A New Deep Learning Algorithm for Detecting the Lag Effect of Fine Particles on Hospital Emergency Visits for Respiratory Diseases

Abstract

There exists a time lag between short-term exposure to fine particulate matter (PM 2.5) and incidence of respiratory diseases. The quantification of length of the time lag is significant for preparation and allocation of relevant medical resources. Several classic lag analysis methods have been applied to determine this length. However, different models often lead to distinct results and which one is better is subtle. The prerequisite of obtaining the reliable length is that the model can truly reveal the underlying pattern hidden in the above relationship. Long short-term memory (LSTM) is an artificial recurrent neural network (RNN) architecture used in the field of deep learning, whose strong capability makes it widely applied in many fields. In this study, we manage to exploit it to acquire the time-lag length in the exposure-response relationship. The relationship between exposure and response is assumed as linear and non-linear, and models with and without confounding factors are performed under these two assumptions. Results of DLNM model show that the best hospital emergency visit prediction appears in 3 lag days, with the maximum RR value of 1.004357 (95% CI: 1.000938-1.009563). Then, a vary of LSTM models with different time steps are performed, which are evaluated by mean absolute error (MAE), the mean absolute percentage error (MAPE), the root of mean square error (RMSE) and R square (R 2). The results show that LSTM of time step 3 achieves the lowest MAE (33), MAPE (9.86), RMSE (42) and the highest R 2 (0.78), consistent with the result of DLNM model. Also, the proposed model is compared with ARIMA model, one of the commonly used forecasting models, showing better accuracy. This demonstrates that LSTM can be used as a new method to detect the lag effect of PM 2.5 on respiratory diseases.

Machine Learning Models for Predicting the Occurrence of Respiratory Diseases Using Climatic and Air-Pollution Factors

“…For the occurrence of respiratory diseases, there exist a few previous studies that applied machine learning to produce forecasting models using air-pollution factors. Long short-term memory, which is a type of artificial recurrent neural network, was applied to analyze the lag effect of fine particles (particulate matter ≤2.5 µm in aerodynamic diameter [PM 2.5 ]) on the frequency of hospital emergency visits for respiratory diseases [ 5 ]. A multilayer perceptron using levels of particulate matter (PM 2.5 and PM 10 ) was also proposed for predicting outpatient visits for upper respiratory tract infections [ 6 ].…”

State feedback control for human inspiratory system

“…The value of 𝑘 𝑟 does effect on the solution of steady state but does not affect on the system stability. The output of steady state and equilibrium point for the closed loop system are written as (15),…”

“…Lu et al [15] have designed a model for time lag between exposure of short term to fine particular matter (PM22) and to determine this length by artificial recurrent neural network with long short term memory used in the field of deep learning. They managed to achieve it to obtain the length of time lag in the relationship of exposure response.…”

Time Series Prediction about Air Quality using LSTM-Based Models: A Systematic Mapping

“…-The main prediction problems were in relation to PM 2.5 , Figure 1 shows the relationships of the predictions made in the studies. Standing out [ Lu et al 2020] for making predictions of the lag effect of pollutants on respiratory diseases, and [Liu et al 2019] for using predictions to treat haze-fog problems.…”