Forecasting Patient Visits to Hospitals using a WD&amp;amp;ANN-based Decomposition and Ensemble Model

Yu, Lean; Hang, Geye; Tang, Ling; Zhao, Yiwen; Lai, Kin Keung

doi:10.12973/ejmste/80308

Cited by 15 publications

(8 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These predictions involve patients not just in the ED but in other departments which have different process flows, service times and lengths-of-stay (LOS). ML based models overcome this input complexity by using relevant factors as predictors [ 25 ].…”

Section: Literature Reviewmentioning

confidence: 99%

“…Depending on the type of strategic decision-making time horizon, there are different models developed for predicting inpatient demand. Longer term strategy needs give rise to models that predict monthly forecasts [ 25 ]. More immediate strategies need to give rise to models with shorter horizons like the next 3, 5, or 7 days [ 24 ].…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Machine learning based forecast for the prediction of inpatient bed demand

Tello

Reich

Puckey

et al. 2022

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

Background Overcrowding is a serious problem that impacts the ability to provide optimal level of care in a timely manner. High patient volume is known to increase the boarding time at the emergency department (ED), as well as at post-anesthesia care unit (PACU). Furthermore, the same high volume increases inpatient bed transfer times, which causes delays in elective surgeries, increases the probability of near misses, patient safety incidents, and adverse events. Objective The purpose of this study is to develop a Machine Learning (ML) based strategy to predict weekly forecasts of the inpatient bed demand in order to assist the resource planning for the ED and PACU, resulting in a more efficient utilization. Methods The data utilized included all adult inpatient encounters at Geisinger Medical Center (GMC) for the last 5 years. The variables considered were class of inpatient encounter, observation, or surgical overnight recovery (SORU) at the time of their discharge. The ML based strategy is built using the K-means clustering method and the Support Vector Machine Regression technique (K-SVR). Results The performance obtained by the K-SVR strategy in the retrospective cohort amounts to a mean absolute percentage error (MAPE) that ranges between 0.49 and 4.10% based on the test period. Additionally, results present a reduced variability, which translates into more stable forecasting results. Conclusions The results from this study demonstrate the capacity of ML techniques to forecast inpatient bed demand, particularly using K-SVR. It is expected that the implementation of this model in the workflow of bed capacity management will create efficiencies, which will translate in a more reliable, inexpensive and timely care for patients.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

Machine learning based forecast for the prediction of inpatient bed demand

Tello

Reich

Puckey

et al. 2022

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

show abstract

“…Demand forecast has been studied in many areas, such as energy [17,18], tourism [19,20], supply chain [21], traffic [22,23], and healthcare [24][25][26][27][28][29][30]. In the area of healthcare, most of the demand forecast focused on emergency department (ED).…”

Section: Literature Reviewmentioning

confidence: 99%

Forecasting Teleconsultation Demand with an Ensemble Attention-Based Bidirectional Long Short-Term Memory Model

Chen¹,

Yu²,

Li³

2021

IJCIS

Self Cite

View full text Add to dashboard Cite

Accurate demand forecast can help improve teleconsultation efficiency. But teleconsultation demand forecast has not been reported in existing literature. For this purpose, the study proposes a novel model based on deep learning algorithm for daily teleconsultation demand forecast to fill in the research gap. Because of the significant effect of holidays on teleconsultation demand, holiday-related variables, and specific prediction technologies were selected to treat it. The technologies attention mechanism and bidirectional long short-term memory (BILSTM) were used to construct a novel forecasting methodology, i.e., ensemble attention-based BILSTM (EA-BILSTM), for the accurate forecasts. Based on actual teleconsultation data, the effectiveness of variable selection is verified by importing different inputs into models, and the superiority of EA-BILSTM is verified by comparison with nine benchmark models. Empirical results show that importing selected variables can lead to better forecasts and EA-BILSTM model can get lowest forecasting errors on two sub-datasets. This indicates that the proposed forecasting model is a high potential approach for teleconsultation demand prediction in the influence of sparse trait, like holiday effects.

show abstract

“…Forecasting Out-Patient Department (OPD) visits in healthcare centres have increasingly induced large interest in both theoretical and applied perspectives [1]. Accurately forecasting the number of patient visits in hospitals is key in the administration of human capital as well as essential equipment and materials resources of the hospital [2].…”

Section: Introductionmentioning

confidence: 99%

Modelling Dynamic Behaviour of Out-Patient Department Visits at the University of Cape Coast Hospital Using Time Series Analysis

Bakr

Prah

Nkrumah

et al. 2021

JAMCS

View full text Add to dashboard Cite

Background: Accurate and reliable forecasting of outpatient department visits enhances decision-making and planning for future healthcare demands and is the foundation for greater and better utilization of healthcare resources and increased levels of outpatient care and satisfaction. Though the literature has proposed several candidate models for predicting outpatient visits in some hospitals in Ghana, the model regulating outpatient visits at the University of Cape Coast Hospital (UCC) is unknown. There is therefore a need to determine the best model applicable to the specific case of UCC Hospital. Aim: This study sought to determine and model the dynamics of outpatient visits in UCC Hospital and to project outpatient healthcare demands at the facility for the period July 2021 to July 2024. Methods: This paper employed a monthly periodicity of 114-time series data sourced from District Health Information Management Systems Two (DHIMS 2) on outpatient department visits at UCC Hospital from January 2012 to June 2021. The autoregressive integrated moving average (ARIMA) models which are a form of the classical Box-Jenkins approach of Time Series Analysis were used to analyse the data. Analysis was performed in EViews 12. Results: The study results showed twenty-five non-seasonal tentative models for the hospital and ARIMA (4, 1, 4) was selected as the best fit model with a fourth-order autoregressive and moving average terms each and one order of nonseasonal differencing. Residual analysis of the fitted model indicates that the model is adequate for forecasting. The findings revealed an overall rising trend in the incidence of outpatient department visits to the hospital over the study period with an average of 6000 visits per month. This is expected to increase to over 7000 visits per month over the next three-year period of July 2021 to June 2024 according to projections. Conclusion: The forecast of outpatient visits in this study serves as early signals to the management of the University hospital and is intended to enhance human and material resource planning and allocation for better-quality healthcare delivery.

show abstract

Forecasting Patient Visits to Hospitals using a WD&ANN-based Decomposition and Ensemble Model

Cited by 15 publications

References 46 publications

Machine learning based forecast for the prediction of inpatient bed demand

Machine learning based forecast for the prediction of inpatient bed demand

Forecasting Teleconsultation Demand with an Ensemble Attention-Based Bidirectional Long Short-Term Memory Model

Modelling Dynamic Behaviour of Out-Patient Department Visits at the University of Cape Coast Hospital Using Time Series Analysis

Contact Info

Product

Resources

About