Can we predict adolescent cannabis use? A Bayesian semi-parametric approach to project future trends

Despite its decrease in many Western countries, cannabis remains the most used illicit substance among adolescents. This study aims to summarize cannabis consumption during the last two decades and project trends among 15-year-olds in the 2021-22 HBSC survey. A Bayesian semi-parametric hierarchical model was adopted to estimate the trend of cannabis consumption using data of about 287,000 adolescents from the 2001/2002 to the 2017/2018 HBSC wave and the 38 countries that met the inclusion criteria. Data show an overall decline in most countries for both boys and girls. However, in 22 countries of 38 cannabis use is expected to increase again in our projection. The discussion of these findings should take into account cultural, policy, social factors and unpredictable events such as the Covid-19 pandemic, that can significantly impact future trends leading to discrepancies between the projected and observed values. However, these discrepancies can provide insight into understanding the potential impact of preventive strategies and the underlying processes responsible for changes in cannabis use over time.

Seasonality of influenza-like illness and short-term forecasting model in Chongqing from 2010 to 2022

BACKGROUND

Influenza-like illness (ILI) imposes a significant burden on patients, employers and society. However, there is no analysis and prediction at the hospital level in Chongqing. We aimed to characterize the seasonality of ILI, examine age heterogeneity in visits, and predict ILI peaks and assess whether they affect hospital operations.

METHODS

The multiplicative decomposition model was employed to decompose the trend and seasonality of ILI, and the Seasonal Auto-Regressive Integrated Moving Average with exogenous factors (SARIMAX) model was used for the trend and short-term prediction of ILI. We used Grid Search and Akaike information criterion (AIC) to calibrate and verify the optimal hyperparameters, and verified the residuals of the multiplicative decomposition and SARIMAX model, which are both white noise.

RESULTS

During the 12-year study period, ILI showed a continuous upward trend, peaking in winter (Dec. - Jan.) and a small spike in May-June in the 2-4-year-old high-risk group for severe disease. The mean length of stay (LOS) in ILI peaked around summer (about Aug.), and the LOS in the 0-1 and ≥ 65 years old severely high-risk group was more irregular than the others. We found some anomalies in the predictive analysis of the test set, which were basically consistent with the dynamic zero-COVID policy at the time.

CONCLUSION

The ILI patient visits showed a clear cyclical and seasonal pattern. ILI prevention and control activities can be conducted seasonally on an annual basis, and age heterogeneity should be considered in the health resource planning. Targeted immunization policies are essential to mitigate potential pandemic threats. The SARIMAX model has good short-term forecasting ability and accuracy. It can help explore the epidemiological characteristics of ILI and provide an early warning and decision-making basis for the allocation of medical resources related to ILI visits.

The future burden of type 2 diabetes in Belgium: a microsimulation model

OBJECTIVE

To forecast the annual burden of type 2 diabetes and related socio-demographic disparities in Belgium until 2030.

METHODS

This study utilized a discrete-event transition microsimulation model. A synthetic population was created using 2018 national register data of the Belgian population aged 0-80 years, along with the national representative prevalence of diabetes risk factors obtained from the latest (2018) Belgian Health Interview and Examination Surveys using Multiple Imputation by Chained Equations (MICE) as inputs to the Simulation of Synthetic Complex Data (simPop) model. Mortality information was obtained from the Belgian vital statistics and used to calculate annual death probabilities. From 2018 to 2030, synthetic individuals transitioned annually from health to death, with or without developing type 2 diabetes, as predicted by the Finnish Diabetes Risk Score, and risk factors were updated via strata-specific transition probabilities.

RESULTS

A total of 6722 [95% UI 3421, 11,583] new cases of type 2 diabetes per 100,000 inhabitants are expected between 2018 and 2030 in Belgium, representing a 32.8% and 19.3% increase in T2D prevalence rate and DALYs rate, respectively. While T2D burden remained highest for lower-education subgroups across all three Belgian regions, the highest increases in incidence and prevalence rates by 2030 are observed for women in general, and particularly among Flemish women reporting higher-education levels with a 114.5% and 44.6% increase in prevalence and DALYs rates, respectively. Existing age- and education-related inequalities will remain apparent in 2030 across all three regions.

CONCLUSIONS

The projected increase in the burden of T2D in Belgium highlights the urgent need for primary and secondary preventive strategies. While emphasis should be placed on the lower-education groups, it is also crucial to reinforce strategies for people of higher socioeconomic status as the burden of T2D is expected to increase significantly in this population segment.

Predicting quantum emitter fluctuations with time-series forecasting models

2D materials have important fundamental properties allowing for their use in many potential applications, including quantum computing. Various Van der Waals materials, including Tungsten disulfide (WS2), have been employed to showcase attractive device applications such as light emitting diodes, lasers and optical modulators. To maximize the utility and value of integrated quantum photonics, the wavelength, polarization and intensity of the photons from a quantum emission (QE) must be stable. However, random variation of emission energy, caused by the inhomogeneity in the local environment, is a major challenge for all solid-state single photon emitters. In this work, we assess the random nature of the quantum fluctuations, and we present time series forecasting deep learning models to analyse and predict QE fluctuations for the first time. Our trained models can roughly follow the actual trend of the data and, under certain data processing conditions, can predict peaks and dips of the fluctuations. The ability to anticipate these fluctuations will allow physicists to harness quantum fluctuation characteristics to develop novel scientific advances in quantum computing that will greatly benefit quantum technologies.

Forecast of agri-residues generation from rice, wheat and oilseed crops in India using machine learning techniques: Exploring strategies for sustainable smart management

Management of agri-residues generated in large quantities necessitates for its accurate estimation. Data analysis using machine learning methods can predict the agri-residues generation. The objective of the study was to forecast agri-residues generation from rice, wheat, and oilseed crops in India using ML methods and their sustainable uses. Prediction of agri-residues was done first by forecasting the crop production via the application of ML techniques for the period 2022 to 2030, and then the amount of crop residues generation calculated by multiplying the crop productions with the residues-to-product-ratio (RPR) values of the respective crops. RPR was estimated by using the gravimetric ratio of the residue to the actual crop production. The crop-specific RPR values were taken from various earlier studies in Indian context. The RPR values of 1.73 for the rice, 1.65 for wheat, and 2.6 for the oilseed crop were used as a conversion factor for residues calculation. Machine learning models linear regression, sequential minimal optimization regression (SMOreg), M5 Rule, and Gaussian process were used in the study. SMOreg performed better in models tested by coefficient of determination, root mean square error, and mean absolute error. The models predicted the generation of residues in 2030 as rice straw and husk 195.76 Mt to 277.68 Mt, wheat straw 188.62 Mt to 266.95 Mt, and oilseed stalk and oil cakes 55.61 Mt to 96.30 Mt in India. An overview of the management of agri-residues discussed. Estimation of agri-residues can provide an opportunity to utilize them with the best possible ways, lessen pollution and promote a zero-waste strategy.

An integrated DEMATEL and system dynamic model for project cost prediction

Actual cost fluctuations in construction projects are common in the construction industry, including the Kingdom of Saudi Arabia (KSA). This study's objective is to establish a simulation forecasting model for Saudi projects' cost changes that will be used to anticipate the actual cost spent at the project's end. It also indicates if there are cost overruns or savings by considering ten identified cost-risk impact factors. The study involves a systematic, integrated approach to developing system dynamics (SD) to reflect the ten cost overrun impact factors (COICs) in the KSA construction industry. Thus, the Decision-Making Trial and Evaluation Laboratory (DEMATEL) technique aids in evolving a Causal Loop Diagram (CLD) in the SD modeling stages. After performing the consistency and extreme tests, the model is verified by being applied in two case studies (an academic building and an infrastructure project) in Riyadh City, KSA. The main findings reveal that the model provided cost savings for the first and second case studies of 4.8% and 3.76%, respectively. Different experts have evaluated the developed dynamic system. According to the experts who support the developed model, the model is applicable if the contractor has a reasonable profit margin. In contrast, opponents' experts noted that the system still generates a profit margin despite change orders and project delays. The main conclusion that the experts recognize is that the approach successfully considered the relationships between the influencing factors. The findings can be utilized to create an integrated conceptual framework for construction management, which could result in a rapid and profitable project launch.

The prediction of influenza-like illness using national influenza surveillance data and Baidu query data

BACKGROUND

Seasonal influenza and other respiratory tract infections are serious public health problems that need to be further addressed and investigated. Internet search data are recognized as a valuable source for forecasting influenza or other respiratory tract infection epidemics. However, the selection of internet search data and the application of forecasting methods are important for improving forecasting accuracy. The aim of the present study was to forecast influenza epidemics based on the long short-term memory neural network (LSTM) method, Baidu search index data, and the influenza-like-illness (ILI) rate.

METHODS

The official weekly ILI% data for northern and southern mainland China were obtained from the Chinese Influenza Center from 2018 to 2021. Based on the Baidu Index, search indices related to influenza infection over the corresponding time period were obtained. Pearson correlation analysis was performed to explore the association between influenza-related search queries and the ILI% of southern and northern mainland China. The LSTM model was used to forecast the influenza epidemic within the same week and at lags of 1-4 weeks. The model performance was assessed by evaluation metrics, including the mean square error (MSE), root mean square error (RMSE) and mean absolute error (MAE).

RESULTS

In total, 24 search queries in northern mainland China and 7 search queries in southern mainland China were found to be correlated and were used to construct the LSTM model, which included the same week and a lag of 1-4 weeks. The LSTM model showed that ILI% + mask with one lag week and ILI% + influenza name were good prediction modules, with reduced RMSE predictions of 16.75% and 4.20%, respectively, compared with the estimated ILI% for northern and southern mainland China.

CONCLUSIONS

The results illuminate the feasibility of using an internet search index as a complementary data source for influenza forecasting and the efficiency of using the LSTM model to forecast influenza epidemics.

Data on the demographic forecast of the Kazakhstan population

The purpose of the study is to forecast the demographic situation in Kazakhstan until 2050 for Kazakhstan and its regions. Forecasts of population size and structure are developed based on analysis of trends in demographic processes, and their cause-and-effect relationships with socio-economic processes. Thus, the calculations take into account the mortality rates observed in 2020-2021 due to COVID-19. The results obtained include data on the total population of Kazakhstan, gender distribution, age structure of the population, data on fertility and mortality (including infant mortality) for the period from 2022 to 2100. The cohort-component method was used, and alternative forecasting methods were proposed. The article presents data on the prospective population of Kazakhstan based on indicators of natural and mechanical population movement, exponential curve, and average growth rate, respectively, for the period 2020-2050.

A nowcast model to predict outdoor flea activity in real time for the contiguous United States

BACKGROUND

The cat flea (Ctenocephalides felis), a parasite commonly found on both dogs and cats, is a competent vector for several zoonotic pathogens, including Dipylidium caninum (tapeworms), Bartonella henselae (responsible for cat scratch disease) and Rickettsia felis (responsible for flea-borne spotted fever). Veterinarians recommend that both cats and dogs be routinely treated with medications to prevent flea infestation. Nevertheless, surveys suggest that nearly one third of pet owners do not routinely administer appropriate preventatives.

METHODS

A mathematical model based on weighted averaging over time is developed to predict outdoor flea activity from weather conditions for the contiguous United States. This 'nowcast' model can be updated in real time as weather conditions change and serves as an important tool for educating pet owners about the risks of flea-borne disease. We validate our model using Google Trends data for searches for the term 'fleas.' This Google Trends data serve as a proxy for true flea activity, as validating the model by collecting fleas over the entire USA is prohibitively costly and time-consuming.

RESULTS

The average correlation (r) between the nowcast outdoor flea activity predictions and the Google Trends data was moderate: 0.65, 0.70, 0.66, 0.71 and 0.63 for 2016, 2017, 2018, 2019 and 2020, respectively. However, there was substantial regional variation in performance, with the average correlation in the East South Atlantic states being 0.81 while the average correlation in the Mountain states was only 0.45. The nowcast predictions displayed strong seasonal and geographic patterns, with predicted activity generally being highest in the summer months.

CONCLUSIONS

The nowcast model is a valuable tool by which to educate pet owners regarding the risk of fleas and flea-borne disease and the need to routinely administer flea preventatives. While it is ideal for domestic cats and dogs to on flea preventatives year-round, many pets remain vulnerable to flea infestation. Alerting pet owners to the local increased risk of flea activity during certain times of the year may motivate them to administer appropriate routine preventives.

Clinical study of different prediction models in predicting diabetic nephropathy in patients with type 2 diabetes mellitus

BACKGROUND

Among older adults, type 2 diabetes mellitus (T2DM) is widely recognized as one of the most prevalent diseases. Diabetic nephropathy (DN) is a frequent complication of DM, mainly characterized by renal microvascular damage. Early detection, aggressive prevention, and cure of DN are key to improving prognosis. Establishing a diagnostic and predictive model for DN is crucial in auxiliary diagnosis.

AIM

To investigate the factors that impact T2DM complicated with DN and utilize this information to develop a predictive model.

METHODS

The clinical data of 210 patients diagnosed with T2DM and admitted to the First People's Hospital of Wenling between August 2019 and August 2022 were retrospectively analyzed. According to whether the patients had DN, they were divided into the DN group (complicated with DN) and the non-DN group (without DN). Multivariate logistic regression analysis was used to explore factors affecting DN in patients with T2DM. The data were randomly split into a training set (n = 147) and a test set (n = 63) in a 7:3 ratio using a random function. The training set was used to construct the nomogram, decision tree, and random forest models, and the test set was used to evaluate the prediction performance of the model by comparing the sensitivity, specificity, accuracy, recall, precision, and area under the receiver operating characteristic curve.

RESULTS

Among the 210 patients with T2DM, 74 (35.34%) had DN. The validation dataset showed that the accuracies of the nomogram, decision tree, and random forest models in predicting DN in patients with T2DM were 0.746, 0.714, and 0.730, respectively. The sensitivities were 0.710, 0.710, and 0.806, respectively; the specificities were 0.844, 0.875, and 0.844, respectively; the area under the receiver operating characteristic curve (AUC) of the patients were 0.811, 0.735, and 0.850, respectively. The Delong test results revealed that the AUC values of the decision tree model were lower than those of the random forest and nomogram models (P < 0.05), whereas the difference in AUC values of the random forest and column-line graph models was not statistically significant (P > 0.05).

CONCLUSION

Among the three prediction models, random forest performs best and can help identify patients with T2DM at high risk of DN.

Wavelets in the analysis of local time series of the Earth's surface air

The practical application of local smoothing and wavelet analysis methods for studying the spectral composition and coherent relationships of local average annual surface air temperatures with solar activity and the displacement of the Earth's North Pole is presented. A preliminary analysis of local time series of surface temperatures revealed the presence of emissions and their localization. It is shown that to eliminate the influence of outliers (short-term events) on the reliability of identifying a long-term nonlinear trend, the wavelet decomposition method, which filters high frequencies, is most suitable. Functional approximation models are constructed and compared at different levels of wavelet decomposition of the data. Time or scale smoothing is used to improve the reliability of the wavelet spectrum. Based on data on average annual surface air temperatures in Yalta (44.48⁰, 34.17⁰, = 72.0 m) for the time interval from 1869 to 2022, functional models of long-term trends were built and used to obtain short-term forecasts. Information about the linear relationship of events in the compared time series is obtained and discussed in the analysis of wavelet cross-correlation, wavelet coherence and phase coherence. Local similarities were discovered between data on surface air temperature and solar activity data (Wolf numbers) for a period of ∼(30-70) years, as well as oscillations with period of 11 years, manifested in the constancy of the phase difference and an increase in the modulus of wavelet coherence power over time. Localized similarities were also found in data on surface air temperature in Yalta and in data on displacements of the Earth's mean pole relative to the conventional beginning of EOP (IERS) CO1 in the interval of periods ∼ (30-70) years.

Effects of climate change on Platanus flowering in Western Mediterranean cities: Current trends and future projections

Ornamental trees can reduce some of the negative impacts of urbanization on citizens but some species, such as Platanus spp., produce pollen with high allergenic potential. This can exacerbate the symptomatology in allergic patients, being a public health problem. Therefore, it would be relevant to determine the environmental conditions regulating the flowering onset of the Platanus species. The aims of this study were to use aerobiological records for modelling the thermal requirements of Platanus flowering and to make future projections based on the effects that climate change could have on it under several possible future scenarios. This study was conducted in Badajoz and Malaga, two Western Mediterranean cities with different climate conditions. In the first step, several main pollen season definitions were applied to the aerobiological data and their onset dates were compared with in situ phenological observations. The main pollen season definition that best fitted the Platanus flowering onset was based on the 4th derivative of a logistic function. This definition was used as a proxy to model the thermal requirements of the Platanus flowering onset by applying the PhenoFlex statistical framework. The errors obtained by this model during the external validation were 3.2 days on average, so it was fed with future temperature estimations to determine possible future trends. According to the different models, the flowering onset of Platanus in Badajoz will show heterogeneous responses in the short and medium term due to different balances in the chilling-forcing compensation, while it will clearly delay in Malaga due to a significant delay in the chilling requirement fulfilment. This may increase the chances of cross-reactivity episodes with other pollen types in the future, increasing its impact on public health.

Perceptions of weather-based pain forecasts and their effect on daily activities

As studies begin to have more success uncovering the relationships between atmospheric conditions and pain, weather-based pain forecasting becomes more of a reality. In this study, a survey was used to determine if people living with migraines and/or other pain-related conditions are receptive to weather-based pain forecasts. Moreover, we wished to identify whether these forecasts actually impact the decision-making of those who use them. Survey respondents were generally eager to use these novel forecasts. Furthermore, when provided with different scenarios involving weather-based pain forecasts, the respondents' actions were altered. When a hypothetical forecast indicated that the weather was conducive to migraines or other types of pain, many indicated that they would likely take preventative measures (e.g., medication). Additionally, respondents were less likely to continue with a planned activity, regardless of length, as forecast severity increased. The results from this survey highlight the importance of developing and improving weather-based pain forecasting.

Forecasting the mortality burden of coronary heart disease and stroke in Germany: National trends and regional inequalities

BACKGROUND

The decline of cardiovascular disease (CVD) mortality has slowed in many countries, including Germany. We examined the implications of this trend for future coronary heart disease (CHD) and stroke mortality in Germany considering persistent mortality inequalities between former East and West Germany.

METHODS

We retrieved demographic and mortality data from 1991 to 2019 from the German Federal Statistical Office. Using a Bayesian age-period-cohort framework, we projected CHD and stroke mortality from 2019 to 2035, stratified by sex and German region. We decomposed annual changes in deaths into three components (mortality rates, population age structure and population size) and assessed regional inequalities with age-sex-standardized mortality ratios.

RESULTS

We confirmed that declines of CVD mortality rates in Germany will likely stagnate. From 2019 to 2035, we projected fewer annual CHD deaths (114,600 to 103,500 [95%-credible interval: 81,700; 134,000]) and an increase in stroke deaths (51,300 to 53,700 [41,400; 72,000]). Decomposing past and projected mortality, we showed that population ageing was and is offset by declining mortality rates. This likely reverses after 2030 leading to increased CVD deaths thereafter. Inequalities between East and West declined substantially since 1991 and are projected to stabilize for CHD but narrow for stroke.

CONCLUSIONS

CVD deaths in Germany likely keep declining until 2030, but may increase thereafter due to population ageing if the reduction in mortality rates slows further. East-West mortality inequalities for CHD remain stable but may converge for stroke. Underlying risk factor trends need to be monitored and addressed by public health policy.

Effectiveness of potato late blight (Phytophthora infestans) forecast by meteorological estimation in mountainous terrain based on CARAH rules

Potato late blight (PLB) caused by Phytophthora infestans (Mont.) de Bary, its incidence and development are highly dependent on meteorological conditions. To solve the problem of PLB in mountainous terrain under the condition of limited meteorological monitoring capability, the air temperature and humidity was estimated based on the basic meteorological datasets, the forecast effect of the onset period and infection cycle of PLB based on CARAH rules was evaluated. The average MAE, RMSE and CI of the estimated air temperature and observations were 1.17 °C, 1.52 °C and 0.95, respectively. The average MAE, RMSE and CI of the estimated relative humidity and observations were 8.0 %, 10.7 % and 0.53, respectively. The curve of the infection cycle of PLB at different locations were estimated from the basic meteorological datasets based on the CARAH rules, and the false alarm and missing ratios were 8.8 % and 4.6 % respectively. It may be delayed by 1 or 2 fungal generations compared to the observations, and then the protective fungicide should be adjusted to a systemic fungicide. The false alarm of the infection cycle of PLB may increase in dry air conditions, and the missing report may occur in humid condition.

Large-scale seasonal forecasts of river discharge by coupling local and global datasets with a stacked neural network: Case for the Loire River system

Accurate prediction of river discharge is critical for a wide range of sectors, from human activities to environmental hazard management, especially in the face of increasing demand for water resources and climate change. To address this need, a multivariate model that incorporates both local and global data sources, including river and piezometer gauges, sea level, and climate parameters. By employing phase shift analysis, the model optimizes correlations between the target discharge and 12 parameters related to hydrologic and climatic systems, all sampled daily. In addition, a stacked LSTM - a more complex neural network architecture - is used to improve information extraction ability. Exploring river dynamics in the Loire-Bretagne basin and its surroundings, the investigation delves into predictions in daily time steps for one, three, and six months ahead. The resulting forecast features high accuracy and efficiency in predicting river discharge fluctuations, showcasing superior performance in forecasting drought periods over flood peaks. A detailed examination on data used highlights the significance of both local and global datasets in predicting river discharge, where the former dictates short-term predictions, while the latter drives long-range forecasts. Seasonally extended forecasting confirms a strong connection between the forecast leading time and the shift in data correlation, with lower correlation at a lag of 3 months due to seasonal changes affecting forecast quality, compensated by a higher correlation at a longer lag of 6 months. Such mutual effect in this multi-time-step forecasting improves the predictive quality of a six-month horizon, thus encourages progress in long-term prediction to a seasonal scale. The research establishes a practical foundation for effectively utilizing big data to leverage long-term forecasting of environmental dynamics.

Modeling and forecasting CO2 emissions in China and its regions using a novel ARIMA-LSTM model

Since China joined the WTO, its economy has experienced rapidly growth, resulting in significantly increase in fossil fuel consumption and corresponding rise in CO2 emissions. Currently, China is the world's largest emitter of CO2, the regional distribution is also extremely uneven. so, it is important to identify the factors influence CO2 emissions in the three regions and predict future trends based on these factors. This paper proposes 14 carbon emission factors and uses the random forest feature ranking algorithm to rank the importance of these factors in three regions. The main factors affecting CO2 emissions in each region are identified. Additionally, an ARIMA + LSTM carbon emission predict model based on the inverse error combination method is developed to address the linear and nonlinear relationships of carbon emission data. The findings suggest that the ARIMA + LSTM is more accurate in predicting the trend of CO2 emissions in China. Moreover, the ARIMA + LSTM is employed to forecast the future CO2 emission trends in China's east, central, and west regions, which can serve as a foundation for China's CO2 emission reduction initiatives.

Mining Google Trends data for nowcasting and forecasting colorectal cancer (CRC) prevalence

Background

Colorectal cancer (CRC) is the third most prevalent and second most lethal form of cancer in the world. Consequently, CRC cancer prevalence projections are essential for assessing the future burden of the disease, planning resource allocation, and developing service delivery strategies, as well as for grasping the shifting environment of cancer risk factors. However, unlike cancer incidence and mortality rates, national and international agencies do not routinely issue projections for cancer prevalence. Moreover, the limited or even nonexistent cancer statistics for large portions of the world, along with the high heterogeneity among world nations, further complicate the task of producing timely and accurate CRC prevalence projections. In this situation, population interest, as shown by Internet searches, can be very important for improving cancer statistics and, in the long run, for helping cancer research.

Methods

This study aims to model, nowcast and forecast the CRC prevalence at the global level using a three-step framework that incorporates three well-established univariate statistical and machine-learning models. First, data mining is performed to evaluate the relevancy of Google Trends (GT) data as a surrogate for the number of CRC survivors. The results demonstrate that population web-search interest in the term "colonoscopy" is the most reliable indicator to nowcast CRC disease prevalence. Then, various statistical and machine-learning models, including ARIMA, ETS, and FNNAR, are trained and tested using relevant GT time series. Finally, the updated monthly query series spanning 2004-2022 and the best forecasting model in terms of out-of-sample forecasting ability (i.e., the neural network autoregression) are utilized to generate point forecasts up to 2025.

Results

Results show that the number of people with colorectal cancer will continue to rise over the next 24 months. This in turn emphasizes the urgency for public policies aimed at reducing the population's exposure to the principal modifiable risk factors, such as lifestyle and nutrition. In addition, given the major drop in population interest in CRC during the first wave of the COVID-19 pandemic, the findings suggest that public health authorities should implement measures to increase cancer screening rates during pandemics. This in turn would deliver positive externalities, including the mitigation of the global burden and the enhancement of the quality of official statistics.

A glimpse into the future: modelling global prevalence of hypertension

BACKGROUND

Hypertension is a major risk factor for cardiovascular diseases. Insights and foresights on trends of hypertension prevalence are crucial to informing health policymaking. We examined and projected the patterns of hypertension prevalence among sexes.

METHODS

Using annual hypertension prevalence (18 + years) data sourced from WHO Global Health Observatory data repository from 1975 to 2015, Prophet models were developed to forecast the 2040 prevalence of hypertension in males, females, and both sexes. We used k-means clustering and self-organising maps to determine the clusters of hypertension prevalence concerning both sexes among 176 countries.

RESULTS

Worldwide, Croatia is estimated to have the highest prevalence of hypertension in males by 2040, while that of females is in Niger. Among the world's most populated countries, Pakistan and India are likely to increase by 7.7% and 4.0% respectively in both sexes. South-East Asia is projected to experience the largest hypertension prevalence in males, whereas Africa is estimated to have the highest prevalence of hypertension in females. Low-income countries are projected to have the highest prevalence of hypertension in both sexes. By 2040, the prevalence of hypertension worldwide is expected to be higher in the male population than in female. Globally, the prevalence of hypertension is projected to decrease from 22.1% in 2015 to 20.3% (20.2 - 20.4%) in 2040. We also identified three patterns of hypertension prevalence in 2040, cluster one countries are estimated to have the highest prevalence of hypertension in males (29.6%, 22.2 - 41.1%) and females (29.6%, 19.4 - 38.7%).

CONCLUSION

These findings emphasise the need for new and effective approaches toward the prevention and control of hypertension in Africa, South-East Asia, and Low-income countries.

Impact of non-pharmaceutical interventions during COVID-19 on future influenza trends in Mainland China

BACKGROUND

Influenza is a common illness for its high rates of morbidity and transmission. The implementation of non-pharmaceutical interventions (NPIs) during the COVID-19 pandemic to manage its dissemination could affect the transmission of influenza.

METHODS

A retrospective analysis, between 2018 and 2023, was conducted to examine the incidence of influenza virus types A and B among patients in sentinel cities located in North or South China as well as in Wuhan City. For validations, data on the total count of influenza patients from 2018 to 2023 were collected at the Central Hospital of Wuhan, which is not included in the sentinel hospital network. Time series methods were utilized to examine seasonal patterns and to forecast future influenza trends.

RESULTS

Northern and southern cities in China had earlier outbreaks during the NPIs period by about 8 weeks compared to the 2018-2019. The implementation of NPIs significantly reduced the influenza-like illness (ILI) rate and infection durations. Influenza B Victoria and H3N2 were the first circulating strains detected after the relaxation of NPIs, followed by H1N1 across mainland China. The SARIMA model predicted synchronized H1N1 outbreak cycles in North and South China, with H3N2 expected to occur in the summer in southern cities and in the winter in northern cities over the next 3 years. The ILI burden is expected to rise in both North and South China over the next 3 years, with higher ILI% levels in southern cities throughout the year, especially in winter, and in northern cities mainly during winter. In Wuhan City and the Central Hospital of Wuhan, influenza levels are projected to peak in the winter of 2024, with 2 smaller peaks expected during the summer of 2023.

CONCLUSIONS

In this study, we report the impact of NPIs on future influenza trends in mainland China. We recommend that local governments encourage vaccination during the transition period between summer and winter to mitigate economic losses and mortality associated with influenza.

Prediction of glaciated area fraction over the Sikkim Himalayan Region, India: a comparative study using response surface method, random forest, and artificial neural network

Glacier area fraction at high altitude mountains is a serious worry in today's time triggered by climate change. The current information on this natural resource is very important for the survival of humanity as it affects the water, food, and energy security of people dependent on it. Due to its problematic accessibility and tough environmental condition, ground monitoring is quite challenging. This study investigates the impact of environmental parameters and pollutants on glacier area fraction over the Eastern Himalaya region and its prediction through random forest (RF), multilayer perceptron (MLP), radial basis function analysis (RBFN), and response surface methodology (RSM) models. The data are obtained from the Goddard Earth Sciences Data and Information Services Center (GES DISC), NASA's data archive portal ( https://giovanni.gsfc.nasa.gov ). The collinearity of independent variables reveals that all selected input parameters are highly correlated with R2 value > 0.9. The RSM and RF model provided valuable insight of the predictor's significance in addition to their capability to predict the response. The model performance was evaluated in terms of R2 value and the error matrices. The model's R2 value was found to be 0.843, 0.839, 0.838, and 0.743 for MLP, RBFN, RF, and RSM respectively. Although, the neural network model R2 values are the highest, but the most reliable and suitable model is RF as the error matrices for this model are much lower than others. This study encourages the investigation of the hybridization of these models for more accurate prediction.

Automatic Forecast of Intensive Care Unit Admissions: The Experience During the COVID-19 Pandemic in Italy

The experience of the COVID-19 pandemic showed the importance of timely monitoring of admissions to the ICU admissions. The ability to promptly forecast the epidemic impact on the occupancy of beds in the ICU is a key issue for adequate management of the health care system.Despite this, most of the literature on predictive COVID-19 models in Italy has focused on predicting the number of infections, leaving trends in ordinary hospitalizations and ICU occupancies in the background.This work aims to present an ETS approach (Exponential Smoothing Time Series) time series forecasting tool for admissions to the ICU admissions based on ETS models. The results of the forecasting model are presented for the regions most affected by the epidemic, such as Veneto, Lombardy, Emilia-Romagna, and Piedmont.The mean absolute percentage errors (MAPE) between observed and predicted admissions to the ICU admissions remain lower than 11% for all considered geographical areas.In this epidemiological context, the proposed ETS forecasting model could be suitable to monitor, in a timely manner, the impact of COVID-19 disease on the health care system, not only during the early stages of the pandemic but also during the vaccination campaign, to quickly adapt possible preventive interventions.

Establishment of a nomogram model for prediction of postoperative heterochronous liver metastasis in young and middle-aged patients with rectal cancer

BACKGROUND

The incidence of rectal cancer is increasing year by year. Radical surgery is often used for the treatment of rectal cancer in clinical practice, but postoperative liver metastasis has become an important reason for the increase in mortality. Therefore, establishing a model to predict the trend of metachronous liver metastasis has become a research focus. Nomogram model has been widely used in the medical field, but there has been no widely accepted nomogram model available for prediction of metachronous liver metastasis after rectal cancer surgery.

AIM

To constuct a nomogram model based on the risk factors for postoperative metachronous liver metastasis in young and middle-aged patients with rectal cancer, and to evaluate the performance of the model for predicting the risk of postoperative metachronous liver metastasis, so as to provide some guidance for clinical prevention and treatment.

METHODS

A total of 120 young and middle-aged patients with rectal cancer admitted to our hospital from March 2019 to February 2022 were selected as research subjects to observe the incidence of postoperative heterochronous liver metastasis. Univariate and multivariate Logistic regression analyses were performed to identify the risk factors for postoperative heterochronous liver metastasis and to construct a nomogram model. ROC curve, decision curve, and correction curve analyses were used to verify the value of nomogram model for the prediction of postoperative heterochronous liver metastasis.

RESULTS

The incidence of anomalous liver metastasis 1 year after surgery was 23.33% in 120 young and middle-aged patients with rectal cancer. Low differentiation, lymph node metastasis, depth of invasion (T3/T4), margin width of primary cancer < 2 cm, high expression of peripheral blood telomerase reverse transcriptase (hTERT), and elevated serum levels of carcinoembryonic antigen (CEA), vascular endothelial growth factor (VEGF), lemur tyrosine kinase-3 (LMTK3), squamous cell carcinoma-associated antigen (SCC-Ag), and axon-guided factor-1 (Netrin-1) were identified to be risk factor for postoperative hetero-chronic liver metastasis (P < 0.05). The C-index and area under the curve of the nomogram model were 0.860 and 0.957, respectively, and the net benefit value was high (P < 0.05).

CONCLUSION

Low differentiation, lymph node metastasis, depth of invasion (T3/T4), margin width of primary cancer < 2 cm, high expression of hTERT in peripheral blood, and elevated levels of serum CEA, VEGF, LMTK3, SC-AG and Netrin-1 are risk factors for postoperative xenotemporal liver metastasis in young and middle-aged patients with rectal cancer. Based on the above risk factors, a nomogram model has been established to predict postoperative heterochronous liver metastasis in such patients.

Forecasting of daily new lumpy skin disease cases in Thailand at different stages of the epidemic using fuzzy logic time series, NNAR, and ARIMA methods

Lumpy skin disease (LSD) is an important transboundary disease affecting cattle in numerous countries in various continents. In Thailand, LSD is regarded as a serious threat to the cattle industry. Disease forecasting can assist authorities in formulating prevention and control policies. Therefore, the objective of this study was to compare the performance of time series models in forecasting a potential LSD epidemic in Thailand using nationwide data. For the forecasting of daily new cases, fuzzy time series (FTS), neural network auto-regressive (NNAR), and auto-regressive integrated moving average (ARIMA) models were applied to various datasets representing the different stages of the epidemic. Non-overlapping sliding and expanding window approaches were also employed to train the forecasting models. The results showed that the FTS outperformed other models in five of the seven validation datasets based on various error metrics. The predictive performance of the NNAR and ARIMA models was comparable, with NNAR outperforming ARIMA in some datasets and vice versa. Furthermore, the performance of models built from sliding and expanding window techniques was different. This is the first study to compare the forecasting abilities of the FTS, NNAR, and ARIMA models across multiple phases of the LSD epidemic. Livestock authorities and decision-makers may incorporate the forecasting techniques demonstrated herein into the LSD surveillance system to enhance its functionality and utility.

Artificial intelligence for improving Nitrogen Dioxide forecasting of Abu Dhabi environment agency ground-based stations

Nitrogen Dioxide (NO2 ) is a common air pollutant associated with several adverse health problems such as pediatric asthma, cardiovascular mortality,and respiratory mortality. Due to the urgent society's need to reduce pollutant concentration, several scientific efforts have been allocated to understand pollutant patterns and predict pollutants' future concentrations using machine learning and deep learning techniques. The latter techniques have recently gained much attention due it's capability to tackle complex and challenging problems in computer vision, natural language processing, etc. In the NO2 context, there is still a research gap in adopting those advanced methods to predict the concentration of pollutants. This study fills in the gap by comparing the performance of several state-of-the-art artificial intelligence models that haven't been adopted in this context yet. The models were trained using time series cross-validation on a rolling base and tested across different periods using NO2 data from 20 monitoring ground-based stations collected by Environment Agency- Abu Dhabi, United Arab Emirates. Using the seasonal Mann-Kendall trend test and Sen's slope estimator, we further explored and investigated the pollutants trends across the different stations. This study is the first comprehensive study that reported the temporal characteristic of NO2 across seven environmental assessment points and compared the performance of the state-of-the-art deep learning models for predicting the pollutants' future concentration. Our results reveal a difference in the pollutants concentrations level due to the geographic location of the different stations, with a statistically significant decrease in the NO2 annual trend for the majority of the stations. Overall, NO2 concentrations exhibit a similar daily and weekly pattern across the different stations, with an increase in the pollutants level during the early morning and the first working day. Comparing the state-of-the-art model performance transformer model demonstrate the superiority of ( MAE:0.04 (± 0.04),MSE:0.06 (± 0.04), RMSE:0.001 (± 0.01), R2 : 0.98 (± 0.05)), compared with LSTM (MAE:0.26 (± 0.19), MSE:0.31 (± 0.21), RMSE:0.14 (± 0.17), R2 : 0.56 (± 0.33)), InceptionTime (MAE: 0.19 (± 0.18), MSE: 0.22 (± 0.18), RMSE:0.08 (± 0.13), R2 :0.38 (± 1.35) ), ResNet (MAE:0.24 (± 0.16), MSE:0.28 (± 0.16), RMSE:0.11 (± 0.12), R2 :0.35 (± 1.19) ), XceptionTime (MAE:0.7 (± 0.55), MSE:0.79 (± 0.54), RMSE:0.91 (± 1.06), R2 : - 4.83 (± 9.38) ), and MiniRocket (MAE:0.21 (± 0.07), MSE:0.26 (± 0.08), RMSE:0.07 (± 0.04), R2 : 0.65 (± 0.28) ) to tackle this challenge. The transformer model is a powerful model for improving the accurate forecast of the NO2 levels and could strengthen the current monitoring system to control and manage the air quality in the region.

Supplementary Information

The online version contains supplementary material available at 10.1186/s40537-023-00754-z.

Improved LSTM-based deep learning model for COVID-19 prediction using optimized approach

Individuals in any country are badly impacted both economically and physically whenever an epidemic of infectious illnesses breaks out. A novel coronavirus strain was responsible for the outbreak of the coronavirus sickness in 2019. Corona Virus Disease 2019 (COVID-19) is the name that the World Health Organization (WHO) officially gave to the pneumonia that was caused by the novel coronavirus on February 11, 2020. The use of models that are informed by machine learning is currently a major focus of study in the field of improved forecasting. By displaying annual trends, forecasting models can be of use in performing impact assessments of potential outcomes. In this paper, proposed forecast models consisting of time series models such as long short-term memory (LSTM), bidirectional long short-term memory (Bi-LSTM), generalized regression unit (GRU), and dense-LSTM have been evaluated for time series prediction of confirmed cases, deaths, and recoveries in 12 major countries that have been affected by COVID-19. Tensorflow1.0 was used for programming. Indices known as mean absolute error (MAE), root means square error (RMSE), Median Absolute Error (MEDAE) and r2 score are utilized in the process of evaluating the performance of models. We presented various ways to time-series forecasting by making use of LSTM models (LSTM, BiLSTM), and we compared these proposed methods to other machine learning models to evaluate the performance of the models. Our study suggests that LSTM based models are among the most advanced models to forecast time series data.

Predicting volatility in natural gas under a cloud of uncertainties

The COVID-19 pandemic has triggered an economic crisis and the ensuing global uncertainty. The current Russian-Ukrainian conflict has escalated tensions in various regions and increased various uncertainties in the financial and economic system. These uncertainties have had a significant impact on the development of the natural gas market during the current critical period of carbon neutrality and energy transition. This paper explores the impact of various uncertainties on price volatility in the U.S. natural gas futures market using the GARCH-MIDAS model. We considered eleven types of uncertainties, including four US economic policy uncertainties, four global uncertainty indicators, and oil supply-demand uncertainty closely related to the natural gas market. The in-sample empirical results find that various uncertainties can impact the natural gas market. However, through out-of-sample testing, we find that economic policy uncertainty has more predictive power than other indicators in predicting natural gas price fluctuations. Interestingly, oil supply-demand uncertainty surpasses global indicators and can provide forecasting information for natural gas markets. Therefore, in the current context of high uncertainty, our research may offer better decision-making opinions for market participants.

Spatial predictors and temporal forecast of total organic carbon levels in boreal lakes

Browning of Fennoscandian boreal lakes is raising concerns for negative ecosystem impacts as well as reduced drinking water quality. Declined sulfur deposition and warmer climate, along with afforestation, other climate impacts and less outfield grazing, have resulted in increased fluxes of Total Organic Carbon (TOC) from catchments to freshwater, and subsequently to coastal waters. This study assesses the major governing factors for increased TOC levels among several catchment characteristics in almost 5000 Fennoscandian lakes and catchments. Normalized Difference Vegetation Index (NDVI), a proxy for plant biomass, and the proportions of peatland in the catchment, along with surface runoff intensity and nitrogen deposition loading, were identified as the main spatial predictors for lake TOC concentrations. A multiple linear model, based on these explanatory variables, was used to simulate future TOC concentration in surface runoff from coastal drainage basins in 2050 and 2100, using the forecasts of climatic variables in two of the Shared Socio-economic Pathways (SSP): 1-2.6 (+2 °C) and 3-7.0 (+4,5 °C). These scenarios yield contrasting effects. SSP 1-2.6 predicts an overall decrease of TOC export to coastal waters, while SSP 3-7.0 in contrast leads to an increase in TOC export.

Forecasting the energy intensity of industrial sector in China based on FCM-RS-SVM model

Analysis of industrial energy intensity is greatly significant in China specifically from the perspective of sector heterogeneity due to considerably different levels of energy utilization in various industrial sub-sectors. This study proposes a new methodology to forecast energy intensity in industrial sub-sectors, considering the complexity of the socioeconomic system. This research collects the data of 36 industrial sub-sectors in China and combines fuzzy C-means clustering (FCM), rough set (RS) and support vector machine (SVM) to predict the energy intensity of industrial sub-sectors in 2030. First, this method classifies all the industrial sub-sectors according to energy intensity level and identifies the main factors that affect the energy consumption of the industrial sub-sectors. Second, the resulting classification paves the way for specifying models to forecast energy consumption. Finally, scenario analysis predicts the energy intensity of each industrial sub-sector in 2030. This exploration has the following results. (1) Energy intensity has significantly different trends in various industrial sub-sectors. For example, industrial sub-sectors with low energy intensity mainly belong to the manufacturing industry (S06-S33). In contrast, the medium- and high-energy intensity categories mainly belong to the mining industry (S01-S05) and energy extraction and supply industry (S34-S36). (2) The critical factors affecting industrial energy consumption are fixed assets, R&D investment, and labor investment. (3) By 2030, the energy intensity has a downward trend in various industrial sub-sectors in China. The scenario analysis implies that China's energy intensity would reach the current world average level under the low-speed development scenario. Also, China's energy intensity would reach the current world advanced level under the medium-speed or high-speed development scenario.

Forecasting daily emergency ambulance service demand using biometeorological indexes

This study aims to study the effectiveness of using biometeorological indexes in the development of a daily emergency ambulance service demand forecast system for Taipei City, Taiwan, compared to typical weather factors. Around 370,000 emergency ambulance service patient records were aggregated into a daily emergency ambulance service demand time series as the study's dependent variable. To assess the effectiveness of biometeorological indexes in making a 1 to 7-day forecast of daily emergency ambulance service demand, five forecast models were developed to make the comparison. The model with average temperature as the only predictor performed the best consistently from 1 to 7-day forecasts. The models with net effective temperature and apparent temperature as their only predictors ranked second and third, respectively. It is surprising that the model with both average temperature and relative humidity as predictors only ranked fourth. The unexpected outperformance of average temperature over net effective temperature and apparent temperature in forecasting daily emergency ambulance service demand suggested the need to develop updated locational-specific biometeorological indexes so that the benefit of the indexes can be fully utilized. Although adopting popular biometeorological indexes that are already available would be cheap and convenient, the benefit from these general indexes may not be guaranteed.

Model Choice for Quantitative Health Impact Assessment and Modelling: An Expert Consultation and Narrative Literature Review

BACKGROUND

Health impact assessment (HIA) is a widely used process that aims to identify the health impacts, positive or negative, of a policy or intervention that is not necessarily placed in the health sector. Most HIAs are done prospectively and aim to forecast expected health impacts under assumed policy implementation. HIAs may quantitatively and/ or qualitatively assess health impacts, with this study focusing on the former. A variety of quantitative modelling methods exist that are used for forecasting health impacts, however, they differ in application area, data requirements, assumptions, risk modelling, complexities, limitations, strengths, and comprehensibility. We reviewed relevant models, so as to provide public health researchers with considerations for HIA model choice.

METHODS

Based on an HIA expert consultation, combined with a narrative literature review, we identified the most relevant models that can be used for health impact forecasting. We narratively and comparatively reviewed the models, according to their fields of application, their configuration and purposes, counterfactual scenarios, underlying assumptions, health risk modelling, limitations and strengths.

RESULTS

Seven relevant models for health impacts forecasting were identified, consisting of (i) comparative risk assessment (CRA), (ii) time series analysis (TSA), (iii) compartmental models (CMs), (iv) structural models (SMs), (v) agent-based models (ABMs), (vi) microsimulations (MS), and (vii) artificial intelligence (AI)/machine learning (ML). These models represent a variety in approaches and vary in the fields of HIA application, complexity and comprehensibility. We provide a set of criteria for HIA model choice. Researchers must consider that model input assumptions match the available data and parameter structures, the available resources, and that model outputs match the research question, meet expectations and are comprehensible to end-users.

CONCLUSION

The reviewed models have specific characteristics, related to available data and parameter structures, computational implementation, interpretation and comprehensibility, which the researcher should critically consider before HIA model choice.

Correlation between platelet distribution width and long-term survival in patients with gastric cancer after radical surgery

BACKGROUND

Gastric cancer is a common digestive system tumor, and surgery is the first choice of treatment, but the long-term survival of patients after surgery is still not satisfactory. Previous studies have showed that platelet distribution width (PDW) plays an important role in the occurrence and development of tumor. This study aimed to analyze the correlation between PDW and long-term survival of patients with stage Ⅱ-ⅢA gastric cancer after radical surgery.

AIM

To explore the relationship between PDW and long-term survival in patients with stage Ⅱ-ⅢA gastric cancer after radical surgery.

METHODS

This is a prospective cohort study, in which 124 patients with gastric cancer who received surgical treatment at our hospital from January 2016 to December 2017 were included as the study subjects. All patients were followed for 5 years and their survival time was recorded. The patients were divided into three groups according to whether their PDW increased or not after surgery: PDW decrease group, PDW normal group, and PDW increase group. The clinicopathological characteristics and long-term survival of patients in different groups were compared. Point binary correlation and COX regression were used to test the correlation between postoperative PDW and long-term survival of patients and the impact of PDW on long-term survival. Receiver operating characteristic (ROC) curve analysis was performed to analyze the value of postoperative PDW in predicting long-term survival.

RESULTS

The levels of CEA, CA199, and PDW in gastric cancer patients after treatment were significantly lower than those before treatment (P < 0.05). Among 111 patients with gastric cancer, 35 (31.53%) had decreased PDW, 24 (21.62%) had normal PDW, and 52 (46.85%) had increased PDW. The rates of lymph node metastasis and advanced tumor-node-metastasis (TNM) stage (ⅢA) in the PDW increase group were significantly higher than those of the PDW normal group and PDW decrease group (P < 0.05). However, there were no statistical significant differences among the three groups in terms of age, sex, degree of differentiation, tumor diameter, depth of muscle invasion, TNM stage, and lymph node metastasis (P > 0.05). Among 111 cases of gastric cancer, 31 survived, with a survival rate of 27.93%; the survival time was 11-60 mo, and the median survival time was 43.00 (31.00, 60.00) mo. Point binary correlation test showed that PDW, lymph node metastasis, and TNM stage were positively correlated with long-term survival after radical surgery(r > 0, P < 0.05). COX regression analysis showed that after adjusting for TNM stage and lymph node metastasis, taking the normal PDW group as a reference, the increase of PDW was a risk factor for long-term survival of gastric cancer patients. The median survival time of the patients with decreased, normal, and increased PDW was 49.50 (33.00, 60.00) mo, 53.50 (49.25, 58.00) mo, and 29.00 (20.00, 35.00) mo, respectively, and the difference among the three groups was statistically significant (P < 0.05). ROC curve analysis showed that postoperative PDW level had appreciated value in predicting long-term survival of gastric cancer patients (AUC = 0.718, 95%CI: 0.614-0.822, P < 0.001).

CONCLUSION

PDW is related to the long-term survival of patients with gastric cancer after radical surgery. Increased PDW indicates that the long-term prognosis of gastric cancer patients is poor and the survival period is short. TNM stage and lymph node metastasis are also closely related to the long-term survival of gastric cancer patients.

Incorporating variant frequencies data into short-term forecasting for COVID-19 cases and deaths in the USA: a deep learning approach

BACKGROUND

Since the US reported its first COVID-19 case on January 21, 2020, the science community has been applying various techniques to forecast incident cases and deaths. To date, providing an accurate and robust forecast at a high spatial resolution has proved challenging, even in the short term.

METHOD

Here we present a novel multi-stage deep learning model to forecast the number of COVID-19 cases and deaths for each US state at a weekly level for a forecast horizon of 1-4 weeks. The model is heavily data driven, and relies on epidemiological, mobility, survey, climate, demographic, and SARS-CoV-2 variant frequencies data. We implement a rigorous and robust evaluation of our model-specifically we report on weekly performance over a one-year period based on multiple error metrics, and explicitly assess how our model performance varies over space, chronological time, and different outbreak phases.

FINDINGS

The proposed model is shown to consistently outperform the CDC ensemble model for all evaluation metrics in multiple spatiotemporal settings, especially for the longer-term (3 and 4 weeks ahead) forecast horizon. Our case study also highlights the potential value of variant frequencies data for use in short-term forecasting to identify forthcoming surges driven by new variants.

INTERPRETATION

Based on our findings, the proposed forecasting framework improves upon the available state-of-the-art forecasting tools currently used to support public health decision making with respect to COVID-19 risk.

FUNDING

This work was funded the NSF Rapid Response Research (RAPID) grant Award ID 2108526 and the CDC Contract #75D30120C09570.

Medical multivariate time series imputation and forecasting based on a recurrent conditional Wasserstein GAN and attention

OBJECTIVE

In the fields of medical care and research as well as hospital management, time series are an important part of the overall data basis. To ensure high quality standards and enable suitable decisions, tools for precise and generic imputations and forecasts that integrate the temporal dynamics are of great importance. Since forecasting and imputation tasks involve an inherent uncertainty, the focus of our work lay on a probabilistic multivariate generative approach that samples infillings or forecasts from an analysable distribution rather than producing deterministic results.

MATERIALS AND METHODS

For this task, we developed a system based on generative adversarial networks that consist of recurrent encoders and decoders with attention mechanisms and can learn the distribution of intervals from multivariate time series conditioned on the periods before and, if available, periods after the values that are to be predicted. For training, validation and testing, a data set of jointly measured blood pressure series (ABP) and electrocardiograms (ECG) (length: 1,250=ˆ10s) was generated. For the imputation tasks, one interval of fixed length was masked randomly and independently in both channels of every sample. For the forecasting task, all masks were positioned at the end.

RESULTS

The models were trained on around 65,000 bivariate samples and tested against 14,000 series of different persons. For the evaluation, 50 samples were produced for every masked interval to estimate the range of the generated infillings or forecasts. The element-wise arithmetic average of these samples served as an estimator for the mean of the learned conditional distribution. The approach showed better results than a state-of-the-art probabilistic multivariate forecasting mechanism based on Gaussian copula transformation and recurrent neural networks. On the imputation task, the proposed method reached a mean squared error (MSE) of 0.057 on the ECG channel and an MSE of 28.30 on the ABP channel, while the baseline approach reached MSEs of 0.095 (ECG) and 229.1 (ABP). Moreover, on the forecasting task, the presented system achieved MSEs of 0.069 (ECG) and 33.73 (ABP), outperforming the recurrent copula approach, which reached MSEs of 0.082 (ECG) and 196.53 (ABP).

CONCLUSION

The presented generative probabilistic system for the imputation and forecasting of (medical) time series features the flexibility to handle masks of different sizes and positions, the ability to quantify uncertainty due to its probabilistic predictions, and an adjustable trade-off between the goals of minimising errors in individual predictions and minimising the distance between the learned and the real conditional distribution of the infillings or forecasts.

National trends and projection of chronic kidney disease incidence according to etiology from 1990 to 2030 in Iran: a Bayesian age-period-cohort modeling study

OBJECTIVES

Chronic kidney disease (CKD) is a major public health problem worldwide. Predicting CKD incidence rates and case numbers at the national and global levels is vital for planning CKD prevention programs.

METHODS

Data on CKD incidence rates and case numbers in Iran from 1990 to 2019 were extracted from the Global Burden of Disease online database. The average annual percentage change was computed to determine the temporal trends in CKD age-standardized incidence rates from 1990 to 2019. A Bayesian age-period-cohort model was used to predict the CKD incidence rate and case numbers through 2030.

RESULTS

Nationally, CKD cases increased from 97,300 in 1990 to 315,500 in 2019. The age-specific CKD incidence rate increased from 168.52 per 100,000 to 382.98 per 100,000 during the same period. Between 2020 and 2030, the number of CKD cases is projected to rise to 423,300. The age-specific CKD incidence rate is projected to increase to 469.04 in 2030 (95% credible interval, 399.20 to 538.87). In all age groups and etiological categories, the CKD incidence rate is forecasted to increase by 2030.

CONCLUSIONS

CKD case numbers and incidence rates are anticipated to increase in Iran through 2030. The high level of CKD incidence in people with diabetes mellitus, hypertension, and glomerulonephritis, as well as in older people, suggests a deficiency of attention to these populations in current prevention plans and highlights their importance in future programs for the national control of CKD.

Evaluation of the model malaria elimination strategy in Mandla district along with its neighbouring districts: a time series analysis from 2008 to 2020

BACKGROUND

Compared to 2017, India achieved a significant reduction in malaria cases in 2020. Madhya Pradesh (MP) is a tribal dominated state of India with history of high malaria burden in some districts. District Mandla of MP state showed a considerable decline in malaria cases between 2000 and 2013, except in 2007. Subsequently, a resurgence of malaria cases was observed during 2014 and 2015. The Malaria Elimination Demonstration Project (MEDP) was launched in 2017 in Mandla with the goal to achieve zero indigenous malaria cases. This project used: (1) active surveillance and case management using T4 (Track fever, Test fever, Treat patient, and Track patient); (2) vector control using indoor residual sprays and long-lasting insecticidal nets; (3) information education communication and behaviour change communication; and (4) regular monitoring and evaluation with an emphasis on operational and management accountability. This study has investigated malaria prevalence trends from 2008 to 2020, and has predicted trends for the next 5 years for Mandla and its bordering districts.

METHODS

The malaria prevalence data of the district Mandla for the period of January 2008 to August 2017 was obtained from District Malaria Office (DMO) Mandla and data for the period of September 2017 to December 2020 was taken from MEDP data repository. Further, the malaria prevalence data for the period of January 2008 to December 2020 was collected from DMOs of the neighbouring districts of Mandla. A univariate time series and forecast analysis was performed using seasonal autoregressive integrated moving average model.

FINDINGS

Malaria prevalence in Mandla showed a sharp decline [- 87% (95% CI - 90%, - 84%)] from 2017 to 2020. The malaria forecast for Mandla predicts zero cases in the next 5 years (2021-2025), provided current interventions are sustained. By contrast, the model has forecasted a risk of resurgence of malaria in other districts in MP (Balaghat, Dindori, Jabalpur, Seoni, and Kawardha) that were not the part of MEDP.

CONCLUSION

The interventions deployed as part of MEDP have resulted in a sustainable zero indigenous malaria cases in Mandla. Use of similar strategies in neighbouring and other malaria-endemic districts in India could achieve similar results. However, without adding extra cost to the existing intervention, sincere efforts are needed to sustain these interventions and their impact using accountability framework, data transparency, and programme ownership from state to district level.

Analysis and numerical simulation of temperature measurements made on earth and from space

The sum of all currently known facts confirms the existence of a global warming process. The development models of this process are statistical in nature and often do not take into account the specifics of local conditions. This fact confirms our analysis of measurements of the average annual surface air temperature during the period 1980-2019 in the city of Krasnodar (Russia). We used data from ground based (World Data Center) and space based (POWER project) measurements. A comparison of the data showed that the discrepancies in ground and space based measurements of surface air temperatures until 1990 do not exceed the data error ( s = ± 0.7 °C). After 1990, the most significant short-term discrepancies were observed in 2014 (-1.12°С) and 2016 (1.33°С). An analysis of the forecast model of the Earth's surface air average annual temperature for 1918-2020 indicates a gradual decrease in the average annual temperature even in the presence of short-term impulses of its increase. The rate of decrease in the average annual temperature from ground based observations is slightly higher than from space based observations, which is probably due to a more complete consideration of local conditions in ground based observations.

Building fuzzy time series model from unsupervised learning technique and genetic algorithm

This paper proposes a new model to interpolate time series and forecast it effectively for the future. The important contribution of this study is the combination of optimal techniques for fuzzy clustering problem using genetic algorithm and forecasting model for fuzzy time series. Firstly, the proposed model finds the suitable number of clusters for a series and optimizes the clustering problem by the genetic algorithm using the improved Davies and Bouldin index as the objective function. Secondly, the study gives the method to establish the fuzzy relationship of each element to the established clusters. Finally, the developed model establishes the rule to forecast for the future. The steps of the proposed model are presented clearly and illustrated by the numerical example. Furthermore, it has been realized positively by the established MATLAB procedure. Performing for a lot of series (3007 series) with the differences about characteristics and areas, the new model has shown the significant performance in comparison with the existing models via some parameters to evaluate the built model. In addition, we also present an application of the proposed model in forecasting the COVID-19 victims in Vietnam that it can perform similarly for other countries. The numerical examples and application show potential in the forecasting area of this research.

Modeling the progression of COVID-19 deaths using Kalman Filter and AutoML

The COVID-19 pandemic continues to have a destructive effect on the health and well-being of the global population. A vital step in the battle against it is the successful screening of infected patients, together with one of the effective screening methods being radiology examination using chest radiography. Recognition of epidemic growth patterns across temporal and social factors can improve our capability to create epidemic transmission designs, including the critical job of predicting the estimated intensity of the outbreak morbidity or mortality impact at the end. The study's primary motivation is to be able to estimate with a certain level of accuracy the number of deaths due to COVID-19, managing to model the progression of the pandemic. Predicting the number of possible deaths from COVID-19 can provide governments and decision-makers with indicators for purchasing respirators and pandemic prevention policies. Thus, this work presents itself as an essential contribution to combating the pandemic. Kalman Filter is a widely used method for tracking and navigation and filtering and time series. Designing and tuning machine learning methods are a labor- and time-intensive task that requires extensive experience. The field of automated machine learning Auto Machine Learning relies on automating this task. Auto Machine Learning tools enable novice users to create useful machine learning units, while experts can use them to free up valuable time for other tasks. This paper presents an objective method of forecasting the COVID-19 outbreak using Kalman Filter and Auto Machine Learning. We use a COVID-19 dataset of Ceará, one of the 27 federative units in Brazil. Ceará has more than 235,222 confirmed cases of COVID-19 and 8850 deaths due to the disease. The TPOT automobile model showed the best result with a 0.99 of R 2 score.

ARIMA MODEL IN PREDICTING OF COVID-19 EPIDEMIC FOR THE SOUTHERN AFRICA REGION

Background

Coronavirus pandemic, a serious global public health threat, affects the Southern African countries more than any other country on the continent. The region has become the epicenter of the coronavirus with South Africa accounting for the most cases. To cap the deadly effect caused by the pandemic, we apply a statistical modelling approach to investigate and predict COVID-19 incidence.

Methods

Using secondary data on the daily confirmed COVID-19 cases per million for Southern Africa Development Community (SADC) member states from March 5, 2020, to July 15, 2021, we model and forecast the spread of coronavirus in the region. We select the best ARIMA model based on the log-likelihood, AIC, and BIC of the fitted models.

Results

The ARIMA (11,1,11) model for the complete data set was finally selected among ARIMA models based upon the parameter test and the Box-Ljung test. The ARIMA(11,1,9) was the best candidate for the training set. A 15-day forecast was also made from the model, which shows a perfect fit with the testing set.

Conclusion

The number of new COVID-19 cases per million for the SADC shows a downward trend, but the trend is characterized by peaks from time to time. Tightening up of the preventive measures continuously needs to be adapted in order to eradicate the coronavirus epidemic from the population.

Forecasting petroleum products consumption in Cameroon's household sector using a sequential GMC(1,n) model optimized by genetic algorithms

Forecasting energy consumption is a major concern for policymakers, oil industry companies, and many other associated businesses. Though there exist many forecasting methodologies, selecting the most appropriate one is critical. GM(1,1) has proven to be one of the most successful forecasting tool. GM(1,1) does not require any specific information and can be adapted to predict energy consumption using a minimum of four observations. Unfortunately, GM(1,1) on its own will generate too large forecast errors because it performs well only when data follow an exponential trend and should be implemented in a political-socio-economic free environment. To reduce these errors, this study proposes a new GM(1,n) convolution model optimized by genetic algorithms integrating a sequential selection mechanism and arc consistency, abbreviated Sequential-GMC(1,n)-GA. Practically, the proposed approach, on one hand, highlights the forecast for petroleum products consumption in Cameroon's household sector. On the other hand, it estimates the amount of CO2 that would be reduced if petroleum products in this sector were switched to clean energy. The new model, like some recent hybrid versions, is robust and reliable, according to the results. Households petroleum products needs by 2025 are estimated to be 150,318 kilo tons of oil equivalent with MAPE of 1.44%, and RMSE of 0.833. Therefore, households GHG emissions would be reduced by 733.85 kilo tons of CO2 equivalent if clean energy was used instead of petroleum products. As a result, the new hybrid model is a valid forecasting tool that can be used to track the growth of Cameroon's household energy demand.

Forecasting on Covid-19 infection waves using a rough set filter driven moving average models

The pandemic outbreak of severe acute respiratory syndrome caused by the Coronavirus 2 disease in 2019, also known as SARS-COV-2 and COVID-19, has claimed over 5.6 million lives till now. The highly infectious nature of the Covid-19 virus has resulted into multiple massive upsurges in counts of new infections termed as ‘waves.’ These waves consist of numerous rising and falling counts of Covid-19 infection cases with changing dates that confuse analysts and researchers. Due to this confusion, the detection of emergence or drop of Covid waves is currently a subject of intensive research. Hence, we propose an algorithmic framework to forecast the upcoming details of Covid-19 infection waves for a region. The framework consists of a displaced double moving average (δDMA) algorithm for forecasting the start, rise, fall, and end of a Covid-19 wave. The forecast is generated by detection of potential dates with specific counts called ‘markers.’ This detection of markers is guided by decision rules generated through rough set theory. We also propose a novel ‘corrected moving average’ (χSMA) technique to forecast the upcoming count of new infections in a region. We implement our proposed framework on a database of Covid-19 infection specifics fetched from 12 countries, namely: Argentina, Colombia, New Zealand, Australia, Cuba, Jamaica, Belgium, Croatia, Libya, Kenya, Iran, and Myanmar. The database consists of day-wise time series of new and total infection counts from the date of first case till 31st January 2022 in each of the countries mentioned above. The δDMA algorithm outperforms other baseline techniques in forecasting the rise and fall of Covid-19 waves with a forecast precision of 94.08%. The χSMA algorithm also surpasses its counterparts in predicting the counts of new Covid-19 infections for the next day with the least mean absolute percentage error (MAPE) of 36.65%. Our proposed framework can be deployed to forecast the upcoming trends and counts of new Covid-19 infection cases under a minimum observation window of 7 days with high accuracy. With no perceptible impact of countermeasures on the pandemic until now, these forecasts will prove supportive to the administration and medical bodies in scaling and allotment of medical infrastructure and healthcare facilities.

[The Delphi technique: Methodology, variants and usage examples]

In the field of medicine and health sciences, Delphi methods are applied mainly in the exploratory or evaluative phases of a research process. Explicit and implicit knowledge of respected experts from research and practice is systematically synthesized. Originally developed as a method for structuring a group communication process, Delphi techniques have been established in the health sector as a consensus method. The findings are used to improve the evidence and acceptance of planned interventions or necessary standards or guidelines and to increase the probability of successful implementation in practice. However, different variants of Delphi methods have been developed in recent years, which are systematically contrasted and reflected in this paper with regard to key epistemological and methodological research activities. Based on this overview, researchers should be enabled to select the most suitable Delphi technique for their own research questions and research endeavors.

Data modelling recipes for SARS-CoV-2 wastewater-based epidemiology

Wastewater based epidemiology is recognized as one of the monitoring pillars, providing essential information for pandemic management. Central in the methodology are data modelling concepts for both communicating the monitoring results but also for analysis of the signal. It is due to the fast development of the field that a range of modelling concepts are used but without a coherent framework. This paper provides for such a framework, focusing on robust and simple concepts readily applicable, rather than applying latest findings from e.g., machine learning. It is demonstrated that data preprocessing, most important normalization by means of biomarkers and equal temporal spacing of the scattered data, is crucial. In terms of the latter, downsampling to a weekly spaced series is sufficient. Also, data smoothing turned out to be essential, not only for communication of the signal dynamics but likewise for regressions, nowcasting and forecasting. Correlation of the signal with epidemic indicators requires multivariate regression as the signal alone cannot explain the dynamics but - for this case study - multiple linear regression proofed to be a suitable tool when the focus is on understanding and interpretation. It was also demonstrated that short term prediction (7 days) is accurate with simple models (exponential smoothing or autoregressive models) but forecast accuracy deteriorates fast for longer periods.

Forecasting time trends of fatal motor vehicle crashes in Iran using an ensemble learning algorithm

OBJECTIVE

This study aimed to introduce the random forest (RF) method as a valuable tool for short-term crash frequency prediction. Besides, the study compares the forecast efficiency of the RF model with the classical seasonal autoregressive integrated moving average (SARIMA) model in the multivariate time-series analysis of crash counts.

METHODS

To this end, fatal accidents reported by the police and intercity traffic flow extracted from the loop detectors were aggregated in intercity highways at the country's level monthly from Farvardin 1395 to Mordad 1400. The first 55 data points were used as the training sample, and the remaining ten months were considered the test sample. The Box-Jenkins and random forest machine learning methods were employed for short-term crash frequency prediction. The mean absolute percentage error (MAPE) criterion was utilized to compare the forecast accuracy of the developed models.

RESULTS

The performance of the random forest model (MAPE = 2.6) with the exogenous variables of traffic flow, crash year, and month outperformed the best SARIMA (1,0,0) (1,0,0)12 model (MAPE = 5.7) with traffic flow as the regressor.

CONCLUSIONS

This study suggests that the random forest as an ensemble learning algorithm is a better crash prediction tool compared to the classical Box-Jenkins method, accounting for the non-linear dependencies in crash count time-series. Besides, the results illustrate that the multivariate SARIMA (SARIMAX) model significantly outperforms its univariate counterpart, accounting for the simultaneous impacts of exogenous variables.

Socioeconomic disruptions of harmful algal blooms in indigenous communities: The case of Quinault Indian nation

Harmful algal blooms (HABs) have been a pervasive challenge across coastal communities of the U.S. West Coast in recent years negatively affecting local economies and livelihoods. We focus on the effects of HABs to the Quinault Indian Nation (QIN) triggered by Pseudo-nitzschia that produce the toxin domoic acid (DA). This toxin accumulates in filter feeders and poses threats to human health via shellfish consumption. Consumption of razor clams with high levels of DA and Dungeness crab that prey on them can cause amnesic shellfish poisoning in humans and therefore requires closure of commercial, recreational and subsistence fisheries, postponing or limiting harvesting seasons. These disruptions result in significant losses in revenues along with negative effects to sociocultural dimensions of key importance to coastal communities. Livelihoods and wellbeing of tribal communities are affected disproportionately due to higher vulnerability and reliance on these marine resources for subsistence. We assess these effects at multiple levels for the QIN and discuss and reflect, through a tribal lens, upon advances and opportunities for impact mitigation and adaptation in the face of HABs, along with persisting challenges.

Climatology and model prediction of aerosol optical properties over the Indo-Gangetic Basin in north India

The current research focuses on the use of different simulation techniques in the future prediction of the crucial aerosol optical properties over the highly polluted Indo-Gangetic Basin in the northern part of India. The time series model was used to make an accurate forecast of aerosol optical depth (AOD) and angstrom exponent (AE), and the statistical variability of both cases was compared in order to evaluate the effectiveness of the model (training and validation). For this, different models were used to simulate the monthly average AOD and AE over Jaipur, Kanpur and Ballia during the period from 2003 to 2018. Further, the study was aimed to construct a comparative model that will be used for time series statistical analysis of MODIS-derived AOD₅₅₀ and AE_412-470. This will provide a more comprehensive information about the levels of AOD and AE that will exist in the future. To test the validity and applicability of the developed models, root-mean-square error (RMSE), mean absolute error (MAE), mean absolute percent error (MAPE), fractional bias (FB), and Pearson coefficient (r) were used to show adequate accuracy in model performance. From the observation, the monthly mean values of AOD and AE were found to be nearly similar at Kanpur and Ballia (0.62 and 1.26) and different at Jaipur (0.25 and 1.14). Jaipur indicates that during the pre-monsoon season, the AOD mean value was found to be highest (0.32 ± 0.15), while Kanpur and Ballia display higher AOD mean values during the winter season (0.72 ± 0.26 and 0.83 ± 0.32, respectively). Among the different methods, the autoregressive integrated moving average (ARIMA) model was found to be the best-suited model for AOD prediction at Ballia based on fitted error (RMSE (0.22), MAE (0.15), MAPE (24.55), FB (0.05)) and Pearson coefficient r (0.83). However, for AE, best prediction was found at Kanpur based on RMSE (0.24), MAE (0.21), MAPE (22.54), FB (-0.09) and Pearson coefficient r (0.82).

[Analysis and forecast of burden of pancreatic cancer along with attributable risk factors in Asia countries between 1990 and 2019]

Objective: To analyze the disease burden of pancreatic cancer in major Asian countries and forecast the burden of that in China, which helps to provide reference for the prevention and control of pancreatic cancer. Methods: Data on disease burden of pancreatic cancer among global and major Asian countries from on the Global Burden of Disease (GBD) 2019 were collected to describe burden distribution through the absolute numbers or standardized rates of incidence, death and disability adjusted life years (DALY) by year, sex and socio-demographic index. Estimated annual percentage changes (EAPC) was used to assess the trend of standardized rate. The proportion of deaths attributable to risk factors for pancreatic cancer in 2019 was used to compare by age, sex and region. ARIMA model was performed with R language to predict change of age-standardized incidence and death rates of pancreatic cancer from 2020 to 2029. Results: From 1990 to 2019, the standardized incidence rates of pancreatic cancer in China increased from 3.17/100 000 to 5.78/100 000, and the standardized death rate increased from 3.34/100 000 to 5.99/100 000. The increases exceeded other high-income Asia countries. In the past three decades, the standardized incidence, death and DALY rates of pancreatic cancer in global have increased year by year. Among the major countries in Asia, China has the highest growth rate of disease burden (EAPC of standardized incidence rates=2.32%, 95% CI: 2.10%-2.48% and EAPC of standardized death rate=2.25%, 95% CI: 2.03%-2.42%). In addition, incidence and death rates of pancreatic cancer in China are expected to continue on the rise between 2000 and 2029 by ARIMA model. Incidence rate is expected to increase 15.92% and death rate is expected to increase 15.86%. Conclusions: The standardized incidence and death rates of pancreatic cancer in China increase year by year with an increasing trend for the burden of disease. The disease burden of pancreatic cancer is expected to rise due to the increase and aging of the population. Preventive measures should be adopted to decrease the burden of the pancreatic cancer.

The African swine fever modelling challenge: Model comparison and lessons learnt

Robust epidemiological knowledge and predictive modelling tools are needed to address challenging objectives, such as: understanding epidemic drivers; forecasting epidemics; and prioritising control measures. Often, multiple modelling approaches can be used during an epidemic to support effective decision making in a timely manner. Modelling challenges contribute to understanding the pros and cons of different approaches and to fostering technical dialogue between modellers. In this paper, we present the results of the first modelling challenge in animal health - the ASF Challenge - which focused on a synthetic epidemic of African swine fever (ASF) on an island. The modelling approaches proposed by five independent international teams were compared. We assessed their ability to predict temporal and spatial epidemic expansion at the interface between domestic pigs and wild boar, and to prioritise a limited number of alternative interventions. We also compared their qualitative and quantitative spatio-temporal predictions over the first two one-month projection phases of the challenge. Top-performing models in predicting the ASF epidemic differed according to the challenge phase, host species, and in predicting spatial or temporal dynamics. Ensemble models built using all team-predictions outperformed any individual model in at least one phase. The ASF Challenge demonstrated that accounting for the interface between livestock and wildlife is key to increasing our effectiveness in controlling emerging animal diseases, and contributed to improving the readiness of the scientific community to face future ASF epidemics. Finally, we discuss the lessons learnt from model comparison to guide decision making.

Forecasting of overall and aggressive prostate cancer incident counts at the small area level

OBJECTIVES

This study aims to forecast overall and aggressive prostate cancer counts at the local government area (LGA) level over 10 years (2019-2028) in Victoria, Australia, using Victorian Cancer Registry (2001-2018) data.

METHODS

We used the Age-Period-Cohort approach to estimate the annual age-specific incidence and used Bayesian spatiotemporal models that account for non-linear temporal trends and area-level risk factors. We evaluated the models' performance by withholding and comparing forecasts with the 2014-2018 data.

RESULTS

There were 80,449 prostate cancer cases between 2001 and 2018, with an overall increasing trend. Compared to 2001, prostate cancer incidence increased by 69%, from 3049 to 5167 cases in 2018. Prostate cancer counts are expected to reach 7631 cases in 2028, a further 48% increase. Unexplained area-level spatial variation was substantially reduced after adjusting for the area-level elderly population. Aggressive prostate cancer cases increased by 107% between 2001 and 2018 and are expected to rise by 123% increase in 2028. The proportion of aggressive prostate cancer cases will increase to 31% in 2028 from 20% in 2018. By 2028, overall and aggressive prostate cancer cases are projected to be increasing in 66% and 61% of LGAs.

CONCLUSION

Prostate cancer cases are projected to rise at the state level and most LGAs in the next 10 years, with much steeper increases in aggressive cases. Population growth and an ageing population have primarily contributed to this rise besides prostate-specific antigen testing. These prediction estimates help inform prostate cancer burden and facilitate efficient healthcare delivery.