Estimating the effects of COVID-19 on essential health services utilization in Uganda and Bangladesh using data from routine health information systems

Background

Since March 2020, the coronavirus disease 2019 (COVID-19) pandemic has been a major shock to health systems across the world. We examined national usage patterns for selected basic, essential health services, before and during the COVID-19 pandemic in Uganda and Bangladesh, to determine whether COVID-19 affected reporting of service utilization and the use of health services in each country.

Methods

We used routine health information system data since January 2017 to analyze reporting and service utilization patterns for a variety of health services. Using time series models to replicate pre-COVID-19 trajectories over time we estimated what levels would have been observed if COVID-19 had not occurred during the pandemic months, starting in March 2020. The difference between the observed and predicted levels is the COVID-19 effect on health services.

Results

The time trend models for Uganda and Bangladesh closely replicated the levels and trajectories of service utilization during the 38 months prior to the COVID-19 pandemic. Our results indicate that COVID-19 had severe effects across all services, particularly during the first months of the pandemic, but COVID-19 impacts on health services and subsequent recovery varied by service type. In general, recovery to expected levels was slow and incomplete across the most affected services.

Conclusion

Our analytical approach based on national information system data could be very useful as a form of surveillance for health services disruptions from any cause leading to rapid responses from health service managers and policymakers.

Exploration of Damage Identification Method for a Large-Span Timber Lattice Shell Structure in Taiyuan Botanical Garden based on Structural Health Monitoring

Large-span spatial lattice structures generally have characteristics such as incomplete modal information, high modal density, and high degrees of freedom. To address the problem of misjudgment in the damage detection of large-span spatial structures caused by these characteristics, this paper proposed a damage identification method based on time series models. Firstly, the order of the autoregressive moving average (ARMA) model was selected based on the Akaike information criterion (AIC). Then, the long autoregressive method was used to estimate the parameters of the ARMA model and extract the residual sequence of the autocorrelation part of the model. Furthermore, principal component analysis (PCA) was introduced to reduce the dimensionality of the model while retaining the characteristic values. Finally, the Mahalanobis distance (MD) was used to construct the damage sensitive feature (DSF). The dome of Taiyuan Botanical Garden in China is one of the largest non-triangular timber lattice shells worldwide. Relying on the structural health monitoring (SHM) project of this structure, this paper verified the effectiveness of the damage identification model through numerical simulation and determined the damage degree of the dome structure through SHM measurement data. The results demonstrated that the proposed damage identification method can effectively identify the damage of large-span timber lattice structures, locate the damage position, and estimate the degree of damage. The constructed DSF had relatively strong robustness to small damage and environmental noise and has practical application value for SHM in engineering.

A neural network model for timing control with reinforcement

How do humans and animals perform trial-and-error learning when the space of possibilities is infinite? In a previous study, we used an interval timing production task and discovered an updating strategy in which the agent adjusted the behavioral and neuronal noise for exploration. In the experiment, human subjects proactively generated a series of timed motor outputs. Positive or negative feedback was provided after each response based on the timing accuracy. We found that the sequential motor timing varied at two temporal scales: long-term correlation around the target interval due to memory drifts and short-term adjustments of timing variability according to feedback. We have previously described these two key features of timing variability with an augmented Gaussian process, termed reward-sensitive Gaussian process (RSGP). In a nutshell, the temporal covariance of the timing variable was updated based on the feedback history to recreate the two behavioral characteristics mentioned above. However, the RSGP was mainly descriptive and lacked a neurobiological basis of how the reward feedback can be used by a neural circuit to adjust motor variability. Here we provide a mechanistic model and simulate the process by borrowing the architecture of recurrent neural networks (RNNs). While recurrent connection provided the long-term serial correlation in motor timing, to facilitate reward-driven short-term variations, we introduced reward-dependent variability in the network connectivity, inspired by the stochastic nature of synaptic transmission in the brain. Our model was able to recursively generate an output sequence incorporating internal variability and external reinforcement in a Bayesian framework. We show that the model can generate the temporal structure of the motor variability as a basis for exploration and exploitation trade-off. Unlike other neural network models that search for unique network connectivity for the best match between the model prediction and observation, this model can estimate the uncertainty associated with each outcome and thus did a better job in teasing apart adjustable task-relevant variability from unexplained variability. The proposed artificial neural network model parallels the mechanisms of information processing in neural systems and can extend the framework of brain-inspired reinforcement learning (RL) in continuous state control.

Impact of the COVID-19 pandemic on the conduct of clinical trials: a quantitative analysis

BACKGROUND

Globally, healthcare has shouldered much of the socioeconomic brunt of the COVID-19 pandemic leading to numerous clinical trials suspended or discontinued.

OBJECTIVE

To estimate the COVID-19 impact on the number of clinical trials worldwide.

METHODS

Data deposited by 219 countries in the ClinicalTrials.gov database (2007-2020) were interrogated using targeted queries. A time series model was fitted to the data for studies ongoing, initiated, or ended between 2007 Quarter (Q) 1 and 2019 Q4 to predict the expected trials number in 2020 in the COVID-19 absence. The predicted values were compared with the actual 2020 data to quantify the pandemic impact.

RESULTS

The ongoing registered trials number grew from 2007 Q1 (33,739) to 2019 Q4 (80,319). By contrast, there were markedly fewer ongoing trials in all four quarters of 2020 compared with forecasted values (1.6%-2.8% decrease). When excluding COVID-19-related studies, this disparity grew further (3.4%-5.8% decrease), to a peak of almost 5,000 fewer ongoing trials than estimated for 2020 Q2. The initiated non-COVID-19 trials number was higher than predicted in 2020 Q4 (9.9%).

CONCLUSIONS

This pandemic has impacted clinical trials. Provided that current trends persist, clinical trial activities may soon recover to at least pre-COVID-19 levels.

Epidemiological and clinical features of cutaneous leishmaniasis and its time trend model in a high-endemic focus of disease in the southwest of Iran from 2014 to 2019

BACKGROUND

Cutaneous leishmaniasis (CL) is a tropical infection with a relatively high incidence rate in Iran. The present study aimed to explore the time trend and associated factors of CL in Dezful, in southwest Iran.

METHODS

This case series study was conducted on all CL patients registered from 2014 to 2019. The descriptive analysis of the data was done using SPSS 20 software and the time series model on the number of cases was run through Interactive Time Series Modeling software.

RESULTS

A total of 5349 leishmaniasis cases were identified in the study area during 2014-2019. The highest incidence rate was 35 840 per 100 000 in 2014. The fitted time series model revealed a decreasing trend with an annual periodic pattern. The mean age of infection was 19.82 y (standard deviation 21.87). The infection was most frequent in the 1-10 y age group (41.7%). Also, females were more prone to leishmaniasis (54.7%). Most lesions were located on the hand (23.1%), face (19.7%), and forearm (17.75%) and 48.5% of patients had only one lesion.

CONCLUSIONS

The results revealed a decreasing trend of leishmaniasis in Dezful. It has been predicted that this infection will reach a minimum rate (300 per 100 000) in the winter of 2021.

A Bidirectional Long Short-Term Memory Model Algorithm for Predicting COVID-19 in Gulf Countries

Accurate prediction models have become the first goal for aiding pandemic-related decisions. Modeling and predicting the number of new active cases and deaths are important steps for anticipating and controlling COVID-19 outbreaks. The aim of this research was to develop an accurate prediction system for the COVID-19 pandemic that can predict the numbers of active cases and deaths in the Gulf countries of Saudi Arabia, Oman, the United Arab Emirates (UAE), Kuwait, Bahrain, and Qatar. The novelty of the proposed approach is that it uses an advanced prediction model—the bidirectional long short-term memory (Bi-LSTM) network deep learning model. The datasets were collected from an available repository containing updated registered cases of COVID-19 and showing the global numbers of active COVID-19 cases and deaths. Statistical analyses (e.g., mean square error, root mean square error, mean absolute error, and Spearman’s correlation coefficient) were employed to evaluate the results of the adopted Bi-LSTM model. The Bi-LSTM results based on the correlation metric gave predicted confirmed COVID-19 cases of 99.67%, 99.34%, 99.94%, 99.64%, 98.95%, and 99.91% for Saudi Arabia, Oman, the UAE, Kuwait, Bahrain, and Qatar, respectively, while testing the Bi-LSTM model for predicting COVID-19 mortality gave accuracies of 99.87%, 97.09%, 99.53%, 98.71%, 95.62%, and 99%, respectively. The Bi-LSTM model showed significant results using the correlation metric. Overall, the Bi-LSTM model demonstrated significant success in predicting COVID-19. The Bi-LSTM-based deep learning network achieves optimal prediction results and is effective and robust for predicting the numbers of active cases and deaths from COVID-19 in the studied Gulf countries.

A recurrent neural network using historical data to predict time series indoor PM2.5 concentrations for residential buildings

Due to the severe outdoor PM2.5 pollution in China, many people have installed air-cleaning systems in homes. To make the systems run automatically and intelligently, we developed a recurrent neural network (RNN) that uses historical data to predict the future indoor PM2.5 concentration. The RNN architecture includes an autoencoder and a recurrent part. We used data measured in an apartment over the course of an entire year to train and test the RNN. The data include indoor/outdoor PM2.5 concentration, environmental parameters and time of day. By comparing three different input strategies, we found that a strategy employing historical PM2.5 and time of day as inputs performed best. With this strategy, the model can be applied to predict the relatively stable trend of indoor PM2.5 concentration in advance. When the input length is 2 h and the prediction horizon is 30 min, the median prediction error is 8.3 µg/m³ for the whole test set. For times with indoor PM2.5 concentrations between (20,50] µg/m³ and (50,100] µg/m³ , the median prediction error is 8.3 and 9.2 µg/m³ , respectively. The low prediction error between the ground-truth and predicted values shows that the RNN can predict indoor PM2.5 concentrations with satisfactory performance.

Establishment and Evaluation of a Time Series Model for Predicting the Seasonality of Acute Upper Gastrointestinal Bleeding

Objective

We aimed to establish and evaluate a time series model for predicting the seasonality of acute upper gastrointestinal bleeding (UGIB).

Methods

Patients with acute UGIB who were admitted to the Emergency Department and Gastrointestinal Endoscopy Center of Guangdong Provincial Hospital of Traditional Chinese Medicine from January 2013 to December 2019 were enrolled in the present study. The incidence trend of UGIB was analyzed by seasonal decomposition method. Then, exponential smoothing model and autoregressive integrated moving average model (ARIMA) were used to establish the model and forecast, respectively.

Results

Finally, the exponential smoothing model with better fitting and prediction effect was selected. The smooth R2 was 0.586, and the Ljung-Box Q (18) statistic value was 22.272 (P = 0.135). The incidence of UGIB had an obvious seasonal trend, with a peak in annual January and a seasonal factor of 140%. After that, the volatility had gradually declined, with a trough in August and a seasonal factor of 67.8%. Since then, it had gradually increased.

Conclusion

The prediction effect of exponential smoothing model is better, which can provide prevention and treatment strategies for UGIB, and provide objective guidance for more medical staff in Emergency Department and Gastrointestinal Endoscopy Center during the peak period of UGIB.

Utilizing time series data embedded in electronic health records to develop continuous mortality risk prediction models using hidden Markov models: A sepsis case study

Continuous mortality risk monitoring is instrumental to manage a patient's care and to efficiently utilize the limited hospital resources. Due to incompleteness and irregularities of electronic health records (EHR), developing continuous mortality risk prediction using EHR data is a challenge. In this study, we propose a framework to continuously monitor mortality risk, and apply it to the real-world EHR data. The proposed method employs hidden Markov models (temporal technique) that take account of both the previous state of patient's health and the current value of clinical signs. Following the Sepsis-3 definition, we selected 3898 encounters of patients with suspected infection to compare the performance of temporal and non-temporal methods (Decision Tree (DT), Logistic Regression (LR), Naive Bayes (NB), Random Forest (RF), and Support Vector Machine (SVM)). The area under receiver operating characteristics (AUROC) curve, sensitivity, specificity and G-mean were used as performance measures. On the selected data, the AUROC of the proposed temporal framework (0.87) is 9-12% greater than the nontemporal methods (DT: 0.78, NB: 0.79, SVM: 0.79, LR: 0.80 and RF: 0.80). The results also show that our model (G-mean=0.78) provides a better balance between sensitivity and specificity compared to clinically acceptable bed-side criteria (G-mean=0.71). The proposed framework leverages the longitudinal data available in EHR and performs better than the non-temporal methods. The proposed method facilitates information related to the time of change of the patient's health that may help practitioners to plan early and develop effective treatment strategies.

Applying Auto-Regressive Model's Yule-Walker Approach to Amyotrophic Lateral Sclerosis (ALS) patients' Data

OBJECTIVE

The purpose of this study is to identifying time series analysis and mathematical model fitting on electroencephalography channels that are placed on Amyotrophic Lateral Sclerosis (ALS) patients with P300 based brain-computer interface (BCI).

METHODS

Amyotrophic Lateral Sclerosis (ALS) or motor neuron diseases are a rapidly progressing neurological disease that attacks and kills neurons responsible for controlling voluntary muscles. There is no cure and treatment effective to reverse, to halt the disease progression. A Brain- Computer Interface enables disable person to communicate & interact with each other and with the environment. To bypass the important motor difficulties present in ALS patient, BCI is useful. An input for BCI system is patient's brain signals and these signals are converted into external operations, for brain signals detection, Electroencephalography (EEG) is normally used. P300 based BCI is used to record the reading of EEG brain signals with the help of non-invasive placement of channels. In EEG, channel analysis Autoregressive (AR) model is a widely used. In the present study, Yule-Walker approach of AR model has been used for channel data fitting. Model fitting as a form of digitization is majorly required for good understanding of the dataset, and also for data prediction.

RESULTS

Fourth order of the mathematical curve for this dataset is selected. The reason is the high accuracy obtained in the 4th order of Autoregressive model (97.51±0.64).

CONCLUSION

In proposed Auto Regressive (AR) model has been used for Amyotrophic Lateral Sclerosis (ALS) patient data analysis. The 4th order of Yule Walker auto-regressive model is giving best fitting on this problem.

A climatological study of scorpion sting incidence from 2007 to 2011 in the Dezful area of southwestern Iran, using a time series model

Scorpion stings are a public health problem in south and southwest Iran. There is little information regarding climatological effects on incidence of scorpion stings in Iran. Therefore, the present systemic survey of scorpion sting data was conducted from the point of view of entomo-meteorological relationships and analyzed statistically for the Dezful area in Khuzestan, southwest of Iran. The time series analysis was implemented using MINITAB version 16 statistical software packages. In total, 3,755 scorpion sting files from the Dezful health centers were monitored from April 2007 to September 2011 in a time series analysis. The results showed that temperature had significant effects on scorpion sting. From the data of this study, it is concluded that the scorpion activity in Dezful County is a climatological-dependent phenomenon.