Feature selection becomes prominent, especially in the data sets with many variables and features. It will eliminate unimportant variables and improve the accuracy as well as the performance of classification. Random Forest has emerged as a quite useful algorithm that can handle the feature selection issue even with a higher number of variables. In this paper, we use three popular datasets with a higher number of variables (Bank Marketing, Car Evaluation Database, Human Activity Recognition Using Smartphones) to conduct the experiment. There are four main reasons why feature selection is essential. First, to simplify the model by reducing the number of parameters, next to decrease the training time, to reduce overfilling by enhancing generalization, and to avoid the curse of dimensionality. Besides, we evaluate and compare each accuracy and performance of the classification model, such as Random Forest (RF), Support Vector Machines (SVM), K-Nearest Neighbors (KNN), and Linear Discriminant Analysis (LDA). The highest accuracy of the model is the best classifier. Practically, this paper adopts Random Forest to select the important feature in classification. Our experiments clearly show the comparative study of the RF algorithm from different perspectives. Furthermore, we compare the result of the dataset with and without essential features selection by RF methodsvarImp(),Boruta, and Recursive Feature Elimination (RFE) to get the best percentage accuracy and kappa. Experimental results demonstrate that Random Forest achieves a better performance in all experiment groups.

The provision of efficient healthcare services is essential, driven by the increasing demand for healthcare resources and the need to optimize hospital operations. In this context, the motivation to innovate and improve services while addressing urgent concerns is critical. Hospitals face challenges in managing internal dispatch services efficiently. Outsourcing such services can alleviate the burden on hospital staff, reduce costs, and introduce professional expertise. However, the pressing motivation lies in enhancing service quality, minimizing costs, and exploring innovative approaches. With the rising demand for healthcare services, there is an immediate need to streamline hospital operations. Delays in internal transportation services can have far-reaching implications for patient care, necessitating a prompt and effective solution. Drawing upon dispatch data from a healthcare center in Taiwan, this study constructed a decision-making model to optimize the allocation of hospital service resources. Employing simulation techniques, we closely examine how hospital services are currently organized and how they work. In our research, we utilized dispatch data gathered from a healthcare center in Taichung, Taiwan, spanning from January 2020 to December 2020. Our findings underscore the potential of an intelligent dispatch strategy combined with deployment restricted to the nearest available workers. Our study demonstrates that for cases requiring urgent attention, delay rates that previously ranged from 5% to 34% can be notably reduced to a much-improved 3% to 18%. However, it is important to recognize that the realm of worker dispatch remains subject to a multifaceted array of influencing factors. It becomes evident that a comprehensive dispatching mechanism must be established as part of a broader drive to enhance the efficiency of hospital service operations.

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.

Inefficient patient transport in hospitals often leads to delays, overworked staff, and suboptimal resource utilization, ultimately impacting patient care. Existing dispatch management algorithms are often evaluated in simulation environments, raising concerns about their real-world applicability. This study presents a real-world experiment that bridges the gap between theoretical dispatch algorithms and real-world implementation. It applies process capability analysis at Taichung Veterans General Hospital in Taichung, Taiwan, and utilizes IoT for real-time tracking of staff and medical devices to address challenges associated with manual dispatch processes. Experimental data collected from the hospital underwent statistical evaluation between January 2021 and December 2021. The results of our experiment, which compared the use of traditional dispatch methods with the Beacon dispatch method, found that traditional dispatch had an overtime delay of 41.0%; in comparison, the Beacon dispatch method had an overtime delay of 26.5%. These findings demonstrate the transformative potential of this solution for not only hospital operations but also for improving service quality across the healthcare industry in the context of smart hospitals.

Taiwan has been an active participant in waste recycling for a long period of time due to the need for resource sustainability. The country believes it can one day eventually achieve the goal of zero waste through the effective use of strategies such as source reduction, resource recovery, reuse, and recycling. Despite Taiwan’s long‐standing commitment to waste recycling for purposes of resource sustainability, achieving the goal of zero waste remains an immense challenge. Therefore, putting into effect the previously mentioned strategies will obviously be necessary in order to realize this goal. However, the effective implementation of these strategies requires both comprehensive planning and coordination, particularly in large medical institutions. Here, we have aimed to promote waste reduction throughout the entire hospital system in Taiwan using 3 strategies: (1) standardizing the colors of garbage bags, marking patterns of waste, and reviewing and establishing an internal audit mechanism on a regular basis; (2) the systematic monitoring of individual departments with regard to on waste consumption, brands, and materials while linking departments to the procurement source management team. In addition, any related hardware has been upgraded, precisely controlled, and automatically uploaded to the cloud system for an improved intelligent management system. In addition, the Department of Nutrition has adjusted the handling of ingredients and consumption patterns of hospital employees in order to reduce food waste; and (3) with regard to the disposal of medical waste, medical centers will be consolidating and advancing the knowledge and ability of all hospital personnel through education and training programs established for them. After the implementation of this program to promote awareness, the ratio of biological waste percentage in regard to total hospital waste dropped from 37.3% in 2018 to 33.6% in 2022, with a 49% decrease being seen in food waste, and a 99.32% increase being realized in green designated procurement items. Such an efficient management of medical waste has no doubt been extremely beneficial to the hospital.