A long short-term memory-fully connected (LSTM-FC) neural network for predicting the incidence of bronchopneumonia in children

Improved prediction of hourly PM2.5 concentrations with a long short-term memory and spatio-temporal causal convolutional network deep learning model

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.

Remimazolam attenuates inflammation in bronchopneumonia through the inhibition of NLRP3 activity by PDPK1 ubiquitination

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.

LSA-ac4C: A hybrid neural network incorporating double-layer LSTM and self-attention mechanism for the prediction of N4-acetylcytidine sites in human mRNA

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.

LSTM model for predicting the daily number of asthma patients in Seoul, South Korea, using meteorological and air pollution data

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.

Fully connected neural network-based serum surface-enhanced Raman spectroscopy accurately identifies non-alcoholic steatohepatitis

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 ).

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

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.

PM2.5 concentration prediction based on WD-SA-LSTM-BP model: a case study of Nanjing city

PM_2.5 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 PM_2.5 concentration. To further improve the accuracy of PM_2.5 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 PM_2.5 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 PM_2.5 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 PM_2.5 concentration to obtain the final predicted PM_2.5 concentration. The study is experimentally validated based on daily PM_2.5 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 PM_2.5 concentration.

Prediction of Bronchopneumonia Inpatients' Total Hospitalization Expenses Based on BP Neural Network and Support Vector Machine Models

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.