Deep Learning Models to Analyze the Non-Linear-Lag Effect of Environmental Factors on the Occurrence of Schizophrenia
Keywords:
Deep neural networks, time series analysis, lag effect, distributed lag nonlinear model, environmental factorsAbstract
In recent years, the distributed lag non-linear Model(DLNM) has dominated over other techniques for measuring risk in environmental epidemiology. The impact of air pollutants or climate factors on schizophrenia is evident from the literature. This study aims to examine the influence of pollution and climate-related variables on the frequency of hospital admissions for individuals diagnosed with schizophrenia. We used DLNM and deep neural networks(DNNs) to explore the non-linear relationship between environmental variables and schizophrenia admissions in Bangalore City, India. The outcomes derived from the DLNM model reveal that the optimal forecast for hospital emergency visits is achieved with a lag of 3 days, resulting in a maximum RR value of 1.6 (95% confidence interval). Subsequently, DNN models, including the Convolutional Neural Network(CNN), hybrid CNN-LSTM, Long Short-Term Memory(LSTM), and the Gated Recurrent Unit(GRU), were employed, each with varying time steps, in the pursuit of refining predictive accuracy. These predictive models are evaluated by mean absolute error(MAE), the mean absolute percentage error(MAPE), mean square error(MSE), the root of mean square error(RMSE), and Symmetric Mean Absolute Percentage(SMAPE). We found results of deep learning models are consistent with the results of DLNM in predicting the number of admissions based on short-term environmental exposure. The short-term exposure-response relationship is evident in all models and it is proved through sensitivity analysis. CNN and GRU models have better performance than other models by using sigmoid activation functions. The CNN and GRU resulted with the lowest MAE(0.46, 0.49), MAPE(35.5%, 34.7%) and RMSE(0.73, 0.75).
Downloads
References
Yolton K, Khoury JC, Burkle J, LeMasters G et al. (2019) Lifetime exposure to traffic-related air pollution and symptoms of depression and anxiety at age 12 years. Environmental Research, 173, 199-206.
Xu H, Jia Y, Sun Z, Su J, Liu Q S et.al (2022) Environmental pollution, a hidden culprit for health issues. Eco-Environment & Health, 1(1), 31-45.
Yackerson N S, Zilberman A, Todder D, Kaplan Z (2014) The influence of air-suspended particulate concentration on the incidence of suicide attempts and exacerbation of schizophrenia. International journal of biometeorology, 58, 61-67.
Qiu H, Tak-sun Yu I, Tse LA, Tian L, Wang X and Wong TW (2013) Is greater temperature change within a day associated with increased emergency hospital admissions for heart failure?. Circulation: Heart Failure, 6(5), pp.930-935.
Wang S, Zhang X, Xie M, Zhao D, Zhang H et al. (2018) Effect of increasing temperature on daily hospital admissions for schizophrenia in Hefei, China: a time-series analysis. Public Health, 159, pp.70-77.
Engemann K, Pedersen CB, Arge L, Tsirogiannis C et.al (2018) Childhood exposure to green space–a novel risk-decreasing mechanism for schizophrenia. Schizophrenia research, 199, 142-148.
Ji Y, Liu B, Song J, Pan R, Cheng J, Wang H, & Su H (2022). Short-term effects and economic burden assessment of ambient air pollution on hospitalizations for schizophrenia. Environmental Science and Pollution Research, 29(30), 45449–45460.
Eguchi R, Onozuka D, Ikeda K, Kuroda K et.al (2018) The relationship between fine particulate matter (PM 2.5) and schizophrenia severity. International archives of occupational and environmental health, 91, 613-622.
Shiloh R, Shapira A, Potchter O, Hermesh H et.al (2005) Effects of climate on admission rates of schizophrenia patients to psychiatric hospitals. European Psychiatry, 20(1), 61-64.
Duan J, Cheng Q, Luo X, Bai L, Zhang H, Wang S, et al. (2018). Is the serious ambient air pollution associated with increased admissions for schizophrenia?. Science of the total environment, 644, pp.14-19.
Song R, Liu L, Wei N, Li X, Liu J et al. (2023) Short-term exposure to air pollution is an emerging but neglected risk factor for schizophrenia: A systematic review and meta-analysis. Science of The Total Environment, 854, p.158823.
Gasparrini A (2016) Modelling lagged associations in environmental time series data: a simulation study. Epidemiology, 27, 835-842.
Pan R, Zhang X, Gao J, Yi W, Wei Q et al. (2019). Impacts of heat and cold on hospitalizations for schizophrenia in Hefei, China: an assessment of disease burden. Science of the Total Environment, 694, 133582.
Zhao D, Zhang X, Xie M, Cheng, Zhang H et al. (2016). Is greater temperature change within a day associated with increased emergency admissions for schizophrenia? Science of The Total Environment, 566, 1545-1551.
Liang Z, Xu C, Cao Y, Kan HD, Chen RJ (2019) The association between short-term ambient air pollution and daily outpatient visits for schizophrenia: A hospital-based study. Environmental Pollution. 244, pp.102-108.
Bai L, Yang J, Zhang Y, Zhao D & Su H (2020). Durational effect of particulate matter air pollution wave on hospital admissions for schizophrenia. Environmental Research, 187, 109571.
Crank PJ, Hondula DM, & Sailor DJ (2023). Mental health and air temperature: Attributable risk analysis for schizophrenia hospital admissions in arid urban climates. Science of The Total Environment, 862, 160599.
Qiu X, Danesh-Yazdi M, Wei Y, Di Q et al. (2022). Associations of short-term exposure to air pollution and increased ambient temperature with psychiatric hospital admissions in older adults in the USA: a case–crossover study. The Lancet Planetary Health, 6(4), e331–e341.
Qiu X, Wei Y, Weisskopf M, Spiro A, Shi L, Castro E et al. (2023). Air pollution, climate conditions and risk of hospital admissions for psychotic disorders in U.S. residents. Environmental Research, 216, 114636.
Gu S, Huang R, Yang J, Sun S, Xu Y, et al. (2019) Exposure-lag-response association between sunlight and schizophrenia in Ningbo, China. Environmental Pollution, 247, 285-292.
Almeida JS (2002). Predictive non-linear modeling of complex data by artificial neural networks. Current opinion in biotechnology, 13(1), 72-76.
Larochelle H, Bengio Y, Louradour J, & Lamblin P (2009). Exploring strategies for training deep neural networks. Journal of machine learning research, 10(1).
Mishra S, Bordin C, Taharaguchi K, & Palu I (2020). Comparison of deep learning models for multivariate prediction of time series wind power generation and temperature. Energy Reports, 6, 273-286.
Sung TI, Chen MJ, Lin CY, Lung SC and Su HJ (2011) Relationship between mean daily ambient temperature range and hospital admissions for schizophrenia: results from a national cohort of psychiatric inpatients. Science of the total environment, 410, pp.41-46.
Dolado JJ, Gonzalo J, & Mayoral L (2002). A fractional Dickey–Fuller test for unit roots. Econometrica, 70(5), 1963-2006.
Gasparrini A, Armstrong B and Kenward MG (2010) Distributed lag non‐linear models. Statistics in medicine, 29(21), pp.2224-2234.
Mode GR, Hoque KA (2020). Adversarial examples in deep learning for multivariate time series regression. In 2020 IEEE Applied Imagery Pattern Recognition Workshop (AIPR) (pp. 1-10). IEEE.
Chung H, & Shin KS (2020). Genetic algorithm-optimized multi-channel convolutional neural network for stock market prediction. Neural Computing and Applications, 32, 7897-7914.
Surakhi O, Zaidan MA, Fung PL, Hossein Motlagh N et al. (2021). Time-lag selection for time-series forecasting using neural network and heuristic algorithm. Electronics, 10(20), 2518.
Wan R, Mei S, Wang J, Liu M, & Yang F (2019). Multivariate temporal convolutional network: A deep neural networks approach for multivariate time series forecasting. Electronics, 8(8), 876.
Dai H, Huang G, Wang J, Zeng H & Zhou F (2021). Prediction of air pollutant concentration based on one-dimensional multi-scale CNN-LSTM considering spatial-temporal characteristics: A case study of Xi’an, China. Atmosphere, 12(12), 1626.
Nwankpa C, Ijomah W, Gachagan A & Marshall S (2018). Activation functions: Comparison of trends in practice and research for deep learning. arXiv preprint arXiv:1811.03378.
Lu J, Bu P, Xia X, Yao L et al. (2020). A new deep learning algorithm for detecting the lag effect of fine particles on hospital emergency visits for respiratory diseases. IEEE Access, 8, 145593-145600.
Hossain I, Rasel HM, Imteaz MA, & Mekanik F (2020). Long-term seasonal rainfall forecasting using linear and non-linear modelling approaches: a case study for Western Australia. Meteorology and Atmospheric Physics, 132, 131-141.
Zhu H, Chen S, Lu W, Chen K, Feng Y et al. (2022). Study on the influence of meteorological factors on influenza in different regions and predictions based on an LSTM algorithm. BMC Public Health, 22(1), 1-17.
Mahmudimanesh M, Mirzaee M, Dehghan A, & Bahrampour A (2022). Forecasts of cardiac and respiratory mortality in Tehran, Iran, using ARIMAX and CNN-LSTM models. Environmental Science and Pollution Research, 29(19), 28469-28479.
Jahan S, Wraith D, Dunne MP, & Naish S (2021). Assessing evidence for seasonality of hospital admissions for schizophrenia in Queensland, Australia: a time series observational study. International journal of biometeorology, 65(12), 2025-2035.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
