Implementing Smart Pumps to Enhance Patient Safety

Davis, Sondra; Blanchard, C; Lewis, Jevon

doi:10.1177/0018578718809252

Cited by 3 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, several technical improvements, in terms of device-equipped smart functions and linkage on the electronic medical record (EMR) server, have been made to promptly detect erroneous device settings. 9–14 However, although such previous research demonstrated improvements in patient safety, several obstacles can prevent hospitals from adopting such devices. First, the price of a smart infusion pump is generally two- or three-times higher than that of conventional non-smart devices; therefore, the financial burden of purchasing sufficient smart infusion pumps can be a barrier for most hospitals.…”

Section: Discussionmentioning

confidence: 99%

Convolutional neural network-based ambient light-independent panel digit surveillance technique for infusion pumps

Hwang

Kim

Sung

et al. 2021

Proc Inst Mech Eng H

View full text Add to dashboard Cite

For effective patient therapy and improved patient safety, it is critical to administer medication accurately in accordance with doctor’s prescription. However, accidents owing to the erroneous programing of infusion pumps caused by users have been consistently reported in several documents. In this study, the authors propose a novel surveillance technique for infusion pumps to continuously monitor the variations in panel digits using a convolutional neural network model, and evaluate the performance of the implemented technique. During the experimental evaluation, 1st-step ROIs and 2nd-step ROIs were successfully extracted from the frame images regardless of the ambient lighting conditions. The final accuracies of the implemented CNN model are 99.9% for both the training (172,800 images) and validation (1080 images) dataset while the final losses for the training and validation datasets are 0.48 and 0.45 after 13th epoch, respectively. In the 24-h continuous monitoring test, the accuracy of the model for volume recognition considering all the 1440 measurements (960 for day-lighting and 480 for night-lighting) is 95.5%, whereas in day-lighting and night-lighting modes the accuracies of the model are 98.2% and 90.0%, respectively. Based on these experimental results, the proposed surveillance technique incorporating infusion pumps is expected to improve the safety of patients who need long-term treatments via infusion pumps, reducing the burden on the nurses and hospitals.

show abstract

Section: Discussionmentioning

confidence: 99%

Convolutional neural network-based ambient light-independent panel digit surveillance technique for infusion pumps

Hwang

Kim

Sung

et al. 2021

Proc Inst Mech Eng H

View full text Add to dashboard Cite

show abstract

“…However, some surveys show that the library arrival rate has shown a downward trend in recent years. The main factors causing the decrease in library arrival rate are as follows (Davis et al, 2018;Fulli and Gangale, 2016;Giuliano et al, 2018): there are many ways and means for people to obtain information nowadays, and the only way to obtain information will no longer be the library; moreover, many bookstores with comprehensive functions have sprung up, including reading, leisure, entertainment and other functions, which have formed competition with the library. In the meanwhile, the unscientific construction of internal library resources, service content and the This paper forms part of a special section "Informetrics on Social Network Mining: Research, Policy and Practice challenges -Part 2", guest edited by Mu-Yen Chen, Chien-Hsiang Liao, Edwin David Lughofer and Erol Egrioglu.…”

Section: Introductionmentioning

confidence: 99%

Investigating users’ willingness of acceptance for background music service in intelligent library

Liu

2019

LHT

View full text Add to dashboard Cite

Purpose The purpose of this paper is to study the users’ willingness for acceptance of background music service in university libraries based on intelligent campus and to improve the intelligence level of university libraries and provide a reference for the atmosphere. Design/methodology/approach The research method of combining theory with practice is applied, and field distribution method and network survey method are used. An algorithm model is established to investigate relevant users, and statistical analysis of the data obtained is made. Findings The results show that in the questionnaire survey, girls are more inclined to study in the environment of library than boys; for grade, sophomores and juniors are more inclined to go to library than other grades; through model analysis, the target users are more inclined to choose light music as background music, accounting for 65 percent. Heavy metals and other users have fewer choices, accounting for only 8 percent. Research limitations/implications This questionnaire is mainly filled out in paper form on site, so it only selects some nearby students as the survey objects. However, the condition of university libraries across the country must be different due to regional differences, disciplinary differences and funding differences, so the representative sample may be insufficient. Therefore, in the follow-up research, the scope of the survey should be expanded, especially the geographical scope. It should collect as much data as possible for students of different types and genders, so as to expand the applicable scope and explanatory power of the model. Practical implications Starting from the library scene, this research studies the acceptance intention of users of background music service in the library, which provides reference for the improvement of the intellectualization of university libraries and their atmosphere. Although different university libraries have different operation modes and service characteristics, the conclusions of this study have certain practical significance for the library industry because the library industry has many commonalities. Originality/value At present, the research on the background music service of University Library based on the smart campus is relatively rare and limited to the theoretical stage. Few people have deeply explored the background music service of the library, and no scholars have quantitatively studied it. In this study, based on the questionnaire and from the perspective of users, the acceptance intention of background music service users is investigated, which provides a reference for the improvement of the intellectualization of university libraries and its atmosphere. It is a research topic of great practical significance.

show abstract

mentioning

confidence: 99%

“…6 Quality assessments may take on many forms and can include a multidisciplinary team reviewing the percentage of drugs being used via the smart pump, top medications which are overridden, soft alerts, and hard alerts. 7 Opportunities for improvement may be found by continuing to review and assess the IV drug library within the smart pumps. Patient safety can be improved when enhancing and optimizing safeguards to the drug library.…”

mentioning

confidence: 99%