Pooling Approach Research Articles

Cross-sectional and Prospective Associations Between Sleep Health and Multimorbidity in Middle to Older-aged Adults: Results from the Canadian Longitudinal Study on Aging (CLSA)

ObjectiveMiddle-aged to older adults often exhibit the co-existence of poor sleep health and multimorbidity. We examined cross-sectional and prospective associations of pooled index of sleep health with prevalent and incident multimorbidity in the framework of an ongoing cohort study in Canada. MethodsData were from approximately 24,000 individuals from the Canadian Longitudinal Study on Aging (CLSA), an ongoing national study of community-dwelling adults aged 45 to 85 years at baseline. Multimorbidity was defined as two or more chronic conditions out of five major condition categories. Sleep variables included sleep duration, quality, initiation, maintenance, and excessive daytime sleepiness, which were combined into an index using pooled approaches. Weighted logistic regression models were computed for each index with additional age- and sex-stratified analyses. ResultsHigher sleep index scores, indicating poorer sleep health, were observed in females and younger age groups (ages 45-54 and 55-64). In cross-sectional analysis, the fully adjusted model showed that a 1-unit increase in pooled scores was significantly associated with 1.48 higher odds (95% CI = 1.38, 1.58; p<0.001) of prevalent multimorbidity at baseline. Similarly, the prospective analysis indicated significant changes in incident multimorbidity with pooled index scores in the fully adjusted model (OR = 1.33; 95% CI = 1.20, 1.48; p<0.001). ConclusionThe pooled sleep index introduced in this study may offer a novel, concise, and comprehensive approach to assessing sleep health among middle-aged and older adults. Those in these age groups experiencing poorer sleep health are at a greater risk of prevalent multimorbidity, as well as of developing multimorbidity over time.

A moment-based pooling approach in convolutional neural networks for breast cancer histopathology image classification

A moment-based pooling approach in convolutional neural networks for breast cancer histopathology image classification

Evaluating the current methodological practices and issues in existing literature in pooling complex surveys: a systematic review.

Pooling data from complex survey designs is increasingly used in the health and medical sciences. However, current methodological practices are not well documented in theliterature while performing the pooling strategy. We aimed to review related pooling studies and evaluate the quality of pooling within the framework of specific methodological guidelines, particularly when combining complex surveys such as Demographic & Health Surveys (DHS) and Multiple Indicator Cluster Surveys (MICS). We performed a systematic literature search focusing on studies utilizing the pooling method with DHS and MICS survey data. These studies were selected from those published between 2010 and 2021 and were retrieved from electronic databases (PubMed and Scopus) in accordance with pre-defined inclusion criteria. Then, we extracted355 studies for the final review and evaluated the reporting quality of the pooling strategy while considering some methodological issues. The majority of studies (81.4%) reported using a pooled (one-stage) approach, while 11.8% used a separate (two-stage) approach, and 6.8% used both approaches. Approximately 63.3% of studies did not clearly describe their pooling strategy. Only 3.4% of the studies mentioned the variable harmonization process, while 66.9% addressed dealing with heterogeneity between surveys. All studies that used the separate (two-stage) approach conducted a meta-analytic procedure, while 38.1% of studies using the pooled approach employed a multilevel model. More than half of the studies (55.6%) mentioned the use of clustered standard errors. The Delta method, Bootstrap, and Taylor linearization were each applied in 11.1% of the studies for variance estimation. Survey weights, primary sampling unit (PSU) or cluster, and strata were used together in 30.5% of the studies. Survey weights were employed by 69.8%, PSU or cluster by 43.8%, and the strata variable by 31.7%. Sensitivity analysis was conducted in 16% of the studies. Our study revealed that fundamental methodological issues associated with pooling complex survey databases, such as the selection of pooling procedures, data harmonization, accounting for cycle effects, quality control checks, addressing heterogeneity, selecting model effects, utilizing survey design variables, and dealing with missing values, etc., were inadequately reported in the included studies. We recommend authors, readers, reviewers, and editors examine pooling studies more attentively and utilize the customized checklist developed by our study to assess the quality of future pooling studies.

Exploring Dataset Bias and Scaling Techniques in Multi-Source Gait Biomechanics: An Explainable Machine Learning Approach

Machine learning has become increasingly important in biomechanics. It allows to unveil hidden patterns from large and complex data, which leads to a more comprehensive understanding of biomechanical processes and deeper insights into human movement. However, machine learning models are often trained on a single dataset with a limited number of participants, which negatively affects their robustness and generalizability. Combining data from multiple existing sources provides an opportunity to overcome these limitations without spending more time on recruiting participants and recording new data. It is furthermore an opportunity for researchers who lack the financial requirements or laboratory equipment to conduct expensive motion capture studies themselves. At the same time, subtle interlaboratory differences can be problematic in an analysis, due to the bias that they introduce. In our study, we investigated differences in motion capture datasets in the context of machine learning, for which we combined overground walking trials from four existing studies. Specifically, our goal was to examine whether a machine learning model was able to predict the original data source based on marker and GRF trajectories of single strides, and how different scaling methods and pooling procedures affected the outcome. Layer-wise relevance propagation was applied to understand which factors were influential to distinguish the original data sources. We found that the model could predict the original data source with a very high accuracy (up to &gt;99%), which decreased by about 15 percentage points when we scaled every dataset individually prior to pooling. However, none of the proposed scaling methods could fully remove the dataset bias. Layer-wise relevance propagation revealed that there was not only one single factor that differed between all datasets. Instead, every dataset had its unique characteristics that were picked up by the model. These variables differed between the scaling and pooling approaches but were mostly consistent between trials belonging to the same dataset. Our results show that motion capture data is sensitive even to small deviations in marker placement and experimental setup and that small inter-group differences should not be overinterpreted during data analysis, especially when the data was collected in different labs. Furthermore, we recommend scaling datasets individually prior to pooling them which led to the lowest accuracy. We want to raise awareness that differences in datasets always exist and are recognizable by machine learning models. Researchers should thus think about how these differences might affect their results when combining data from different studies.

The women's cardiovascular disease risk perception after hypertensive disorders of pregnancy: A qualitative meta-synthesis

BackgroundHypertensive disorders of pregnancy is associated with increased risk of cardiovascular disease later in life, but studies suggest that women with previous hypertensive disorders of pregnancy are not aware of this. Little is known about how these women perceive the condition and the associated long-term risks. ObjectivesThis study aims to examine and synthesize qualitative evidence on the perceptions and awareness of women with hypertensive disorders of pregnancy following perceived cardiovascular disease risk. MethodsComputer searches of Pub Med, Embase, Web of Science, Cochrane Library, CINAHL, CNKI, Wanfang database, Vip and SinoMed for all qualitative studies that met the inclusion criteria. The time frame for the search was from the establishment of the database to April 2024. Literature quality was assessed using the Australian Joanna Briggs Institute Centre for Evidence-Based Health Care Qualitative Research quality assessment criteria, and results were summarised and integrated using a pooled integration approach. ResultsEleven studies that fulfilled the inclusion criteria and quality assessment were included in the meta synthesis. Three themes were identified during the analysis: (1)Factors affecting perceived cardiovascular risk in women with hypertensive disorders of pregnancy; (2)Women with hypertensive disorders of pregnancy use different strategies to cope with cardiovascular risk; (3)Needs and expectations for coping with cardiovascular disease risk. ConclusionsBoth women with hypertensive disorders of pregnancy and healthcare providers lack knowledge of the link between hypertensive disorders of pregnancy and cardiovascular risk. Healthcare professionals should establish a multidimensional support model, pay timely attention to postpartum women's psycho-emotional and risk awareness, and give individualised health education to promote health behaviour change. At the same time, professionals should be given standardised training and personalised follow-up services to reduce the incidence of cardiovascular disease in the future.

ROMI: a randomized two-stage basket trial design to optimize doses for multiple indications.

Optimizing doses for multiple indications is challenging. The pooled approach of finding a single optimal biological dose (OBD) for all indications ignores that dose-response or dose-toxicity curves may differ between indications, resulting in varying OBDs. Conversely, indication-specific dose optimization often requires a large sample size. To address this challenge, we propose a Randomized two-stage basket trial design that Optimizes doses in Multiple Indications (ROMI). In stage 1, for each indication, response and toxicity are evaluated for a high dose, which may be a previously obtained maximum tolerated dose, with a rule that stops accrual to indications where the high dose is unsafe or ineffective. Indications not terminated proceed to stage 2, where patients are randomized between the high dose and a specified lower dose. A latent-cluster Bayesian hierarchical model is employed to borrow information between indications, while considering the potential heterogeneity of OBD across indications. Indication-specific utilities are used to quantify response-toxicity trade-offs. At the end of stage 2, for each indication with at least one acceptable dose, the dose with highest posterior mean utility is selected as optimal. Two versions of ROMI are presented, one using only stage 2 data for dose optimization and the other optimizing doses using data from both stages. Simulations show that both versions have desirable operating characteristics compared to designs that either ignore indications or optimize dose independently for each indication.

Hybrid convolutional neural networks in human resource recommendation

The study proposes a new algorithm combining a gradient boosting tree algorithm with a hybrid convolutional neural network in order to design a better human resource recommendation algorithm to solve the problem of employment difficulties and recruitment difficulties. The algorithm combines the excellent feature transformation ability of gradient boosting trees with the excellent classification ability of hybrid convolutional neural networks, complementing the shortcomings of each of the two algorithms. The outcomes showed that the algorithm performed best with the learning rate set to 0.3 and the maximum tree depth set to 3. The algorithm now has the lowest loss percentage and highest F1-Score value. The maximum-median hybrid pooling approach used in the study had considerable improvements over the algorithm’s pooling strategy (PS), and it had the greatest recall and F1-Score values of all pooling strategies (0.8108 and 0.7418, respectively). The new algorithm outperformed the gradient boosting tree algorithm and the hybrid convolutional neural network algorithm in terms of recall and F1-Score values, and regardless of the length of the job recommendation, the recall and F1-Score values of the new algorithm were consistently higher than those of the old algorithm. The recall and F1-Score values of the new algorithm, with a job recommendation length of 70, were 0.8198 and 0.7432, respectively, both greater than those of the other algorithms, according to a comparison of it with other conventional HR recommendation algorithms. The study’s newly created algorithm increases the efficacy and precision of HR suggestions.

Using Vaccine Safety Data to Demonstrate the Potential of Pooled Data Analysis.

In Canada, vaccine safety studies are often conducted at the provincial/territorial level where the primary data on vaccination reside. Combining health services data from multiple jurisdictions using a pooled data analytic approach would reduce the amount of time needed to detect vaccine safety signals. To determine the difference in the time it would take to identify safety signals using different proportions of the Canadian population, we conducted power and sample size calculations for a hypothetical self-controlled case series-based surveillance analysis. We used scenarios modeled after the real-world examples of myocarditis and vaccine-induced immune thrombotic thrombocytopenia (VITT) following COVID-19 vaccination as our base cases. Our calculations demonstrated that in the case of a myocarditis-type event, a pooled analysis would reduce the time needed to detect a safety signal by over 60% compared to using Ontario data alone. In the case of a VITT-type event, a pooled analysis could detect a safety signal 49 days sooner than using Ontario data alone, potentially averting as many as 30 events. Our analysis demonstrates that there is substantial value in using pan-Canadian health services data to evaluate the safety of vaccines. Efforts should be made to develop a pan-Canadian vaccine data source to allow for an earlier evaluation of suspected adverse events following immunization.

Algorithms of Cross-Domain Redundancy Management for Resilient of Dual-Priority Critical Communication Systems

The paper presents models for managing cross-domain redundancy to enhance the reliability of two priority communication channels within critical infrastructure systems. Employing Markov chain models, the paper analyzes the impact of two distinct redundancy management strategies: a unified reserve pool and a separate pool approach with cross-domain resource sharing. The study introduces reliability improvement factors to quantify system performance, exploring their dependency on the number of additional redundant elements, their inherent reliability, and the chosen strategy for managing cross-domain redundancy. An air traffic control system serves as a case study of the application of the proposed management algorithms. Results indicate that the integration of resources from different priority domains significantly improves communication reliability. The findings may be useful for the design and operation of secure communication networks.

Analysis of the structure and efficiency of national health care systems

It was noted that the right to health care is a key topic of discussion around the world, and ensuring the realization of this right and the opportunity to access the necessary medical care is in the spotlight. The realization of the right to health care in each country directly depends on the national health policy. The analysis is focused on assessing the effectiveness of health care systems of states according to several models. The data for this study were obtained from the existing WHO database, which provides accumulated data for groups of countries. Thus, it was possible to compare different countries, whose state health statistics may have their own characteristics. For data processing, an input-oriented analysis model of a dynamic network data shell was used. The analysis combines the use of traditional and non-traditional methods for measuring health performance. The analysis shows that there are no pure health systems financing models, most states use mixed funding models. The only way to reduce dependence on direct payments is for the government to encourage the use of a prepayment and risk pooling approach.

Dynamic convergence of autism disorder risk genes across neurodevelopment.

Over a hundred risk genes underlie risk for autism spectrum disorder (ASD) but the extent to which they converge on shared downstream targets to increase ASD risk is unknown. To test the hypothesis that cellular context impacts the nature of convergence, here we apply a pooled CRISPR approach to target 29 ASD loss-of-function genes in human induced pluripotent stem cell (hiPSC)-derived neural progenitor cells, glutamatergic neurons, and GABAergic neurons. Two distinct approaches (gene-level and network-level analyses) demonstrate that convergence is greatest in mature glutamatergic neurons. Convergent effects are dynamic, varying in strength, composition, and biological role between cell types, increasing with functional similarity of the ASD genes examined, and driven by cell-type-specific gene co-expression patterns. Stratification of ASD genes yield targeted drug predictions capable of reversing gene-specific convergent signatures in human cells and ASD-related behaviors in zebrafish. Altogether, convergent networks downstream of ASD risk genes represent novel points of individualized therapeutic intervention.

Genetic Screen in a Preclinical Model of Sarcoma Development Defines Drivers and Therapeutic Vulnerabilities.

High-grade complex karyotype sarcomas are a heterogeneous group of tumors with a uniformly poor prognosis. Within complex karyotype sarcomas, there are innumerable genetic changes but identifying those that are clinically relevant has been challenging. To address this, we utilized a pooled genetic screening approach, informed by The Cancer Genome Atlas (TCGA) data, to identify key drivers and modifiers of sarcoma development that were validated in vivo. YAP1 and wild-type KRAS were validated as drivers and transformed human mesenchymal stem cells into two distinct sarcoma subtypes, undifferentiated pleomorphic sarcoma and myxofibrosarcoma, respectively. A subset of tumors driven by CDK4 and PIK3CA reflected leiomyosarcoma and osteosarcoma demonstrating the plasticity of this approach and the potential to investigate sarcoma subtype heterogeneity. All generated tumors histologically reflected human sarcomas and had increased aneuploidy as compared to simple karyotype sarcomas. Comparing differential gene expression of TCGA samples to model data identified increased oxidative phosphorylation signaling in YAP1 tumors. Treatment of a panel of soft tissue sarcomas with a combination of YAP1 and oxidative phosphorylation inhibitors led to significantly decreased viability. Transcriptional co-analysis of TCGA patient samples to YAP1 and KRAS model tumors supports that these sarcoma subtypes lie along a spectrum of disease and adds guidance for further transcriptome-based refinement of sarcoma subtyping. This approach can be used to begin to understand pathways and mechanisms driving human sarcoma development, the relationship between sarcoma subtypes, and to identify and validate new therapeutic vulnerabilities for this aggressive and heterogeneous disease.

Maximizing efficiency in sedimentary ancient DNA analysis: a novel extract pooling approach

In the last few decades, the field of ancient DNA has taken a new direction towards using sedimentary ancient DNA (sedaDNA) for studying human and mammalian population dynamics as well as past ecosystems. However, the screening of numerous sediment samples from archaeological sites remains a time-consuming and costly endeavor, particularly when targeting hominin DNA. Here, we present a novel high-throughput method that facilitates the fast and efficient analysis of sediment samples by applying a pooled testing approach. This method combines multiple extracts, enabling early parallelization of laboratory procedures and effective aDNA screening. Pooled samples with detectable aDNA signals undergo detailed analysis, while empty pools are discarded. We have successfully applied our method to multiple sediment samples from Middle and Upper Paleolithic sites in Europe, Asia, and Africa. Notably, our results reveal that an aDNA signal remains discernible even when pooled with four negative samples. We also demonstrate that the DNA yield of double-stranded libraries increases significantly when reducing the extract input, potentially mitigating the effects of inhibition. By embracing this innovative approach, researchers can analyze large numbers of sediment samples for aDNA preservation, achieving significant cost reductions of up to 70% and reducing hands-on laboratory time to one-fifth.

Physiologically Based Pharmacokinetic Model of OATP1B Substrates with a Nonlinear Mixed Effect Approach: Estimating Empirical In Vitro-to-In Vivo Scaling Factors.

Physiologically based pharmacokinetic (PBPK) models are valuable for translating in vitro absorption, distribution, metabolism, and excretion (ADME) data to predict clinical pharmacokinetics, and can enable discovery and early clinical stages of pharmaceutical research. However, in predicting pharmacokinetics of organic anion transporting polypeptide (OATP) 1B substrates based on in vitro transport and metabolism data, PBPK models typically require additional empirical in vitro-to-in vivo scaling factors (ESFs) in order to accurately recapitulate observed clinical profiles. As model simulation is very sensitive to ESFs, a critical evaluation of ESF estimation is prudent. Previously studies have applied classic 'two-stage' and 'naïve pooled data' approaches in identifying a set of compound independent ESFs. However, the 'two-stage' approach has the parameter identification issue in separately fitting data for individual compounds, while the 'naïve pooled data' approach ignores interstudy variability, leading to potentially biased ESF estimates. In this study, we have applied a nonlinear mixed-effect approach in estimating ESF of the PBPK model and incorporated additional data from 86 runs of in vitro uptake assay and 49 clinical studies of 12 training compounds in model development to further enhance the translation of in vitro data to predict the pharmacokinetics of OATP1B substrate drugs. To test predication accuracy of the model, a 'leave-one-out' analysis has been performed. The established model can reasonably describe the clinical observations, with both mean values and interstudy variabilities quantified for ESF and volume of distribution parameters. The mean estimates are largely consistent with values in the previous reports. The interstudy variabilities of these parameters are estimated to be at least 50% (as coefficient of variation). Most compounds can be reasonably predicted in the 'leave-one-out' analysis. This study improves the confidence in predicting the pharmacokinetics of OATP1B substrates in individual studies of small sample sizes, and quantifies the variability associated with the prediction.

Breaking Barriers in Cancer Diagnosis: Super‐Light Compact Convolution Transformer for Colon and Lung Cancer Detection

ABSTRACTAccording to the World Health Organization, lung and colon cancers are known for their high mortality rates which necessitate the diagnosis of these cancers at an early stage. However, the limited availability of data such as histopathology images used for diagnosis of these cancers, poses a significant challenge while developing computer‐aided detection system. This makes it necessary to keep a check on the number of parameters in the artificial intelligence (AI) model used for the detection of these cancers considering the limited availability of the data. In this work, a customised compact and efficient convolution transformer architecture, termed, C3‐Transformer has been proposed for the diagnosis of colon and lung cancers using histopathological images. The proposed C3‐Transformer relies on convolutional tokenisation and sequence pooling approach to keep a check on the number of parameters and to combine the advantage of convolution neural network with the advantages of transformer model. The novelty of the proposed method lies in efficient classification of colon and lung cancers using the proposed C3‐Transformer architecture. The performance of the proposed method has been evaluated on the ‘LC25000’ dataset. Experimental results shows that the proposed method has been able to achieve average classification accuracy, precision and recall value of 99.30%, 0.9941 and 0.9950, in classifying the five different classes of colon and lung cancer with only 0.0316 million parameters. Thus, the present computer‐aided detection system developed using proposed C3‐Transformer can efficiently detect the colon and lung cancers using histopathology images with high detection accuracy.

Adaptive loss-guided multi-stage residual ASPP for lesion segmentation and disease detection in cucumber under complex backgrounds

BackgroundIn complex agricultural environments, the presence of shadows, leaf debris, and uneven illumination can hinder the performance of leaf segmentation models for cucumber disease detection. This is further exacerbated by the imbalance in pixel ratios between background and lesion areas, which affects the accuracy of lesion extraction.ResultsAn original image segmentation framework, the LS-ASPP model, which utilizes a two-stage Atrous Spatial Pyramid Pooling (ASPP) approach combined with adaptive loss to address these challenges has been proposed. The Leaf-ASPP stage employs attention modules and residual structures to capture multi-scale semantic information and enhance edge perception, allowing for precise extraction of leaf contours from complex backgrounds. In the Spot-ASPP stage, we adjust the dilation rate of ASPP and introduce a Convolutional Attention Block Module (CABM) to accurately segment lesion areas.ConclusionsThe LS-ASPP model demonstrates improved performance in semantic segmentation accuracy under complex conditions, providing a robust solution for precise cucumber lesion segmentation. By focusing on challenging pixels and adapting to the specific requirements of agricultural image analysis, our framework has the potential to enhance disease detection accuracy and facilitate timely and effective crop management decisions.

Fully Convolutional Hybrid Fusion Network with Heterogeneous Representations for Identification of S1 and S2 from Phonocardiogram.

Heart auscultation is a simple and inexpensive first-line diagnostic test for the early screening of heart abnormalities. A phonocardiogram (PCG) is a digital recording of an analog heart sound acquired using an electronic stethoscope. A computerized algorithm for PCG analysis can aid in detecting abnormal signal patterns and support the clinical use of auscultation. It is important to detect fundamental components, such as the first and second heart sounds (S1 and S2), to accurately diagnose heart abnormalities. In this study, we developed a fully convolutional hybrid fusion network to identify S1 and S2 locations in PCG. It enables timewise, high-level feature fusion from dimensionally heterogeneous features: 1D envelope and 2D spectral features. For the fusion of heterogeneous features, we proposed a novel convolutional multimodal factorized bilinear pooling approach that enables high-level fusion without temporal distortion. We experimentally demonstrated the benefits of the comprehensive interpretation of heterogeneous features, with the proposed method outperforming other state-of-the-art PCG segmentation methods. To the best of our knowledge, this is the first study to interpret heterogeneous features through a high level of feature fusion in PCG analysis.

GNN-MgrPool: Enhanced graph neural networks with multi-granularity pooling for graph classification

Graph neural networks (GNNs) have gained sufficient attention and are applied to various domain tasks. At present, numerous pooling approaches are being proposed to aggregate node features and obtain node embeddings. However, current GNNs are black-box models that typically use a flat or single pooling step to aggregate nodes, which only considers the similarity between nodes within the cluster. These approaches ignore the influence of relationships within and between clusters in the learning process. To address this issue, we propose a novel multi-granular pooling method that aggregates nodes by simultaneously considering density and relationships among nodes and clusters. This method allows us to obtain multi-granular node-embedding clusters from GNN layers. The clusters in the current layer are built upon those in the previous layer, and these clusters change from fine to coarse as the number of clusters decreases during learning, which is achieved by using multi-granular pooling (MgrPool). Additionally, there is an inclusion relation between adjacent layers, and the node representation of each layer is established through the ratio of node distance within clusters to that between clusters. Finally, we conducted several experiments on node and graph classification tasks by combining GNN models with this pooling approach. The results demonstrate that our GNN-MgrPool model outperforms similar state-of-the-art algorithms and largely improves the interpretability of the learning process.

Semiparametric g-computation for survival outcomes with time-fixed exposures: An illustration

PurposeGeneralized (g-) computation is a useful tool for causal inference in epidemiology. However, in settings when the outcome is a survival time subject to right censoring, the standard pooled logistic regression approach to g-computation requires arbitrary discretization of time, parametric modeling of the baseline hazard function, and the need to expand one’s dataset. We illustrate a semiparametric Breslow estimator for g-computation with time-fixed treatments and survival outcomes that is not subject to these limitations. MethodsWe compare performance of the Breslow g-computation estimator to the pooled logistic g-computation estimator in simulations and illustrate both approaches to estimate the effect of a 3-drug vs 2-drug antiretroviral therapy regimen among people with HIV. ResultsIn simulations, both approaches performed well at the end of follow-up. The pooled logistic approach was biased at times between the endpoints of the discrete time intervals used, while the Breslow approach was not. In the example, both approaches estimated a 1-year risk difference of about 6 % in favor of the 3-drug regimen, but the shape of the survival curves differed. ConclusionsThe Breslow g-computation estimator of counterfactual risk functions does not rely on strong parametric assumptions about the time-to-event distribution or onerous dataset expansions.

Using Power Analysis to Choose the Unit of Randomization, Outcome, and Approach for Subgroup Analysis for a Multilevel Randomized Controlled Clinical Trial to Reduce Disparities in Cardiovascular Health

We give examples of three features in the design of randomized controlled clinical trials which can increase power and thus decrease sample size and costs. We consider an example multilevel trial with several levels of clustering. For a fixed number of independent sampling units, we show that power can vary widely with the choice of the level of randomization. We demonstrate that power and interpretability can improve by testing a multivariate outcome rather than an unweighted composite outcome. Finally, we show that using a pooled analytic approach, which analyzes data for all subgroups in a single model, improves power for testing the intervention effect compared to a stratified analysis, which analyzes data for each subgroup in a separate model. The power results are computed for a proposed prevention research study. The trial plans to randomize adults to either telehealth (intervention) or in-person treatment (control) to reduce cardiovascular risk factors. The trial outcomes will be measures of the Essential Eight, a set of scores for cardiovascular health developed by the American Heart Association which can be combined into a single composite score. The proposed trial is a multilevel study, with outcomes measured on participants, participants treated by the same provider, providers nested within clinics, and clinics nested within hospitals. Investigators suspect that the intervention effect will be greater in rural participants, who live farther from clinics than urban participants. The results use published, exact analytic methods for power calculations with continuous outcomes. We provide example code for power analyses using validated software.