The COVID-19 pandemic and the use of benzodiazepines and benzodiazepine-related drugs in Estonia: an interrupted time-series analysis.

BACKGROUND: The COVID-19 pandemic has posed challenges that worsened people's mental health. We explored the impact of the COVID-19 pandemic on the mental well-being of the population, as indicated by the prevalence rates of benzodiazepine and benzodiazepine-related drug (BDZ) use. METHODS: This population-based, time-series analysis included all prescriptions of BDZs dispensed in Estonia between 2012 and 2021. The monthly prevalence rates of BDZ use were calculated. Autoregressive integrated moving average models with pulse and slope intervention functions tested for temporary and long-term changes in monthly prevalence rates after the onset of the COVID-19 pandemic. RESULTS: Throughout the 10-year study period, a total of 5,528,911 BDZ prescriptions were dispensed to 397,436 individuals. A significant temporary increase in the overall prevalence rate of BDZ use in March 2020 (2.698 users per 1000, 95% CI 1.408-3.988) was observed, but there was no statistically significant long-term change. This temporary increase affected all the examined subgroups, except for new users, individuals aged 15-29 years, and prescribing specialists other than general practitioners and psychiatrists. The long-term increase in BDZ use was confined to females aged 15-29 years (0.056 users per 1000 per month, 95% CI 0.033-0.079), while no significant change was observed among males of the same age (0.009 users per 1000 per month, 95% CI - 0.017 to 0.035). Among females aged 15-29 years, a significant long-term increase in BDZ use was observed for anxiety disorders (0.017 users per 1000 per month, 95% CI 0.010-0.023), depressive disorders (0.021 users per 1000 per month, 95% CI 0.012-0.030), and other mental and behavioral disorders (0.020 users per 1000 per month, 95% CI 0.010-0.030), but not for sleep disorders (- 0.008 users per 1000 per month, 95% CI - 0.018-0.002). CONCLUSION: The COVID-19 pandemic led to a short-term increase in BDZ use immediately after the pandemic was declared. In the long term, young females experienced a sustained increase in BDZ use. The prolonged effect on girls and young women suggests their greater vulnerability. These results underscore the need to effectively address the long-term effects of the pandemic among youth.

Time-Series MR Images Identifying Complete Response to Neoadjuvant Chemotherapy in Breast Cancer Using a Deep Learning Approach.

BACKGROUND: Pathological complete response (pCR) is an essential criterion for adjusting follow-up treatment plans for patients with breast cancer (BC). The value of the visual geometry group and long short-term memory (VGG-LSTM) network using time-series dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) for pCR identification in BC is unclear. PURPOSE: To identify pCR to neoadjuvant chemotherapy (NAC) using deep learning (DL) models based on the VGG-LSTM network. STUDY TYPE: Retrospective. POPULATION: Center A: 235 patients (47.7 ± 10.0 years) were divided 7:3 into training (n = 164) and validation set (n = 71). Center B: 150 patients (48.5 ± 10.4 years) were used as test set. FIELD STRENGTH/SEQUENCE: 3-T, T2-weighted spin-echo sequence imaging, and gradient echo DCE sequence imaging. ASSESSMENT: Patients underwent MRI examinations at three sequential time points: pretreatment, after three cycles of treatment, and prior to surgery, with tumor regions of interest manually delineated. Histopathology was the gold standard. We used VGG-LSTM network to establish seven DL models using time-series DCE-MR images: pre-NAC images (t0 model), early NAC images (t1 model), post-NAC images (t2 model), pre-NAC and early NAC images (t0 + t1 model), pre-NAC and post-NAC images (t0 + t2 model), pre-NAC, early NAC and post-NAC images (t0 + t1 + t2 model), and the optimal model combined with the clinical features and imaging features (combined model). The models were trained and optimized on the training and validation set, and tested on the test set. STATISTICAL TESTS: The DeLong, Student's t-test, Mann-Whitney U, Chi-squared, Fisher's exact, Hosmer-Lemeshow tests, decision curve analysis, and receiver operating characteristics analysis were performed. P < 0.05 was considered significant. RESULTS: Compared with the other six models, the combined model achieved the best performance in the test set yielding an AUC of 0.927. DATA CONCLUSION: The combined model that used time-series DCE-MR images, clinical features and imaging features shows promise for identifying pCR in BC. TECHNICAL EFFICACY: Stage 4.

Integrating gated recurrent unit in graph neural network to improve infectious disease prediction: an attempt.

Objective: This study focuses on enhancing the precision of epidemic time series data prediction by integrating Gated Recurrent Unit (GRU) into a Graph Neural Network (GNN), forming the GRGNN. The accuracy of the GNN (Graph Neural Network) network with introduced GRU (Gated Recurrent Units) is validated by comparing it with seven commonly used prediction methods. Method: The GRGNN methodology involves multivariate time series prediction using a GNN (Graph Neural Network) network improved by the integration of GRU (Gated Recurrent Units). Additionally, Graphical Fourier Transform (GFT) and Discrete Fourier Transform (DFT) are introduced. GFT captures inter-sequence correlations in the spectral domain, while DFT transforms data from the time domain to the frequency domain, revealing temporal node correlations. Following GFT and DFT, outbreak data are predicted through one-dimensional convolution and gated linear regression in the frequency domain, graph convolution in the spectral domain, and GRU (Gated Recurrent Units) in the time domain. The inverse transformation of GFT and DFT is employed, and final predictions are obtained after passing through a fully connected layer. Evaluation is conducted on three datasets: the COVID-19 datasets of 38 African countries and 42 European countries from worldometers, and the chickenpox dataset of 20 Hungarian regions from Kaggle. Metrics include Average Root Mean Square Error (ARMSE) and Average Mean Absolute Error (AMAE). Result: For African COVID-19 dataset and Hungarian Chickenpox dataset, GRGNN consistently outperforms other methods in ARMSE and AMAE across various prediction step lengths. Optimal results are achieved even at extended prediction steps, highlighting the model's robustness. Conclusion: GRGNN proves effective in predicting epidemic time series data with high accuracy, demonstrating its potential in epidemic surveillance and early warning applications. However, further discussions and studies are warranted to refine its application and judgment methods, emphasizing the ongoing need for exploration and research in this domain.

Resilience in sports: a multidisciplinary, dynamic, and personalized perspective.

Athletes are exposed to various psychological and physiological stressors, such as losing matches and high training loads. Understanding and improving the resilience of athletes is therefore crucial to prevent performance decrements and psychological or physical problems. In this review, resilience is conceptualized as a dynamic process of bouncing back to normal functioning following stressors. This process has been of wide interest in psychology, but also in the physiology and sports science literature (e.g. load and recovery). To improve our understanding of the process of resilience, we argue for a collaborative synthesis of knowledge from the domains of psychology, physiology, sports science, and data science. Accordingly, we propose a multidisciplinary, dynamic, and personalized research agenda on resilience. We explain how new technologies and data science applications are important future trends (1) to detect warning signals for resilience losses in (combinations of) psychological and physiological changes, and (2) to provide athletes and their coaches with personalized feedback about athletes' resilience.

Robust autoregressive modeling and its diagnostic analytics with a COVID-19 related application.

Autoregressive models in time series are useful in various areas. In this article, we propose a skew-t autoregressive model. We estimate its parameters using the expectation-maximization (EM) method and develop the influence methodology based on local perturbations for its validation. We obtain the normal curvatures for four perturbation strategies to identify influential observations, and then to assess their performance through Monte Carlo simulations. An example of financial data analysis is presented to study daily log-returns for Brent crude futures and investigate possible impact by the COVID-19 pandemic.

Exploring the dynamics of monkeypox transmission with data-driven methods and a deterministic model.

Introduction: Mpox (formerly monkeypox) is an infectious disease that spreads mostly through direct contact with infected animals or people's blood, bodily fluids, or cutaneous or mucosal lesions. In light of the global outbreak that occurred in 2022-2023, in this paper, we analyzed global Mpox univariate time series data and provided a comprehensive analysis of disease outbreaks across the world, including the USA with Brazil and three continents: North America, South America, and Europe. The novelty of this study is that it delved into the Mpox time series data by implementing the data-driven methods and a mathematical model concurrently-an aspect not typically addressed in the existing literature. The study is also important because implementing these models concurrently improved our predictions' reliability for infectious diseases. Methods: We proposed a traditional compartmental model and also implemented deep learning models (1D- convolutional neural network (CNN), long-short term memory (LSTM), bidirectional LSTM (BiLSTM), hybrid CNN-LSTM, and CNN-BiLSTM) as well as statistical time series models: autoregressive integrated moving average (ARIMA) and exponential smoothing on the Mpox data. We also employed the least squares method fitting to estimate the essential epidemiological parameters in the proposed deterministic model. Results: The primary finding of the deterministic model is that vaccination rates can flatten the curve of infected dynamics and influence the basic reproduction number. Through the numerical simulations, we determined that increased vaccination among the susceptible human population is crucial to control disease transmission. Moreover, in case of an outbreak, our model showed the potential for epidemic control by adjusting the key epidemiological parameters, namely the baseline contact rate and the proportion of contacts within the human population. Next, we analyzed data-driven models that contribute to a comprehensive understanding of disease dynamics in different locations. Additionally, we trained models to provide short-term (eight-week) predictions across various geographical locations, and all eight models produced reliable results. Conclusion: This study utilized a comprehensive framework to investigate univariate time series data to understand the dynamics of Mpox transmission. The prediction showed that Mpox is in its die-out situation as of July 29, 2023. Moreover, the deterministic model showed the importance of the Mpox vaccination in mitigating the Mpox transmission and highlighted the significance of effectively adjusting key epidemiological parameters during outbreaks, particularly the contact rate in high-risk groups.

Reporting delays: A widely neglected impact factor in COVID-19 forecasts.

Epidemic forecasts are only as good as the accuracy of epidemic measurements. Is epidemic data, particularly COVID-19 epidemic data, clean, and devoid of noise? The complexity and variability inherent in data collection and reporting suggest otherwise. While we cannot evaluate the integrity of the COVID-19 epidemic data in a holistic fashion, we can assess the data for the presence of reporting delays. In our work, through the analysis of the first COVID-19 wave, we find substantial reporting delays in the published epidemic data. Motivated by the desire to enhance epidemic forecasts, we develop a statistical framework to detect, uncover, and remove reporting delays in the infectious, recovered, and deceased epidemic time series. Using our framework, we expose and analyze reporting delays in eight regions significantly affected by the first COVID-19 wave. Further, we demonstrate that removing reporting delays from epidemic data by using our statistical framework may decrease the error in epidemic forecasts. While our statistical framework can be used in combination with any epidemic forecast method that intakes infectious, recovered, and deceased data, to make a basic assessment, we employed the classical SIRD epidemic model. Our results indicate that the removal of reporting delays from the epidemic data may decrease the forecast error by up to 50%. We anticipate that our framework will be indispensable in the analysis of novel COVID-19 strains and other existing or novel infectious diseases.

Measuring multi-year changes in the Symbiodiniaceae algae in Caribbean corals on coral-depleted reefs.

Monitoring coral cover can describe the ecology of reef degradation, but rarely can it reveal the proximal mechanisms of change, or achieve its full potential in informing conservation actions. Describing temporal variation in Symbiodiniaceae within corals can help address these limitations, but this is rarely a research priority. Here, we augmented an ecological time series of the coral reefs of St. John, US Virgin Islands, by describing the genetic complement of symbiotic algae in common corals. Seventy-five corals from nine species were marked and sampled in 2017. Of these colonies, 41% were sampled in 2018, and 72% in 2019; 28% could not be found and were assumed to have died. Symbiodiniaceae ITS2 sequencing identified 525 distinct sequences (comprising 42 ITS2 type profiles), and symbiont diversity differed among host species and individuals, but was in most cases preserved within hosts over 3 yrs that were marked by physical disturbances from major hurricanes (2017) and the regional onset of stony coral tissue loss disease (2019). While changes in symbiont communities were slight and stochastic over time within colonies, variation in the dominant symbionts among colonies was observed for all host species. Together, these results indicate that declining host abundances could lead to the loss of rare algal lineages that are found in a low proportion of few coral colonies left on many reefs, especially if coral declines are symbiont-specific. These findings highlight the importance of identifying Symbiodiniaceae as part of a time series of coral communities to support holistic conservation planning. Repeated sampling of tagged corals is unlikely to be viable for this purpose, because many Caribbean corals are dying before they can be sampled multiple times. Instead, random sampling of large numbers of corals may be more effective in capturing the diversity and temporal dynamics of Symbiodiniaceae metacommunities in reef corals.

Multivariate Time Series Change-Point Detection with a Novel Pearson-like Scaled Bregman Divergence.

Change-point detection is a challenging problem that has a number of applications across various real-world domains. The primary objective of CPD is to identify specific time points where the underlying system undergoes transitions between different states, each characterized by its distinct data distribution. Precise identification of change points in time series omics data can provide insights into the dynamic and temporal characteristics inherent to complex biological systems. Many change-point detection methods have traditionally focused on the direct estimation of data distributions. However, these approaches become unrealistic in high-dimensional data analysis. Density ratio methods have emerged as promising approaches for change-point detection since estimating density ratios is easier than directly estimating individual densities. Nevertheless, the divergence measures used in these methods may suffer from numerical instability during computation. Additionally, the most popular α-relative Pearson divergence cannot measure the dissimilarity between two distributions of data but a mixture of distributions. To overcome the limitations of existing density ratio-based methods, we propose a novel approach called the Pearson-like scaled-Bregman divergence-based (PLsBD) density ratio estimation method for change-point detection. Our theoretical studies derive an analytical expression for the Pearson-like scaled Bregman divergence using a mixture measure. We integrate the PLsBD with a kernel regression model and apply a random sampling strategy to identify change points in both synthetic data and real-world high-dimensional genomics data of Drosophila. Our PLsBD method demonstrates superior performance compared to many other change-point detection methods.

Investigating the relationship between extreme weather and cryptosporidiosis and giardiasis in Colorado: A multi-decade study using distributed-lag nonlinear models.

Environmentally-mediated protozoan diseases like cryptosporidiosis and giardiasis are likely to be highly impacted by extreme weather, as climate-related conditions like temperature and precipitation have been linked to their survival, distribution, and overall transmission success. Our aim was to investigate the relationship between extreme temperature and precipitation and cryptosporidiosis and giardiasis infection using monthly weather data and case reports from Colorado counties over a twenty-one year period. Data on reportable diseases and weather among Colorado counties were collected using the Colorado Electronic Disease Reporting System (CEDRS) and the Daily Surface Weather and Climatological Summaries (Daymet) Version 3 dataset, respectively. We used a conditional Poisson distributed-lag nonlinear modeling approach to estimate the lagged association (between 0 and 12-months) between relative temperature and precipitation extremes and the risk of cryptosporidiosis and giardiasis infection in Colorado counties between 1997 and 2017, relative to the risk found at average values of temperature and precipitation for a given county and month. We found distinctly different patterns in the associations between temperature extremes and cryptosporidiosis, versus temperature extremes and giardiasis. When maximum or minimum temperatures were high (90th percentile) or very high (95th percentile), we found a significant increase in cryptosporidiosis risk, but a significant decrease in giardiasis risk, relative to risk at the county and calendar-month mean. Conversely, we found very similar relationships between precipitation extremes and both cryptosporidiosis and giardiasis, which highlighted the prominent role of long-term (>8 months) lags. Our study presents novel insights on the influence that extreme temperature and precipitation can have on parasitic disease transmission in real-world settings. Additionally, we present preliminary evidence that the standard lag periods that are typically used in epidemiological studies to assess the impacts of extreme weather on cryptosporidiosis and giardiasis may not be capturing the entire relevant period.

Assessing the effect of automated speed enforcement and comprehensive measures on road safety in Rwanda.

OBJECTIVES: Daily, approximately 3,400 traffic-related deaths occur globally, with over 90% concentrated in low and middle-income countries (LMICs). Notably, Rwanda has one of the highest road traffic death rates in the world (29.7 per 100,000 people) and is the first low-income country to implement a national Automated Speed Enforcement (ASE) policy. The primary goal of this study is to evaluate the effectiveness of ASE cameras in reducing the primary outcome of road traffic deaths and secondary outcomes of serious injury crashes and fatal crashes. METHODS: The study used data on road traffic deaths, and serious injury and fatal crashes collected by the Rwanda National Police between 2010 and 2022. Interrupted time series (ITS) models were fit to quantify the association between ASE and change in road traffic crash outcomes, adjusted for COVID-19-related variables (such as the start of the pandemic, the closure of schools and bars), along with exposure variables (such as GDP and population), and other concurrent road safety measures (such as road safety campaigns). RESULTS: The ITS models show that the implementation of ASE cameras significantly reduced road traffic deaths, serious injury crashes, and fatal crashes at the provincial level. For instance, the implementation of ASE cameras in the whole of Rwanda in April 2021 was significantly associated with a 0.14 (95% CI [0.072, 0.212]) reduction in monthly death incidence, equating to a 38.16% monthly decrease compared to the period before their installation (January 2010-March 2021). CONCLUSION: This study emphasizes the significant association of ASE in Rwanda with improved road traffic crash outcomes, a result that may inform road safety policy in other LMICs. Rwanda has become the first low-income country to implement nationwide scaling of ASE in Africa, paving the way for the generation of valuable evidence on speed-related interventions. In addition to new knowledge generation, African road safety research efforts like this one are opportunities to grow academic and law enforcement cooperations while improving data systems and sources for future research benefits.

Evaluation of a regional tobacco control programme (Greater Manchester's Making Smoking History) on quitting and smoking in England 2014 to 2022: a time-series analysis.

INTRODUCTION: This study aimed to assess the impact of Greater Manchester's Making Smoking History programme - a region-wide smoking cessation programme launched in January 2018 - on key smoking and quitting outcomes. METHODS: Data were from a nationally-representative monthly survey, 2014-2022 (n=171,281). We used interrupted time-series analyses (Autoregressive Integrated Moving Average [ARIMA] and generalised additive models [GAM]) to examine regional differences between Greater Manchester and the rest of England, before and during the programme's first five years. Outcomes were rates of quit attempts and overall quits among smokers, quit success rates among smokers who tried to quit (pre-registered outcomes), and current smoking prevalence among adults (unregistered outcome). RESULTS: Results showed mixed effects of the programme on quitting. Primary ARIMA models showed comparative reductions in quit success rates (change in quarterly difference between regions = -11.03%; 95%CI -18.96;-3.11) and overall quit rates in Greater Manchester compared with the rest of England (-2.56%; 95%CI -4.95;-0.18), and no significant change in the difference in the quit attempt rate (+2.95%; 95%CI -11.64;17.54). These results were not consistently observed across sensitivity analyses or GAM analyses. Exploratory ARIMA models consistently showed smoking prevalence in Greater Manchester declined more quickly than in the rest of England following initiation of the programme (-2.14%; 95%CI -4.02;-0.27). CONCLUSIONS: The first five years of Greater Manchester's Making Smoking History programme did not appear to be associated with substantial increases in quitting activity. However, exploratory analyses showed a significant reduction in the regional smoking rate, over and above changes in the rest of England over the same period. IMPLICATIONS: Taken together, these results show a relative decline in smoking prevalence in Greater Manchester but equivocal data on quitting, introducing some uncertainty. It is possible the programme has reduced smoking prevalence in the absence of any substantial change in quitting activity by changing norms around smoking and reducing uptake, or by reducing the rate of late relapse. It is also possible that an undetected effect on quitting outcomes has still contributed to the programme's impact on reducing prevalence to some degree. It will be important to evaluate the overall impact of the programme over a longer timeframe.

ContrAttNet: Contribution and attention approach to multivariate time-series data imputation.

The imputation of missing values in multivariate time-series data is a basic and popular data processing technology. Recently, some studies have exploited Recurrent Neural Networks (RNNs) and Generative Adversarial Networks (GANs) to impute/fill the missing values in multivariate time-series data. However, when faced with datasets with high missing rates, the imputation error of these methods increases dramatically. To this end, we propose a neural network model based on dynamic contribution and attention, denoted as ContrAttNet. ContrAttNet consists of three novel modules: feature attention module, iLSTM (imputation Long Short-Term Memory) module, and 1D-CNN (1-Dimensional Convolutional Neural Network) module. ContrAttNet exploits temporal information and spatial feature information to predict missing values, where iLSTM attenuates the memory of LSTM according to the characteristics of the missing values, to learn the contributions of different features. Moreover, the feature attention module introduces an attention mechanism based on contributions, to calculate supervised weights. Furthermore, under the influence of these supervised weights, 1D-CNN processes the time-series data by treating them as spatial features. Experimental results show that ContrAttNet outperforms other state-of-the-art models in the missing value imputation of multivariate time-series data, with average 6% MAPE and 9% MAE on the benchmark datasets.

Machine Learning Methods for the Analysis of the Patch-Clamp Signals.

Patch-clamp technique provides a unique possibility to record the ion channels' activity. This method enables tracking the changes in their functional states at controlled conditions on a real-time scale. Kinetic parameters evaluated for the patch-clamp signals form the fundamentals of electrophysiological characteristics of the channel functioning. Nevertheless, the noisy series of ionic currents flowing through the channel protein(s) seem to be bountiful of information, and the standard data processing techniques likely unravel only its part. Rapid development of artificial intelligence (AI) techniques, especially machine learning (ML), gives new prospects for whole channelology. Here we consider the question of the AI applications in the patch-clamp signal analysis. It turns out that the AI methods may not only enable for automatizing of signal analysis, but also they can be used in finding inherent patterns of channel gating and allow the researchers to uncover the details of gating machinery, which had been never considered before. In this work, we outline the currently known AI methods that turned out to be utilizable and useful in the analysis of patch-clamp signals. This chapter can be considered an introductory guide to the application of AI methods in the analysis of the time series of channel currents (together with its advantages, disadvantages, and limitations), but we also propose new possible directions in this field.

COVID-19 pandemic and the consumption of self-care products for pediculosis capitis in Portugal: an interrupted time-series analysis.

This study aims to assess the effect of the COVID-19 pandemic on the consumption of self-care products for pediculosis capitis management, in Portugal. A segmented regression analysis of interrupted time series (March 2020) was performed from January 2017 to August 2023 to analyze the short- and long-term impact of the COVID-19 pandemic on the consumption of pediculicides and related products. Monthly rates of absolute consumption were estimated by community pharmacies' dispensing records. Portuguese municipalities were organized into quintiles according to their purchasing power index and percentage of youth, to study the association of these social and demographic variables on the sale of these products. COVID-19 pandemic significantly reduced the sales of products indicated for pediculosis. Since the start of the pandemic, an absolute decrease of 21.0 thousand packages was observed in the monthly average consumption (p < 0.0001) compared to the pre-pandemic period. After this reduction, the average monthly trend increased in the pandemic period in comparison with the previous period, although not significant (267.0 packages per month, p = 0.1102). Regions with higher disposable income and more young people were associated with higher sales of these products. The outbreak of the COVID-19 pandemic has had a notable impact on the sales of self-care products for pediculosis capitis in Portugal, in the short term. The lockdowns and other isolation measures implemented to control the spread of the virus may have led to a decrease in the number of head lice cases, consequently resulting in a reduction in sales of products.

Consumption of antibiotics in Brazil - an analysis of sales data between 2014 and 2019.

BACKGROUND: Antibiotic consumption is a driver for the increase of antimicrobial resistance. The objective of this study is to analyze variations in antibiotic consumption and its appropriate use in Brazil from 2014 to 2019. METHODS: We conducted a time series study using the surveillance information system database (SNGPC) from the Brazilian Health Regulatory Agency. Antimicrobials sold in retail pharmacies were evaluated. All antimicrobials recorded for systemic use identified by the active ingredient were eligible. Compounded products and formulations for topic use (dermatological, gynecological, and eye/ear treatments) were excluded. The number of defined daily doses (DDDs)/1,000 inhabitants/day for each antibiotic was attributed. The number of DDDs per 1,000 inhabitants per day (DDIs) was used as a proxy for consumption. Results were stratified by regions and the average annual percentage change in the whole period studied was estimated. We used the WHO Access, Watch, and Reserve (AWaRe) framework to categorize antimicrobial drugs. RESULTS: An overall increase of 30% in consumption from 2014 to 2019 was observed in all Brazilian regions. Amoxicillin, azithromycin and cephalexin were the antimicrobials more consumed, with the Southeast region responsible for more than 50% of the antibiotic utilization. Among all antimicrobials analyzed 45.0% were classified as watch group in all Brazilian regions. CONCLUSION: We observed a significant increase in antibiotics consumption from 2014 to 2019 in Brazil restricted to the Northeast and Central West regions. Almost half of the antibiotics consumed in Brazil were classified as watch group, highlighting the importance to promote rational use in this country.

A Novel Video-Based Methodology for Automated Classification of Dystonia and Choreoathetosis in Dyskinetic Cerebral Palsy During a Lower Extremity Task.

BACKGROUND: Movement disorders in children and adolescents with dyskinetic cerebral palsy (CP) are commonly assessed from video recordings, however scoring is time-consuming and expert knowledge is required for an appropriate assessment. OBJECTIVE: To explore a machine learning approach for automated classification of amplitude and duration of distal leg dystonia and choreoathetosis within short video sequences. METHODS: Available videos of a heel-toe tapping task were preprocessed to optimize key point extraction using markerless motion analysis. Postprocessed key point data were passed to a time series classification ensemble algorithm to classify dystonia and choreoathetosis duration and amplitude classes (scores 0, 1, 2, 3, and 4), respectively. As ground truth clinical scoring of dystonia and choreoathetosis by the Dyskinesia Impairment Scale was used. Multiclass performance metrics as well as metrics for summarized scores: absence (score 0) and presence (score 1-4) were determined. RESULTS: Thirty-three participants were included: 29 with dyskinetic CP and 4 typically developing, age 14 years:6 months ± 5 years:15 months. The multiclass accuracy results for dystonia were 77% for duration and 68% for amplitude; for choreoathetosis 30% for duration and 38% for amplitude. The metrics for score 0 versus score 1 to 4 revealed an accuracy of 81% for dystonia duration, 77% for dystonia amplitude, 53% for choreoathetosis duration and amplitude. CONCLUSIONS: This methodology study yielded encouraging results in distinguishing between presence and absence of dystonia, but not for choreoathetosis. A larger dataset is required for models to accurately represent distinct classes/scores. This study presents a novel methodology of automated assessment of movement disorders solely from video data.

A wearable sensors dataset for stress & boredom associated activity recognition.

This article presents a dataset of activities associated with stress and boredom obtained through wearable sensors. Data was collected from 40 right-handed participants aged 20 to 25, evenly split between males and females. Each individual wore a smart device on their dominant arm's wrists to facilitate the capture of data. This dataset covers five activities associated with stress and boredom, namely, smoking, eating, nail biting, face touching, and staying still. These activities were selected for their potential psychological implications and captured in an uncontrolled environment to mimic real-life scenarios. The data provides a unique resource for developing machine learning models aimed at recognizing these behaviors, which could lead to real-time analysis and interventions for stress. A custom holder was used to hold the device on the wrists in order to ensure that all participants had consistent orientation and placement. This holder was situated just above the wrist joint, a location typically associated with the placement of smartwatches. The dataset provides a unique opportunity for developing machine learning models for stress & boredom associated activities recognition apart from real-time symptomatic analysis of stress and boredom.

Changes in the incidence of cannabis-related disorders after the Cannabis Act and the COVID-19 pandemic in Québec, Canada.

BACKGROUND: The Canadian Cannabis Act (CCA, implemented in October 2018) and the COVID-19 pandemic (April 2020) might have contributed to cannabis-related harms in Québec, known for its stringent cannabis legal framework. We explored changes in incidence rates of cannabis-related disorders (CRD) diagnoses associated with these events in Québec. METHODS: We utilized linked administrative health data to identify individuals aged 15 year+ newly diagnosed with CRD during hospitalizations, emergency, and outpatients clinics across Québec, from January 2010 and March 2022 (147 months). Interrupted time-series analyses (ITSA) assessed differences (as percentage changes) in sex- and age-standardized, and sex-stratified, monthly incidence rates (per 100,000 population) attributed to the CCA and the COVID-19 pandemic, compared to counterfactual scenarios where pre-events trends would continue unchanged. RESULTS: The overall monthly mean rates of incident diagnoses nearly doubled from the pre-CCA period (1.56 per 100,000 population) to the COVID-19 pandemic period (3.02 per 100,000 population). ITSA revealed no statistically significant level or slope changes between adjacent study periods, except for a decrease in the slope of incidence rates among males by 1.84 % (95 % CI -3.41 to -0.24) during the COVID-19 pandemic compared to the post-CCA period. During the post-CCA period, the trends of incidence rates in the general and male populations grew significantly by 1.22 % (95 % CI 0.08 to 2.35) and 1.44 % (0.04 to 2.84) per month, respectively. Similarly significant increases were observed for the general and female populations during the COVID-19 pandemic, with monthly rates rising by 1.43 % (95 % CI 0.75 to 2.12) and 1.75 % (95 % CI 0.13 to 3.37), respectively. These increases more than doubled pre-CCA rates. CONCLUSIONS: The incidence rates of CRD diagnoses across Québec appears to have increased following the implementation of the CCA and during the COVID-19 pandemic. Our findings echo public health concerns regarding potential cannabis-related harms and are consistent with previous Canadian studies.

Mathematical analysis and prediction of future outbreak of dengue on time-varying contact rate using machine learning approach.

This article introduces a novel mathematical model analyzing the dynamics of Dengue in the recent past, specifically focusing on the 2023 outbreak of this disease. The model explores the patterns and behaviors of dengue fever in Bangladesh. Incorporating a sinusoidal function reveals significant mid-May to Late October outbreak predictions, aligning with the government's exposed data in our simulation. For different amplitudes (A) within a sequence of values (A = 0.1 to 0.5), the highest number of infected mosquitoes occurs in July. However, simulations project that when ßM = 0.5 and A = 0.1, the peak of human infections occurs in late September. Not only the next-generation matrix approach along with the stability of disease-free and endemic equilibrium points are observed, but also a cutting-edge Machine learning (ML) approach such as the Prophet model is explored for forecasting future Dengue outbreaks in Bangladesh. Remarkably, we have fitted our solution curve of infection with the reported data by the government of Bangladesh. We can predict the outcome of 2024 based on the ML Prophet model situation of Dengue will be detrimental and proliferate 25 % compared to 2023. Finally, the study marks a significant milestone in understanding and managing Dengue outbreaks in Bangladesh.