Fitness models provide accurate short-term forecasts of SARS-CoV-2 variant frequency.

Genomic surveillance of pathogen evolution is essential for public health response, treatment strategies, and vaccine development. In the context of SARS-COV-2, multiple models have been developed including Multinomial Logistic Regression (MLR) describing variant frequency growth as well as Fixed Growth Advantage (FGA), Growth Advantage Random Walk (GARW) and Piantham parameterizations describing variant Rt. These models provide estimates of variant fitness and can be used to forecast changes in variant frequency. We introduce a framework for evaluating real-time forecasts of variant frequencies, and apply this framework to the evolution of SARS-CoV-2 during 2022 in which multiple new viral variants emerged and rapidly spread through the population. We compare models across representative countries with different intensities of genomic surveillance. Retrospective assessment of model accuracy highlights that most models of variant frequency perform well and are able to produce reasonable forecasts. We find that the simple MLR model provides ∼0.6% median absolute error and ∼6% mean absolute error when forecasting 30 days out for countries with robust genomic surveillance. We investigate impacts of sequence quantity and quality across countries on forecast accuracy and conduct systematic downsampling to identify that 1000 sequences per week is fully sufficient for accurate short-term forecasts. We conclude that fitness models represent a useful prognostic tool for short-term evolutionary forecasting.

Comparison of RNN-LSTM, TFDF and stacking model approach for weather forecasting in Bangladesh using historical data from 1963 to 2022.

Forecasting the weather in an area characterized by erratic weather patterns and unpredictable climate change is a challenging endeavour. The weather is classified as a non-linear system since it is influenced by various factors that contribute to climate change, such as humidity, average temperature, sea level pressure, and rainfall. A reliable forecasting system is crucial in several industries, including transportation, agriculture, tourism, & development. This study showcases the effectiveness of data mining, meteorological analysis, and machine learning techniques such as RNN-LSTM, TensorFlow Decision Forest (TFDF), and model stacking (including ElasticNet, GradientBoost, KRR, and Lasso) in improving the precision and dependability of weather forecasting. The stacking model strategy entails aggregating multiple base models into a meta-model to address issues of overfitting and underfitting, hence improving the accuracy of the prediction model. To carry out the study, a comprehensive 60-year meteorological record from Bangladesh was gathered, encompassing data on rainfall, humidity, average temperature, and sea level pressure. The results of this study suggest that the stacking average model outperforms the TFDF and RNN-LSTM models in predicting average temperature. The stacking average model achieves an RMSLE of 1.3002, which is a 10.906% improvement compared to the TFDF model. It is worth noting that the TFDF model had previously outperformed the RNN-LSTM model. The performance of the individual stacking model is not as impressive as that of the average model, with the validation results being better in TFDF.

Data-driven blood glucose level prediction in type 1 diabetes: a comprehensive comparative analysis.

Accurate prediction of blood glucose level (BGL) has proven to be an effective way to help in type 1 diabetes management. The choice of input, along with the fundamental choice of model structure, is an existing challenge in BGL prediction. Investigating the performance of different data-driven time series forecasting approaches with different inputs for BGL prediction is beneficial in advancing BGL prediction performance. Limited work has been made in this regard, which has resulted in different conclusions. This paper performs a comprehensive investigation of different data-driven time series forecasting approaches using different inputs. To do so, BGL prediction is comparatively investigated from two perspectives; the model's approach and the model's input. First, we compare the performance of BGL prediction using different data-driven time series forecasting approaches, including classical time series forecasting, traditional machine learning, and deep neural networks. Secondly, for each prediction approach, univariate input, using BGL data only, is compared to a multivariate input, using data on carbohydrate intake, injected bolus insulin, and physical activity in addition to BGL data. The investigation is performed on two publicly available Ohio datasets. Regression-based and clinical-based metrics along with statistical analyses are performed for evaluation and comparison purposes. The outcomes show that the traditional machine learning model is the fastest model to train and has the best BGL prediction performance especially when using multivariate input. Also, results show that simply adding extra variables does not necessarily improve BGL prediction performance significantly, and data fusion approaches may be required to effectively leverage other variables' information.

Parametric seasonal-trend autoregressive neural network for long-term crop price forecasting.

Crop price forecasting is difficult in that supply is not as elastic as demand, therefore, supply and demand should be stabilized through long-term forecasting and pre-response to the price. In this study, we propose a Parametric Seasonal-Trend Autoregressive Neural Network (PaSTANet), which is a hybrid model that includes both a multi-kernel residual convolution neural network model and a Gaussian seasonality-trend model. To compare the performance of the PaSTANet, we used daily data from the Garak market for four crops: onion, radish, Chinese cabbage, and green onion, and performed long-term price forecasts for one year in 2023. The PaSTANet shows good performance on all four crops compared to other conventional statistical and deep learning-based models. In particular, for onion, the (mean absolute error (MAE) for the long-term forecast of 2023 is 107, outperforming the second-best Prophet (152) by 29.6%. Chinese cabbage, radish, and green onion all outperform the existing models with MAE of 2008, 3703, and 557, respectively. Moreover, using the confidence interval, the predicted price was categorized into three intervals: probability, caution, and warning. Comparing the percentage of classified intervals about the true prices in our test set, we found that they accurately detect the large price volatility.

Projections of Extreme Temperature-Related Deaths in the US.

Importance: Extreme heat in the US is increasing due to climate change, while extreme cold is projected to decline. Understanding how extreme temperature along with demographic changes will affect population health is important for devising policies to mitigate the health outcome of climate change. Objective: To assess the burden of extreme temperature-related deaths in the contiguous US currently (2008-2019) and estimate the burden in the mid-21st century (2036-2065). Design, Setting, and Participants: This cross-sectional study used historical (1979-2000) daily mean temperatures to calculate monthly extreme heat (>97.5th percentile value) and extreme cold days (<2.5th percentile value) for all contiguous US counties for 2008 to 2019 (current period). Temperature projections from 20 climate models and county population projections were used to estimate extreme temperature-related deaths for 2036 to 2065 (mid-21st century period). Data were analyzed from November 2023 to July 2024. Exposure: Current monthly frequency of extreme heat days and projected mid-21st century frequency using 2 greenhouse gas emissions scenarios: Shared Socioeconomic Pathway (SSP)2-4.5, representing socioeconomic development with a lower emissions increase, and SSP5-8.5, representing higher emissions increase. Main Outcomes and Measures: Mean annual estimated number of extreme temperature-related excess deaths. Poisson regression model with county, month, and year fixed effects was used to estimate the association between extreme temperature and monthly all-cause mortality for older adults (aged ≥65 years) and younger adults (aged 18-64 years). Results: Across the contiguous US, extreme temperature days were associated with 8248.6 (95% CI, 4242.6-12 254.6) deaths annually in the current period and with 19 348.7 (95% CI, 11 388.7-27 308.6) projected deaths in the SSP2-4.5 scenario and 26 574.0 (95% CI, 15 408.0-37 740.1) in the SSP5-8.5 scenario. The mortality data included 30 924 133 decedents, of whom 15 573 699 were males (50.4%), with 6.3% of Hispanic ethnicity, 11.5% of non-Hispanic Black race, and 79.3% of non-Hispanic White race. Non-Hispanic Black adults (278.2%; 95% CI, 158.9%-397.5%) and Hispanic adults (537.5%; 95% CI, 261.6%-813.4%) were projected to have greater increases in extreme temperature-related deaths from the current period to the mid-21st century period compared with non-Hispanic White adults (70.8%; 95% CI, -5.8% to 147.3%). Conclusions and Relevance: This cross-sectional study found that extreme temperature-related deaths in the contiguous US were projected to increase substantially by mid-21st century, with certain populations, such as non-Hispanic Black and Hispanic adults, projected to disproportionately experience this increase. The results point to the need to mitigate the adverse outcome of extreme temperatures for population health.

Forecasting extremely high ischemic stroke incidence using meteorological time serie.

MOTIVATION: The association between weather conditions and stroke incidence has been a subject of interest for several years, yet the findings from various studies remain inconsistent. Additionally, predictive modelling in this context has been infrequent. This study explores the relationship of extremely high ischaemic stroke incidence and meteorological factors within the Slovak population. Furthermore, it aims to construct forecasting models of extremely high number of strokes. METHODS: Over a five-year period, a total of 52,036 cases of ischemic stroke were documented. Days exhibiting a notable surge in ischemic stroke occurrences (surpassing the 90th percentile of historical records) were identified as extreme cases. These cases were then scrutinized alongside daily meteorological parameters spanning from 2015 to 2019. To create forecasts for the occurrence of these extreme cases one day in advance, three distinct methods were employed: Logistic regression, Random Forest for Time Series, and Croston's method. RESULTS: For each of the analyzed stroke centers, the cross-correlations between instances of extremely high stroke numbers and meteorological factors yielded negligible results. Predictive performance achieved by forecasts generated through multivariate logistic regression and Random Forest for time series analysis, which incorporated meteorological data, was on par with that of Croston's method. Notably, Croston's method relies solely on the stroke time series data. All three forecasting methods exhibited limited predictive accuracy. CONCLUSIONS: The task of predicting days characterized by an exceptionally high number of strokes proved to be challenging across all three explored methods. The inclusion of meteorological parameters did not yield substantive improvements in forecasting accuracy.

Prediction of acute onset of chronic cor pulmonale: comparative analysis of Holt-Winters exponential smoothing and ARIMA model.

BACKGROUND: The aim of this study is to analyze the trend of acute onset of chronic cor pulmonale at Chenggong Hospital of Kunming Yan'an Hospital between January 2018 and December 2022.Additionally, the study will compare the application of the ARIMA model and Holt-Winters model in predicting the number of chronic cor pulmonale cases. METHODS: The data on chronic cor pulmonale cases from 2018 to 2022 were collected from the electronic medical records system of Chenggong Hospital of Kunming Yan'an Hospital. The ARIMA and Holt-Winters models were constructed using monthly case numbers from January 2018 to December 2022 as training data. The performance of the model was tested using the monthly number of cases from January 2023 to December 2023 as the test set. RESULTS: The number of acute onset of chronic cor pulmonale in Chenggong Hospital of Kunming Yan'an Hospital exhibited a downward trend overall from 2018 to 2022. There were more cases in winter and spring, with peaks observed in November to December and January of the following year. The optimal ARIMA model was determined to be ARIMA (0,1,1) (0,1,1)12, while for the Holt-Winters model, the optimal choice was the Holt-Winters multiplicative model. It was found that the Holt-Winters multiplicative model yielded the lowest error. CONCLUSION: The Holt-Winters multiplicative model predicts better accuracy. The diagnosis of acute onset of chronic cor pulmonale is related to many risk factors, therefore, when using temporal models to fit and predict the data, we must consider such factors' influence and try to incorporate them into the models.

Forecasting for Haditha reservoir inflow in the West of Iraq using Support Vector Machine (SVM).

Accurate inflow forecasting is an essential non-engineering strategy to guarantee flood management and boost the effectiveness of the water supply. As inflow is the primary reservoir input, precise inflow forecasting may also offer appropriate reservoir design and management assistance. This study aims to generalize the machine learning model using the support vector machine (SVM), which is support vector regression (SVR), to predict the discharges of the Euphrates River upstream of the Haditha Dam reservoir in Anbar province West of Iraq. Time series data were collected for the period (1986-2024) for the river's daily, monthly, and seasonal flow. Different kernel functions of SVR were applied in this study. The kernels are linear, Quadratic, and Gaussian (RBF). The results showed that the daily time scale is better than the monthly and seasonal performance. In contrast, the linear kernel outperformed the other SVR kernel with a time delay of one day based on the value of the coefficient of determination (R2 = 0.95) and the root mean square error (RMSE = 53.29) m3/sec for predicting daily river flow. The results showed that the proposed machine learning model performed well in predicting the daily flow of the Euphrates River upstream of the Haditha Dam reservoir; this indicates that the model might effectively forecast flows, which helps improve water resource management and dam operations.

CL-Informer: Long time series prediction model based on continuous wavelet transform.

Time series, a type of data that measures how things change over time, remains challenging to predict. In order to improve the accuracy of time series prediction, a deep learning model CL-Informer is proposed. In the Informer model, an embedding layer based on continuous wavelet transform is added so that the model can capture the characteristics of multi-scale data, and the LSTM layer is used to capture the data dependency further and process the redundant information in continuous wavelet transform. To demonstrate the reliability of the proposed CL-Informer model, it is compared with mainstream forecasting models such as Informer, Informer+, and Reformer on five datasets. Experimental results demonstrate that the CL-Informer model achieves an average reduction of 30.64% in MSE across various univariate prediction horizons and a reduction of 10.70% in MSE across different multivariate prediction horizons, thereby improving the accuracy of Informer in long sequence prediction and enhancing the model's precision.

Nonlinear model predictive control of a conductance-based neuron model via data-driven forecasting.

Objective. Precise control of neural systems is essential to experimental investigations of how the brain controls behavior and holds the potential for therapeutic manipulations to correct aberrant network states. Model predictive control, which employs a dynamical model of the system to find optimal control inputs, has promise for dealing with the nonlinear dynamics, high levels of exogenous noise, and limited information about unmeasured states and parameters that are common in a wide range of neural systems. However, the challenge still remains of selecting the right model, constraining its parameters, and synchronizing to the neural system.Approach. As a proof of principle, we used recent advances in data-driven forecasting to construct a nonlinear machine-learning model of a Hodgkin-Huxley type neuron when only the membrane voltage is observable and there are an unknown number of intrinsic currents.Main Results. We show that this approach is able to learn the dynamics of different neuron types and can be used with model predictive control (MPC) to force the neuron to engage in arbitrary, researcher-defined spiking behaviors.Significance.To the best of our knowledge, this is the first application of nonlinear MPC of a conductance-based model where there is only realistically limited information about unobservable states and parameters.

Performance analysis of mathematical methods used to forecast the 2022 New York City Mpox outbreak.

In mid-2022, New York City (NYC) became the epicenter of the US mpox outbreak. We provided real-time mpox case forecasts to the NYC Department of Health and Mental Hygiene to aid in outbreak response. Forecasting methodologies evolved as the epidemic progressed. Initially, lacking knowledge of at-risk population size, we used exponential growth models to forecast cases. Once exponential growth slowed, we used a Susceptible-Exposed-Infectious-Recovered (SEIR) model. Retrospectively, we explored if forecasts could have been improved using an SEIR model in place of our early exponential growth model, with or without knowing the case detection rate. Early forecasts from exponential growth models performed poorly, as 2-week mean absolute error (MAE) grew from 53 cases/week (July 1-14) to 457 cases/week (July 15-28). However, when exponential growth slowed, providing insight into susceptible population size, an SEIR model was able to accurately predict the remainder of the outbreak (7-week MAE: 13.4 cases/week). Retrospectively, we found there was not enough known about the epidemiological characteristics of the outbreak to parameterize an SEIR model early on. However, if the at-risk population and case detection rate were known, an SEIR model could have improved accuracy over exponential growth models early in the outbreak.

Forecasting of coronavirus active cases by utilizing logistic growth model and fuzzy time series techniques.

Coronavirus has long been considered a global epidemic. It caused the deaths of nearly 7.01 million individuals and caused an economic downturn. The number of verified coronavirus cases is increasing daily, putting the whole human race at danger and putting strain on medical experts to eradicate the disease as rapidly as possible. As a consequence, it is vital to predict the upcoming coronavirus positive patients in order to plan actions in the future. Furthermore, it has been discovered all across the globe that asymptomatic coronavirus patients play a significant part in the disease's transmission. This prompted us to incorporate similar examples in order to accurately forecast trends. A typical strategy for analysing the rate of pandemic infection is to use time-series forecasting technique. This would assist us in developing better decision support systems. To anticipate COVID-19 active cases for a few countries, we recommended a hybrid model utilizing a fuzzy time series (FTS) model mixed with a non-linear growth model. The coronavirus positive case outbreak has been evaluated for Italy, Brazil, India, Germany, Pakistan, and Myanmar through June 5, 2020 in phase-1, and January 15, 2022 in phase-2, and forecasts active cases for the next 26 and 14 days respectively. The proposed framework fitting effect outperforms individual logistic growth and the fuzzy time series techniques, with R-scores of 0.9992 in phase-1 and 0.9784 in phase-2. The proposed model provided in this article may be utilised to comprehend a country's epidemic pattern and assist the government in developing better effective interventions.

Real-time AIoT platform for monitoring and prediction of air quality in Southwestern Morocco.

Urbanization and industrialization have led to a significant increase in air pollution, posing a severe environmental and public health threat. Accurate forecasting of air quality is crucial for policymakers to implement effective interventions. This study presents a novel AIoT platform specifically designed for PM2.5 monitoring in Southwestern Morocco. The platform utilizes low-cost sensors to collect air quality data, transmitted via WiFi/3G for analysis and prediction on a central server. We focused on identifying optimal features for PM2.5 prediction using Minimum Redundancy Maximum Relevance (mRMR) and LightGBM Recursive Feature Elimination (LightGBM-RFE) techniques. Furthermore, Bayesian optimization was employed to fine-tune hyperparameters of popular machine learning models for the most accurate PM2.5 concentration forecasts. Model performance was evaluated using Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and the coefficient of determination (R2). Our results demonstrate that the LightGBM model achieved superior performance in PM2.5 prediction, with a significant reduction in RMSE compared to other evaluated models. This study highlights the potential of AIoT platforms coupled with advanced feature selection and hyperparameter optimization for effective air quality monitoring and forecasting.

Prediction of daily new COVID-19 cases - Difficulties and possible solutions.

Epidemiological compartmental models, such as SEIR (Susceptible, Exposed, Infectious, and Recovered) models, have been generally used in analyzing epidemiological data and forecasting the trajectory of transmission of infectious diseases such as COVID-19. Experience shows that accurately forecasting the trajectory of COVID-19 transmission curve is a big challenge for researchers in the field of epidemiological modeling because multiple unquantified factors can affect the trajectory of COVID-19 transmission. In the past years, we used a new compartmental model, l-i SEIR model, to analyze the COVID-19 transmission trend in the United States. Unlike the conventional SEIR model and the delayed SEIR model that use or partially use the approximation of temporal homogeneity, the l-i SEIR model takes into account chronological order of infected individuals in both latent (l) period and infectious (i) period, and thus improves the accuracy in forecasting the trajectory of transmission of infectious diseases, especially during periods of rapid rise or fall in the number of infections. This paper describes (1) how to use the new SEIR model (a mechanistic model) combined with fitting methods to simulate or predict trajectory of COVID-19 transmission, (2) how social interventions and new variants of COVID-19 significantly change COVID-19 transmission trends by changing transmission rate coefficient ßn, the fraction of susceptible people (Sn/N), and the reinfection rate, (3) why accurately forecasting COVID-19 transmission trends is difficult, (4) what are the strategies that we have used to improve the forecast outcome and (5) what are some successful examples that we have obtained.

Forecasting rheumatoid arthritis patient arrivals by including meteorological factors and air pollutants.

The burden of rheumatoid arthritis (RA) has gradually elevated, increasing the need for medical resource redistribution. Forecasting RA patient arrivals can be helpful in managing medical resources. However, no relevant studies have been conducted yet. This study aims to construct a long short-term memory (LSTM) model, a deep learning model recently developed for novel data processing, to forecast RA patient arrivals considering meteorological factors and air pollutants and compares this model with traditional methods. Data on RA patients, meteorological factors and air pollutants from 2015 to 2022 were collected and normalized to construct moving average (MA)- and autoregressive (AR)-based and LSTM models. After data normalization, the root mean square error (RMSE) was adopted to evaluate models' forecast ability. A total of 2422 individuals were enrolled. Not using the environmental data, the RMSEs of the MA- and AR-based models' test sets are 0.131, 0.132, and 0.117 when the training set: test set ratio is 2:1, 3:1, and 7:1, while they are 0.110, 0.130, and 0.112 for the univariate LSTM models. Considering meteorological factors and air pollutants, the RMSEs of the MA- and AR-based model test sets were 0.142, 0.303, and 0.164 when the training set: test set ratio is 2:1, 3:1, and 7:1, while they were 0.108, 0.119, and 0.109 for the multivariable LSTM models. Our study demonstrated that LSTM models can forecast RA patient arrivals more accurately than MA- and AR-based models for datasets of all three sizes. Considering the meteorological factors and air pollutants can further improve the forecasting ability of the LSTM models. This novel method provides valuable information for medical management, the optimization of medical resource redistribution, and the alleviation of resource shortages.

A comparative analysis of classical and machine learning methods for forecasting TB/HIV co-infection.

TB/HIV coinfection poses a complex public health challenge. Accurate forecasting of future trends is essential for efficient resource allocation and intervention strategy development. This study compares classical statistical and machine learning models to predict TB/HIV coinfection cases stratified by gender and the general populations. We analyzed time series data using exponential smoothing and ARIMA to establish the baseline trend and seasonality. Subsequently, machine learning models (SVR, XGBoost, LSTM, CNN, GRU, CNN-GRU, and CNN-LSTM) were employed to capture the complex dynamics and inherent non-linearities of TB/HIV coinfection data. Performance metrics (MSE, MAE, sMAPE) and the Diebold-Mariano test were used to evaluate the model performance. Results revealed that Deep Learning models, particularly Bidirectional LSTM and CNN-LSTM, significantly outperformed classical methods. This demonstrates the effectiveness of Deep Learning for modeling TB/HIV coinfection time series and generating more accurate forecasts.

Valuing Nursing Practice: Laying the Future Foundations for Nursing.

Nursing has always been a cost for the institutions within which nurses work. This fact has influenced almost everything that affects how nurses are utilized and valued. As a cost, nurses are closely managed on the margin, always constrained by the resource machinations of organizations and systems with little determination or enumeration of the contributions nurses make to the service and financial value represented by algorithms and metrics that enumerate and demonstrate nurse's impact and contribution to service and financial value. This article further pushes the boundaries of this circumstance, challenging nurse and health leaders to reconceptualize nursing contribution and recalibrate the determination and calculation of nursing value as a sustainable baseline for nursing leadership for the future.

Joint-outcome prediction markets for climate risks.

Predicting future climate requires the integration of knowledge and expertise from a wide range of disciplines. Predictions must account for climate-change mitigation policies which may depend on climate predictions. This interdependency, or "circularity", means that climate predictions must be conditioned on emissions of greenhouse gases (GHGs). Long-range forecasts also suffer from information asymmetry because users cannot use track records to judge the skill of providers. The problems of aggregation, circularity, and information asymmetry can be addressed using prediction markets with joint-outcome spaces, allowing simultaneous forecasts of GHG concentrations and temperature. The viability of prediction markets with highly granular, joint-outcome spaces was tested with markets for monthly UK rainfall and temperature. The experiments demonstrate these markets can aggregate the judgments of experts with relevant expertise, and suggest similarly structured markets, with longer horizons, could provide a mechanism to produce credible forecasts of climate-related risks for policy making, planning, and risk disclosure.

Enhancing COVID-19 forecasting precision through the integration of compartmental models, machine learning and variants.

Predicting epidemic evolution is essential for making informed decisions and guiding the implementation of necessary countermeasures. Computational models are vital tools that provide insights into illness progression and enable early detection, proactive intervention, and targeted preventive measures. This paper introduces Sybil, a framework that integrates machine learning and variant-aware compartmental models, leveraging a fusion of data-centric and analytic methodologies. To validate and evaluate Sybil's forecasts, we employed COVID-19 data from several European and U.S. states. The dataset included the number of new and recovered cases, fatalities, and variant presence over time. We evaluate the forecasting precision of Sybil in periods in which there is a change in the trend of the pandemic evolution or a new variant appears. Results demonstrate that Sybil outperforms conventional data-centric approaches, being able to forecast accurately the changes in the trend, the magnitude of these changes, and the future prevalence of new variants.

Preseason maize and wheat yield forecasts for early warning of crop failure.

Provided the considerable logistical challenges of anticipatory action and disaster response programs, there is a need for early warning of crop failures at lead times of six to twelve months. But crop yield forecasts at these lead times are virtually nonexistent. By leveraging recent advances in climate forecasting, we demonstrate that global preseason crop yield forecasts are not only possible but are skillful over considerable portions of cropland. Globally, maize and wheat forecasts are skillful at lead times of up to a year ahead of harvest for 15% and 30% of harvested areas, respectively. Forecasts are most skillful in Southeast Africa and Southeast Asia for maize and parts of South and Central Asia, Australia, and Southeast South America for wheat. Wheat forecasts, furthermore, remain skillful at lead times of over 18 months ahead of harvest in some locations. Our results demonstrate that the potential for preseason crop yield forecasts is greater than previously appreciated.