Radiological characterization of the tailings of an abandoned copper mine using a neural network and geostatistical analysis through the Co-Kriging method.

The radiological characterization of soil contaminated with natural radionuclides enables the classification of the area under investigation, the optimization of laboratory measurements, and informed decision-making on potential site remediation. Neural networks (NN) are emerging as a new candidate for performing these tasks as an alternative to conventional geostatistical tools such as Co-Kriging. This study demonstrates the implementation of a NN for estimating radiological values such as ambient dose equivalent (H*(10)), surface activity and activity concentrations of natural radionuclides present in a waste dump of a Cu mine with a high level of natural radionuclides. The results obtained using a NN were compared with those estimated by Co-Kriging. Both models reproduced field measurements equivalently as a function of spatial coordinates. Similarly, the deviations from the reference concentration values obtained in the output layer of the NN were smaller than the deviations obtained from the multiple regression analysis (MRA), as indicated by the results of the root mean square error. Finally, the method validation showed that the estimation of radiological parameters based on their spatial coordinates faithfully reproduced the affected area. The estimation of the activity concentrations was less accurate for both the NN and MRA; however, both methods gave statistically comparable results for activity concentrations obtained by gamma spectrometry (Student's t-test and Fisher's F-test).

Multi level perspectives in stock price forecasting: ICE2DE-MDL.

This study proposes a novel hybrid model, called ICE2DE-MDL, integrating secondary decomposition, entropy, machine and deep learning methods to predict a stock closing price. In this context, first of all, the noise contained in the financial time series was eliminated. A denoising method, which utilizes entropy and the two-level ICEEMDAN methodology, is suggested to achieve this. Subsequently, we applied many deep learning and machine learning methods, including long-short term memory (LSTM), LSTM-BN, gated recurrent unit (GRU), and SVR, to the IMFs obtained from the decomposition, classifying them as noiseless. Afterward, the best training method was determined for each IMF. Finally, the proposed model's forecast was obtained by hierarchically combining the prediction results of each IMF. The ICE2DE-MDL model was applied to eight stock market indices and three stock data sets, and the next day's closing price of these stock items was predicted. The results indicate that RMSE values ranged from 0.031 to 0.244, MAE values ranged from 0.026 to 0.144, MAPE values ranged from 0.128 to 0.594, and R-squared values ranged from 0.905 to 0.998 for stock indices and stock forecasts. Furthermore, comparisons were made with various hybrid models proposed within the scope of stock forecasting to evaluate the performance of the ICE2DE-MDL model. Upon comparison, The ICE2DE-MDL model demonstrated superior performance relative to existing models in the literature for both forecasting stock market indices and individual stocks. Additionally, to our knowledge, this study is the first to effectively eliminate noise in stock item data using the concepts of entropy and ICEEMDAN. It is also the second study to apply ICEEMDAN to a financial time series prediction problem.

Primary urethral carcinoma in female: An extremely rare case series at a single tertiary referral hospital and literature review.

INTRODUCTION AND IMPORTANCE: Primary urethral carcinoma (PUC) is exceedingly uncommon and accounts for 0.02 % of all female cancers and <1 % of female genitourinary tract malignancy. PUC in female usually presents late with a higher disease stage and, hence, has higher cancer-specific mortality. Due to its rarity, the current recommendation for the management of PUC is still unclear. CASE PRESENTATION: This study reports two rare cases of 59-year-old and 65-year-old women with PUC, presenting with chief complaint of hematuria. Urethrocystoscopy and biopsy were performed. Pathology results revealed mucinous adenocarcinoma (AC) and urothelial carcinoma (UC) of the urethra, respectively. Radiological imaging was conducted for staging. Both were diagnosed with cT4N2M0. The first patient underwent anterior pelvic exenteration with bilateral ureterocutaneoustomy (UCS), while the second patient received cisplatin-based chemotherapy before the surgery. Radiological follow-up was planned 3 months after the surgery. CLINICAL DISCUSSION: Both mucinous AC and UC are considered incredibly unusual subtypes, with no defined treatment guidelines. Anterior exenteration with or without neoadjuvant chemotherapy may be opted for advanced PUC affecting the proximal urethra and adjacent organs. Following the previous studies, in this case series, both patients (locally advanced) underwent anterior exenteration. Additionally, the UC subtype received multimodal treatment with neoadjuvant chemotherapy which was shown to improve overall survival. CONCLUSION: In conclusion, PUC is extremely rare, and the choice of management remained various. Long-term follow-up for these patients is mandatory to improve understanding of this incredibly uncommon disease.

Dataset of air pollutants (PM2.5, PM10, CO) concentrations in the export processing area of Dhaka, Bangladesh.

This study presents a valuable dataset on air quality in the densely populated Dhaka Export Processing Zone (DEPZ) of Bangladesh. It included a dataset of Particulate Matter (PM2.5, PM10) and CO concentrations with Air Quality Index (AQI) values. PM data was collected 24h, and CO data was collected 8h monthly from 2019 to 2023 using respirable dust sampler APS-113NL for PM2.5, APS-113BL for PM10, and LUTRON AQ9901SD Air Quality Monitor Data Logger used to measure CO concentration data. Data sampling locations are selected based on population density, and employment data for DEPZ is also included, highlighting a potential rise in population density. This article also forecasted pollutant concentrations, AQI values, and health hazards associated with air pollutants using the Auto Regressive Moving Average (ARIMA) model. The performance of the ARIMA model was also measured using root mean squared error (RMSE) and mean absolute error (MAE). However, this can be used to raise awareness among the public about the health hazards associated with air pollution and encourage them to take measures to reduce their exposure to air pollutants. In addition, this data can be instrumental for researchers and policymakers to assess air pollution risks, develop control strategies, and improve air quality in the DEPZ.

Changes in cannabis involvement in emergency department visits for anxiety disorders after cannabis legalization: a repeated cross-sectional study.

Background: An increasing number of countries have or are considering legalizing cannabis. One concern is that legalization of cannabis will result in increased cannabis use and in turn a higher prevalence of anxiety disorders. We examined changes in emergency department (ED) visits for anxiety disorders with cannabis involvement in Ontario, over a period that involved medical and non-medical cannabis legalization. Methods: This repeated cross-sectional population-based study identified all ED visits for anxiety disorders from residents of Ontario, Canada aged 10-105 between 2008 and 2022 (n = 15.7 million individuals). We used interrupted time series analyses to examine immediate and gradual changes in cannabis-involvement and alcohol-involvement (control condition) over four policy periods: medical cannabis legalization (January 2008-November 2015), expanded medical access (December 2015-September 2018), non-medical cannabis legalization with restrictions (October 2018-February 2020), and commercialization which overlapped with the COVID-19 pandemic (March 2020-December 2022). Poisson models were used to generate incidence rate ratios with 95% confidence intervals. Findings: Over the 14-year study, there were 438,700 individuals with one or more ED visits for anxiety disorders of which 3880 (0.89%) individuals had cannabis involvement and 6329 (1.45%) individuals had alcohol involvement. During the commercialization/COVID-19 period monthly rates of anxiety disorders with cannabis-involvement were 156% higher (0.11 vs 0.29 per 100,000 individuals) relative to the pre-legalization period, compared to a 27% increase for alcohol-involvement (0.27 vs 0.35 per 1100,000 individuals). Rates of anxiety ED visits with cannabis involvement per 100,000 individuals increased gradually over the study period with no immediate or gradual changes after expanded medical access, legalization with restrictions or commercialization/COVID-19. However, during the commercialization/COVID-19 period there were large declines in total anxiety disorder ED visits and anxiety disorder ED visits with alcohol-involvement. Consequently, during this period there was an immediate 31.4% relative increase in the proportion of anxiety visits with cannabis-involvement (incidence rate ratio [IRR], 1.31; 95% CI 1.05-1.65). Interpretation: We found large relative increases in anxiety disorder ED visits with cannabis involvement over a 14-year period involving medical and non-medical cannabis legalization. These findings may reflect increasing anxiety disorder problems from cannabis use, increasing self-medication of anxiety disorders with cannabis use, or both. The proportion of anxiety ED visits with cannabis involvement increased during the final period of the study but could have been the results of the market commercialization, COVID-19 or both and ongoing monitoring is indicated. Funding: Canadian Institutes of Health Research (grant #452360).

Impacts of Major Changes in China's COVID-19 Prevention and Control Policies on Emergency Department Visits: A Quasi-Experiment.

Objective: This study aims to evaluate the impact of COVID-19 prevention and control policies on the frequency of emergency department (ED) visits in a large tertiary hospital in central China, from January 2018 to September 2023. Methods: We conducted a multi-stage interrupted time series analysis to investigate the impact of various epidemic control policies on weekly ED visits at a tertiary hospital in Hunan Province, China. The study period ranged from January 1, 2018, to September 30, 2023, and was divided into four distinct periods: pre-epidemic, pandemic, normalized control, and end of control. Using a quasi-Poisson regression model, we examined the specific effects of these policies on emergency visits, with a particular focus on stratifying patients based on respiratory versus non-respiratory diseases. Results: Compared to the pre-pandemic period, the number of ED visits in a tertiary hospital decreased by 38.5% (95% CI: 25.1% to 49.8%) during the COVID-19 pandemic, of which the number of ED visits for respiratory diseases increased by 79.4% (95% CI: 13.2% to 177.2%) and the number of ED visits for non-respiratory diseases decreased by 45.9% (95% CI: -55.7% to -34.2%). After the end of the epidemic control, the total number of ED visits increased by 31.5% (95% CI: 19.1% to 45.0%), with the number of ED visits for respiratory diseases rising by 379.2% (95% CI: 275.9% to 511.8%), but with no significant change in the number of ED visits for non-respiratory emergencies. Conclusion: Control policies were associated with people avoiding emergency care for non-respiratory related reasons during the pandemic, while the end of control policies was associated with a sharp rise in emergency care for respiratory diseases. This study provides a scientific basis for the different changes in ED visits under the implementation of varying epidemic prevention and control policies.

Effects of pay-for-performance based antimicrobial stewardship on antimicrobial consumption and expenditure: An interrupted time series analysis.

Objectives: To evaluate the impact of pay-for-performance on antimicrobial consumption and antimicrobial expenditure in a large teaching hospital in Guangzhou, China. Methods: We collected data from hospital information system from January 2018 through September 2022 in the inpatient wards. Antimicrobial consumption was evaluated using antibiotic use density (AUD) and antibiotic use rate (AUR). The economic impact of intervention was assessed by antimicrobial expenditure percentage. The data was analyzed using interrupted time series (ITS) analysis. Results: Following the implementation of the intervention, immediate decreases in the level of AUD were observed in Department of Hematology Unit 3 (ß = -66.93 DDDs/100PD, P = 0.002), Urology (ß = -32.80 DDDs/100PD, P < 0.001), Gastrointestinal Surgery Unit 3 (ß = -11.44 DDDs/100PD, P = 0.03), Cardiac Surgery (ß = -14.30 DDDs/100PD, P = 0.01), ICU, Unit 2 (ß = -81.91 DDDs/100PD, P = 0.02) and Cardiothoracic Surgery ICU (ß = -41.52 DDDs/100PD, P = 0.05). Long-term downward trends in AUD were also identified in Organ Transplant Unit (ß = -1.64 DDDs/100PD, P = 0.02). However, only Urology (ß = -6.56 DDDs/100PD, P = 0.02) and Gastrointestinal Surgery Unit 3 (ß = -8.50 %, P = 0.01) showed an immediate decrease in AUR, and long-term downward trends in AUR were observed in Pediatric ICU (ß = -1.88 %, P = 0.05) and ICU Unit 1 (ß = -0.55 %, P = 0.02). Conclusion: This study demonstrates that the adoption of pay-for-performance effectively reduces antibiotic consumption in specific departments of a hospital in Guangzhou in the short term. However, it is important to recognize that the long-term impact of such interventions is often limited. Additionally, it should be noted that the overall effectiveness of the intervention across the entire hospital was not significant.

Pantoea agglomerans Infection in Neonates: A Systematic Review of Case Reports.

Pantoea agglomerans, a gram-negative bacterium, has emerged as an opportunistic pathogen, particularly within neonatal healthcare settings. Initially perceived as an innocuous environmental contaminant, P. agglomerans has been increasingly implicated in a spectrum of clinical infections, including neonatal sepsis and bacteremia. This systematic review conducts an in-depth analysis of the clinical cases published in 2003-2023, elucidating the multifaceted clinical presentations and therapeutic challenges associated with P. agglomerans infections in neonates. In total, 11 case reports and case series of 45 neonates from eight different countries were included. Most of the infected patients (57.8%) were reported in Asian countries (Sri Lanka, India, Kuwait) and involved preterm neonates (64.4%) with extremely low to low birth weight, and concurrent medical conditions including co-infections in a few of them (15.6%). Blood was the main culture source of the pathogen, accounting for 42 cases (91.1%) whereas clinical presentations in neonates exhibited considerable heterogeneity, encompassing common symptoms such as feeding difficulties, respiratory distress, fever, lethargy, and sepsis. Neonatal survival largely depended on the infection's origin and the timing of diagnosis. Considering antibiotic susceptibility as a criterion for treatment selection led to a 74% survival rate. Usually, a combination of antibiotics was used. There were 11 neonatal deaths reported, leading to an estimated mortality rate of 24.4%. We conclude that outbreaks within neonatal intensive care units underscore the importance of stringent infection control practices and heightened surveillance, especially considering the rapid disease progression noted in the included studies. Enhanced awareness and understanding of the clinical and microbiological characteristics of P. agglomerans infections are paramount for optimizing outcomes and reducing the burden of disease in neonatal populations.

Improving Motor Skills in Five Children With Developmental Coordination Disorder Traits and Its Impact on Parenting Stress: A Case Series.

Poor motor skills in children with developmental coordination disorder (DCD) are associated with childcare stress. This study aimed to assess whether improving the motor skills of children with DCD could reduce parenting stress. The participants were five boys aged 7-10 years with probable DCD and their parents. The intervention comprised 1 hour per week of motor skills training for nine weeks. We measured improvements in the children's motor skills and reductions in parenting stress before and after the intervention. All five children showed improvements in motor skills. Parenting stress was reduced in two parents, whereas it worsened in three parents. Improving motor skills in children with probable DCD may not necessarily reduce parenting stress.

scMaSigPro: Differential Expression Analysis along Single-Cell Trajectories.

MOTIVATION: Understanding the dynamics of gene expression across different cellular states is crucial for discerning the mechanisms underneath cellular differentiation. Genes that exhibit variation in mean expression as a function of Pseudotime and between branching trajectories are expected to govern cell fate decisions. We introduce scMaSigPro, a method for the identification of differential gene expression patterns along Pseudotime and branching paths simultaneously. RESULTS: We assessed the performance of scMaSigPro using synthetic and public datasets. Our evaluation shows that scMaSigPro outperforms existing methods in controlling the False Positive Rate and is computationally efficient. AVAILABILITY AND IMPLEMENTATION: scMaSigPro is available as a free R package (version 4.0 or higher) under the GPL(≥2) license on GitHub at 'github.com/BioBam/scMaSigPro' and archived with version 0.03 on Zenodo at 'zenodo.org/records/12568922'.

Machine learning-based prediction of clinical outcomes after traumatic brain injury: Hidden information of early physiological time series.

AIMS: To assess the predictive value of early-stage physiological time-series (PTS) data and non-interrogative electronic health record (EHR) signals, collected within 24 h of ICU admission, for traumatic brain injury (TBI) patient outcomes. METHODS: Using data from TBI patients in the multi-center eICU database, we focused on in-hospital mortality, neurological status based on the Glasgow Coma Score (mGCS) motor subscore at discharge, and prolonged ICU stay (PLOS). Three machine learning (ML) models were developed, utilizing EHR features, PTS signals collected 24 h after ICU admission, and their combination. External validation was performed using the MIMIC III dataset, and interpretability was enhanced using the Shapley Additive Explanations (SHAP) algorithm. RESULTS: The analysis included 1085 TBI patients. Compared to individual models and existing scoring systems, the combination of EHR and PTS features demonstrated comparable or even superior performance in predicting in-hospital mortality (AUROC = 0.878), neurological outcomes (AUROC = 0.877), and PLOS (AUROC = 0.835). The model's performance was validated in the MIMIC III dataset, and SHAP algorithms identified six key intervention points for EHR features related to prognostic outcomes. Moreover, the EHR results (All AUROC >0.8) were translated into online tools for clinical use. CONCLUSION: Our study highlights the importance of early-stage PTS signals in predicting TBI patient outcomes. The integration of interpretable algorithms and simplified prediction tools can support treatment decision-making, contributing to the development of accurate prediction models and timely clinical intervention.

COVID-19 pandemic effects on neonatal inpatient admissions and mortality: interrupted time series analysis of facilities implementing NEST360 in Kenya, Malawi, Nigeria, and Tanzania.

BACKGROUND: The emergence of COVID-19 precipitated containment policies (e.g., lockdowns, school closures, etc.). These policies disrupted healthcare, potentially eroding gains for Sustainable Development Goals including for neonatal mortality. Our analysis aimed to evaluate indirect effects of COVID-19 containment policies on neonatal admissions and mortality in 67 neonatal units across Kenya, Malawi, Nigeria, and Tanzania between January 2019 and December 2021. METHODS: The Oxford Stringency Index was applied to quantify COVID-19 policy stringency over time for Kenya, Malawi, Nigeria, and Tanzania. Stringency increased markedly between March and April 2020 for these four countries (although less so in Tanzania), therefore defining the point of interruption. We used March as the primary interruption month, with April for sensitivity analysis. Additional sensitivity analysis excluded data for March and April 2020, modelled the index as a continuous exposure, and examined models for each country. To evaluate changes in neonatal admissions and mortality based on this interruption period, a mixed effects segmented regression was applied. The unit of analysis was the neonatal unit (n = 67), with a total of 266,741 neonatal admissions (January 2019 to December 2021). RESULTS: Admission to neonatal units decreased by 15% overall from February to March 2020, with half of the 67 neonatal units showing a decline in admissions. Of the 34 neonatal units with a decline in admissions, 19 (28%) had a significant decrease of ≥ 20%. The month-to-month decrease in admissions was approximately 2% on average from March 2020 to December 2021. Despite the decline in admissions, we found no significant changes in overall inpatient neonatal mortality. The three sensitivity analyses provided consistent findings. CONCLUSION: COVID-19 containment measures had an impact on neonatal admissions, but no significant change in overall inpatient neonatal mortality was detected. Additional qualitative research in these facilities has explored possible reasons. Strengthening healthcare systems to endure unexpected events, such as pandemics, is critical in continuing progress towards achieving Sustainable Development Goals, including reducing neonatal deaths to less than 12 per 1000 live births by 2030.

Obstetric and anesthetic management in parturients with ventriculoperitoneal shunt: a case series.

Further study is needed to determine the safest mode of delivery and anesthetic management for parturients with ventriculoperitoneal shunts (VP). Prior recommendation for delivery in women with ventriculoperitoneal shunts was cesarean delivery. However, both vaginal delivery and neuraxial anesthesia have been shown to be safe in women with appropriately functioning VP shunts. We present a case series of parturients with VP shunt. Parturients with VP shunts were identified and VP shunt placement indications, neurologic symptoms during pregnancy, delivery mode, anesthetic type, and postpartum complications were reviewed. Forty patients were identified, and fifteen women with twenty deliveries were included. Two women experienced neurological symptoms during pregnancy and one required postpartum shunt revision for blurry vision and ataxia. There were ten cesarean deliveries and ten vaginal deliveries (eight normal spontaneous, one vacuum assisted, and one forceps assisted). Assisted vaginal deliveries were performed to decrease Valsalva including the patient with neurological symptoms related to shunt malfunction. Of the vaginal deliveries, six (60%) had epidural analgesia. Anesthesia for cesarean delivery included neuraxial anesthesia (n = 5) and general anesthesia (n = 5). In our cohort, women with VP shunt received neuraxial blockade without complication. Neuraxial techniques should be offered to women with appropriately functioning VP shunt.

Dural arteriovenous fistulas in the falx cerebri: case series and literature review.

Dural arteriovenous fistulas (DAVFs) within the falx cerebri are infrequently documented and may be linked with the falcine sinus/venous plexus. The falcine sinus/venous plexus, often regarded as a normal venous structure, can exhibit pathological characteristics, differing from the persistent fetal falcine sinus. A retrospective analysis was conducted at a single center to identify all cases of DAVFs within the falx cerebri spanning from 2002 to 2022. Demographic data, fistula features, treatment modalities, clinical outcomes, and fistula closure were collected and analyzed. Additionally, relevant literature on DAVFs in this location was reviewed. Ten cases were identified at our center, supplemented by 13 cases reported in the literature. In our cohort, patients had an average age of 49.4 ± 8.1 years, with a male predominance of 90%. Trans-arterial embolization (TAE) alone achieved immediate complete occlusion in eight cases, while conservative treatment was pursued in two cases. No treatment-related complications or fistula recurrences were observed. In the literature, seven patients underwent direct surgery, three underwent TAE, and one underwent both direct surgery and radiosurgery for complete fistula closure. No instances of fistula recurrence or treatment complications were reported. Dural arteriovenous fistulas within the falx cerebri are rare, with limited literature available. They typically present as aggressive lesions. Treatment options include direct surgery or TAE. However, due to a lack of long-term DSA follow-up, the cure and recurrence rates are unknown for endovasdcular therapy. Further investigation is warranted to elucidate the involvement of the falcine sinus/venous plexus in falx cerebri DAVFs.

A Bayesian non-stationary heteroskedastic time series model for multivariate critical care data.

We propose a multivariate GARCH model for non-stationary health time series by modifying the observation-level variance of the standard state space model. The proposed model provides an intuitive and novel way of dealing with heteroskedastic data using the conditional nature of state-space models. We follow the Bayesian paradigm to perform the inference procedure. In particular, we use Markov chain Monte Carlo methods to obtain samples from the resultant posterior distribution. We use the forward filtering backward sampling algorithm to efficiently obtain samples from the posterior distribution of the latent state. The proposed model also handles missing data in a fully Bayesian fashion. We validate our model on synthetic data and analyze a data set obtained from an intensive care unit in a Montreal hospital and the MIMIC dataset. We further show that our proposed models offer better performance, in terms of WAIC than standard state space models. The proposed model provides a new way to model multivariate heteroskedastic non-stationary time series data. Model comparison can then be easily performed using the WAIC.

Erratum: Effects of COVID-19-targeted non-pharmaceutical interventions on pediatric hospital admissions in North Italian hospitals, 2017 to 2022: a quasi-experimental study interrupted time-series analysis.

[This corrects the article DOI: 10.3389/fpubh.2024.1393677.].

Did the COVID-19 quarantine policies applied in Cochabamba, Bolivia mitigated cases successfully? an interrupted time series analysis.

BACKGROUND: The COVID-19 pandemic prompted varied policy responses globally, with Latin America facing unique challenges. A detailed examination of these policies' impacts on health systems is crucial, particularly in Bolivia, where information about policy implementation and outcomes is limited. OBJECTIVE: To describe the COVID-19 testing trends and evaluate the effects of quarantine measures on these trends in Cochabamba, Bolivia. METHODS: Utilizing COVID-19 testing data from the Cochabamba Department Health Service for the 2020-2022 period. Stratified testing rates in the health system sectors were first estimated followed by an interrupted time series analysis using a quasi-Poisson regression model for assessing the quarantine effects on the mitigation of cases during surge periods. RESULTS: The public sector reported the larger percentage of tests (65%), followed by the private sector (23%) with almost double as many tests as the public-social security sector (11%). In the time series analysis, a correlation between the implementation of quarantine policies and a decrease in the slope of positive rates of COVID-19 cases was observed compared to periods without or with reduced quarantine policies. CONCLUSION: This research underscores the local health system disparities and the effectiveness of stringent quarantine measures in curbing COVID-19 transmission in the Cochabamba region. The findings stress the importance of the measures' intensity and duration, providing valuable lessons for Bolivia and beyond. As the global community learns from the pandemic, these insights are critical for shaping resilient and effective health policy responses.

Main findings: The findings highlight the importance of stringent quarantine measures in managing infectious disease outbreaks, offering valuable insights for policymakers worldwide in strategizing effective public health interventions.Added knowledge: By providing a detailed analysis of testing disparities and quarantine policies' effectiveness within a specific Latin American context, our research fills a critical gap in understanding their impacts on health system responses and disease control.Global health impact for policy and action: The findings highlight the importance of stringent quarantine measures in managing infectious disease outbreaks, offering valuable insights for policymakers worldwide in strategizing effective public health interventions.

Multi-step ahead forecasting of electrical conductivity in rivers by using a hybrid Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) model enhanced by Boruta-XGBoost feature selection algorithm.

Electrical conductivity (EC) is widely recognized as one of the most essential water quality metrics for predicting salinity and mineralization. In the current research, the EC of two Australian rivers (Albert River and Barratta Creek) was forecasted for up to 10 days using a novel deep learning algorithm (Convolutional Neural Network combined with Long Short-Term Memory Model, CNN-LSTM). The Boruta-XGBoost feature selection method was used to determine the significant inputs (time series lagged data) to the model. To compare the performance of Boruta-XGB-CNN-LSTM models, three machine learning approaches-multi-layer perceptron neural network (MLP), K-nearest neighbour (KNN), and extreme gradient boosting (XGBoost) were used. Different statistical metrics, such as correlation coefficient (R), root mean square error (RMSE), and mean absolute percentage error, were used to assess the models' performance. From 10 years of data in both rivers, 7 years (2012-2018) were used as a training set, and 3 years (2019-2021) were used for testing the models. Application of the Boruta-XGB-CNN-LSTM model in forecasting one day ahead of EC showed that in both stations, Boruta-XGB-CNN-LSTM can forecast the EC parameter better than other machine learning models for the test dataset (R = 0.9429, RMSE = 45.6896, MAPE = 5.9749 for Albert River, and R = 0.9215, RMSE = 43.8315, MAPE = 7.6029 for Barratta Creek). Considering the better performance of the Boruta-XGB-CNN-LSTM model in both rivers, this model was used to forecast 3-10 days ahead of EC. The results showed that the Boruta-XGB-CNN-LSTM model is very capable of forecasting the EC for the next 10 days. The results showed that by increasing the forecasting horizon from 3 to 10 days, the performance of the Boruta-XGB-CNN-LSTM model slightly decreased. The results of this study show that the Boruta-XGB-CNN-LSTM model can be used as a good soft computing method for accurately predicting how the EC will change in rivers.

Temporal dynamics of depressive symptoms and cognitive decline in the oldest old: dynamic time warp analysis of the Leiden 85-plus study.

BACKGROUND: The prevalence of depressive symptoms and cognitive decline increases with age. We investigated their temporal dynamics in individuals aged 85 and older across a 5-year follow-up period. METHODS: Participants were selected from the Leiden 85-plus study and were eligible if at least three follow-up measurements were available (325 of 599 participants). Depressive symptoms were assessed at baseline and at yearly assessments during a follow-up period of up to 5 years, using the 15-item Geriatric Depression Scale (GDS-15). Cognitive decline was measured through various tests, including the Mini Mental State Exam, Stroop test, Letter Digit Coding test and immediate and delayed recall. A novel method, dynamic time warping analysis, was employed to model their temporal dynamics within individuals, in undirected and directed time-lag analyses, to ascertain whether depressive symptoms precede cognitive decline in group-level aggregated results or vice versa. RESULTS: The 325 participants were all 85 years of age at baseline; 68% were female, and 45% received intermediate to higher education. Depressive symptoms and cognitive functioning significantly covaried in time, and directed analyses showed that depressive symptoms preceded most of the constituents of cognitive impairment in the oldest old. Of the GDS-15 symptoms, those with the strongest outstrength, indicating changes in these symptoms preceded subsequent changes in other symptoms, were worthlessness, hopelessness, low happiness, dropping activities/interests, and low satisfaction with life (all P's < 0.01). CONCLUSION: Depressive symptoms preceded cognitive impairment in a population based sample of the oldest old.