Combining Deep Neural Networks and Classical Time Series Regression Models for Forecasting Patient Flows in Hong Kong

Jiang, Shancheng; Xiao, Ran; Wang, Long; Luo, Xiong; Huang, Chao; Wang, Long; Chin, Kwai‐Sang; Nie, Ximing

doi:10.1109/access.2019.2936550

Cited by 24 publications

(24 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The MAPE values for combinatorial models were also significantly smaller than those from the ARIMA and SES models during weekdays and weekends. Compared to the combined ARIMA and ANN models [ 51 ], our proposed combinatorial model has MAPE ranging from 1.93% to 8.34% for day of the week and achieved lower forecast error for daily presentations in most days. For weekday-wise time series, the model was able to accurately predict day visits, with MAPE ranging from 1.93% to 5.27%, which is significantly lower than most of the other hybrid models, such as the EMD-PSO-BPANN model [ 52 ] and the SVR-FA model [ 53 ].…”

Section: Discussionmentioning

confidence: 99%

Prediction of Daily Blood Sampling Room Visits Based on ARIMA and SES Model

Zhang

Xiong

et al. 2020

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

This paper is aimed at establishing a combined prediction model to predict the demand for medical care in terms of daily visits in an outpatient blood sampling room, which provides a basis for rational arrangement of human resources and planning. On the basis of analyzing the comprehensive characteristics of the randomness, periodicity, trend, and day-of-the-week effects of the daily number of blood collections in the hospital, we firstly established an autoregressive integrated moving average model (ARIMA) model to capture the periodicity, volatility, and trend, and secondly, we constructed a simple exponential smoothing (SES) model considering the day-of-the-week effect. Finally, a combined prediction model of the residual correction is established based on the prediction results of the two models. The models are applied to data from 60 weeks of daily visits in the outpatient blood sampling room of a large hospital in Chengdu, for forecasting the daily number of blood collections about 1 week ahead. The result shows that the MAPE of the combined model is the smallest overall, of which the improvement during the weekend is obvious, indicating that the prediction error of extreme value is significantly reduced. The ARIMA model can extract the seasonal and nonseasonal components of the time series, and the SES model can capture the overall trend and the influence of regular changes in the time series, while the combined prediction model, taking into account the comprehensive characteristics of the time series data, has better fitting prediction accuracy than a single model. The new model can well realize the short-to-medium-term prediction of the daily number of blood collections one week in advance.

show abstract

Section: Discussionmentioning

confidence: 99%

Prediction of Daily Blood Sampling Room Visits Based on ARIMA and SES Model

Zhang

Xiong

et al. 2020

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

show abstract

“…Some patients have multiple examinations in the hospital, and some examinations have multiple tasks [19][20][21]. Without proper time control, patients will spend a lot of time waiting.…”

Section: Smart Device Applicationsmentioning

confidence: 99%

A Real-time Approach for Dynamic Scheduling Pet Activities in a Hospital

Chiou

Yaxin

Lin

2020

Preprint

View full text Add to dashboard Cite

Background: At present, medical personnel use manual scheduling methods to calculate usage times of PET devices, hospital beds, operating rooms, and other treatment spaces. However, as patient treatment and recovery times are unequal and uncertain, arriving times of the scheduled/temporary patients are unexpected, examination items, beds requirements, and drugs waiting times are different, and scan-again requirements are unexpected. Manual scheduling arrangements are easy to make mistakes and put pressure on employees. With changing scheduling arrangements, it is difficult to announce the estimated time to patients and their families in real time. As a result, family members keep asking medical staff about various situations and waiting time. This makes the process unstable and exhausts the medical staff. Although previous researches proposed algorithms for specific inspections to solve the equipment resource allocation problems and calculate outpatient visit time for outpatient clinics, there is no research on improving the PET process. This paper proposes a real-time automatic scheduling and control system for PET patients with Bluetooth Beacon positioning. Results: This system can automatically schedule, estimate, and instantly update the start and end time of various tasks of PET patients during examinations, and automatically allocate beds and real-time announce schedule information, allowing the schedule being automated, instant and almost optimized. Moreover, this system promptly reminds medical staffs in each area. This can greatly reduce the work of medical staff, avoid human error, improve the safety of drugs, and provide medical staff, patients and family members to view the inspection progress and estimated waiting time in real time, reducing the number of patients and family members to query medical staff. We implemented this system in an application for the Android system to prove the feasibility of the system. We also collected time data of 200 actual patients for 2 weeks in the Department of Nuclear Medicine of Chang Gung Memorial Hospital, Linkou, and put these data into the implementation program for simulation and comparison. It was found that the average time difference between manual and automatic scheduling was 7.32 minutes, and it could reduce the average examination time of 82% of patients by 6.14 minutes, proving the system's correctness and efficiency. To our knowledge, this paper is the first to propose a real-time automatic scheduling and control system for PET patients.

show abstract

“…However, the relationship between dengue cases and meteorological features is highly complex and cannot be easily fitted by the classical time series model. The deep learning method offers more advantages for the health care field as compared with the traditional statistical model [25][26][27][28], and is being actively applied in the prediction the prevalence of infectious disease dynamics [29,30]. Lee et al showed that artificial neural networks (ANNs) offer a potential benefit in forecasting fluctuations in the mosquito population (especially the extreme values).…”

Section: Introductionmentioning

confidence: 99%

Forecast of Dengue Cases in 20 Chinese Cities Based on the Deep Learning Method

et al. 2020

IJERPH

View full text Add to dashboard Cite

Dengue fever (DF) is one of the most rapidly spreading diseases in the world, and accurate forecasts of dengue in a timely manner might help local government implement effective control measures. To obtain the accurate forecasting of DF cases, it is crucial to model the long-term dependency in time series data, which is difficult for a typical machine learning method. This study aimed to develop a timely accurate forecasting model of dengue based on long short-term memory (LSTM) recurrent neural networks while only considering monthly dengue cases and climate factors. The performance of LSTM models was compared with the other previously published models when predicting DF cases one month into the future. Our results showed that the LSTM model reduced the average the root mean squared error (RMSE) of the predictions by 12.99% to 24.91% and reduced the average RMSE of the predictions in the outbreak period by 15.09% to 26.82% as compared with other candidate models. The LSTM model achieved superior performance in predicting dengue cases as compared with other previously published forecasting models. Moreover, transfer learning (TL) can improve the generalization ability of the model in areas with fewer dengue incidences. The findings provide a more precise forecasting dengue model and could be used for other dengue-like infectious diseases.

show abstract

Combining Deep Neural Networks and Classical Time Series Regression Models for Forecasting Patient Flows in Hong Kong

Cited by 24 publications

References 17 publications

Prediction of Daily Blood Sampling Room Visits Based on ARIMA and SES Model

Prediction of Daily Blood Sampling Room Visits Based on ARIMA and SES Model

A Real-time Approach for Dynamic Scheduling Pet Activities in a Hospital

Forecast of Dengue Cases in 20 Chinese Cities Based on the Deep Learning Method

Contact Info

Product

Resources

About