A Parallel Patient Treatment Time Prediction Algorithm and Its Applications in Hospital Queuing-Recommendation in a Big Data Environment

Chen, Jianguo; Li, Kenli; Tang, Zhuo; Bilal, Kashif

doi:10.1109/access.2016.2558199

Cited by 51 publications

(34 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Simulation is conducted for both proposed and existing model for varied datasets shows significant performance improvement of proposed prediction model over exiting prediction model. The overall result shows the proposed patient inflow prediction model is efficient when compared to model in [33], [34] and [37] that adopted artificial intelligence. The result outcome obtained pushes the proposed model to forecast other types of dataset such as ambulance prediction for scheduling, disease, medical risk assessment prediction for diagnosis and so on.…”

Section: Resultsmentioning

confidence: 83%

An Efficient Patient Inflow Prediction Model for Hospital Resource Management

Srikanth

Arivazhagan

2017

IJSC

View full text Add to dashboard Cite

There has been increasing demand in improving service provisioning in hospital resources management. Hospital industries work with strict budget constraint at the same time assures quality care. To achieve quality care with budget constraint an efficient prediction model is required. Recently there has been various time series based prediction model has been proposed to manage hospital resources such ambulance monitoring, emergency care and so on. These models are not efficient as they do not consider the nature of scenario such climate condition etc. To address this artificial intelligence is adopted. The issues with existing prediction are that the training suffers from local optima error. This induces overhead and affects the accuracy in prediction. To overcome the local minima error, this work presents a patient inflow prediction model by adopting resilient backpropagation neural network. Experiment are conducted to evaluate the performance of proposed model inter of RMSE and MAPE. The outcome shows the proposed model reduces RMSE and MAPE over existing back propagation based artificial neural network. The overall outcomes show the proposed prediction model improves the accuracy of prediction which aid in improving the quality of health care management.

show abstract

Section: Resultsmentioning

confidence: 83%

An Efficient Patient Inflow Prediction Model for Hospital Resource Management

Srikanth

Arivazhagan

2017

IJSC

View full text Add to dashboard Cite

show abstract

“…There could be other patients with more than one treatment task to perform. So X|s i will be the set of treatment tasks for patient during specific visit, X|s i = {x 1 The real time patient data will be analyzed, like patient no., gender, age, task name, department name, doctor name, start time, end time. With the patient conditions the treatment time will be analyzed.…”

Section: A Problem Definitionmentioning

confidence: 99%

“…The real-time data the patients like its symptoms, name, age etc is also been verified to manage the queue for the treatment to get completed. Thus with huge amount of hospitals data the PTTP and HQR system performs better for patients data processing [1].…”

Section: Related Work a Paper Title: A Parallel Patient Treatmenmentioning

confidence: 99%

Hospitals Patient Treatment Time Prediction and Its Analysis in Hospital Queuing Recommendation using Data Mining Techniques

Jagtap¹

2018

IJRASET

View full text Add to dashboard Cite

Hospitals patient queue and its management to lower patient waits delays daily is considered as challenging tasks. Time wasting waits for long period results in to poor service and also lowers the hospitals reputation. Patient waiting for the treatment task to be completed need to wait for all the other patients who are appointed before him. This all the factors can be avoided if patient receive the updates about the queue, required time he need to wait for on his mobile phone. Understanding these problems faced by the hospitals, I proposed an individual Parallel Treatment Time Prediction (PTTP) system which will be responsible for analyzing the waiting period for every treatment activity for a patient. Here the realistic patient data from hospitals will be analyzed to calculate estimated patient treatment time for every task. The system will be responsible for getting the updates regarding huge and realtime data-set, the treatments time taken by each and patient among the list of present queue of every task is analyzed. With the successful recognition about the time taken by patient and waiting time, the Hospital Queuing Recommendation (HQR) system is implemented. HQR responsible for the suggestion about the time efficient treatment tasks for the individual. The models thus helps us to overcome the problems faced by hospitals with the help of HQRs time efficiency.

show abstract

“…Therefore, Spark is suitable for P-PSO training, as it is multi-iteration and multiple-parallel. In fact, Spark is already widely used in intruder detection in heterogeneous wireless sensor networks (WSN) [44], hospital queuing recommendation [26], etc., and it is accepted in this work.…”

Section: Distributed Frameworkmentioning

confidence: 99%

“…We chose Apache Spark [25] as a training framework, as Spark is an efficient and stretchable cloud platform that is suitable for data mining and machine learning. In the Spark framework, data are cached in memory and iterations for the same data come directly from memory [26]. Upon a stretchable experimental platform, the training time, training error and number of iterations are recorded under different data sizes and platform scales.…”

Section: Introductionmentioning

confidence: 99%

Algorithm and Implementation of Distributed ESN Using Spark Framework and Parallel PSO

Wu¹,

Zhu²,

Li³

et al. 2017

Applied Sciences

View full text Add to dashboard Cite

Abstract:The echo state network (ESN) employs a huge reservoir with sparsely and randomly connected internal nodes and only trains the output weights, which avoids the suboptimal problem, exploding and vanishing gradients, high complexity and other disadvantages faced by traditional recurrent neural network (RNN) training. In light of the outstanding adaption to nonlinear dynamical systems, ESN has been applied into a wide range of applications. However, in the era of Big Data, with an enormous amount of data being generated continuously every day, the data are often distributed and stored in real applications, and thus the centralized ESN training process is prone to being technologically unsuitable. In order to achieve the requirement of Big Data applications in the real world, in this study we propose an algorithm and its implementation for distributed ESN training. The mentioned algorithm is based on the parallel particle swarm optimization (P-PSO) technique and the implementation uses Spark, a famous large-scale data processing framework. Four extremely large-scale datasets, including artificial benchmarks, real-world data and image data, are adopted to verify our framework on a stretchable platform. Experimental results indicate that the proposed work is accurate in the era of Big Data, regarding speed, accuracy and generalization capabilities.

show abstract

A Parallel Patient Treatment Time Prediction Algorithm and Its Applications in Hospital Queuing-Recommendation in a Big Data Environment

Cited by 51 publications

References 22 publications

An Efficient Patient Inflow Prediction Model for Hospital Resource Management

An Efficient Patient Inflow Prediction Model for Hospital Resource Management

Hospitals Patient Treatment Time Prediction and Its Analysis in Hospital Queuing Recommendation using Data Mining Techniques

Algorithm and Implementation of Distributed ESN Using Spark Framework and Parallel PSO

Contact Info

Product

Resources

About