Dataset Information

Big data ordination towards intensive care event count cases using fast computing GLLVMS.

ABSTRACT:

Background

In heart data mining and machine learning, dimension reduction is needed to remove multicollinearity. Meanwhile, it has been proven to improve the interpretation of the parameter model. In addition, dimension reduction can also increase the time of computing in high dimensional data.

Methods

In this paper, we perform high dimensional ordination towards event counts in intensive care hospital for Emergency Department (ED 1), First Intensive Care Unit (ICU1), Second Intensive Care Unit (ICU2), Respiratory Care Intensive Care Unit (RICU), Surgical Intensive Care Unit (SICU), Subacute Respiratory Care Unit (RCC), Trauma and Neurosurgery Intensive Care Unit (TNCU), Neonatal Intensive Care Unit (NICU) which use the Generalized Linear Latent Variable Models (GLLVM's).

Results

During the analysis, we measure the performance and calculate the time computing of GLLVM by employing variational approximation and Laplace approximation, and compare the different distributions, including Negative Binomial, Poisson, Gaussian, ZIP, and Tweedie, respectively. GLLVMs (Generalized Linear Latent Variable Models), an extended version of GLMs (Generalized Linear Models) with latent variables, have fast computing time. The major challenge in latent variable modelling is that the function [Formula: see text] is not trivial to solve since the marginal likelihood involves integration over the latent variable u.

Conclusions

In a nutshell, GLLVMs lead as the best performance reaching the variance of 98% comparing other methods. We get the best model negative binomial and Variational approximation, which provides the best accuracy by accuracy value of AIC, AICc, and BIC. In a nutshell, our best model is GLLVM-VA Negative Binomial with AIC 7144.07 and GLLVM-LA Negative Binomial with AIC 6955.922.

SUBMITTER: Caraka RE

PROVIDER: S-EPMC8939086 | biostudies-literature | 2022 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Big data ordination towards intensive care event count cases using fast computing GLLVMS.

Caraka Rezzy Eko RE Chen Rung-Ching RC Huang Su-Wen SW Chiou Shyue-Yow SY Gio Prana Ugiana PU Pardamean Bens B

BMC medical research methodology 20220321 1

<h4>Background</h4>In heart data mining and machine learning, dimension reduction is needed to remove multicollinearity. Meanwhile, it has been proven to improve the interpretation of the parameter model. In addition, dimension reduction can also increase the time of computing in high dimensional data.<h4>Methods</h4>In this paper, we perform high dimensional ordination towards event counts in intensive care hospital for Emergency Department (ED 1), First Intensive Care Unit (ICU1), Second Inten ...[more]

PMID: 35313816

Similar Datasets

Project description:BackgroundThe evolving concepts of pervasive computing, ubiquitous computing and ambient intelligence are increasingly influencing health care and medicine. Summarizing published research, this literature review provides an overview of recent developments and implementations of pervasive computing systems in health care. It also highlights some of the experiences reported in deployment processes.MethodsThere is no clear definition of pervasive computing in the current literature. Thus specific inclusion criteria for selecting articles about relevant systems were developed. Searches were conducted in four scientific databases alongside manual journal searches for the period of 2002 to 2006. Articles included present prototypes, case studies and pilot studies, clinical trials and systems that are already in routine use.ResultsThe searches identified 69 articles describing 67 different systems. In a quantitative analysis, these systems were categorized into project status, health care settings, user groups, improvement aims, and systems features (i.e., component types, data gathering, data transmission, systems functions). The focus is on the types of systems implemented, their frequency of occurrence and their characteristics. Qualitative analyses were performed of deployment issues, such as organizational and personnel issues, privacy and security issues, and financial issues. This paper provides a comprehensive access to the literature of the emerging field by addressing specific topics of application settings, systems features, and deployment experiences.ConclusionBoth an overview and an analysis of the literature on a broad and heterogeneous range of systems are provided. Most systems are described in their prototype stages. Deployment issues, such as implications on organization or personnel, privacy concerns, or financial issues are mentioned rarely, though their solution is regarded as decisive in transferring promising systems to a stage of regular operation. There is a need for further research on the deployment of pervasive computing systems, including clinical studies, economic and social analyses, user studies, etc.

Project description:BackgroundThe health care sector is among the most carbon-intensive sectors, contributing to societal problems like climate change. Previous research demonstrated that especially the use of personal protective equipment (e.g., aprons) in critical care contributes to this problem. To reduce personal protective equipment waste, new sustainable policies are needed. Policies are only effective if people comply.AimOur aim is to examine whether compliance with sustainable policies in critical care can be increased through behavioural influencing. Specifically, we examined the effectiveness of two sets of nudges (i.e., a Prime + Visual prompt nudge and a Social norm nudge) on decreasing apron usage in an intensive care unit (ICU).Study designWe conducted a field experiment with a pre- and post-intervention measurement. Upon the introduction of the new sustainable policy, apron usage data were collected for 9 days before (132 observations) and 9 days after (114 observations) the nudge interventions were implemented.ResultsNeither the Prime + Visual prompt nudge, nor the Social norm nudge decreased apron usage.ConclusionsWhile previous studies have found that primes, visual nudges and social norm nudges can increase sustainable behaviour, we did not find evidence for this in our ICU field experiment. Future research is needed to determine whether this null finding reflects reality, or whether it was due to methodological decisions and limitations of the presented experiment.Relevance to clinical practiceThe presented study highlights the importance of studying behavioural interventions that were previously proven successful in the lab and in other field contexts, in the complex setting of critical care. Results previously found in other contexts may not generalize directly to a critical care context. The unique characteristics of the critical care context also pose methodological challenges that may have affected the outcomes of this experiment.

Dataset Information

Big data ordination towards intensive care event count cases using fast computing GLLVMS.

Background

Methods

Results

Conclusions

Publications

Big data ordination towards intensive care event count cases using fast computing GLLVMS.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets