Dataset Information

Incorporating a real-time automatic alerting system based on electronic medical records could improve rapid response systems: a retrospective cohort study.

ABSTRACT:

Background

Rapid response systems (RRSs) are essential components of patient safety systems; however, limited evidence exists regarding their effectiveness and optimal structures. We aimed to assess the activation patterns and outcomes of RRS implementation with/without a real-time automatic alerting system (AAS) based on electronic medical records (EMRs).

Methods

We retrospectively analyzed clinical data of patients for whom the RRS was activated in the surgical wards of a tertiary university hospital. We compared the code rate, in-hospital mortality, unplanned intensive care unit (ICU) admission, and other clinical outcomes before and after applying RRS and AAS as follows: pre-RRS (January 2013-July 2015), RRS without AAS (August 2015-November 2016), and RRS with AAS (December 2016-December 2017).

Results

In-hospital mortality per 1000 admissions decreased from 15.1 to 12.9 after RRS implementation (p < 0.001). RRS activation per 1000 admissions increased from 14.4 to 26.3 after AAS implementation. The severity of patients' condition calculated using the modified early warning score increased from 2.5 (± 2.1) in the RRS without AAS to 3.6 (± 2.1) (p < 0.001) in the RRS with AAS. The total and preventable code rates and in-hospital mortality rates were comparable between the RRS implementation periods without/with AAS. ICU duration and mortality results improved in patients with RRS activation and unplanned ICU admission. The data of RRS non-activated group remained unaltered during the study.

Conclusions

Real-time AAS based on EMRs might help identify unstable patients. Early detection and intervention with RRS may improve patient outcomes.

SUBMITTER: You SH

PROVIDER: S-EPMC8643026 | biostudies-literature | 2021 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Incorporating a real-time automatic alerting system based on electronic medical records could improve rapid response systems: a retrospective cohort study.

You Seung-Hun SH Jung Sun-Young SY Lee Hyun Joo HJ Kim Sulhee S Yang Eunjin E

Scandinavian journal of trauma, resuscitation and emergency medicine 20211204 1

<h4>Background</h4>Rapid response systems (RRSs) are essential components of patient safety systems; however, limited evidence exists regarding their effectiveness and optimal structures. We aimed to assess the activation patterns and outcomes of RRS implementation with/without a real-time automatic alerting system (AAS) based on electronic medical records (EMRs).<h4>Methods</h4>We retrospectively analyzed clinical data of patients for whom the RRS was activated in the surgical wards of a tertia ...[more]

PMID: 34863275

Similar Datasets

Project description:BackgroundKnowledge graphs are a powerful tool for organizing knowledge, processing information and integrating scattered information, effectively visualizing the relationships among entities and supporting further intelligent applications. One of the critical tasks in building knowledge graphs is knowledge extraction. The existing knowledge extraction models in the Chinese medical domain usually require high-quality and large-scale manually labeled corpora for model training. In this study, we investigate rheumatoid arthritis (RA)-related Chinese electronic medical records (CEMRs) and address the automatic knowledge extraction task with a small number of annotated samples from CEMRs, from which an authoritative RA knowledge graph is constructed.MethodsAfter constructing the domain ontology of RA and completing manual labeling, we propose the MC-bidirectional encoder representation from transformers-bidirectional long short-term memory-conditional random field (BERT-BiLSTM-CRF) model for the named entity recognition (NER) task and the MC-BERT + feedforward neural network (FFNN) model for the entity extraction task. The pretrained language model (MC-BERT) is trained with many unlabeled medical data and fine-tuned using other medical domain datasets. We apply the established model to automatically label the remaining CEMRs, and then an RA knowledge graph is constructed based on the entities and entity relations, a preliminary assessment is conducted, and an intelligent application is presented.ResultsThe proposed model achieved better performance than that of other widely used models in knowledge extraction tasks, with mean F1 scores of 92.96% in entity recognition and 95.29% in relation extraction. This study preliminarily confirmed that using a pretrained medical language model could solve the problem that knowledge extraction from CEMRs requires a large number of manual annotations. An RA knowledge graph based on the above identified entities and extracted relations from 1,986 CEMRs was constructed. Experts verified the effectiveness of the constructed RA knowledge graph.ConclusionsIn this paper, an RA knowledge graph based on CEMRs was established, the processes of data annotation, automatic knowledge extraction, and knowledge graph construction were described, and a preliminary assessment and an application were presented. The study demonstrated the viability of a pretrained language model combined with a deep neural network for knowledge extraction tasks from CEMRs based on a small number of manually annotated samples.

Project description:BackgroundIn South Korea, most graduated medical students undertake a 1-year internship before beginning residency and specialization. Interns usually work in a tertiary hospital and rotate between different, randomly assigned departments to be exposed to different medical specialties. Their jobs are mostly simple and repetitive but are still essential for the patient care process. However, owing to the lack of experience and overwhelming workload, interns at tertiary hospitals in South Korea are usually inefficient, often delaying the entire clinical process. Health care providers have widely adopted mobile electronic medical records (mEMRs) as they have been shown to improve workflow efficiency.ObjectiveThis study investigates the association between the frequency of mEMR usage and the clinical task completion interval time among interns in a tertiary hospital.MethodsThis mixed methods study was conducted at the Samsung Medical Center, Seoul, South Korea. Interns who worked at the Samsung Medical Center from March 2018 to February 2019 were included. The hospital electronic medical record (EMR) system known as DARWIN (Data Analysis and Research Window for Integrated kNowledge) was launched with PC and mobile. Both versions are actively used in hospitals by personnel in various positions. We collected the log data from the mEMR server and the intern clinical task time-series data from the EMR server. Interns can manage the process of identifying patients, assigning the clinical task, finishing the requested clinical intern tasks, etc, through the use of the mEMR system. We compared the clinical task completion interval among 4 groups of interns divided by the mEMR frequency quantile. Then, System Usability Score (SUS) questionnaires and semistructured interviews were conducted.ResultsThe regular mEMR users were defined as those who logged in more than once a day on average and used the mEMR until the level after login. Among a total of 87 interns, 84 used the mEMR to verify the requested clinical tasks. The most frequently used item was "Intern task list." Analysis of the 4 intern groups revealed an inverse relationship between the median time of the task completion interval and the frequency of mEMR use. Correlation analysis showed that the intern task completion time interval had a significant inverse relationship with the individual frequency of mEMR usage (coefficient=-0.27; 95% CI -0.46 to -0.04; P=.02). In the additional survey, the mean SUS value was 81.67, which supported the results of the data analysis.ConclusionsOur findings suggest that frequent mEMR use is associated with improved work efficiency in hospital interns with good usability of the mEMR. Such finding supports the idea that the use of mEMR improves the effectiveness and workflow efficiency of interns working in hospitals and, more generally, in the context of health care.

Dataset Information

Incorporating a real-time automatic alerting system based on electronic medical records could improve rapid response systems: a retrospective cohort study.

Background

Methods

Results

Conclusions

Publications

Incorporating a real-time automatic alerting system based on electronic medical records could improve rapid response systems: a retrospective cohort study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets