|
|
condLSTM-Q: A novel deep learning model for predicting COVID-19 mortality in fine geographical scale |
HyeongChan Jo1, Juhyun Kim2, Tzu-Chen Huang3, Yu-Li Ni1( ) |
1. Division of Biology and Biological Engineering, Caltech, Pasadena CA 91125, USA 2. The Division of Physics, Mathematics and Astronomy, Caltech, Pasadena CA 91125, USA 3. Walter Burke Institute for Theoretical Physics, Caltech, Pasadena CA 91125, USA |
|
|
Abstract Background: Modern machine learning-based models have not been harnessed to their total capacity for disease trend predictions prior to the COVID-19 pandemic. This work is the first use of the conditional RNN model in predicting disease trends that we know of during development that complemented classical epidemiological approaches. Methods: We developed the long short-term memory networks with quantile output (condLSTM-Q) model for making quantile predictions on COVID-19 death tolls. Results: We verified that the condLSTM-Q was accurately predicting fine-scale, county-level daily deaths with a two-week window. The model’s performance was robust and comparable to, if not slightly better than well-known, publicly available models. This provides unique opportunities for investigating trends within the states and interactions between counties along state borders. In addition, by analyzing the importance of the categorical data, one could learn which features are risk factors that affect the death trend and provide handles for officials to ameliorate the risks. Conclusion: The condLSTM-Q model performed robustly, provided fine-scale, county-level predictions of daily deaths with a two-week window. Given the scalability and generalizability of neural network models, this model could incorporate additional data sources with ease and could be further developed to generate other valuable predictions such as new cases or hospitalizations intuitively.
|
Keywords
COVID-19
machine learning
deep learning
epidemiology
time series forecast
|
Corresponding Author(s):
Yu-Li Ni
|
Online First Date: 15 June 2022
Issue Date: 07 July 2022
|
|
1 |
IHME COVID-19 health service utilization forecasting team, C. J. Murray. ( 2020) Forecasting COVID-19 impact on hospital bed-days, ICU-days, ventilator-days and deaths by US state in the next 4 months. medRxiv, doi:
|
2 |
Y. Abu-Mostafa. ( 2020) Caltech CS156 COVID-19 Model. . Accessed: Accessed: February 1, 2021
|
3 |
N., Khan, S., Shahid, L., Juneng, K., Ahmed, T. Ismail, ( 2019). Prediction of heat waves in Pakistan using quantile regression forests. Atmos. Res., 221 : 1– 11
https://doi.org/10.1016/j.atmosres.2019.01.024
|
4 |
A., Brennan P. C. Cross. ( 2015) Managing more than the mean: using quantile regression to identify factors related to large elk groups. J. Appl. Ecol., 52, 1656– 1664
|
5 |
IHME. ( 2020) Institute for health metrics and evaluation COVID-19 estimate. . Accessed: February 1, 2021
|
6 |
S. Hochreiter. ( 1997) Long short-term memory. Neural Comput., 9, 1735– 1780
|
7 |
R., Pal, A. A., Sekh, S. Kar, D. Prasad, ( 2020). Neural network based country wise risk prediction of COVID-19. Appl. Sci. (Basel), 10 : 6448
https://doi.org/10.3390/app10186448
|
8 |
P., Melin J. C., Monica D. Sanchez. ( 2020) Multiple ensemble neural network models with fuzzy response aggregation for predicting COVID-19 time series: The case of Mexico. Healthcare (Basel), 8, 181
|
9 |
Rémy. ( 2020) Conditional RNNs made easy with Tensorflow and Keras. . Accessed: February 1, 2021
|
10 |
A. Karpathy, ( 2015). Deep visual-semantic alignments for generating image descriptions. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3128– 3137
https://doi.org/10.1109/CVPR.2015.7298932
|
11 |
L. Breiman, ( 2001). Random forests. Mach. Learn., 45 : 5– 32
https://doi.org/10.1023/A:1010933404324
|
12 |
A., Fisher C. Rudin. ( 2019) All models are wrong, but many are useful: Learning a variable’s importance by studying an entire class of prediction models simultaneously. J. Mach. Learn Res., 20, 177
|
13 |
Analytics ( 2020) DELPHI Model. . Accessed: February 1, 2021
|
14 |
Alamos National Laboratory Los. ( 2020) LANL Model. . Accessed: February 1, 2021
|
15 |
W. Tan. ( 2020) The cardiovascular burden of coronavirus disease 2019 (COVID-19) with a focus on congenital heart disease. Int. J. Cardiol., 309, 70– 77
|
16 |
R., Chen W., Liang M., Jiang W., Guan C., Zhan T., Wang C., Tang L., Sang J., Liu Z., Ni, ( 2020) Risk factors of fatal outcome in hospitalized subjects with coronavirus disease 2019 from a nationwide analysis in China. Chest, 158, 97– 105
|
17 |
Y., Chen X., Gong L. Wang. ( 2020) Effects of hypertension, diabetes and coronary heart disease on COVID-19 diseases severity: a systematic review and meta-analysis. medRxiv, doi:
|
18 |
C., Chen C., Chen J. T., Yan N., Zhou J. P. Zhao D. Wang. ( 2020) Analysis of myocardial injury in patients with COVID-19 and association between concomitant cardiovascular diseases and severity of COVID-19. Zhonghua Xin Xue Guan Bing Za Zhi (in Chinese), 48, 567– 571
|
19 |
Y., Zhang H., Tian Y. Zhang. ( 2020) Is the epidemic spread related to GDP? Visualizing the distribution of COVID-19 in Chinese mainland. arXiv, 2004.04387
|
20 |
Bureau of Economic Analysis (BEA) U.S.. ( 2020) Local area gross domestic product, 2018. . Accessed: February 1, 2021
|
21 |
Institutes of Health National. ( 2019) COVID-19 treatment guidelines panel. Coronavirus disease 2019 (COVID-19) treatment guidelines. National Institutes of Health. . Accessed: February 1, 2021
|
22 |
U.S. Food and Drug Administration Pfizer-BioNTech COVID-19 Vaccine. . Accessed: February 1, 2021
|
23 |
for Disease Control Centers. COVID-19 vaccinations in the United States. . Accessed: February 1, 2021
|
24 |
Covidvis team The. ( 2020) Covidvis. . Accessed: February 1, 2021
|
25 |
for Disease Control Centers. ( 2020) Pneumonia and influenza mortality surveillance from the national center for health statistics mortality surveillance system. . Accessed: February 1, 2021
|
26 |
H. Zimmermann C. Tietz. ( 2012) Forecasting with recurrent neural networks: 12 tricks. In Neural Networks: Tricks of the Trade. pp. 687– 707. Springer
|
27 |
D. P. Kingma. ( 2017) Adam: A Method for Stochastic Optimization. arXiv, 1412.6980
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
|
Shared |
|
|
|
|
|
Discussed |
|
|
|
|