Subgroup Size Research Articles

The impact of predators and vegetation on shoaling in wild zebrafish.

In their natural habitats, animals experience multiple ecological factors and regulate their social responses accordingly. To unravel the impact of two ecological factors on the immediate behavioural response of groups, we conducted experiments on wild zebrafish shoals in arenas with vegetation, predator cues, and both factors simultaneously or neither (control treatments). Analysis of 297 trials revealed that while shoals formed significantly larger subgroups in the presence of predator cues, their subgroup size was comparable to control treatments when they faced predator cues and vegetation. Shoals were highly polarized in open arenas, in the absence of either ecological factors and in the presence of predator cues (with/without vegetation). The presence of vegetation alone, however, significantly reduced shoal polarization. Furthermore, food intake was significantly reduced when predator cues and/or vegetation were present. Tracking individuals revealed that (i) individuals within shoals receiving predator cues had a significantly higher probability to continue being in a group compared with control treatments and (ii) individuals occupying the front positions deviated less from their median position within a shoal as compared with other individuals regardless of predator cues. The adaptability of animals depends on behavioural responses to changing environments, making this study significant in the context of environmental changes.

Quality control for serological testing

ObjectivesThe quality control of serological assays remains controversial. The aim of this project was to describe the problems associated with a working model for controlling these assays and solutions, including using a source of well-defined targets and acceptable limits, a process to identify lot-to-lot reagent variation and an interpretation of the result that accounted for the clinical situation. False-negative results are problematic but can be reduced by identifying and comparing reagent lot variation with previous results. MethodsThe components of the Quality Assurance strategy are the following: Lot-to-lot reagent and calibrator variation assessment; dynamic, big-data approach to determine accurate targets and acceptable limits for manufacturer-provided QC material; negative QC monitoring process; use of commutable EQA with a sufficient method subgroup size to assess bias; clinical assessment of any statistically flagged error; and provision of support to the clinician for the interpretation of results. ResultsThe model described has been used for twelve months, and acceptable variation has been maintained. ConclusionsThe paper presents a solution that emphasizes the early detection of reagent lot variation and patient risk rather than instrument control.Reducing the risk of a false result to patients requires optimal assay quality control and an effective mechanism to support the clinician’s use of these results in diagnosis and monitoring. The problems of serological assays are well-known, but there remain few integrated solutions in the literature.

Evolutionary Niche Artificial Fish Swarm Algorithm for Dynamic Subgroup Size Adjustment in Robot Swarms

Evolutionary Niche Artificial Fish Swarm Algorithm for Dynamic Subgroup Size Adjustment in Robot Swarms

Testing for marginal covariate effect when the subgroup size induced by the covariate is informative.

In many cluster-correlated data analyses, informative cluster size poses a challenge that can potentially introduce bias in statistical analyses. Different methodologies have been introduced in statistical literature to address this bias. In this study, we consider a complex form of informativeness where the number of observations corresponding to latent levels of a unit-level continuous covariate within a cluster is associated with the response variable. This type of informativeness has not been explored in prior research. We present a novel test statistic designed to evaluate the effect of the continuous covariate while accounting for the presence of informativeness. The covariate induces a continuum of latent subgroups within the clusters, and our test statistic is formulated by aggregating values from an established statistic that accounts for informative subgroup sizes when comparing group-specific marginal distributions. Through carefully designed simulations, we compare our test with four traditional methods commonly employed in the analysis of cluster-correlated data. Only our test maintains the size across all data-generating scenarios with informativeness. We illustrate the proposed method to test for marginal associations in periodontal data with this distinctive form of informativeness.

A large-scale multi-attribute group decision-making method with R-numbers and its application to hydrogen fuel cell logistics path selection

The large-scale multi-attribute group decision-making (LSMAGDM) problem has become a hot research topic in the field of decision science. An R-numbers large-scale multi-attribute group decision-making (R-LSMAGDM) model is proposed to be constructed in this paper based on the advantages of R-numbers in capturing risks. First, the most commonly used clustering method, k-means, is introduced to determine the sub-groups. Then, a new sub-group weighting determination model is constructed by considering sub-group size and sub-group entropy. Next, we also build an optimized consensus-reaching model by improving the calculation method of the mean value. Then, the R-numbers weighted Hamy mean (RNWHM) operator is proposed to aggregate the sub-group information. In addition, the logarithmic percentage change-driven objective weighting (LOPCOW) method and the compromise ranking of alternatives from distance to ideal solution (CRADIS) method are used for attribute weighting calculation and alternative ranking, respectively. Finally, the effectiveness of the model is verified by an application example of hydrogen fuel cell logistics path selection.

Finding the best subgroup with differential treatment effect with multiple outcomes.

Precision medicine aims to identify specific patient subgroups that may benefit the most from a particular treatment than the whole population. Existing definitions for the best subgroup in subgroup analysis are based on a single outcome and do not consider multiple outcomes; specifically, outcomes of different types. In this article, we introduce a definition for the best subgroup under a multiple-outcome setting with continuous, binary, and censored time-to-event outcomes. Our definition provides a trade-off between the subgroup size and the conditional average treatment effects (CATE) in the subgroup with respect to each of the outcomes while taking the relative contribution of the outcomes into account. We conduct simulations to illustrate the proposed definition. By examining the outcomes of urinary tract infection and renal scarring in the RIVUR clinical trial, we identify a subgroup of children that would benefit the most from long-term antimicrobial prophylaxis.

Abstract CT255: AdvanTIG-204: A phase 2, multicenter, randomized, 3-arm, open-label study investigating the preliminary efficacy and safety of ociperlimab (anti-TIGIT) + tislelizumab (anti-PD-1) + concurrent chemoradiotherapy (cCRT) in patients with untreated limited-stage small cell lung cancer (SCLC)

Abstract Background: Despite a high response rate to cCRT, patients with limited-stage SCLC generally experience recurrence of disease after a few months and survival remains poor. Immunotherapy has shown benefit in many tumor types, including SCLC. In preclinical and clinical studies of solid tumors, co-inhibition of T-cell immunoreceptor with immunoglobulin and immunoreceptor tyrosine-based inhibitor motif domains (TIGIT) and PD-1 enhanced antitumor activity of anti-PD-1. AdvanTIG-204 (NCT04952597) investigated the efficacy and safety of ociperlimab + tislelizumab + cCRT in patients with untreated limited-stage SCLC. Methods: Patients with limited-stage SCLC and no prior systemic therapy were randomized 1:1:1 to Arm A (ociperlimab [900 mg IV Q3W] + tislelizumab [200 mg IV Q3W] + cCRT for 4 cycles, then ociperlimab + tislelizumab), Arm B (tislelizumab + cCRT for 4 cycles, then tislelizumab), or Arm C (cCRT for 4 cycles). Study drugs (Arms A and B) were continued for up to 12 months or until progression, unacceptable toxicity, or withdrawal. Primary endpoint: investigator-assessed PFS per RECIST v1.1. Secondary analyses included additional efficacy and safety endpoints in the ITT population, and efficacy in patient subgroups by PD-L1 and TIGIT expression (both <1% vs ≥1%), using tumor area positivity (PD-L1) and immune cell scoring (TIGIT). No hypothesis testing was predefined (p-value for descriptive purposes only). Descriptive comparisons were conducted for Arm A vs C, B vs C, and A vs B. Results: As of July 26, 2023, 126 patients (median age, 61.5 years) were randomized to Arm A (n=41), Arm B (n=42), or Arm C (n=43). Median follow-up: ~18 months (all arms). There was a trend of improvement in median PFS in Arm A (12.6 months) and Arm B (13.2 months) vs Arm C (9.5 months); HR (95% CI): Arm A vs C, 0.84 (0.46-1.52; p=0.2793); Arm B vs C, 0.80 (0.45-1.44; p=0.2414). ORR was 85.4% (3 CR) in Arm A, 88.1% (4 CR) in Arm B, and 76.7% (1 CR) in Arm C. Median DoR was 10.1 months in Arm A, 11.5 months in Arm B, and 8.2 months in Arm C. Median OS was not reached in any arm. Analyses showed that PD-L1 or TIGIT expression did not correlate with efficacy, however, small subgroup size limits interpretability. All patients experienced ≥1 treatment-related adverse event (TRAE); rates of grade ≥3 TRAEs were 73.2%, 78.6% and, 65.1% in Arms A, B, and C, respectively. The most common TRAEs included anemia (80.5% in Arm A vs 83.3% in Arm B vs 81.4% in Arm C), nausea (80.5% vs 76.2% vs 65.1%), and WBC count decreased (78.0% vs 76.2% vs 62.8%). Rates of TRAEs leading to any treatment discontinuation were 26.8%, 21.4%, and 4.7% in Arms A, B, and C, respectively. One patient in each arm experienced a TRAE leading to death. Conclusion: In patients with untreated limited-stage SCLC, tislelizumab + cCRT yielded a trend of improvement in PFS and ORR vs cCRT; addition of ociperlimab did not show detectable improvement. The overall safety profile of the treatments was tolerable, manageable, and generally consistent with the known risks of ociperlimab, tislelizumab, and cCRT. Citation Format: Youling Gong, Qingsong Pang, Rong Yu, Zhengfei Zhu, Jiangqiong Huang, Yufeng Cheng, Diansheng Zhong, Hongbo Wu, Seung Soo Yoo, Tracy Dobbs, Zinan Bao, Yunxia Zuo, Boxian Wei, Pu Sun, You Lu. AdvanTIG-204: A phase 2, multicenter, randomized, 3-arm, open-label study investigating the preliminary efficacy and safety of ociperlimab (anti-TIGIT) + tislelizumab (anti-PD-1) + concurrent chemoradiotherapy (cCRT) in patients with untreated limited-stage small cell lung cancer (SCLC) [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 2 (Late-Breaking, Clinical Trial, and Invited Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(7_Suppl):Abstract nr CT255.

Two-stage consensus reaching process in social network large group decision-making with application to battery supplier selection

Trust relationships play an important role in social network large group decision making (SN-LGDM). Extant studies overlook the self-adjustment stage of decision makers (DMs) and the binding force of subgroup on preference adjustment in consensus reaching process (CRP). This article proposes a new two-stage CRP for SN-LGDM considering self-adjustment and binding force of subgroup. A new trust propagation approach is presented based on individual trust level. An improved grey clustering algorithm is devised based on the fusion of preference similarity and trust relationship. The preference stability and the awareness of big picture are defined to determine the weights of DMs. The subgroup size, cohesion and influence are integrated to determine the weights of subgroups comprehensively. For the new two-stage CRP, the first stage is self-adjustment stage. DMs may proactively choose to adjust the preference or update the trust relationship according to the degree of matching between the trust relationship and preference difference. In the second stage, four scenarios are identified and the corresponding adjustment strategies are given considering the intention of DM to modify and the binding force of subgroup, which makes the consensus more consistent with reality. A battery supplier selection case is offered to illustrate the proposed method.

Let's not use it! A dynamic no-use zone between the home ranges of two spider monkey groups.

It is common that neighboring groups of the same species use some of the same areas, resulting in home-range overlap. Areas between the home ranges of neighboring groups not used by either group (no-use zone or NUZ) are rarely reported. Here, we report the existence of a NUZ between the home ranges of two Geoffroy's spider monkey groups, and examine its spatial changes over time and the ecological and behavioral underpinnings of such phenomenon. Although its size and location changed between 2017 and 2022, the NUZ was always present. We did not find any differences in the vegetation structure and composition between the NUZ and the ranging areas and in the monkeys' activity patterns between areas adjacent to the NUZ and the other parts of the ranging areas. The number of monkey vocalizations was lower and subgroup size was smaller (although the number of males did not differ) in areas adjacent to the NUZ than in the other parts of the ranging areas. Both changes possibly reflect the tendency to conceal their presence to the neighboring group. Our findings contribute to the understanding of primate space use and highlight the need to focus on the areas delimiting home ranges.

Effect of ecological and anthropogenic factors on grouping patterns in African lions across Kenya.

Social carnivores frequently live in fission-fusion societies, where individuals that share a common territory or home range may be found alone, in subgroups, or altogether. Absolute group size and subgroup size is expected to vary according to resource distribution, but for species that are susceptible to anthropogenic pressures, other factors may be important drivers. African lions (Panthera leo) are the only truly social felid and lion prides are characterized by fission-fusion dynamics with social groups frequently splitting and reforming, and subgroup membership can change continuously and frequently. The number of individuals in a group can be reflective of social, ecological, and anthropogenic conditions. This dynamic behavior makes understanding lion grouping patterns crucial for tailoring conservation measures. The evolution of group living in lions has been the topic of numerous studies, and we drew on these to formulate hypotheses relating to group size and subgroup size variation. Based on data collected from 199 lion groups across eight sites in Kenya, we found that group sizes were smaller when lions were closer to human settlements, suggesting that edge effects are impacting lions at a national scale. Smaller groups were also more likely when they were far from water, and were associated with very low and very high levels of non-tree vegetation. We found significant differences between the study sites, with the Maasai Mara having the largest groups (mean ± SD = 7.7 ± 4.7, range = 1-19), and Amboseli conservation area the smallest (4.3 ± 3.5, range = 1-14). While long-term studies within a single site are well suited to thoroughly differentiate between absolute group size and subgroup size, our study provides unique insight into the correlates of grouping patterns in a vulnerable species at a national scale.

Experimental study on the decision-making and motion behavior of subgroups when facing a static obstacle during movement

The interaction between pedestrians and obstacles is an interesting research topic in pedestrian and evacuation dynamics. Many studies on this topic have treated single individuals or human crowds as objects and have drawn a lot of research findings. However, as an intermediate layer linking the individual and group levels, subgroups have rarely been considered in such studies, and little is known about their behavioral mechanisms when interacting with obstacles. From this, we want to understand how certain key factors affect the decision-making and motion behavior of subgroups when facing a static obstacle during movement. Here, we organize a series of controlled experiments, in which the obstacle width, time pressure, and subgroup size serve as three control variables to create various experimental conditions. The analysis of the experimental data shows that a wider obstacle width, a more urgent time pressure, and a larger subgroup size correspond to a higher proportion of the splitting–merging state. The strong right-side preference emerges in the maintaining state, but the movement preference in the splitting–merging state largely depends on the difference in subgroup sizes. The path lengths in the splitting–merging state are longer than those in the maintaining state, but no significant difference exists in movement times between the two movement states. The conclusion that the average speeds decrease with increasing subgroup size at normal densities can be extended to most conditions of different obstacle widths, time pressures, and movement states. Besides, the three control variables have various influence degrees on centroid positions, movement times, and average speeds in the splitting and merging processes, and the herding effect of subgroup members can be observed in the merging process. Overall, these findings may advance the understanding of subgroup behaviors and support the development of subgroup models.

509. A Comparison of Tocilizumab and Baricitinib for Hospitalized Patients with Severe COVID-19

Abstract Background Baricitinib (BARI) and tocilizumab (TOCI) are two FDA-approved immunomodulating agents for the treatment of COVID-19 patients with worsening respiratory status, but early studies suggest no differences in outcomes between the two therapies. Methods This is a single-center retrospective analysis of adult patients who received TOCI or BARI for severe COVID-19 from April 2021 to February 2022. Severe COVID-19 was defined as having a National Institute of Allergy and Infectious Disease (NIAID) Ordinal Scale (OS) score of 6 or 7 as described in the Table I. The primary outcome was days to clinical improvement defined as a reduction by ≥ 2 scores on the NIAID OS after the first dose of TOCI or BARI (Day 1) and analyzed using a stratified log-rank test with stratification by the Day 1 NIAID OS score of 6 or 7. Patients who did not show clinical improvement were removed from this analysis. Secondary outcomes include hospital and intensive care unit (ICU) length-of-stay (LOS) and adverse events (AE). Categorical variables were analyzed using Chi-square or Fisher’s exact test, and continuous variables were analyzed using Student’s t-test or Mann-Whitney U test as appropriate. Results A total of 258 patients met inclusion criteria (121 BARI; 137 TOCI). Of patients receiving NIV/HFO (n=224) or MV/ECMO (n=34) at baseline, 33.9% and 71% of patients did not show clinical improvement, respectively. The time to clinical improvement did not differ significantly between BARI and TOCI in patients with baseline NIV/HFO (11.9 vs. 12.6 days respectively; p=0.79). A significant difference in days to clinical improvement was observed in MV/ECMO patients who received BARI or TOCI (7.0 vs. 25.7 days respectively; p=0.04). Hospital LOS, ICU LOS, and AE were similar between groups. Mortality rates were higher in patients who had MV/ECMO at baseline compared to those who received NIV/HFO (50% vs 20.1%, p >0.05), but there were no significant differences in mortality between treatment groups. Conclusion Days to clinical improvement did not differ between TOCI and BARI. A significant difference in days to clinical improvement was observed in the MV/ECMO group. However, application of this finding to clinical practice in patients with MV/ECMO is limited due to a small subgroup size and low rates of survival. Disclosures All Authors: No reported disclosures

Vigilance has mainly a social function in a wild group of spider monkeys (Ateles geoffroyi).

Vigilance is a widespread behavior that allows individuals to socially acquire information and/or effectively detect potential risks posed by predators and conspecifics. In this study, we aimed to investigate how social factors (i.e., subgroup size, number of males and immatures in the subgroup, presence of fission and fusion events, subgroup activity), individual characteristics (i.e., sex, presence of dependent offspring) and possible vulnerability to predation (i.e., being in smaller subgroups or lower in the canopy) explain variation in vigilance behavior in a wild group of spider monkeys (Ateles geoffroyi). We collected vigilance data during focal samples of all adults, subadults and juveniles of the group (N = 38), and ran generalized linear mixed models with a Bayesian approach. We found that the proportion of time both sexes spent in vigilance increased with subgroup size and during fusion events. Individuals also spent more time in vigilance when the subgroup was resting or socializing compared to other activities. Moreover, the proportion of time spent in vigilance increased in subgroups with more immatures. An alternative model with similar fit suggested that the proportion of time spent in vigilance increased in females when subgroups included more adult and subadult males. Overall, these results suggest that our study group mainly directed vigilance toward conspecifics (i.e., social vigilance), probably as a result of the relatively low predation pressure experienced, and contribute to the understanding of the multiple social factors affecting vigilance in group-living primates.

Inference on tree-structured subgroups with subgroup size and subgroup effect relationship in clinical trials.

When multiple candidate subgroups are considered in clinical trials, we often need to make statistical inference on the subgroups simultaneously. Classical multiple testing procedures might not lead to an interpretable and efficient inference on the subgroups as they often fail to take subgroup size and subgroup effect relationship into account. In this paper, built on the selective traversed accumulation rules (STAR), we propose a data-adaptive and interactive multiple testing procedure for subgroups which can take subgroup size and subgroup effect relationship into account under prespecified tree structure. The proposed method is easy-to-implement and can lead to a more interpretable and efficient inference on prespecified tree-structured subgroups. Possible accommodations to post hoc identified tree-structure subgroups are also discussed in the paper. We demonstrate the merit of our proposed method by re-analyzing the panitumumab trial with the proposed method.

Analyzing a designed experiment with a dispersion response and many replicates per condition

AbstractMost designed experiments (DOEs) seek to shift a mean response, but a few aim to minimize the dispersion of a response, using the standard deviation (STD) of replicates at each condition. Obtaining sufficient statistical power is often a challenge; dozens of replicates may well be needed to detect a substantial reduction in dispersion. For the problem which motivated this paper, many replicates were feasible, since the two‐level factorial DOE studied a highly automated gage for measuring the axial strength of a mass‐produced metal object. After 30 replicates per condition had been collected, the question arose whether to calculate one dispersion estimate per condition (based on 30 raw data), two estimates per condition (15 raw data each), three estimates (10 each) etc.? A Monte Carlo simulation showed that the best arrangement of the raw data is often one that approximately balances the number of dispersion estimates and the dispersion subgroup size per each condition (e.g., five dispersion estimates of subgroup size 6) for all but the most severely skewed raw data distributions. The authors provide free access to a simulator which may be used by the reader to explore a variety of two‐level factorial DOEs, as needed. This enables experimenters in any subject domain to design such DOEs with sufficient power, while making best use of the raw data in the analysis.

EEG Monitoring in Critically Ill Children: Establishing High-Yield Subgroups.

Continuous EEG monitoring (CEEG) is increasingly used to identify electrographic seizures (ES) in critically ill children, but it is resource intense. We aimed to assess how patient stratification by known ES risk factors would impact CEEG utilization. This was a prospective observational study of critically ill children with encephalopathy who underwent CEEG. We calculated the average CEEG duration required to identify a patient with ES for the full cohort and subgroups stratified by known ES risk factors. ES occurred in 345 of 1,399 patients (25%). For the full cohort, an average of 90 hours of CEEG would be required to identify 90% of patients with ES. If subgroups of patients were stratified by age, clinically evident seizures before CEEG initiation, and early EEG risk factors, then 20 to 1,046 hours of CEEG would be required to identify a patient with ES. Patients with clinically evident seizures before CEEG initiation and EEG risk factors present in the initial hour of CEEG required only 20 (<1 year) or 22 (≥1 year) hours of CEEG to identify a patient with ES. Conversely, patients with no clinically evident seizures before CEEG initiation and no EEG risk factors in the initial hour of CEEG required 405 (<1 year) or 1,046 (≥1 year) hours of CEEG to identify a patient with ES. Patients with clinically evident seizures before CEEG initiation or EEG risk factors in the initial hour of CEEG required 29 to 120 hours of CEEG to identify a patient with ES. Stratifying patients by clinical and EEG risk factors could identify high- and low-yield subgroups for CEEG by considering ES incidence, the duration of CEEG required to identify ES, and subgroup size. This approach may be critical for optimizing CEEG resource allocation.

Evaluating the performance of variable sampling interval Hotelling T2 charting scheme for compositional data in the presence of measurement error

AbstractThe variable sampling interval (VSI) scheme is a well‐known technique for improving the detection ability of control charts (CCs). In the proposed study, measurement error (ME) has been applied to investigate the effectiveness of the Hotelling T2 charting scheme for compositional data (CoDa) using VSI. The current study considered the case of the monitoring phase, assuming that process parameters are known using the continuous times Markov chain model. The evaluation of the proposed scheme has been done using the average time to signal. The authors studied the impact of MEs on the performance of the Hotelling T2 CC for CoDa using VSI, and additionally, the authors also examined the impact of linearly covariate error model parameters on the performance of Hotelling T2 VSI CoDa CC. Six cases for the variance–covariance matrix were used to study the impact of different involved parameters. The effect of ME, sampling interval (SI), powering operator (b), error variance (, and subgroup size (m) has been studied on the performance of proposed CCs by increasing the value of one parameter while keeping the other parameters fixed. The ME and σ have a negative impact on the performance of the proposed CC, while SI, b and m have a positive impact on the performance of the proposed CC. Among all the six cases, the correlated cases (negatively and positively) with equal variance performed better than all the other four cases. In the end, an illustrative example of muesli production with part CoDa (where p is the number of variables in CoDa vector) is provided for the practical implementation of the Hotelling T2 VSI CoDa CC in the presence of ME.

Investigating zero-state and steady-state performance of MEWMA-CoDa control chart using variable sampling interval

ABSTRACT Traditional process monitoring control charts (CCs) focused on sampling methods using fixed sampling intervals ( FSI s). The variable sampling intervals ( VSI s) scheme is receiving increasing attention, in which the sampling interval ( SI ) length varies according to the process monitoring statistics. A shorter SI is considered when the process quality indicates the possibility of an out-of-control (OOC) situation; otherwise, a longer SI is preferred. The VSI multivariate exponentially moving average for compositional data ( VSI - MEWMA CoDa ) CC based on a coordinate representation using isometric log-ratio ( ilr ) transformation is proposed in this study. A methodology is proposed to obtain the optimal parameters by considering the zero-state ( ZS ) average time to signal ( ZATS ) and the steady-state (SS) average time to signal ( SATS ). The statistical performance of the proposed CC is evaluated based on a continuous-time Markov chain ( CTMC ) method for both cases, the ZS and the SS using a fixed value of in-control (IC) ATS 0 . Simulation results demonstrate that the VSI - MEWMA CoDa CC has significantly decreased the OOC average time to signal ( ATS ) than the FSI MEWMA CoDa CC. Moreover, it is found that the number of variables (d) has a negative impact on the ATS of the VSI - MEWMA CoDa CC, and the subgroup size (n) has a mildly positive impact on the ATS of the VSI - MEWMA CoDa CC. At the same time, the SATS of the VSI - MEWMA CoDa CC is less than the ZATS of the VSI - MEWMA CoDa CC for all the values of n and d. The proposed VSI - MEWMA CoDa CC under steady-State performs effectively compared to its competitors, such as the FSI - MEWMA CoDa CC, the VSI - T 2 CoDa CC and the FSI - T 2 CoDa CC. An example of an industrial problem from a plant in Europe is also given to study the statistical significance of the VSI - MEWMA CoDa CC.

Effect of Measurement Error on the Multivariate CUSUM Control Chart for燙ompositional Data

Control charts (CCs) are one of the main tools in Statistical Process Control that have been widely adopted in manufacturing sectors as an effective strategy for malfunction detection throughout the previous decades. Measurement errors (M.E’s) are involved in the quality characteristic of interest, which can effect the CC’s performance. The authors explored the impact of a linear model with additive covariate M.E on the multivariate cumulative sum (CUSUM) CC for a specific kind of data known as compositional data (CoDa). The average run length is used to assess the performance of the proposed chart. The results indicate that M.E’s significantly affects the multivariate CUSUM-CoDa CCs. The authors have used the Markov chain method to study the impact of different involved parameters using six different cases for the variance-covariance matrix (VCM) (i.e., uncorrelated with equal variances, uncorrelated with unequal variances, positively correlated with equal variances, positively correlated with unequal variances, negatively correlated with equal variances and negatively correlated with unequal variances). The authors concluded that the error VCM has a negative impact on the performance of the multivariate CUSUM-CoDa CC, as the increases with an increase in the value of the error VCM. The subgroup size m and powering operator b positively impact the proposed CC, as the decreases with an increase in m or b. The number of variables p also has a negative impact on the performance of the proposed CC, as the values of increase with an increase in p. For the implementation of the proposal, two illustrated examples have been reported for multivariate CUSUM-CoDa CCs in the presence of M.E’s. One deals with the manufacturing process of uncoated aspirin tablets, and the other is based on monitoring the machines involved in the muesli manufacturing process.

Quantitative Assessment of Hypovascular Component in Arterial Phase to Help the Discrimination of Combined Hepatocellular-Cholangiocarcinoma and Hepatocellular Carcinoma.

To explore the imaging performance for discrimination of combined hepatocellular- cholangiocarcinoma (cHCC-CCA) and hepatocellular carcinoma (HCC). In total, 35 patients with cHCC-CCA and a matched control group of HCC patients (n = 35) were included retrospectively. We quantitatively evaluated the hypovascular component in tumor and qualitatively assessed LI-RADS features and other aggressive features to develop model for cHCC-CCA diagnose. Subgroup analyses were performed by tumor size and LI-RADS category. cHCC-CCA frequently showed a larger proportion (≥50%) of hypovascular areas followed by HCC (P = 0.000). Among those patients with ≥50% hypovascular areas, 8 patients did not present rim enhancement in atrial phase. The LI-RADS major features were more commonly observed in HCC (82.9-45.7%,), than cHCC-CCA (P = 0.003-0.022). The targetoid appearances and non-smooth margin frequently appeared in cHCC-CCA (34.3-63.9%), compared with HCC (P = 0.000-0.023). We developed a radiologic model based on ≥50% hypovascular component and delayed enhancement, which presented AUC of 0.821, accuracy of 80%. We also obtained good performance by radiologic model in LR-M group and tumor size <50mm group (AUC: 0.841 and 0.866, respectively). Combined group which included CA 19-9 and ≥50% hypovascular component and delayed enhancement did not improve the distinction performance between cHCC-CCA and HCC, which presented good performance of identifying cHCC-CCA in the LR-4/5 subgroup and tumor size ≥50 mm subgroup (AUC: 0.717, 0.730, respectively). cHCC-CCA group presented heterogeneous dominant pathology involving 15 of HCC, 7 of intrahepatic cholangiocarcinoma (iCCA) or cholangiolocellular carcinoma (CLC), 13 of intermediate cells component. Macrotrabecular appearances were higher in cHCC-CCA than that in HCC. The proportion of Hepa-1 was significantly higher in true negative (TN) patients (29 [93.5%]) and false negative (FN) patients (10 [100%]) than in true positive (TP) patients (16 [64%]; P = 0.036). Quantitative assessment of hypovascular component could help the discrimination of cHCC-CCA. Macrotrabecular appearances were more exhibited in cHCC-CCA than that in HCC.