient to obtain estimates of species diversity that were at least 95% of values obtained from the whole dataset. Species richness as a function of number of quadrats sampled did not plateau, which suggests that rather than increasing the number of sampling quadrats, richness could be estimated more efficiently using nonquadrat based sampling techniques. Nonmetric multidimensional scaling analysis revealed that plant species composition largely stabilized by 3–5 years postrestoration depending on habitat type. By that time, native, seeded species dominated the restoration, and the benefits of annual sampling for tracking changes in species composition diminished.