Forecasting influenza epidemics in China using transmission dynamic model with absolute humidity.

Background: An influenza forecasting system is critical to influenza epidemic preparedness. Low temperature has long been recognized as a condition favoring influenza epidemic, yet it fails to justify the summer influenza peak in tropics/subtropics. Recent studies have suggested that absolute humidity (AH) had a U-shape relationship with influenza survival and transmission across climate zones, indicating that a unified influenza forecasting system could be established for China with various climate conditions. Methods: Our study has generated weekly influenza forecasts by season and type/subtype in northern and southern China from 2011 to 2021, using a forecasting system combining an AH-driven susceptible-infected-recovered-susceptible (SIRS) model and the ensemble adjustment Kalman filter (EAKF). Model performance was assessed by sensitivity and specificity in predicting epidemics, and by accuracies in predicting peak timing and magnitude. Results: Our forecast system can generally well predict seasonal influenza epidemics (mean sensitivity>87.5%; mean specificity >80%). The average forecast accuracies were 82% and 60% for peak timing and magnitude at 3-6 weeks ahead for northern China, higher than those of 42% and 20% for southern China. The accuracy was generally better when the forecast was made closer to the actual peak time. Discussion: The established AH-driven forecasting system can generally well predict the occurrence of seasonal influenza epidemics in China.

Seizure forecasting with ultra long-term EEG signals.

OBJECTIVE: The apparent randomness of seizure occurrence affects greatly the quality of life of persons with epilepsy. Since seizures are often phase-locked to multidien cycles of interictal epileptiform activity, a recent forecasting scheme, exploiting RNS data, is capable of forecasting seizures days in advance. METHODS: We tested the use of a bandpass filter to capture the universal mid-term dynamics enabling both patient-specific and cross-patient forecasting. In a retrospective study, we explored the feasibility of the scheme on three long-term recordings obtained by the NeuroPace RNS System, the NeuroVista intracranial, and the UNEEG subcutaneous devices, respectively. RESULTS: Better-than-chance forecasting was observed in 15 (83 %) of 18 patients, and in 16 (89 %) patients for daily and hourly forecast, respectively. Meaningful forecast up to 30 days could be achieved in 4 (22 %) patients for hourly forecast frequency. The cross-patient performance decreased only marginally and was patient-wise strongly correlated with the patient-specific one. Comparable performance was obtained for NeuroVista and UNEEG data sets. SIGNIFICANCE: The feasibility of cross-patient forecasting supports the universal importance of mid-term dynamics for seizure forecasting, demonstrates promising inter-subject-applicability of the scheme on ultra long-term EEG recordings, and highlights its huge potential for clinical use.

Analysis of risk factors and construction of nomogram model for arthroscopic single-row rivet repair.

BACKGROUND: The factors influencing the clinical outcome of arthroscopic rotator cuff repair are not fully understood. PURPOSE: To explore the factors related to the postoperative outcome of arthroscopic single-row rivet rotator cuff repair in patients with rotator cuff injury and to construct the related nomogram risk prediction model. METHODS: 207 patients with rotator cuff injury who underwent arthroscopic single-row rivet rotator cuff repair were reviewed. The differences of preoperative and postoperative Visual Analogue Score (VAS) scores and University of California, Los Angeles (UCLA) scores were analyzed and compared. The postoperative UCLA score of 29 points was taken as the critical point, and the patients were divided into good recovery group and poor recovery group, and binary logstic regression analysis was performed. According to the results of multivariate logistic regression analysis, the correlation nomogram model was constructed, and the calibration chart was used, AUC, C-index. The accuracy, discrimination and clinical value of the prediction model were evaluated by decision curve analysis. Finally, internal validation is performed using self-random sampling. RESULTS: The mean follow-up time was 29.92 ± 17.20 months. There were significant differences in VAS score and UCLA score between preoperative and final follow-up (p < 0.05); multivariate regression analysis showed: Combined frozen shoulder (OR = 3.890, 95% CI: 1.544 ∼ 9.800), massive rotator cuff tear (OR = 3.809, 95%CI: 1.218 ∼ 11.908), More rivets number (OR = 2.118, 95%CI: 1.386 ∼ 3.237), lower preoperative UCLA score (OR = 0.831, 95%CI: 0.704-0.981) were adverse factors for the postoperative effect of arthroscopic rotator cuff repair. Use these factors to build a nomogram. The nomogram showed good discriminant and predictive power, with AUC of 0.849 and C-index of 0.900 (95% CI: 0.845 ∼ 0.955), and the corrected C index was as high as 0.836 in internal validation. Decision curve analysis also showed that the nomogram could be used clinically when intervention was performed at a threshold of 2%∼91%. CONCLUSION: Combined frozen shoulders, massive rotator cuff tears, and increased number of rivets during surgery were all factors associated with poor outcome after arthroscopic rotator cuff repair, while higher preoperative UCLA scores were factors associated with good outcome after arthroscopic rotator cuff repair. This study provides clinicians with a new and relatively accurate nomogram model.

Transferability of ecological forecasting models to novel biotic conditions in a long-term experimental study.

Ecological forecasting models play an increasingly important role for managing natural resources and assessing our fundamental knowledge of processes driving ecological dynamics. As global environmental change pushes ecosystems beyond their historical conditions, the utility of these models may depend on their transferability to novel conditions. Because species interactions can alter resource use, timing of reproduction, and other aspects of a species' realized niche, changes in biotic conditions, which can arise from community reorganization events in response to environmental change, have the potential to impact model transferability. Using a long-term experiment on desert rodents, we assessed model transferability under novel biotic conditions to better understand the limitations of ecological forecasting. We show that ecological forecasts can be less accurate when the models generating them are transferred to novel biotic conditions and that the extent of model transferability can depend on the species being forecast. We also demonstrate the importance of incorporating uncertainty into forecast evaluation with transferred models generating less accurate and more uncertain forecasts. These results suggest that how a species perceives its competitive landscape can influence model transferability and that when uncertainties are properly accounted for, transferred models may still be appropriate for decision making. Assessing the extent of the transferability of forecasting models is a crucial step to increase our understanding of the limitations of ecological forecasts.

How can restaurants entice patrons to order environmentally sustainable dishes? Testing new approaches based on hedonic psychology and affective forecasting theory.

Encouraging restaurant guests to order vegetarian dishes plays a key role in creating a more environmentally sustainable tourism sector. However, for many consumers eating a meat dish is an important aspect of their enjoyment-focused restaurant experience. Identifying new approaches that support restaurants in selling more vegetarian dishes are urgently needed. Drawing from hedonic psychology and affective forecasting theory, this study tests two interventions aimed at directing ordering towards specific vegetarian dishes in a scenario-based survey experiment with 742 consumers. Results show the potential of affective forecasting as a promising psychological mechanism. Displaying an appetising picture of a vegetarian dish on a menu increases stated ordering of the dish because the picture directs consumer attention to the dish and triggers them to imagine eating the dish. Consumers who imagine eating the dish feel stronger anticipated enjoyment of eating it. Adding to the picture an invitation to imagine eating the dish does not further increase the effect. This study explains the psychological mechanism of how a picture of an appetising vegetarian dish changes food choices and provides restaurants with a cost-effective measure to direct ordering towards more environmentally sustainable dishes.

Forecasting severe respiratory disease hospitalizations using machine learning algorithms.

BACKGROUND: Forecasting models predicting trends in hospitalization rates have the potential to inform hospital management during seasonal epidemics of respiratory diseases and the associated surges caused by acute hospital admissions. Hospital bed requirements for elective surgery could be better planned if it were possible to foresee upcoming peaks in severe respiratory illness admissions. Forecasting models can also guide the use of intervention strategies to decrease the spread of respiratory pathogens and thus prevent local health system overload. In this study, we explore the capability of forecasting models to predict the number of hospital admissions in Auckland, New Zealand, within a three-week time horizon. Furthermore, we evaluate probabilistic forecasts and the impact on model performance when integrating laboratory data describing the circulation of respiratory viruses. METHODS: The dataset used for this exploration results from active hospital surveillance, in which the World Health Organization Severe Acute Respiratory Infection (SARI) case definition was consistently used. This research nurse-led surveillance has been implemented in two public hospitals in Auckland and provides a systematic laboratory testing of SARI patients for nine respiratory viruses, including influenza, respiratory syncytial virus, and rhinovirus. The forecasting strategies used comprise automatic machine learning, one of the most recent generative pre-trained transformers, and established artificial neural network algorithms capable of univariate and multivariate forecasting. RESULTS: We found that machine learning models compute more accurate forecasts in comparison to naïve seasonal models. Furthermore, we analyzed the impact of reducing the temporal resolution of forecasts, which decreased the model error of point forecasts and made probabilistic forecasting more reliable. An additional analysis that used the laboratory data revealed strong season-to-season variations in the incidence of respiratory viruses and how this correlates with total hospitalization cases. These variations could explain why it was not possible to improve forecasts by integrating this data. CONCLUSIONS: Active SARI surveillance and consistent data collection over time enable these data to be used to predict hospital bed utilization. These findings show the potential of machine learning as support for informing systems for proactive hospital management.

Harnessing Flex Point Symmetry to Estimate Logistic Tumor Population Growth.

The observed time evolution of a population is well approximated by a logistic growth function in many research fields, including oncology, ecology, chemistry, demography, economy, linguistics, and artificial neural networks. Initial growth is exponential, then decelerates as the population approaches its limit size, i.e., the carrying capacity. In mathematical oncology, the tumor carrying capacity has been postulated to be dynamically evolving as the tumor overcomes several evolutionary bottlenecks and, thus, to be patient specific. As the relative tumor-over-carrying capacity ratio may be predictive and prognostic for tumor growth and treatment response dynamics, it is paramount to estimate it from limited clinical data. We show that exploiting the logistic function's rotation symmetry can help estimate the population's growth rate and carry capacity from fewer data points than conventional regression approaches. We test this novel approach against published pan-cancer animal and human breast cancer data, achieving a 30% to 40% reduction in the time at which subsequent data collection is necessary to estimate the logistic growth rate and carrying capacity correctly. These results could improve tumor dynamics forecasting and augment the clinical decision-making process.

MLFGCN: short-term residential load forecasting via graph attention temporal convolution network.

Introduction: Residential load forecasting is a challenging task due to the random fluctuations caused by complex correlations and individual differences. The existing short-term load forecasting models usually introduce external influencing factors such as climate and date. However, these additional information not only bring computational burden to the model, but also have uncertainty. To address these issues, we propose a novel multi-level feature fusion model based on graph attention temporal convolutional network (MLFGCN) for short-term residential load forecasting. Methods: The proposed MLFGCN model fully considers the potential long-term dependencies in a single load series and the correlations between multiple load series, and does not require any additional information to be added. Temporal convolutional network (TCN) with gating mechanism is introduced to learn potential long-term dependencies in the original load series. In addition, we design two graph attentive convolutional modules to capture potential multi-level dependencies in load data. Finally, the outputs of each module are fused through an information fusion layer to obtain the highly accurate forecasting results. Results: We conduct validation experiments on two real-world datasets. The results show that the proposed MLFGCN model achieves 0.25, 7.58% and 0.50 for MAE, MAPE and RMSE, respectively. These values are significantly better than those of baseline models. Discussion: The MLFGCN algorithm proposed in this paper can significantly improve the accuracy of short-term residential load forecasting. This is achieved through high-quality feature reconstruction, comprehensive information graph construction and spatiotemporal features capture.

The impact of a web-based prognostic calculator on prognostic confidence in outpatient palliative care.

PURPOSE: Clinicians are often uncertain about their prognostic estimates, which may impede prognostic communication and clinical decision-making. We assessed the impact of a web-based prognostic calculator on physicians' prognostic confidence. METHODS: In this prospective study, palliative care physicians estimated the prognosis of patients with advanced cancer in an outpatient clinic using the temporal, surprise, and probabilistic approaches for 6 m, 3 m, 2 m, 1 m, 2 w, 1 w, and 3 d. They then reviewed information from www.predictsurvival.com , which calculated survival estimates from seven validated prognostic scores, including the Palliative Prognostic Score, Palliative Prognostic Index, and Palliative Performance Status, and again provided their prognostic estimates after calculator use. The primary outcome was prognostic confidence in temporal CPS (0-10 numeric rating scale, 0 = not confident, 10 = most confident). RESULTS: Twenty palliative care physicians estimated prognoses for 217 patients. The mean (standard deviation) prognostic confidence significantly increased from 5.59 (1.68) before to 6.94 (1.39) after calculator use (p < 0.001). A significantly greater proportion of physicians reported feeling confident enough in their prognosis to share it with patients (44% vs. 74%, p < 0.001) and formulate care recommendations (80% vs. 94%, p < 0.001) after calculator use. Prognostic accuracy did not differ significantly before or after calculator use, ranging from 55-100%, 29-98%, and 48-100% for the temporal, surprise, and probabilistic approaches, respectively. CONCLUSION: This web-based prognostic calculator was associated with increased prognostic confidence and willingness to discuss prognosis. Further research is needed to examine how prognostic tools may augment prognostic discussions and clinical decision-making.

Predicting public mental health needs in a crisis using social media indicators: a Singapore big data study.

Mental health issues have increased substantially since the onset of the COVID-19 pandemic. However, health policymakers do not have adequate data and tools to predict mental health demand, especially amid a crisis. Using time-series data collected in Singapore, this study examines if and how algorithmically measured emotion indicators from Twitter posts can help forecast emergency mental health needs. We measured the mental health needs during 549 days from 1 July 2020 to 31 December 2021 using the public's daily visits to the emergency room of the country's largest psychiatric hospital and the number of users with "crisis" state assessed through a government-initiated online mental health self-help portal. Pairwise Granger-causality tests covering lag length from 1 day to 5 days indicated that forecast models using Twitter joy, anger and sadness emotions as predictors perform significantly better than baseline models using past mental health needs data alone (e.g., Joy Intensity on IMH Visits, χ2 = 14·9, P < ·001***; Sadness Count on Mindline Crisis, χ2 = 4·6, P = ·031*, with a one-day lag length). The findings highlight the potential of new early indicators for tracking emerging public mental health needs.

A combined neural ODE-Bayesian optimization approach to resolve dynamics and estimate parameters for a modified SIR model with immune memory.

We propose a novel hybrid approach that integrates Neural Ordinary Differential Equations (NODEs) with Bayesian optimization to address the dynamics and parameter estimation of a modified time-delay-type Susceptible-Infected-Removed (SIR) model incorporating immune memory. This approach leverages a neural network to produce continuous multi-wave infection profiles by learning from both data and the model. The time-delay component of the SIR model, expressed through a convolutional integral, results in an integro-differential equation. To resolve these dynamics, we extend the NODE framework, employing a Runge-Kutta solver, to handle the challenging convolution integral, enabling us to fit the data and learn the parameters and dynamics of the model. Additionally, through Bayesian optimization, we enhance prediction accuracy while focusing on long-term dynamics. Our model, applied to COVID-19 data from Mexico, South Africa, and South Korea, effectively learns critical time-dependent parameters and provides accurate short- and long-term predictions. This combined methodology allows for early prediction of infection peaks, offering significant lead time for public health responses.

Long- and short-run asymmetric impacts of climate variation on tuberculosis based on a time series study.

Distinguishing between long-term and short-term effects allows for the identification of different response mechanisms. This study investigated the long- and short-run asymmetric impacts of climate variation on tuberculosis (TB) and constructed forecasting models using the autoregressive distributed lag (ARDL) and nonlinear ARDL (NARDL). TB showed a downward trend, peaking in March-May per year. A 1 h increment or decrement in aggregate sunshine hours resulted in an increase of 32 TB cases. A 1 m/s increment and decrement in average wind velocity contributed to a decrement of 3600 and 5021 TB cases, respectively (Wald long-run asymmetry test [WLR] = 13.275, P < 0.001). A 1% increment and decrement in average relative humidity contributed to an increase of 115 and 153 TB cases, respectively. A 1 hPa increment and decrement in average air pressure contributed to a decrease of 318 and 91 TB cases, respectively (WLR = 7.966, P = 0.005). ∆temperature(-), ∆(sunshine hours)( -), ∆(wind velocity)(+) and ∆(wind velocity)(-) at different lags had a meaningful short-run effect on TB. The NARDL outperformed the ARDL in forecasting. Climate variation has significant long- and short-run asymmetric impacts on TB. By incorporating both dimensions of effects into the NARDL, the accuracy of the forecasts and policy recommendations for TB can be enhanced.

Predicting agricultural and meteorological droughts using Holt Winter Conventional 2D-Long Short-Term Memory (HW-Conv2DLSTM).

Drought is an extended shortage of rainfall resulting in water scarcity and affecting a region's social and economic conditions through environmental deterioration. Its adverse environmental effects can be minimised by timely prediction. Drought detection uses only ground observation stations, but satellite-based supervision scans huge land mass stretches and offers highly effective monitoring. This paper puts forward a novel drought monitoring system using satellite imagery by considering the effects of droughts that devastated agriculture in Thanjavur district, Tamil Nadu, between 2000 and 2022. The proposed method uses Holt Winter Conventional 2D-Long Short-Term Memory (HW-Conv2DLSTM) to forecast meteorological and agricultural droughts. It employs Climate Hazards Group InfraRed Precipitation with Station (CHIRPS) data precipitation index datasets, MODIS 11A1 temperature index, and MODIS 13Q1 vegetation index. It extracts the time series data from satellite images using trend and seasonal patterns and smoothens them using Holt Winter alpha, beta, and gamma parameters. Finally, an effective drought prediction procedure is developed using Conv2D-LSTM to calculate the spatiotemporal correlation amongst drought indices. The HW-Conv2DLSTM offers a better R2 value of 0.97. It holds promise as an effective computer-assisted strategy to predict droughts and maintain agricultural productivity, which is vital to feed the ever-increasing human population.

Performance analysis of deep learning-based electric load forecasting model with particle swarm optimization.

With the widespread application of deep learning technology in various fields, power load forecasting, as an important link in power system operation and planning, has also ushered in new opportunities and challenges. Traditional forecasting methods perform poorly when faced with the high uncertainty and complexity of power loads. In view of this, this paper proposes a power load forecasting model PSO-BiTC based on deep learning and particle swarm optimization. This model combines a temporal convolutional network (TCN) and a bidirectional long short-term memory network (BiLSTM), using TCN to process long sequence data and capture features and patterns in time series, while using BiLSTM to capture long-term and short-term dependencies. In addition, the particle swarm optimization algorithm (PSO) is used to optimize model parameters to improve the model's predictive performance and generalization ability. Experimental results show that the PSO-BiTC model performs well in power load forecasting. Compared with traditional methods, this model reduces the MAE (Mean Absolute Error) to 20.18, 17.57, 18.61 and 16.7 on four extensive data sets, respectively. It has been proven that it achieves the best performance in various indicators, with a low number of parameters and training time. This research is of great significance for improving the operating efficiency of the power system, optimizing resource allocation, and promoting carbon emission reduction goals in the urban building sector.

OceanNet: a principled neural operator-based digital twin for regional oceans.

While data-driven approaches demonstrate great potential in atmospheric modeling and weather forecasting, ocean modeling poses distinct challenges due to complex bathymetry, land, vertical structure, and flow non-linearity. This study introduces OceanNet, a principled neural operator-based digital twin for regional sea-suface height emulation. OceanNet uses a Fourier neural operator and predictor-evaluate-corrector integration scheme to mitigate autoregressive error growth and enhance stability over extended time scales. A spectral regularizer counteracts spectral bias at smaller scales. OceanNet is applied to the northwest Atlantic Ocean western boundary current (the Gulf Stream), focusing on the task of seasonal prediction for Loop Current eddies and the Gulf Stream meander. Trained using historical sea surface height (SSH) data, OceanNet demonstrates competitive forecast skill compared to a state-of-the-art dynamical ocean model forecast, reducing computation by 500,000 times. These accomplishments demonstrate initial steps for physics-inspired deep neural operators as cost-effective alternatives to high-resolution numerical ocean models.

Prioritizing social vulnerability in urban heat mitigation.

We utilized city-scale simulations to quantitatively compare the diverse urban overheating mitigation strategies, specifically tied to social vulnerability and their cooling efficacies during heatwaves. We enhanced the Weather Research and Forecasting model to encompass the urban tree effect and calculate the Universal Thermal Climate Index for assessing thermal comfort. Taking Houston, Texas, and United States as an example, the study reveals that equitably mitigating urban overheat is achievable by considering the city's demographic composition and physical structure. The study results show that while urban trees may yield less cooling impact (0.27 K of Universal Thermal Climate Index in daytime) relative to cool roofs (0.30 K), the urban trees strategy can emerge as an effective approach for enhancing community resilience in heat stress-related outcomes. Social vulnerability-based heat mitigation was reviewed as vulnerability-weighted daily cumulative heat stress change. The results underscore: (i) importance of considering the community resilience when evaluating heat mitigation impact and (ii) the need to assess planting spaces for urban trees, rooftop areas, and neighborhood vulnerability when designing community-oriented urban overheating mitigation strategies.

The improved integrated Exponential Smoothing based CNN-LSTM algorithm to forecast the day ahead electricity price.

The deregulation of electricity market has led to the development of the short-term electricity market. The power generators and consumers can sell and purchase the electricity in the day ahead terms. The market clearing electricity price varies throughout the day due to the increase in the consumers bidding for electricity. Forecasting of the electricity in the day ahead market is of significance for appropriate bidding. To predict the electricity price the modified method of Exponential Smoothing-CNN-LSTM is proposed based on the time series method of Exponential Smoothing and Deep Learning methods of Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM). The dataset used for assessment of the forecasting algorithms is collected from the day ahead electricity market at the Indian Energy Exchange (IEX). The forecasting results of the Exponential Smoothing-CNN-LSTM method evaluated in terms of Mean Absolute Error (MAE) as 0.11, Root Mean Squared Error (RMSE) as 0.17 and Mean Absolute Percentage Error (MAPE) as 1.53 % indicates improved performance. The proposed algorithm can be used to forecast the time series in other domains as finance, retail, healthcare, manufacturing.•The method of Exponential Smoothing-CNN-LSTM is proposed for forecasting the electricity price a day ahead for accurate bidding for the short-term electricity market participants.•The forecasting results indicate the better performance of the proposed method than the existing techniques of Exponential Smoothing, LSTM and CNN-LSTM due to the advantages of the Exponential Smoothing to extract the levels and seasonality and with the CNN-LSTM methods ability to model the complex spatial and temporal dependencies in the time series.

An ensemble approach integrating LSTM and ARIMA models for enhanced financial market predictions.

Forecasting financial markets is a complex task that requires addressing various challenges, such as market complexity, data heterogeneity, the need for rapid response and constant changes in conditions, to gain a competitive advantage. To effectively address these challenges, it is necessary to constantly improve existing and develop new methods of intelligent forecasting, which will improve the accuracy of forecasts, reduce risks and increase the productivity of financial decision-making processes. In this article, we study and analyse forecasting methods in financial markets, such as support vector regression (SVR), autoregressive integrated moving average (ARIMA), long short-term memory recurrent neural network (LSTM) and extreme gradient boosting algorithm (XG-Boost). Based on this analysis, we propose an ensemble forecasting procedure that integrates LSTM and ARIMA models. Due to the careful combination of these models, our approach yields better results than individual methods. For example, our model demonstrates a significant 15% improvement in root mean square error (RMSE) and a slight improvement in coefficient of determination compared with LSTM. Furthermore, simulation results obtained on three real-world datasets and evaluated using the RMSE criterion confirm the superiority of our proposed method over alternative methods such as LSTMs, transformer models and optimized deep recurrent neural networks with long short-term memory for financial market forecasting. Furthermore, our approach creates the prerequisites for parallelizing both models, thus providing an opportunity to accelerate forecasting results in future research.

Unifying mortality forecasting model: an investigation of the COM-Poisson distribution in the GAS model for improved projections.

Forecasting mortality rates is crucial for evaluating life insurance company solvency, especially amid disruptions caused by phenomena like COVID-19. The Lee-Carter model is commonly employed in mortality modelling; however, extensions that can encompass count data with diverse distributions, such as the Generalized Autoregressive Score (GAS) model utilizing the COM-Poisson distribution, exhibit potential for enhancing time-to-event forecasting accuracy. Using mortality data from 29 countries, this research evaluates various distributions and determines that the COM-Poisson model surpasses the Poisson, binomial, and negative binomial distributions in forecasting mortality rates. The one-step forecasting capability of the GAS model offers distinct advantages, while the COM-Poisson distribution demonstrates enhanced flexibility and versatility by accommodating various distributions, including Poisson and negative binomial. Ultimately, the study determines that the COM-Poisson GAS model is an effective instrument for examining time series data on mortality rates, particularly when facing time-varying parameters and non-conventional data distributions.