1
|
Chen Y, Huang L, Xie X, Liu Z, Hu J. Improved prediction of hourly PM 2.5 concentrations with a long short-term memory and spatio-temporal causal convolutional network deep learning model. THE SCIENCE OF THE TOTAL ENVIRONMENT 2024; 912:168672. [PMID: 38016563 DOI: 10.1016/j.scitotenv.2023.168672] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/05/2023] [Revised: 11/15/2023] [Accepted: 11/16/2023] [Indexed: 11/30/2023]
Abstract
Accurate prediction of particulate matter with aerodynamic diameter ≤ 2.5 μm (PM2.5) is important for environmental management and human health protection. In recent years, many efforts have been devoted to develop air quality predictions using the machine learning and deep learning techniques. In this study, we propose a deep learning model for short-term PM2.5 predictions. The salient feature of the proposed model is that the convolution in the model architecture is causal, where the output of a time step is only convolved with components of the same or earlier time step from the previous layer. The model also weighs the spatial correlation between multiple monitoring stations. Through temporal and spatial correlation analysis, relevant information is screened from the monitoring stations with a strong relationship with the target station. Information from the target and related sites is then taken as input and fed into the model. A case study is conducted in Nanjing, China from January 1, 2020 to December 31, 2020. Using historical air quality and meteorological data from nine monitoring stations, the model predicts PM2.5 concentrations for the next hour. The experimental results show that the predicted PM2.5 concentrations are consistent with observation, with correlation coefficient (R2) and Root Mean Squared Error (RMSE) of our model are 0.92 and 6.75 μg/m3. Additionally, to better understand the factors affecting PM2.5 levels in different seasons, a machine learning algorithm based on Principal Component Analysis (PCA) is used to analyze the correlations between PM2.5 and its influencing factors. By identifying the main factors affecting PM2.5 and optimizing the input of the predictive model, the application of PCA in the model further improves the prediction accuracy, with decrease of up to 17.2 % in RMSE and 38.6 % in mean absolute error (MAE). The deep learning model established in this study provide a valuable tool for air quality management and public health protection.
Collapse
Affiliation(s)
- Yinsheng Chen
- Jiangsu Key Laboratory of Atmospheric Environment Monitoring and Pollution Control, Collaborative Innovation Center of Atmospheric Environment and Equipment Technology, Nanjing University of Information Science & Technology, Nanjing 210044, China
| | - Lin Huang
- Jiangsu Key Laboratory of Atmospheric Environment Monitoring and Pollution Control, Collaborative Innovation Center of Atmospheric Environment and Equipment Technology, Nanjing University of Information Science & Technology, Nanjing 210044, China.
| | - Xiaodong Xie
- Jiangsu Key Laboratory of Atmospheric Environment Monitoring and Pollution Control, Collaborative Innovation Center of Atmospheric Environment and Equipment Technology, Nanjing University of Information Science & Technology, Nanjing 210044, China
| | - Zhenxin Liu
- Jiangsu Key Laboratory of Atmospheric Environment Monitoring and Pollution Control, Collaborative Innovation Center of Atmospheric Environment and Equipment Technology, Nanjing University of Information Science & Technology, Nanjing 210044, China
| | - Jianlin Hu
- Jiangsu Key Laboratory of Atmospheric Environment Monitoring and Pollution Control, Collaborative Innovation Center of Atmospheric Environment and Equipment Technology, Nanjing University of Information Science & Technology, Nanjing 210044, China.
| |
Collapse
|
2
|
Yang M, Li L. Remimazolam attenuates inflammation in bronchopneumonia through the inhibition of NLRP3 activity by PDPK1 ubiquitination. Chem Biol Drug Des 2024; 103:e14438. [PMID: 38230783 DOI: 10.1111/cbdd.14438] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/18/2023] [Revised: 12/12/2023] [Accepted: 12/18/2023] [Indexed: 01/18/2024]
Abstract
Bronchopneumonia is the most common pneumonia in childhood. Therefore, we tested the effects of Remimazolam presented Bronchopneumonia and its possible mechanisms. Phillygenin increased survival rate, reduced W/D ratio, and lung injury score, and inhibited IL-1β, IL-6, TNF-α, and INF-γ levels in mice model of bronchopneumonia. Remimazolam induced PDPK1 and p-AKT protein expressions, and suppressed NLRP3 protein expression in lung tissue of mice model. In vitro model, Remimazolam also induced PDPK1 and p-AKT protein expressions, and suppressed NLRP3 protein expression. Remimazolam also inhibited inflammation levels in vitro model. PDPK1 inhibitor, PHT-427 (100 mg/kg) reduced survival rate, increased W/D ratio and lung injury score, and promoted inflammation levels in mice model of bronchopneumonia by treated with Remimazolam. PHT-427 suppressed PDPK1 and p-AKT protein expressions and induced NLRP3 protein expression in mice model of bronchopneumonia by treated with Remimazolam. Remimazolam interlinked PDPK1 protein. Remimazolam increased the expressions of PDPK1 and p-AKT in vitro model. Remimazolam reduced PDPK1 ubiquitination in vitro model.
Collapse
Affiliation(s)
- Min Yang
- Department of Anesthesiology, The Central Hospital of Enshi Tujia and Miao Autonomous Prefecture, Enshi City, China
| | - Ling Li
- Department of Pediatrics, The Central Hospital of Enshi Tujia and Miao Autonomous Prefecture, Enshi City, China
| |
Collapse
|
3
|
Lai FL, Gao F. LSA-ac4C: A hybrid neural network incorporating double-layer LSTM and self-attention mechanism for the prediction of N4-acetylcytidine sites in human mRNA. Int J Biol Macromol 2023; 253:126837. [PMID: 37709212 DOI: 10.1016/j.ijbiomac.2023.126837] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/05/2023] [Revised: 08/08/2023] [Accepted: 09/01/2023] [Indexed: 09/16/2023]
Abstract
N4-acetylcytidine (ac4C) is a vital constituent of the epitranscriptome and plays a crucial role in the regulation of mRNA expression. Numerous studies have established correlations between ac4C and the incidence, progression and prognosis of various cancers. Therefore, accurately predicting ac4C sites is an important step towards comprehending the biological functions of this modification and devising effective therapeutic interventions. Wet experiments are primary methods for studying ac4C, but computational methods have emerged as a promising supplement due to their cost-effectiveness and shorter research cycles. However, current models still have inherent limitations in terms of predictive performance and generalization ability. Here, we utilized automated machine learning technology to establish a reliable baseline and constructed a deep hybrid neural network, LSA-ac4C, which combines double-layer Long Short-Term Memory (LSTM) and self-attention mechanism for accurate ac4C sites prediction. Benchmarking comparisons demonstrate that LSA-ac4C exhibits superior performance compared to the current state-of-the-art method, with ACC, MCC and AUROC improving by 2.89 %, 5.96 % and 1.53 %, respectively, on an independent test set. Overall, LSA-ac4C serves as a powerful tool for predicting ac4C sites in human mRNA, thus benefiting research on RNA modification. For the convenience of the research community, a web server has been established at http://tubic.org/ac4C.
Collapse
Affiliation(s)
- Fei-Liao Lai
- Department of Physics, School of Science, Tianjin University, Tianjin 300072, China
| | - Feng Gao
- Department of Physics, School of Science, Tianjin University, Tianjin 300072, China; Frontiers Science Center for Synthetic Biology and Key Laboratory of Systems Bioengineering (Ministry of Education), Tianjin University, Tianjin 300072, China; SynBio Research Platform, Collaborative Innovation Center of Chemical Science and Engineering (Tianjin), Tianjin 300072, China.
| |
Collapse
|
4
|
Chang M, Ku Y. LSTM model for predicting the daily number of asthma patients in Seoul, South Korea, using meteorological and air pollution data. ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH INTERNATIONAL 2023; 30:37440-37448. [PMID: 36574119 DOI: 10.1007/s11356-022-24956-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/29/2022] [Accepted: 12/20/2022] [Indexed: 06/18/2023]
Abstract
Asthma is a common respiratory disease that is affected by air pollutants and meteorological factors. In this study, we developed models that predict the daily number of patients receiving treatment for asthma using air pollution and meteorological data. A neural network with long short-term memory (LSTM) and fully connected (FC) layers was used. The daily number of asthma patients in the city of Seoul, the capital of South Korea, was collected from the National Health Insurance Service. The data from 2015 to 2018 were used as the training and validation datasets for model development. Unseen data from 2019 were used for testing. The daily number of asthma patients per 100,000 inhabitants was predicted. The LSTM-FC neural network model achieved a Pearson correlation coefficient of 0.984 (P < 0.001) and root mean square error of 3.472 between the predicted and original values on the unseen testing dataset. The factors that impacted the prediction were the number of asthma patients in the previous time step before the predicted date, type of day (regular day and day after a holiday), minimum temperature, SO2, daily changes in the amount of cloud, and daily changes in diurnal temperature range. We successfully developed a neural network that predicts the onset and exacerbation of asthma, and we identified the crucial influencing air pollutants and meteorological factors. This study will help us to establish appropriate measures according to the daily predicted number of asthma patients and reduce the daily onset and exacerbation of asthma in the susceptible population.
Collapse
Affiliation(s)
- Munyoung Chang
- Department of Otorhinolaryngology-Head and Neck Surgery, Chung-Ang University College of Medicine, 84 Heukseok-Ro, Dongjak-Gu, 06974, Seoul, South Korea.
- Department of Electrical and Computer Engineering, Seoul National University, 1 Gwanak-Ro, Gwanak-Gu, 08826, Seoul, South Korea.
| | - Yunseo Ku
- Department of Biomedical Engineering, Chungnam National University College of Medicine, 99 Daehak-Ro, Yuseong-Gu, 34134, Daejeon, South Korea
| |
Collapse
|
5
|
Gao F, Lu DC, Zheng TL, Geng S, Sha JC, Huang OY, Tang LJ, Zhu PW, Li YY, Chen LL, Targher G, Byrne CD, Huang ZF, Zheng MH. Fully connected neural network-based serum surface-enhanced Raman spectroscopy accurately identifies non-alcoholic steatohepatitis. Hepatol Int 2022; 17:339-349. [PMID: 36369430 PMCID: PMC9651904 DOI: 10.1007/s12072-022-10444-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/13/2022] [Accepted: 10/23/2022] [Indexed: 11/13/2022]
Abstract
BACKGROUND/PURPOSE OF THE STUDY There is a need to find a standardized and low-risk diagnostic tool that can non-invasively detect non-alcoholic steatohepatitis (NASH). Surface enhanced Raman spectroscopy (SERS), which is a technique combining Raman spectroscopy (RS) with nanotechnology, has recently received considerable attention due to its potential for improving medical diagnostics. We aimed to investigate combining SERS and neural network approaches, using a liver biopsy dataset to develop and validate a new diagnostic model for non-invasively identifying NASH. METHODS Silver nanoparticles as the SERS-active nanostructures were mixed with blood serum to enhance the Raman scattering signals. The spectral data set was used to train the NASH classification model by a neural network primarily consisting of a fully connected residual module. RESULTS Data on 261 Chinese individuals with biopsy-proven NAFLD were included and a prediction model for NASH was built based on SERS spectra and neural network approaches. The model yielded an AUROC of 0.83 (95% confidence interval [CI] 0.70-0.92) in the validation set, which was better than AUROCs of both serum CK-18-M30 levels (AUROC 0.63, 95% CI 0.48-0.76, p = 0.044) and the HAIR score (AUROC 0.65, 95% CI 0.51-0.77, p = 0.040). Subgroup analyses showed that the model performed well in different patient subgroups. CONCLUSIONS Fully connected neural network-based serum SERS analysis is a rapid and practical tool for the non-invasive identification of NASH. The online calculator website for the estimated risk of NASH is freely available to healthcare providers and researchers ( http://www.pan-chess.cn/calculator/RAMAN_score ).
Collapse
Affiliation(s)
- Feng Gao
- Department of Gastroenterology, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou, China
| | - De-Chan Lu
- Key Laboratory of Opto-Electronic Science and Technology for Medicine of Ministry of Education, Fujian Provincial Key Laboratory for Photonics Technology, Fujian Normal University, Fuzhou, 350000, China
| | - Tian-Lei Zheng
- Artificial Intelligence Unit, Department of Medical Equipment Management, Affiliated Hospital of Xuzhou Medical University, Xuzhou, China
- School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China
| | - Shi Geng
- Artificial Intelligence Unit, Department of Medical Equipment Management, Affiliated Hospital of Xuzhou Medical University, Xuzhou, China
| | - Jun-Cheng Sha
- Interventional Radiology, Affiliated Hospital of Xuzhou Medical University, Xuzhou, China
| | - Ou-Yang Huang
- NAFLD Research Center, Department of Hepatology, The First Affiliated Hospital of Wenzhou Medical University, No. 2 Fuxue Lane, Wenzhou, 325000, China
| | - Liang-Jie Tang
- NAFLD Research Center, Department of Hepatology, The First Affiliated Hospital of Wenzhou Medical University, No. 2 Fuxue Lane, Wenzhou, 325000, China
| | - Pei-Wu Zhu
- Department of Laboratory Medicine, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou, China
| | - Yang-Yang Li
- Department of Pathology, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou, China
| | - Li-Li Chen
- NAFLD Research Center, Department of Hepatology, The First Affiliated Hospital of Wenzhou Medical University, No. 2 Fuxue Lane, Wenzhou, 325000, China
| | - Giovanni Targher
- Section of Endocrinology, Diabetes and Metabolism, Department of Medicine, University and Azienda Ospedaliera Universitaria Integrata of Verona, Verona, Italy
| | - Christopher D Byrne
- Southampton National Institute for Health Research Biomedical Research Centre, University Hospital Southampton, Southampton General Hospital, Southampton, UK
| | - Zu-Fang Huang
- Key Laboratory of Opto-Electronic Science and Technology for Medicine of Ministry of Education, Fujian Provincial Key Laboratory for Photonics Technology, Fujian Normal University, Fuzhou, 350000, China.
| | - Ming-Hua Zheng
- NAFLD Research Center, Department of Hepatology, The First Affiliated Hospital of Wenzhou Medical University, No. 2 Fuxue Lane, Wenzhou, 325000, China.
- Key Laboratory of Diagnosis and Treatment for the Development of Chronic Liver Disease in Zhejiang Province, Wenzhou, China.
- Institute of Hepatology, Wenzhou Medical University, Wenzhou, China.
| |
Collapse
|
6
|
Chen Y, He J, Wang M. A hybrid of long short-term memory neural network and autoregressive integrated moving average model in forecasting HIV incidence and morality of post-neonatal population in East Asia: global burden of diseases 2000-2019. BMC Public Health 2022; 22:1938. [PMID: 36261815 PMCID: PMC9580197 DOI: 10.1186/s12889-022-14321-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/14/2022] [Accepted: 09/26/2022] [Indexed: 11/10/2022] Open
Abstract
Background To forecast the human immunodeficiency virus (HIV) incidence and mortality of post-neonatal population in East Asia including North Korea, South Korea, Mongolia, Japan and China Mainland and Taiwan province. Methods The data on the incidence and mortality of HIV in post-neonatal population from East Asia were obtained from the Global Burden of Diseases (GBD). The morbidity and mortality of post-neonatal HIV population from GBD 2000 to GBD 2013 were applied as the training set and the morbidity and mortality from GBD 2014 to GBD 2019 were used as the testing set. The hybrid of ARIMA and LSTM model was used to construct the model for assessing the morbidity and mortality in the countries and territories of East Asia, and predicting the morbidity and mortality in the next 5 years. Results In North Korea, the incidence and mortality of HIV showed a rapid increase during 2000–2010 and a gradual decrease during 2010–2019. The incidence of HIV was predicted to be increased and the mortality was decreased. In South Korea, the incidence was increased during 2000–2010 and decreased during 2010–2019, while the mortality showed fluctuant trend. As predicted, the incidence of HIV in South Korea might be increased and the mortality might be decreased during 2020–2025. In Mongolia, the incidence and mortality were slowly decreased during 2000–2005, increased during 2005–2015, and rapidly decreased till 2019. The predicted incidence and mortality of HIV showed a decreased trend. As for Japan, the incidence of HIV was rapidly increased till 2010 and then decreased till 2015. The predicted incidence of HIV in Japan was gradually increased. The mortality of HIV in Japan was fluctuant during 2000–2019 and was slowly decreased as predicted. The incidence and mortality of HIV in Taiwan during 2000–2019 was increased on the whole. The predicted incidence of HIV during was stationary and the mortality was decreased. In terms of China Mainland, the incidence and mortality of HIV was fluctuant during 2000–2019. The predicted incidence of HIV in China Mainland was stationary while the mortality was rapidly decreased. Conclusion On the whole, the incidence of HIV combined with other diseases in post-neonatal population was increased before 2010 and then decreased during 2010–2019 while the mortality of those patients was decreased in East Asia.
Collapse
Affiliation(s)
- Ying Chen
- Respiratory Medicine Department, XiXi Hospital of HangZhou (Affiliated HangZhou XiXi Hospital, Zhe Jiang University School of Medicine), No.2 Hengbu Road, Liuxia Street, Xihu District, Hangzhou, 310000, Zhejiang Province, China
| | - Jiawen He
- Respiratory Medicine Department, XiXi Hospital of HangZhou (Affiliated HangZhou XiXi Hospital, Zhe Jiang University School of Medicine), No.2 Hengbu Road, Liuxia Street, Xihu District, Hangzhou, 310000, Zhejiang Province, China
| | - Meihua Wang
- Respiratory Medicine Department, XiXi Hospital of HangZhou (Affiliated HangZhou XiXi Hospital, Zhe Jiang University School of Medicine), No.2 Hengbu Road, Liuxia Street, Xihu District, Hangzhou, 310000, Zhejiang Province, China.
| |
Collapse
|
7
|
Hu S, Liu P, Qiao Y, Wang Q, Zhang Y, Yang Y. PM 2.5 concentration prediction based on WD-SA-LSTM-BP model: a case study of Nanjing city. ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH INTERNATIONAL 2022; 29:70323-70339. [PMID: 35588035 DOI: 10.1007/s11356-022-20744-7] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/11/2021] [Accepted: 05/06/2022] [Indexed: 06/15/2023]
Abstract
PM2.5 concentration is an important indicator to measure the concentration of air pollutants, and it is of important social significance and application value to realize accurate prediction of PM2.5 concentration. To further improve the accuracy of PM2.5 concentration prediction, this paper proposes a hybrid machine learning model (WD-SA-LSTM-BP model) based on simulated annealing (SA) optimization and wavelet decomposition. Firstly, the wavelet decomposition algorithm was used to realize the multiscale decomposition and single-branch reconstruction of PM2.5 concentrations to weaken the prediction error caused by time series data. Secondly, the SA optimization method was used to optimize the super-parameters of each machine learning model under each reconstructed component, so as to solve the problem that it is difficult to determine the parameters of machine learning model. Thirdly, the optimized machine learning model was used to predict the PM2.5 concentration, and the error value was calculated from the actual measured value. Then, the optimized machine learning model was used to predict the error value. Finally, the predicted error value was added to the predicted PM2.5 concentration to obtain the final predicted PM2.5 concentration. The study is experimentally validated based on daily PM2.5 data collected from Nanjing air quality monitoring stations. The experimental results showed that the RMSE and MAE values of the constructed WD-SA-LSTM-BP model were 5.26 and 3.72, respectively, which were superior to those of the WD-LSTM and LSTM models, indicating that the hybrid machine learning model based on SA optimization and wavelet decomposition could better predict the PM2.5 concentration.
Collapse
Affiliation(s)
- Shuo Hu
- School of Instrument Science and Engineering, Southeast University, Nanjing, 210096, China
- Nanjing South New Town Development and Construction Group Co., Ltd, Nanjing, 210096, China
| | - Pengfei Liu
- School of Instrument Science and Engineering, Southeast University, Nanjing, 210096, China.
| | - Yunxia Qiao
- School of Instrument Science and Engineering, Southeast University, Nanjing, 210096, China
| | - Qing Wang
- School of Instrument Science and Engineering, Southeast University, Nanjing, 210096, China
| | - Ying Zhang
- School of Instrument Science and Engineering, Southeast University, Nanjing, 210096, China
| | - Yuan Yang
- School of Instrument Science and Engineering, Southeast University, Nanjing, 210096, China
| |
Collapse
|
8
|
Prediction of Bronchopneumonia Inpatients' Total Hospitalization Expenses Based on BP Neural Network and Support Vector Machine Models. COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE 2022; 2022:9275801. [PMID: 35633928 PMCID: PMC9132643 DOI: 10.1155/2022/9275801] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 03/08/2022] [Revised: 04/13/2022] [Accepted: 05/05/2022] [Indexed: 01/09/2023]
Abstract
Objective BP neural network (BPNN) model and support vector machine (SVM) model were used to predict the total hospitalization expenses of patients with bronchopneumonia. Methods A total of 355 patients with bronchopneumonia from January 2018 to December 2020 were collected and sorted out. The data set was randomly divided into a training set (n = 249) and a test set (n = 106) according to 7 : 3. The BPNN model and SVM model were constructed to analyze the predictors of total hospitalization expenses. The effectiveness was compared between these two prediction models. Results The top three influencing factors and their importance for predicting total hospitalization cost by the BPNN model were hospitalization days (0.477), age (0.154), and discharge department (0.083). The top 3 factors predicted by the SVM model were hospitalization days (0.215), age (0.196), and marital status (0.172). The area under the curve of these two models is 0.838 (95% CI: 0.755~0.921) and 0.889 (95% CI: 0.819~0.959), respectively. Conclusion Both the BPNN model and SVM model can predict the total hospitalization expenses of patients with bronchopneumonia, but the prediction effect of the SVM model is better than the BPNN model.
Collapse
|