Deep Learning-Based Patient Visits Forecasting Using Long Short Term Memory

Predicting the number of patient visits to hospitals has been acknowledged remarkably helpful in the decision-making related to allocating limited human and material resources of hospitals. More accurate its prediction can contribute to higher efficiency of hospital management without any doubt. This study proposes Long Short Term Memory (LSTM) method to predict the number of patient visits to a community health center in South Tangerang City on a monthly basis. LSTM is chosen because it is known to perform well in time series data. Toward a fair evaluation, the performance of the proposed model is compared to the AutoRegressive Integrated Moving Average (ARIMA), simple exponential smoothing, linear regression, and conventional artificial neural networks. The results show that the proposed LSTM model surpasses the benchmark methods with a Mean Absolute Percentage Error (MAPE) value of 4.714.

[1]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[2]  Muhammad Ali Syakur,et al.  Method Extreme Learning Machine for Forecasting Number of Patients’ Visits in Dental Poli (A Case Study: Community Health Centers Kamal Madura Indonesia) , 2018 .

[3]  Ling Tang,et al.  Forecasting Patient Visits to Hospitals using a WD&ANN-based Decomposition and Ensemble Model , 2017 .

[4]  Adhistya Erna Permanasari,et al.  Predicting the Amount of Digestive Enzymes Medicine Usage with LSTM , 2018 .

[5]  G. Hejblum,et al.  A systematic review of models for forecasting the number of emergency department visits , 2009, Emergency Medicine Journal.

[6]  Wang-Chuan Juang,et al.  Application of time series analysis in modelling and forecasting emergency department visits in a medical centre in Southern Taiwan , 2017, BMJ Open.

[7]  Varun Dutt,et al.  Using LSTMs for Predicting Patient's Expenditure on Medications , 2017, 2017 International Conference on Machine Learning and Data Science (MLDS).

[8]  Jitendra Kumar,et al.  Long Short Term Memory Recurrent Neural Network (LSTM-RNN) Based Workload Forecasting Model For Cloud Datacenters , 2018 .

[9]  Li Luo,et al.  Hospital daily outpatient visits forecasting using a combinatorial model based on ARIMA and SES models , 2017, BMC Health Services Research.

[10]  Morten Hertzum,et al.  Forecasting Hourly Patient Visits in the Emergency Department to Counteract Crowding , 2017 .

[11]  Flavio S. Fogliatto,et al.  Forecasting Daily Volume and Acuity of Patients in the Emergency Department , 2016, Comput. Math. Methods Medicine.

[12]  S. Hajat,et al.  Forecasting daily emergency department visits using calendar variables and ambient temperature readings. , 2013, Academic emergency medicine : official journal of the Society for Academic Emergency Medicine.

[13]  Farid Kadri,et al.  Time Series Modelling and Forecasting of Emergency Department Overcrowding , 2014, Journal of Medical Systems.

[14]  Fernando Luiz Cyrino Oliveira,et al.  Time series analysis with explanatory variables: A systematic literature review , 2018, Environ. Model. Softw..

[15]  Wei Jiang,et al.  A Hybrid Approach for Forecasting Patient Visits in Emergency Department , 2016, Qual. Reliab. Eng. Int..

[16]  Ting Zhu,et al.  Time-Series Approaches for Forecasting the Number of Hospital Daily Discharged Inpatients. , 2017 .

[17]  Jochen Bergs,et al.  Knowing what to expect, forecasting monthly emergency department visits: A time-series analysis. , 2014, International emergency nursing.