Predictor Of Future Events Research Articles

Prediction errors drive dynamic changes in neural patterns that guide behavior

Learning describes the process by which our internal expectation models of the world are updated by surprising outcomes (prediction errors [PEs]) to improve predictions of future events. However, the mechanisms through which error signals dynamically influence existing neural representations are unknown. Here, we use functional magnetic resonance imaging (fMRI) in humans solving a two-step Markov decision task to investigate changes in neural activation patterns following PEs. Using a dynamic multivariate pattern analysis, we can show that PE-related fMRI responses in error-coding regions predict trial-by-trial changes in multivariate neural patterns in the orbitofrontal cortex, the precuneus, and the ventromedial prefrontal cortex (vmPFC). Importantly, the dynamics of these pattern changes in the vmPFC also predicted upcoming changes in choice strategies and thus highlight the importance of these pattern changes for behavior.

Proposal to Supplement Slovenian Legislation in the Military Field

Abstract The foundation of any activity of all state bodies must primarily be based on state legislation. The military field, which is narrower than the defense field, with all the characteristics and properties of the largest collection of kinetic energy and at the same time the integrated energy of state institutionalized coercion, is even more dependent on the meaning and purpose of state legislation. It would be recommended that in the future Slovenian legislation in the military field would more effectively and above all more successfully follow international developments in the field of military legislation, science and military research and development. It should be emphasized that interdisciplinary content in the military field requires special attention, caution and, above all, far-reaching predictability, which is extremely difficult in the modern world, but not impossible. The predictability of future military events requires clear, target-specific and unambiguous legislative content.

SERUM PROTEOMIC PROFILING OF CAROTID ATHEROSCLEROSIS: A POPULATION OUTCOME STUDY

Objective: Circulating proteins linked to atherosclerosis may improve cardiovascular (CV) disease prediction. Here, we applied proteomic profiling, feature selection and unbiased clustering to identify proteins associated with carotid atherosclerosis and integrate them in a protein-based classification system for prediction of future CV events. Design and method: 491 community-dwelling participants (mean age, 58±11 years; 51% women) underwent carotid ultrasonography and proteomic profiling (CVD II panel, Olink Proteomics) at baseline. Subsequently, we collected cardiovascular outcome for a median follow-up period of 10.2 years. We applied partial least squares (PLS) and a machine learning algorithm (Random Forest, RF) to identify proteins associated with carotid intima-media thickness (cIMT) and the presence of atherosclerotic plaques. Next, we assessed the association of future CV events with protein-based phenogroups defined by unbiased clustering (Gaussian Mixture modelling) based on influential proteins in PLS and RF. Results: Of 92 measured proteins, 13 were labelled as important by PLS and RF and were independently associated with cIMT and/or the presence of plaques after multivariable adjustment: pro-adrenomedullin, agouti-related protein, brother of CDO, CD40 ligand, CD84, GLO1, HB-EGF, HSP27, lipoprotein lipase, lymphotactin, PAR-1, PDGF subunit B and TGM2. Based on these proteins, the clustering algorithm subdivided the cohort into two distinct phenogroups. Compared to the first (n = 174), participants in the second phenogroup (n = 317) had: i) a more unfavourable lipid profile with higher total cholesterol and triglycerides and lower HDL cholesterol (P<0.014 for all), but no differences in other CV risk factors such as age, blood pressure, smoking status and diabetes mellitus (P>0.061 for all); ii) higher cIMT (P = 0.0020); and iii) a significantly higher risk for future CV events during follow-up (multivariable-adjusted hazard ratio (95% CI) versus cluster 1: 2.63 (1.25 to 5.56); P = 0.01). Conclusions: Carotid atherosclerosis was linked to proteins reflecting haemostasis, angiogenesis, blood pressure regulation and inflammation. Focused proteomic phenomapping adequately identified individuals at high risk for future CV events and may thus complement current CV risk stratification strategies.

Free Light Chains κ and λ as New Biomarkers of Selected Diseases.

Diagnostic and prognostic markers are necessary to help in patient diagnosis and the prediction of future clinical events or disease progression. As promising biomarkers of selected diseases, the free light chains (FLCs) κ and λ were considered. Measurements of FLCs are currently used in routine diagnostics of, for example, multiple myeloma, and the usefulness of FLCs as biomarkers of monoclonal gammopathies is well understood. Therefore, this review focuses on the studies concerning FLCs as new potential biomarkers of other disorders in which an inflammatory background has been observed. We performed a bibliometric review of studies indexed in MEDLINE to assess the clinical significance of FLCs. Altered levels of FLCs were observed both in diseases strongly connected with inflammation such as viral infections, tick-borne diseases or rheumatic disorders, and disorders that are moderately associated with immune system reactions, e.g., multiple sclerosis, diabetes, cardiovascular disorders and cancers. Increased concentrations of FLCs appear to be a useful prognostic marker in patients with multiple sclerosis or tick-borne encephalitis. Intensive synthesis of FLCs may also reflect the production of specific antibodies against pathogens such as SARS-CoV-2. Moreover, abnormal FLC concentrations might predict the development of diabetic kidney disease in patients with type 2 diabetes. Markedly elevated levels are also associated with increased risk of hospitalization and death in patients with cardiovascular disorders. Additionally, FLCs have been found to be increased in rheumatic diseases and have been related to disease activity. Furthermore, it has been suggested that inhibition of FLCs would reduce the progression of tumorigenesis in breast cancer or colitis-associated colon carcinogenesis. In conclusion, abnormal levels of κ and λ FLCs, as well as the ratio of κ:λ, are usually the result of disturbances in the synthesis of immunoglobulins as an effect of overactive inflammatory reactions. Therefore, it seems that κ and λ FLCs may be significant diagnostic and prognostic biomarkers of selected diseases. Moreover, the inhibition of FLCs appears to be a promising therapeutical target for the treatment of various disorders where inflammation plays an important role in the development or progression of the disease.

Does inclusion of cognitive measures improve the predictive performance of SCORE2 for future cardiovascular events in older adults?

Abstract Funding Acknowledgements Type of funding sources: Public grant(s) – EU funding. Main funding source(s): National Institute for Research of Metabolic and Cardiovascular Diseases (Programme EXCELES, ID Project No. LX22NPO5104) - Funded by the European Union – Next Generation EU. Introduction The cardiovascular disease (CVD) risk prediction model SCORE2 uses several biomedical and behavioural factors. It is likely that other factors also contribute to CVD risk prediction. Cognitive impairment and CVD are associated and share several risk factors. While the causality of this relationship remains unclear, adding cognitive measures to risk prediction may improve the prediction of future CVD events. Objective We tested the hypothesis that including simple measures of cognitive functions improve the prediction of SCORE2 for future CVD events among middle aged and older subjects. Methods We used data on 13,391 Polish, Lithuanian and Czech adults without CVD at baseline (45–69 years) from the Health, Alcohol and Psychosocial factors In Eastern Europe cohort. Incident cases of myocardial infarction (MI), stroke, CVD mortality and composite (fatal and non-fatal) CVD events were identified over a 10-year follow-up. Baseline cognitive measures included immediate and delayed word recall (verbal memory and learning), animal naming (verbal fluency) and letter cancellation (attention, mental speed and concentration). Using competing-risks regression, relationships between cognitive functions and CVD outcomes were examined. Improvement in Area Under Curve Receiver Operator Characteristic (AUC-ROC) was used to compare predictive performance for CVD events of models including SCORE2 variables combined with cognitive tests vs SCORE2 alone. Results The incidence rates of MI, stroke, CVD mortality and composite CVD events were 5%, 4%, 4% and 11%, respectively. In multivariable analyses, all four cognitive measures were inversely associated with CVD outcomes; e.g. one standard deviation increase in immediate word recall score was associated with a 28% and 17% reduction in risk of CVD mortality and composite CVD events, respectively (all p-values <0.001). Adding cognitive measures to SCORE2 variables slightly improved the AUC-ROC for prediction of MI, CVD mortality and composite CVD events. For example, for the composite CVD measure, inclusion of all four cognitive measures increased the AUC-ROC from 0.6948 to 0.7030 (p<0.001) and similar improvement was seen for word recall. The results were consistent across countries. Conclusion Inclusion of a simple cognitive test in the assessment of cardiovascular health is feasible and it may improve prediction of future CVD risk, although in our data the improvement was not clinically important (despite being statistically significant). Further studies are needed to assess this proposition in larger prospective datasets.

The incorporation of repeated measurements of risk factors at current and previous visits improves the accuracy of cardiovascular risk assessment: an analysis of the EXSCEL trial

Abstract Funding Acknowledgements Type of funding sources: None. Background Risk prediction tools play an important role in cardiovascular risk stratification. One major limitation of most of these tools is their use of only single values of each risk factor, measured usually at a particular clinical visit, ignoring measurements made at previous visits. Purpose The aim of this study is to demonstrate the gain in predictive performance when CVD risk prediction tools incorporate repeated, rather than only single, measurements of risk factors. Methods We used data from the Exenatide Study of Cardiovascular Event Lowering (EXSCEL) randomized controlled trial to compare the quality of predictions of future major adverse cardiovascular events (MACE) in the Cox proportional hazards model that uses single values of risk factors, compared to the Bayesian joint model that uses repeated measures of risk factors. The risk of MACE was calculated in patients with type 2 diabetes with and without established CVD. We assessed the predictive ability of the following cardiovascular risk factors: glycated haemoglobin (HbA1c), high-density lipoprotein cholesterol (HDL-C), non-HDL-C, triglycerides, estimated glomerular filtration rate, low-density lipoprotein cholesterol (LDL-C), total cholesterol, and systolic blood pressure (SBP) using the time-dependent area under the receiver operating characteristic curve (aROC) for discrimination and the time-dependent Brier score for calibration. Results In participants without history of CVD, the aROC of systolic blood pressure increased from 0.62 to 0.69 when repeated, rather than only single, measurements of SBP were incorporated into the predictive model. Similarly, the aROC increased from 0.67 to 0.80 when repeated, rather than only single, measurements of both SBP and LDL-C were incorporated into the predictive model. For all other investigated cardiovascular risk factors, the measures of discrimination and calibration both improved when using the joint model as compared to the Cox proportional hazards model. The improvement was evident in participants with and without history of CVD but was more pronounced in the latter group. Conclusion This analysis demonstrates that the joint modeling approach, considering trajectories of cardiovascular risk factors, provides superior predictive performance of CVD risk stratification compared to standard risk prediction tools, using only a single time point.

Future-oriented repetitive thought, depressive symptoms, and suicide ideation severity: Role of future-event fluency and depressive predictive certainty

BackgroundKnowing how future-oriented repetitive thought – i.e., repeated consideration of whether positive or negative outcomes will happen in one's future – leads to hopelessness-related cognitions may elucidate the role of anticipating the future in depressive symptoms and suicide ideation. This study examined future-event fluency and depressive predictive certainty – i.e., the tendency to make pessimistic future-event predictions with certainty – as mechanisms explaining the relation between future-oriented repetitive thought, depressive symptoms, and suicide ideation. MethodsYoung adults (N = 354), oversampled for suicide ideation or attempt history, completed baseline measures of pessimistic future-oriented repetitive thought (i.e., the degree to which people consider whether negative outcomes will happen or positive outcomes will not happen in their futures), future-event fluency, depressive predictive certainty, depressive symptoms, and suicide ideation severity and were followed up 6 months later (N = 324). ResultsPessimistic future-oriented repetitive thought predicted depressive predictive certainty at 6-months, partially mediated by lower positive but not increased negative future-event fluency. There was an indirect relationship between pessimistic future-oriented repetitive thought and 6-month suicide ideation severity via 6-month depressive predictive certainty through 6-month depressive symptoms, and also via 6-month depressive symptoms (but not depressive predictive certainty) alone. LimitationsLack of an experimental design limits inferences about causality, and a predominantly female sample may limit generalizability by sex. ConclusionClinical interventions should address pessimistic future-oriented repetitive thought – and its impact on how easily people can think about positive future outcomes – as one potential way to reduce depressive symptoms and, indirectly, suicide ideation.

Segment aorta and localize landmarks simultaneously on noncontrast CT using a multitask learning framework for patients without severe vascular disease

BackgroundNon-contrast chest CT is widely used for lung cancer screening, and its images carry potential information of the thoracic aorta. The morphological assessment of the thoracic aorta may have potential value in the presymptomatic detection of thoracic aortic-related diseases and the risk prediction of future adverse events. However, due to low vasculature contrast in such images, visual assessment of aortic morphology is challenging and highly depends on physicians’ experience. PurposeThe main objective of this study is to propose a novel multi-task framework based on deep learning for simultaneous aortic segmentation and localization of key landmarks on unenhanced chest CT. The secondary objective is to use the algorithm to measure quantitative features of thoracic aorta morphology. MethodsThe proposed network is composed of two subnets to carry out segmentation and landmark detection, respectively. The segmentation subnet aims to demarcate the aortic sinuses of the Valsalva, aortic trunk and aortic branches, whereas the detection subnet is devised to locate five landmarks on the aorta to facilitate morphology measures. The networks share a common encoder and run decoders in parallel, taking full advantage of the synergy of the segmentation and landmark detection tasks. Furthermore, the volume of interest (VOI) module and the squeeze-and-excitation (SE) block with attention mechanisms are incorporated to further boost the capability of feature learning. ResultsBenefiting from the multitask framework, we achieved a mean Dice score of 0.95, average symmetric surface distance of 0.53 mm, Hausdorff distance of 2.13 mm for aortic segmentation, and mean square error (MSE) of 3.23 mm for landmark localization in 40 testing cases. ConclusionWe proposed a multitask learning framework which can perform segmentation of the thoracic aorta and localization of landmarks simultaneously and achieved good results. It can support quantitative measurement of aortic morphology for further analysis of aortic diseases, such as hypertension.

An Analysis of Microplastics Ingested by the Mediterranean Detritivore Holothuria tubulosa (Echinodermata: Holothuroidea) Sheds Light on Patterns of Contaminant Distribution in Different Marine Areas

Microplastic pollution constitutes a serious environmental problem that requires more effective scientific research to describe its potential impacts on marine fauna. The interaction between microplastics and marine biota can have significant negative effects through the trophic chain, up to human health. To date, several steps forward have been made in our understanding of this phenomenon; however, large knowledge gaps still exist for several taxa and areas. In particular, the pattern of spatial and temporal distribution of microplastics in marine sediments and their interaction with benthic detritivore species still needs to be addressed. The Mediterranean Sea is one of the most impacted areas of the world, and its biota is deeply affected by microplastic pollution. To investigate the effects of the presence of microplastics in the sediments in this area, the echinoderm Holothuria tubulosa was chosen as a model species, and specimens were collected along the Salento peninsula in Apulia, Southern Italy. This peculiar geographic area extends between two ecoregions of the Mediterranean Sea, the Northern Ionian and the Southern Adriatic seas, characterized by peculiar and distinct currents and submarine topologies, resulting in a complex and dynamic ecosystem affected by seasonal fluctuations that make the Salento peninsula an interesting natural laboratory for predictions of future dispersion events on a wider scale. Microplastics were analyzed by investigating the gut contents of H. tubulosa individuals, and the SEM/EDX method was used to confirm the plastic material extracted. Results revealed microplastics in all the specimens analyzed and with a homogeneous pattern of distribution in time and some differences in space, suggesting that the presence of this anthropogenic material is constant throughout the year and its quantity is only slightly affected by the level of conservation and management strategies characterizing the sampling sites.

Cooperative Swarm Learning for Distributed Cyclic Edge Intelligent Computing

Emerging technologies and applications including the Internet of Things (IoT), social networking, and crowd-sourcing generate large amounts of data at the network edge. Machine learning models are often built from the collected data, to enable the detection, classification, and prediction of future events. Due to bandwidth, storage, and privacy concerns, it is often impractical to send all the data to a centralized location. Recently, the emerging Federated Learning (FL) systems mitigates some of those concerns, by keeping data private to cater the confidentiality issues. Although FL has drawn the attention of researchers and developers, the involvement of an aggregator server for global model updates, makes the system prone to privacy and security breaches. To resolve this issue Swarm Learning (SL) securely onboards edge clients and dynamically elects the swarm leader, to perform collaborative model training in an extremely decentralized, private and secured manner. However, the conventional blockchain-enabled dynamic selection of leader at every communication round is resource intensive and degrades SL’s effectiveness. In this paper, we propose a lightweight communication and computation efficient cooperative swarm learning framework for cyclic edge intelligent computing. The proposed cooperative swarm learning provides cyclic learning based on Deep Neural Networks procedure for training a global model in a sequential ring topology in one iteration which reduces the computational and communication overhead. The global model update method trains a shared global thermal comfort prediction model. Since there is model updating being performed in each participant of the cyclic edge intelligent computing network, bandwidth and computing power demand are reduced. An empirical investigation on Non-IID thermal comfort dataset demonstrates the superiority of the proposed framework.

Guest Editorial Robust Learning of Spatio-Temporal Point Processes: Modeling, Algorithm, and Applications

Temporal data are ubiquitous in real-world applications, and they can be generally divided into two categories: 1) synchronous temporal data which are basically equivalent to time series data; and 2) the asynchronous data which are often in the form of event data with a time stamp in continuous time-space. In fact, the event data are often converted to the time series by aggregating the event count in equal time intervals in many previous approaches. While it is often of one’s greater interest to directly establish models based on the raw event data whose time stamps carry useful information, especially for those time-sensitive tasks, ranging from earthquake prediction, crime analysis, to infectious disease diffusion forecasting, etc. Developing the spatio-temporal point process and the related applications is the theme of this Special Issue, which treats an event as a point in the spatio-temporal space, with possibly extra attributes. The model captures the instantaneous happening rate of the events and their potential dependency. The derived use cases often refer to future events prediction, and causality estimation.

Big Data in Chronic Kidney Disease: Evolution or Revolution?

Digital information storage capacity and biomedical technology advancements in recent decades have stimulated the maturity and popularization of “big data” in medicine. The value of utilizing big data as a diagnostic and prognostic tool has continued to rise given its potential to provide accurate and insightful predictions of future health events and probable outcomes for individuals and populations, which may aid early identification of disease and timely treatment interventions. Whilst the implementation of big data methods for this purpose is more well-established in specialties such as oncology, cardiology, ophthalmology, and dermatology, big data use in nephrology and specifically chronic kidney disease (CKD) remains relatively novel at present. Nevertheless, increased efforts in the application of big data in CKD have been observed over recent years, with aims to achieve a more personalized approach to treatment for individuals and improved CKD screening strategies for the general population. Considering recent developments, we provide a focused perspective on the current state of big data and its application in CKD and nephrology, with hope that its ongoing evolution and revolution will gradually identify more solutions to improve strategies for CKD prevention and optimize the care of patients with CKD.

Expectation violations enhance neuronal encoding of sensory information in mouse primary visual cortex

The response of cortical neurons to sensory stimuli is shaped both by past events (adaptation) and the expectation of future events (prediction). Here we employed a visual stimulus paradigm with different levels of predictability to characterise how expectation influences orientation selectivity in the primary visual cortex (V1) of male mice. We recorded neuronal activity using two-photon calcium imaging (GCaMP6f) while animals viewed sequences of grating stimuli which either varied randomly in their orientations or rotated predictably with occasional transitions to an unexpected orientation. For single neurons and the population, there was significant enhancement in the gain of orientation-selective responses to unexpected gratings. This gain-enhancement for unexpected stimuli was prominent in both awake and anaesthetised mice. We implemented a computational model to demonstrate how trial-to-trial variability in neuronal responses were best characterised when adaptation and expectation effects were combined.

Toward a Multi-Column Knowledge-Oriented Neural Network for Web Corpus Causality Mining

In the digital age, many sources of textual content are devoted to studying and expressing many sorts of relationships, including employer–employee, if–then, part–whole, product–producer, and cause–effect relations/causality. Mining cause–effect relations are a key topic in many NLP (natural language processing) applications, such as future event prediction, information retrieval, healthcare, scenario generation, decision making, commerce risk management, question answering, and adverse drug reaction. Many statistical and non-statistical methods have been developed in the past to address this topic. Most of them frequently used feature-driven supervised approaches and hand-crafted linguistic patterns. However, the implicit and ambiguous statement of causation prevented these methods from achieving great recall and precision. They cover a limited set of implicit causality and are difficult to extend. In this work, a novel MCKN (multi-column knowledge-oriented network) is introduced. This model includes various knowledge-oriented channels/columns (KCs), where each channel integrates prior human knowledge to capture language cues of causation. MCKN uses unique convolutional word filters (wf) generated automatically using WordNet and FrameNet. To reduce MCKN’s dimensionality, we use filter selection and clustering approaches. Our model delivers superior performance on the Alternative Lexicalization (AltLexes) dataset, proving that MCKN is a simpler and distinctive approach for informal datasets.

Does Coronary Plaque Morphology Matter Beyond Plaque Burden?

Imaging of adverse coronary plaque features by coronary computed tomography angiography (CCTA) has advanced greatly and at a fast pace. We aim to describe the evolution, present and future in plaque analysis, and its value in comparison to plaque burden. Recently, it has been demonstrated that in addition to plaque burden, quantitative and qualitative assessment of coronary plaque by CCTA can improve the prediction of future major adverse cardiovascular events in diverse coronary artery disease scenarios. The detection of high-risk non-obstructive coronary plaque can lead to higher use of preventive medical therapies such as statins and aspirin, help identify culprit plaque, and differentiate between myocardial infarction types. Even more, over traditional plaque burden, plaque analysis including pericoronary inflammation can potentially be useful tools for tracking disease progression and response to medical therapy. The identification of the higher risk phenotypes with plaque burden, plaque characteristics, or ideally both can allow the allocation of targeted therapies and potentially monitor response. Further observational data are now required to investigate these key issues in diverse populations, followed by rigorous randomized controlled trials.

Successor-like representation guides the prediction of future events in human visual cortex and hippocampus.

Human agents build models of their environment, which enable them to anticipate and plan upcoming events. However, little is known about the properties of such predictive models. Recently, it has been proposed that hippocampal representations take the form of a predictive map-like structure, the so-called successor representation (SR). Here, we used human functional magnetic resonance imaging to probe whether activity in the early visual cortex (V1) and hippocampus adhere to the postulated properties of the SR after visual sequence learning. Participants were exposed to an arbitrary spatiotemporal sequence consisting of four items (A-B-C-D). We found that after repeated exposure to the sequence, merely presenting single sequence items (e.g., - B - -) resulted in V1 activation at the successor locations of the full sequence (e.g., C-D), but not at the predecessor locations (e.g., A). This highlights that visual representations are skewed toward future states, in line with the SR. Similar results were also found in the hippocampus. Moreover, the hippocampus developed a coactivation profile that showed sensitivity to the temporal distance in sequence space, with fading representations for sequence events in the more distant past and future. V1, in contrast, showed a coactivation profile that was only sensitive to spatial distance in stimulus space. Taken together, these results provide empirical evidence for the proposition that both visual and hippocampal cortex represent a predictive map of the visual world akin to the SR.

Extreme Drought around Tomsk, Russia in Summer 2012 in Comparison with Other Regions in Western Siberia

The objective of this study is to clarify the regional difference in hydrometeorological parameters in Western Siberia (WS), an area which suffered from severe drought in the summer of 2012. The drought was especially apparent in middle WS. Regional differences in the hydrometeorological parameters have not been fully investigated so far; therefore, we investigated them based on the temporal variation in the hydrometeorological data. All of WS experienced an extremely hot summer in 2012, particularly in June and July. In middle WS, the snow water equivalent in March 2012 was the third lowest recorded from 1985 to 2019. The runoff during April–September 2012 was smaller than the long-term mean. Precipitation during April–August 2012 was also continuously lower. All this resulted in a severe drought in the summer. In particular, precipitation in July 2012 in middle WS was among the lowest recorded for the period of 1966–2019. These characteristics were unique to middle WS in July 2012. North and south WS did not suffer from a severe drought in 2012 because substantial precipitation was observed in summer. The findings of this study will contribute to the prediction of future hydrometeorological events, as extreme phenomena are more likely to occur in accordance with the progress of global warming.

Prediction of meteorological drought and standardized precipitation index based on the random forest (RF), random tree (RT), and Gaussian process regression (GPR) models.

Agriculture, meteorological, and hydrological drought is a natural hazard which affects ecosystems in the central India of Maharashtra state. Due to limited historical data for drought monitoring and forecasting available in the central India of Maharashtra state, implementing machine learning (ML) algorithms could allow for the prediction of future drought events. In this paper, we have focused on the prediction accuracy of meteorological drought in the semi-arid region based on the standardized precipitation index (SPI) using the random forest (RF), random tree (RT), and Gaussian process regression (GPR-PUK kernel) models. A different combination of machine learning models and variables has been performed for the forecasting of metrological drought based on the SPI-6 and 12months. Models were developed using monthly rainfall data for the period of 2000-2019 at two meteorological stations, namely, Karanjali and Gangawdi, each representing a geographical region of Upper Godavari river basin area in the central India of Maharashtra state which frequently experiences droughts. Historical data from the SPI from 2000 to 2013 was processed to train the model into machine learning model, and the rest of the 2014 to 2019-year data were used for testing to forecast the SPI and metrological drought. The mean square error (MSE), root mean square error (RMSE), adjustedR2, Mallows' (Cp), Akaike's (AIC), Schwarz's (SBC), and Amemiya's PC were used to identify the best combination input model and best subregression analysis for both stations of SPI-6 and 12. The correlation coefficient ([Formula: see text]), mean absolute error (MAE), root mean square error (RMSE), relative absolute error (RAE), and root relative squared error (RRSE) were used to perform evaluation for SPI-6 and 12months of both stations with RF, RT, and GPR-PUK kernel models during the training and testing scenarios. The results during testing phase revealed that the RF was found as the best model in forecasting droughts with values of [Formula: see text], MAE, RMSE, RAE (%), and RRSE (%) being 0.856, 0.551, 0.718, 74.778, and 54.019, respectively, for SPI-6 while 0.961, 0.361, 0.538, 34.926, and 28.262, respectively, for SPI-12 scales at Gangawdi station. Further, the respective values of evaluators at Karanjali station were 0.913 and 0.966, 0.541 and 0.386, 0.604 and 0.589, 52.592 and 36.959, and 42.315 and 31.394 for PUK kernel and RT models, respectively, during SPI-6 and SPI-12. Machine learning models are potential drought warning techniques because they take less time, have fewer inputs, and are less sophisticated than dynamic or scientific models.

Plasma levels of CCL21, but not CCL19, independently predict future coronary events in a prospective population-based cohort

Background and aimsThe homeostatic chemokines CCL21 and CCL19 have been explored as biomarkers in cardiovascular disease prediction in patients with established cardiovascular disease, but associations between these chemokines and first-time coronary event incidence have not been investigated before. Here, we explored associations between CCL21 or CCL19 and first-time incident coronary events in the general population-based Malmö Diet and Cancer cohort with two decades of follow-up. MethodsCCL21 and CCL19 levels in plasma were analysed with ELISA and proximity extension assay and associations with disease incidence were explored with conditional logistic regression in a nested case-control cohort (CCL21; n = 676) and with Cox regression in a population-based cohort (CCL19; n = 4636). ResultsHigh CCL21 levels in plasma were associated with incident first-time coronary events independently of traditional risk factors (odds ratio of 2.64 with 95% confidence interval 1.62–4.31, p < 0.001, comparing the highest versus the lowest tertile of CCL21), whereas CCL19 was not. CCL19 was, however, associated with incident heart failure, as well as increased all-cause, cardiovascular and cancer mortality independently of age and sex. ConclusionsEven though CCL21 and CCL19 both signal through CCR7, these chemokines may not be interchangeable as disease predictors and CCL21 could be used for prediction of future coronary events in individuals without any previous coronary heart disease history.

Future Event Prediction Based on Temporal Knowledge Graph Embedding

Accurate prediction of future events brings great benefits and reduces losses for society in many domains, such as civil unrest, pandemics, and crimes. Knowledge graph is a general language for describing and modeling complex systems. Different types of events continually occur, which are often related to historical and concurrent events. In this paper, we formalize the future event prediction as a temporal knowledge graph reasoning problem. Most existing studies either conduct reasoning on static knowledge graphs or assume knowledges graphs of all timestamps are available during the training process. As a result, they cannot effectively reason over temporal knowledge graphs and predict events happening in the future. To address this problem, some recent works learn to infer future events based on historical event-based temporal knowledge graphs. However, these methods do not comprehensively consider the latent patterns and influences behind historical events and concurrent events simultaneously. This paper proposes a new graph representation learning model, namely Recurrent Event Graph ATtention Network (RE-GAT), based on a novel historical and concurrent events attention-aware mechanism by modeling the event knowledge graph sequence recurrently. More specifically, our RE-GAT uses an attention-based historical events embedding module to encode past events, and employs an attention-based concurrent events embedding module to model the associations of events at the same timestamp. A translation-based decoder module and a learning objective are developed to optimize the embeddings of entities and relations. We evaluate our proposed method on four benchmark datasets. Extensive experimental results demonstrate the superiority of our RE-GAT model comparing to various baselines, which proves that our method can more accurately predict what events are going to happen.