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.].

Melanin-based color variation in response to changing climates in snakes.

Melanism, the process of heavier melanin deposition, can interact with climate variation at both micro and macro scales, ultimately influencing color evolution in organisms. While the ecological processes regulating melanin production in relation to climate have been extensively studied, intraspecific variations of melanism are seldom considered. Such scientific gap hampers our understanding of how species adapt to rapidly changing climates. For example, dark coloration may lead to higher heat absorption and be advantageous in cool climates, but also in hot environments as a UV or antimicrobial protection mechanism. To disentangle such opposing predictions, here we examined the effect of climate on shaping melanism variation in 150 barred grass snakes (Natrix helvetica) and 383 green whip snakes (Hierophis viridiflavus) across Italy. By utilizing melanistic morphs (charcoal and picturata in N. helvetica, charcoal and abundistic in H. viridiflavus) and compiling observations from 2002 to 2021, we predicted that charcoal morphs in H. viridiflavus would optimize heat absorption in cold environments, while offering protection from excessive UV radiation in N. helvetica within warm habitats; whereas picturata and abundistic morphs would thrive in humid environments, which naturally have a denser vegetation and wetter substrates producing darker ambient light, thus providing concealment advantages. While picturata and abundistic morphs did not align with our initial humidity expectations, the charcoal morph in N. helvetica is associated with UV environments, suggesting protection mechanisms against damaging solar radiation. H. viridiflavus is associated with high precipitations, which might offer antimicrobial protection. Overall, our results provide insights into the correlations between melanin-based color morphs and climate variables in snake populations. While suggestive of potential adaptive responses, future research should delve deeper into the underlying mechanisms regulating this relationship.

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.

A causal machine-learning framework for studying policy impact on air pollution: A case-study in COVID-19 lockdowns.

When studying the impact of policy interventions or natural experiments on air pollution, such as new environmental policies and opening or closing an industrial facility, careful statistical analysis is needed to separate causal changes from other confounding factors. Using COVID-19 lockdowns as a case-study, we present a comprehensive framework for estimating and validating causal changes from such perturbations. We propose using flexible machine learning-based comparative interrupted time series (CITS) models for estimating such a causal effect. We outline the assumptions required to identify causal effects, showing that many common methods rely on strong assumptions that are relaxed by machine learning models. For empirical validation, we also propose a simple diagnostic criterion, guarding against false effects in baseline years when there was no intervention. The framework is applied to study the impact of COVID-19 lockdowns on NO2 in the eastern US. The machine learning approaches guard against false effects better than common methods and suggest decreases in NO2 in Boston, New York City, Baltimore, and Washington D.C. The study showcases the importance of our validation framework in selecting a suitable method and the utility of a machine learning based CITS model for studying causal changes in air pollution time series.

Leveraging VQ-VAE tokenization for autoregressive modeling of medical time series.

In this work, we present CodeAR, a medical time series generative model for electronic health record (EHR) synthesis. CodeAR employs autoregressive modeling on discrete tokens obtained using a vector quantized-variational autoencoder (VQ-VAE), which addresses key challenges of accurate distribution modeling and patient privacy preservation in the medical domain. The proposed model is trained with next-token prediction instead of a regression problem for more accurate distribution modeling, where the autoregressive property of CodeAR is useful to capture the inherent causality in time series data. In addition, the compressive property of the VQ-VAE prevents CodeAR from memorizing the original training data, which ensures patient privacy. Experimental results demonstrate that CodeAR outperforms the baseline autoregressive-based and GAN-based models in terms of maximum mean discrepancy (MMD) and Train on Synthetic, Test on Real tests. Our results highlight the effectiveness of autoregressive modeling on discrete tokens, the utility of CodeAR in causal modeling, and its robustness against data memorization.

The Role of Robotics in Meeting Institutional Goals: A Unified Strategy to Facilitate Program Excellence.

PURPOSE: The rapid expansion of robotic surgical equipment necessitates a review of the needs and challenges faced by hospitals introducing robots for the first time to compete with experienced institutions. The aim of this study was to analyze the impact of robotic surgery on our hospital compared to open and laparoscopic surgery, examine internal transformations, and assess regional, domestic, and international implications. METHODS: A retrospective review was conducted of electronic medical records (EMRs) from 2019 to 2022 at Inha University Hospital, including patients who underwent common robotic procedures and equivalent open and laparoscopic operations. The study investigated clinical and operational performance changes in the hospital after the introduction of robotic technology. It also evaluated the operational effectiveness of robot implementation in local, national, and international contexts. To facilitate comparison with other hospitals, the data were transmitted to Intuitive Surgical, Inc. for analysis. The study was conducted in compliance with domestic personal information regulations and received approval from our Institutional Review Board. RESULTS: We analyzed EMR data from 3,147 patients who underwent surgical treatment. Over a period of 3.5 years, the adoption of robotic technology in a hospital setting significantly enhanced the technical skills of all professors involved. The introduction of robotic systems led to increased patient utilization of conventional surgical techniques, as well as a rise in the number of patients choosing robotic surgery. This collective trend contributed to an overall increase in patient numbers. This favorable evaluation of the operational effectiveness of our hospital's robot implementation in the context of local, national, and global factors is expected to positively influence policy changes. CONCLUSION: Stakeholders should embrace data science and evidence-based techniques to generate valuable insights from objective data, assess the health of robot-assisted surgery programs, and identify opportunities for improvement and excellence.

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.

Promoting fairness in activity recognition algorithms for patient's monitoring and evaluation systems in healthcare.

Researchers face the challenge of defining subject selection criteria when training algorithms for human activity recognition tasks. The ongoing uncertainty revolves around which characteristics should be considered to ensure algorithmic robustness across diverse populations. This study aims to address this challenge by conducting an analysis of heterogeneity in the training data to assess the impact of physical characteristics and soft-biometric attributes on activity recognition performance. The performance of various state-of-the-art deep neural network architectures (tCNN, hybrid-LSTM, Transformer model) processing time-series data using the IntelliRehab (IRDS) dataset was evaluated. By intentionally introducing bias into the training data based on human characteristics, the objective is to identify the characteristics that influence algorithms in motion analysis. Experimental findings reveal that the CNN-LSTM model achieved the highest accuracy, reaching 88%. Moreover, models trained on heterogeneous distributions of disability attributes exhibited notably higher accuracy, reaching 51%, compared to those not considering such factors, which scored an average of 33%. These evaluations underscore the significant influence of subjects' characteristics on activity recognition performance, providing valuable insights into the algorithm's robustness across diverse populations. This study represents a significant step forward in promoting fairness and trustworthiness in artificial intelligence by quantifying representation bias in multi-channel time-series activity recognition data within the healthcare domain.

Predictability of ecological and evolutionary dynamics in a changing world.

Ecological and evolutionary predictions are being increasingly employed to inform decision-makers confronted with intensifying pressures on biodiversity. For these efforts to effectively guide conservation actions, knowing the limit of predictability is pivotal. In this study, we provide realistic expectations for the enterprise of predicting changes in ecological and evolutionary observations through time. We begin with an intuitive explanation of predictability (the extent to which predictions are possible) employing an easy-to-use metric, predictive power PP(t). To illustrate the challenge of forecasting, we then show that among insects, birds, fishes and mammals, (i) 50% of the populations are predictable at most 1 year in advance and (ii) the median 1-year-ahead predictive power corresponds to a prediction R 2 of only 20%. Predictability is not an immutable property of ecological systems. For example, different harvesting strategies can impact the predictability of exploited populations to varying degrees. Moreover, incorporating explanatory variables, accounting for time trends and considering multivariate time series can enhance predictability. To effectively address the challenge of biodiversity loss, researchers and practitioners must be aware of the information within the available data that can be used for prediction and explore efficient ways to leverage this knowledge for environmental stewardship.

Accuracy of US CDC COVID-19 forecasting models.

Accurate predictive modeling of pandemics is essential for optimally distributing biomedical resources and setting policy. Dozens of case prediction models have been proposed but their accuracy over time and by model type remains unclear. In this study, we systematically analyze all US CDC COVID-19 forecasting models, by first categorizing them and then calculating their mean absolute percent error, both wave-wise and on the complete timeline. We compare their estimates to government-reported case numbers, one another, as well as two baseline models wherein case counts remain static or follow a simple linear trend. The comparison reveals that around two-thirds of models fail to outperform a simple static case baseline and one-third fail to outperform a simple linear trend forecast. A wave-by-wave comparison of models revealed that no overall modeling approach was superior to others, including ensemble models and errors in modeling have increased over time during the pandemic. This study raises concerns about hosting these models on official public platforms of health organizations including the US CDC which risks giving them an official imprimatur and when utilized to formulate policy. By offering a universal evaluation method for pandemic forecasting models, we expect this study to serve as the starting point for the development of more accurate models.

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.

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'.

Trends and projections of mild and moderate hearing loss among adolescents, young adults, middle-aged adults and age-standardised population in Malaysia from 1996 to 2030.

PURPOSE: This study aims to assess the prevalence of mild and moderate hearing loss spanning three decades, from 1990 to 2019, and to project the anticipated trends from 2020 to 2030 among adolescents, young adults, middle-aged adults, and age-standardised groups in Malaysia. METHODS: This study involved secondary data analysis of mild and moderate hearing loss prevalence over 30 years among the Malaysian population aged 15-19, 25-29, 35-39, 45-49, and age-standardised groups. Subsequently, three time-series models were evaluated and the best models with the minimal Mean Absolute Percentage Error (MAPE) and Root Mean Squared Error (RMSE) were selected for projecting the prevalence of hearing loss until 2030. RESULTS: A relatively stable trend of mild hearing loss prevalence and gradual decline of moderate hearing loss were observed across all age groups throughout the study period. The prevalence of mild hearing loss was consistently higher than moderate hearing loss across all age groups, with its prevalence increasing with age. The projected prevalence of hearing loss exhibits a gradual declining trend in the future for all age groups, except for mild hearing loss for the 15-19-year-old group. CONCLUSION: Over the past 30 years, there has been a relatively stable and slightly declining trend in the prevalence of mild and moderate hearing loss among the Malaysian population, respectively with projections showing a slow reduction in the future. These findings highlighted the need for identifying the best intervention and vulnerable age groups, directing increased resources and prioritization towards them.

Eigen-entropy based time series signatures to support multivariate time series classification.

Most current algorithms for multivariate time series classification tend to overlook the correlations between time series of different variables. In this research, we propose a framework that leverages Eigen-entropy along with a cumulative moving window to derive time series signatures to support the classification task. These signatures are enumerations of correlations among different time series considering the temporal nature of the dataset. To manage dataset's dynamic nature, we employ preprocessing with dense multi scale entropy. Consequently, the proposed framework, Eigen-entropy-based Time Series Signatures, captures correlations among multivariate time series without losing its temporal and dynamic aspects. The efficacy of our algorithm is assessed using six binary datasets sourced from the University of East Anglia, in addition to a publicly available gait dataset and an institutional sepsis dataset from the Mayo Clinic. We use recall as the evaluation metric to compare our approach against baseline algorithms, including dependent dynamic time warping with 1 nearest neighbor and multivariate multi-scale permutation entropy. Our method demonstrates superior performance in terms of recall for seven out of the eight datasets.

Improving pressure injury risk assessment using real-world data from skilled nursing facilities: A cohort study.

This study aimed to improve the predictive accuracy of the Braden assessment for pressure injury risk in skilled nursing facilities (SNFs) by incorporating real-world data and training a survival model. A comprehensive analysis of 126 384 SNF stays and 62 253 in-house pressure injuries was conducted using a large calibrated wound database. This study employed a time-varying Cox Proportional Hazards model, focusing on variations in Braden scores, demographic data and the history of pressure injuries. Feature selection was executed through a forward-backward process to identify significant predictive factors. The study found that sensory and moisture Braden subscores were minimally contributive and were consequently discarded. The most significant predictors of increased pressure injury risk were identified as a recent (within 21 days) decrease in Braden score, low subscores in nutrition, friction and activity, and a history of pressure injuries. The model demonstrated a 10.4% increase in predictive accuracy compared with traditional Braden scores, indicating a significant improvement. The study suggests that disaggregating Braden scores and incorporating detailed wound histories and demographic data can substantially enhance the accuracy of pressure injury risk assessments in SNFs. This approach aligns with the evolving trend towards more personalized and detailed patient care. These findings propose a new direction in pressure injury risk assessment, potentially leading to more effective and individualized care strategies in SNFs. The study highlights the value of large-scale data in wound care, suggesting its potential to enhance quantitative approaches for pressure injury risk assessment and supporting more accurate, data-driven clinical decision-making.