In machine learning problems, high dimensional data, especially in terms of many features, is increasingly these days [1]. Many researchers focus on the experiment to solve these problems. Besides, to extract important features from these high dimensional of variables and data. The statistical techniques were used to minimize noise and redundant data. Nevertheless, we do not use all the features to train a model. We may improve our model with the features correlated and non-redundant, so feature selection plays an important role.

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 $$f\left(\varTheta \right)=\int f\left(u\varTheta \right)h\left(u\right)du$$ f Θ = ∫ f u Θ h u d u 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.

Background: competition in the healthcare market is becoming increasingly intense. Health technology continues to evolve, so hospitals and clinics need to strengthen hospital management techniques and also adopt a more patient-centered approach in order to provide high-quality healthcare services, including a more simplified process and shorter waiting times for examinations. The Lean and Six Sigma methodologies and smart technology were introduced and implemented into the integrated perioperative management (PERIO) processes for the purpose of decreasing pre-admission management waiting time, as well as increasing the completion rate and quality of pre-admission management for surgical patients in a 1576-bed medical center in central Taiwan. Methods: in order to improve hospital admission procedures for surgical patients by shortening process waiting times, simplifying admission processes, emphasizing a patient-centered approach, and providing the most efficient service process, the present study applied the DMAIC architecture of the Lean Six Sigma. This approach allowed the patients to save time on the hospital admission process. The current workflow used value flow mapping to identify wasted time caused by unnecessary walking and waiting during the hospital admission process. Therefore, we improved the process cycle for each patient by simultaneously selecting and controlling the process for the purpose of saving time. Results: the experimental results show that the percentage of Process Cycle Efficiency (PCE) increased from 35.42% to 42.47%, Value Added was reduced from 34 to 31 min, and Non-Value Added was reduced from 62 to 42 min. The satisfaction score of the 97 pre-implementation patients was 4.29 compared with 4.40 among the 328 post-implementation patients (p < 0.05). The LOS (Length of Stay) of 2660 pre-implementation patients was 2.49~3.31 days and for 304 after-implementation patients it was 1.16~1.57 days. Conclusions: by integrating different units and establishing standard perioperative management (PERIO) procedures, together with the support of the information systems, the time spent by patients on hospital admission procedures was shortened. These changes also improved the comprehensiveness of the preoperative preparations and the surgical safety of patients, thereby facilitating the provisions necessary for high-quality healthcare services. This in turn reduced the average length of hospital stays and increased the turnover of patients, benefiting the overall operations of the hospital.