Forecasting emergency department admissions

2021 ◽  
Vol 25 (6) ◽  
pp. 1579-1601
Author(s):  
Carlos Narciso Rocha ◽  
Fátima Rodrigues
Keyword(s):  
Neural Network ◽  
Emergency Department ◽  
Recurrent Neural Network ◽  
Patient Flow ◽  
Clinical Staff ◽  
Quality Service ◽  
Emergency Admissions ◽  
Machine Learning Methods ◽  
Recurrent Neuronal Network ◽  
High Quality Service

The emergency department of a hospital plays an extremely important role in the healthcare of patients. To maintain a high quality service, clinical professionals need information on how patient flow will evolve in the immediate future. With accurate emergency department forecasts it is possible to better manage available human resources by allocating clinical staff before peak periods, thus preventing service congestion, or releasing clinical staff at less busy times. This paper describes a solution developed for the presentation of hourly, four-hour, eight-hour and daily number of admissions to a hospital’s emergency department. A 10-year history (2009–2018) of the number of emergency admissions in a Portuguese hospital was used. To create the models several methods were tested, including exponential smoothing, SARIMA, autoregressive and recurrent neural network, XGBoost and ensemble learning. The models that generated the most accurate hourly time predictions were the recurrent neural network with one-layer (sMAPE = 23.26%) and with three layers (sMAPE = 23.12%) and XGBoost (sMAPE = 23.70%). In terms of efficiency, the XGBoost method has by far outperformed all others. The success of the recurrent neuronal network and XGBoost machine learning methods applied to the prediction of the number of emergency department admissions has been demonstrated here, with an accuracy that surpasses the models found in the literature.

scholarly journals Detection of Fraud Transactions Using Recurrent Neural Network during COVID-19

2020 ◽  
Vol 07 (03) ◽  
pp. 16-21
Author(s):  
Samir Kuma Bandyopadhyay ◽  
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Credit Card ◽  
Usage Pattern ◽  
Financial Loss ◽  
Online Transactions ◽  
Machine Learning Methods ◽  
Payment Schemes ◽  
Money Transfer ◽  
Clustering Approach

Online transactions are becoming more popular in present situation where the globe is facing an unknown disease COVID-19. Now authorities of several countries have requested people to use cashless transaction as far as possible. Practically, it is not always possible to use it in all transactions. Since number of such cashless transactions has been increasing during lockdown period due to COVID-19, fraudulent transactions are also increasing in a rapid way. Fraud can be analysed by viewing a series of customer transactions data that was done in his/ her previous transactions. Normally banks or other transaction authorities warn their customers about the transaction, if they notice any deviation from available patterns; the authorities consider it as a possibly fraudulent transaction. For detection of fraud during COVID-19, banks and credit card companies are applying various methods such as data mining, decision tree, rule based mining, neural network, fuzzy clustering approach and machine learning methods. The approach tries to find out normal usage pattern of customers based on their former activities. The objective of this paper is to propose a method to detect such fraud transactions during such unmanageable situation of the pandemic. Digital payment schemes are often threatened by fraudulent activities. Detecting fraud transactions during money transfer may save customers from financial loss. Mobile-based money transactions are focused in this paper for fraud detection. A Deep Learning (DL) framework is suggested in the paper that monitors and detects fraudulent activities. Implementing and applying Recurrent Neural Network on PaySim generated synthetic financial dataset, deceptive transactions are identified. The proposed method is capable to detect deceptive transactions with an accuracy of 99.87%, F1-Score of 0.99 and MSE of 0.01.

National Emergency Access Targets metrics of the emergency department–inpatient interface: measures of patient flow and mortality for emergency admissions to hospital

2015 ◽  
Vol 39 (5) ◽  
pp. 533 ◽  
Author(s):  
Clair Sullivan ◽  
Andrew Staib ◽  
Rob Eley ◽  
Alan Scanlon ◽  
Judy Flores ◽  
...  
Keyword(s):  
Emergency Department ◽  
Patient Flow ◽  
Time Interval ◽  
Inverse Relation ◽  
Bed Occupancy ◽  
Emergency Admissions ◽  
Emergency Patients ◽  
Number Of Patients ◽  
Hospital Bed ◽  
National Emergency

Background Movement of emergency patients across the emergency department (ED)–inpatient ward interface influences compliance with National Emergency Access Targets (NEAT). Uncertainty exists as to how best measure patient flow, NEAT compliance and patient mortality across this interface. Objective To compare the association of NEAT with new and traditional markers of patient flow across the ED–inpatient interface and to investigate new markers of mortality and NEAT compliance across this interface. Methods Retrospective study of consecutive emergency admissions to a tertiary hospital (January 2012 to June 2014) using routinely collected hospital data. The practical access number for emergency (PANE) and inpatient cubicles in emergency (ICE) are new measures reflecting boarding of inpatients in ED; traditional markers were hospital bed occupancy and ED attendance numbers. The Hospital Standardised Mortality Ratio (HSMR) for patients admitted via ED (eHSMR) was correlated with inpatient NEAT compliance rates. Linear regression analyses assessed for statistically significant associations (expressed as Pearson R coefficient) between all measures and inpatient NEAT compliance rates. Results PANE and ICE were inversely related to inpatient NEAT compliance rates (r = 0.698 and 0.734 respectively, P < 0.003 for both); no significant relation was seen with traditional patient flow markers. Inpatient NEAT compliance rates were inversely related to both eHSMR (r = 0.914, P = 0.0006) and all-patient HSMR (r = 0.943, P = 0.0001). Conclusions Traditional markers of patient flow do not correlate with inpatient NEAT compliance in contrast to two new markers of inpatient boarding in ED (PANE and ICE). Standardised mortality rates for both emergency and all patients show a strong inverse relation with inpatient NEAT compliance. What is known about the topic? Impaired flow of emergency admissions across the interface between ED and inpatient wards retards achievement of NEAT-compliance rates and adversely affects patient outcomes. Uncertainty exists as to which measures of patient flow and mortality outcomes correlate closely with NEAT-compliance rates for patients admitted from emergency departments. What does this paper add? This study investigates the utility of two new markers of patient flow from ED to inpatient wards. The Practical Access Number for Emergency (PANE) is the number of patients in ED who have had their episode of ED care completed and are awaiting an inpatient bed at a particular point in time. The Inpatient Cubicles in Emergency (ICE) represents the theoretical number of ED cubicles blocked by boarding patients over a specified time interval (in this study 5 weekdays, Monday–Friday), based on the mean time boarders spent in ED during that interval. Both measures were shown to be significantly inversely related to inpatient NEAT compliance rates (i.e. as PANE and ICE increased, NEAT compliance decreased). In contrast, no relation was seen with traditional markers of patient flow (i.e. hospital bed occupancy and ED attendance numbers). HSMR for both all patients and emergency patients only demonstrated a strong inverse relation with inpatient NEAT compliance. What are the implications for practitioners? When pursuing higher NEAT compliance rates, traditional markers of patient flow across the ED–inpatient interface may be misleading and adversely impact bed-management strategies and patient safety. Identifying when hospitals may be at risk of developing, or already in, a state of reduced access to emergency care may be performed more accurately using new flow markers such as PANE and ICE. The inverse relationship between inpatient NEAT compliance and HSMR, whether calculated for all patients or for emergency patients only, underscores the dependence of inpatient mortality on the swift flow of large volumes of emergency admissions across the ED–inpatient interface. This flow may be compromised by imposing additional demands on a limited number of commissionable beds by way of increasing ED demand and/or use of more beds for elective admissions.

Transfer Learning Based Recurrent Neural Network Algorithm for Linguistic Analysis

2021 ◽  
Vol 20 (3) ◽  
pp. 1-16
Author(s):  
Peipei Jiang ◽  
Liailun Chen ◽  
Min-Feng Wang
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Transfer Learning ◽  
Recurrent Neural Network ◽  
Research Area ◽  
Machine Learning Algorithms ◽  
The Core ◽  
Machine Learning Methods ◽  
Neural Network Algorithm ◽  
Comparative Results

Each language is a system of understanding and skills that allows language users to interact, express thoughts, hypotheses, feelings, wishes, and all that needs to be expressed. Linguistics is the research of these structures in all respects: the composition, usage, and sociology of language, in particular, are the core of linguistics. Machine Learning is the research area that allows machines to learn without being specifically scheduled. In linguistics, the design of writing is understood to be a foundation for many distinct company apps and probably the most useful if incorporated with machine learning methods. Research shows that besides text tagging and algorithm training, there are major problems in the field of Big Data. This article provides a collaborative effort (transfer learning integrated into Recurrent Neural Network) to analyze the distinct kinds of writing between the language's linear and non-computational sides, and to enhance granularity. The outcome demonstrates stronger incorporation of granularity into the language from both sides. Comparative results of machine learning algorithms are used to determine the best way to analyze and interpret the structure of the language.

scholarly journals Online Urban Waterlogging Monitoring Based on Recurrent Neural Network for Classification of Microblogging Text

2020 ◽  
Author(s):  
Hui Liu ◽  
Ya Hao ◽  
Wenhao Zhang ◽  
Hanyue Zhang ◽  
Fei Gao ◽  
...  
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Global Climate ◽  
Flood Disaster ◽  
Rapid Urbanization ◽  
Urban Flood ◽  
Sina Weibo ◽  
Machine Learning Methods ◽  
Online Monitoring System

Abstract. With the global climate change and rapid urbanization, urban flood disaster spreads and becomes increasingly serious in China. The urban rainstorm and waterlogging have become an urgent challenge that needs to be real-time monitored and further predicted for the improvement of urbanization construction. In this paper, we trained a recurrent neural network (RNN) model to classify microblogging posts related to urban waterlogging, and establish an online monitoring system of urban waterlogging caused by flood disaster. We manually curated more than 4,400 waterlogging posts to train the RNN model so that it can precisely identify waterlogging-related posts of Sina Weibo to timely find out urban waterlogging. The RNN model has been thoroughly evaluated, and our experimental results showed that it achieved higher accuracy than traditional machine learning methods, such as SVM and GBDT. Furthermore, we build a nationwide map of urban waterlogging based on recent two-year microblogging data.

scholarly journals Detection of Fraud Transactions Using Recurrent Neural Network during COVID-19

2020 ◽  
Author(s):  
Samir Bandyopadhyay ◽  
SHAWNI DUTTA
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Credit Card ◽  
Usage Pattern ◽  
Financial Loss ◽  
Online Transactions ◽  
Machine Learning Methods ◽  
Payment Schemes ◽  
Money Transfer ◽  
Clustering Approach

Online transactions are becoming more popular in present situation where the globe is facing an unknown disease COVID-19. Now authorities of Countries requested peoples to use cashless transaction as far as possible. Practically it is not always possible to use it in all transactions. Since number of such cashless transactions have been increasing during lockdown period due to COVID-19, fraudulent transactions are also increasing in a rapid way. Fraud can be analysed by viewing a series of customer transactions data that was done in his/her previous transactions. Normally banks or other transaction authorities warned their customers about the transaction If any deviation is noticed by them from available patterns. These authorities think that it is possibly of fraudulent transaction. For detection of fraud during COVID-19, banks and credit card companies are applying various methods such as data mining , decision tree, rule based mining, neural network, fuzzy clustering approach and machine learning methods. These approaches is try to find out normal usage pattern of customers based on their past activities. The objective of this paper is to find out such fraud transactions during such unmanageable situation.Digital payment schemes are often threatened by fraudulent activities. Detecting fraud transaction in during money transfer may save customers from financial loss. Mobile based money transactions are focused in this paper for fraud detection. A Deep Learning (DL) framework is suggested in this paper that monitors and detects fraudulent activities. Implementing and applying recurrent neural network on PaySim generated synthetic financial dataset, deceptive transactions are identified. The proposed method is capable to detect deceptive transactions with an accuracy of 99.87%, F1-Score of 0.99 and MSE of 0.01.

Research on behavior recognition based on feature fusion of automatic coder and recurrent neural network

2020 ◽  
Vol 39 (6) ◽  
pp. 8927-8935
Author(s):  
Bing Zheng ◽  
Dawei Yun ◽  
Yan Liang
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Behavior Pattern ◽  
Rapid Development ◽  
Video Data ◽  
Support Vector ◽  
Behavior Recognition ◽  
Learning Methods ◽  
The Impact ◽  
Internet Of Things Technology

Under the impact of COVID-19, research on behavior recognition are highly needed. In this paper, we combine the algorithm of self-adaptive coder and recurrent neural network to realize the research of behavior pattern recognition. At present, most of the research of human behavior recognition is focused on the video data, which is based on the video number. At the same time, due to the complexity of video image data, it is easy to violate personal privacy. With the rapid development of Internet of things technology, it has attracted the attention of a large number of experts and scholars. Researchers have tried to use many machine learning methods, such as random forest, support vector machine and other shallow learning methods, which perform well in the laboratory environment, but there is still a long way to go from practical application. In this paper, a recursive neural network algorithm based on long and short term memory (LSTM) is proposed to realize the recognition of behavior patterns, so as to improve the accuracy of human activity behavior recognition.

Deadlift Recognition and Application based on Multiple Modalities using Recurrent Neural Network

2020 ◽  
Vol 2020 (17) ◽  
pp. 2-1-2-6
Author(s):  
Shih-Wei Sun ◽  
Ting-Chen Mou ◽  
Pao-Chi Chang
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Network Structure ◽  
Inertial Sensors ◽  
Body Movement ◽  
The Body ◽  
Body Parts ◽  
Multimodal Sensing ◽  
Multiple Devices ◽  
Neural Network Structure

To improve the workout efficiency and to provide the body movement suggestions to users in a “smart gym” environment, we propose to use a depth camera for capturing a user’s body parts and mount multiple inertial sensors on the body parts of a user to generate deadlift behavior models generated by a recurrent neural network structure. The contribution of this paper is trifold: 1) The multimodal sensing signals obtained from multiple devices are fused for generating the deadlift behavior classifiers, 2) the recurrent neural network structure can analyze the information from the synchronized skeletal and inertial sensing data, and 3) a Vaplab dataset is generated for evaluating the deadlift behaviors recognizing capability in the proposed method.

Sign in / Sign up

Export Citation Format

Share Document