基于Partial New Causality的因果脑网络情绪识别

为了研究情绪产生过程中脑区以及通道之间的因果作用,在部分格兰杰与新型因果关系的基础上,提出一种用于研究时间序列之间因果关系的部分新型因果关系(PNC)方法。在不同情绪下选取脑区内的8个通道,用PNC计算脑区内通道之间的因果连接关系,根据连接关系构建因果网络;对因果网络中节点的信息流向和介数属性进行分析,将PNC因果网络和Granger因果网络节点之间的因果连接视为一种特征送入SVM中训练分类。实验结果表明,基于PNC因果网络和Granger因果网络的平均识别精度分别为76.4%和68.5%,PNC可用于计算时间序列之间的因果关系。

Immune cell signatures and causal association with irritable bowel syndrome:A mendelian randomization study

BACKGROUND The mucosal barrier's immune-brain interactions,pivotal for neural development and function,are increasingly recognized for their potential causal and therapeutic relevance to irritable bowel syndrome(IBS).Prior studies linking immune inflammation with IBS have been inconsistent.To further elucidate this relationship,we conducted a Mendelian randomization(MR)analysis of 731 immune cell markers to dissect the influence of various immune phenotypes on IBS.Our goal was to deepen our understanding of the disrupted brain-gut axis in IBS and to identify novel therapeutic targets.AIM To leverage publicly available data to perform MR analysis on 731 immune cell markers and explore their impact on IBS.We aimed to uncover immunophenotypic associations with IBS that could inform future drug development and therapeutic strategies.METHODS We performed a comprehensive two-sample MR analysis to evaluate the causal relationship between immune cell markers and IBS.By utilizing genetic data from public databases,we examined the causal associations between 731 immune cell markers,encompassing median fluorescence intensity,relative cell abundance,absolute cell count,and morphological parameters,with IBS susceptibility.Sensitivity analyses were conducted to validate our findings and address potential heterogeneity and pleiotropy.RESULTS Bidirectional false discovery rate correction indicated no significant influence of IBS on immunophenotypes.However,our analysis revealed a causal impact of IBS on 30 out of 731 immune phenotypes(P<0.05).Nine immune phenotypes demonstrated a protective effect against IBS[inverse variance weighting(IVW)<0.05,odd ratio(OR)<1],while 21 others were associated with an increased risk of IBS onset(IVW≥0.05,OR≥1).CONCLUSION Our findings underscore a substantial genetic correlation between immune cell phenotypes and IBS,providing valuable insights into the pathophysiology of the condition.These results pave the way for the development of more precise biomarkers and targeted therapies for IBS.Furthermore,this research enriches our comprehension of immune cell roles in IBS pathogenesis,offering a foundation for more effective,personalized treatment approaches.These advancements hold promise for improving IBS patient quality of life and reducing the disease burden on individuals and their families.

Causal role of immune cells in obstructive sleep apnea hypopnea syndrome:Mendelian randomization study

BACKGROUND Despite being one of the most prevalent sleep disorders,obstructive sleep apnea hypoventilation syndrome(OSAHS)has limited information on its immunologic foundation.The immunological underpinnings of certain major psychiatric diseases have been uncovered in recent years thanks to the extensive use of genome-wide association studies(GWAS)and genotyping techniques using highdensity genetic markers(e.g.,SNP or CNVs).But this tactic hasn't yet been applied to OSAHS.Using a Mendelian randomization analysis,we analyzed the causal link between immune cells and the illness in order to comprehend the immunological bases of OSAHS.AIM To investigate the immune cells'association with OSAHS via genetic methods,guiding future clinical research.METHODS A comprehensive two-sample mendelian randomization study was conducted to investigate the causal relationship between immune cell characteristics and OSAHS.Summary statistics for each immune cell feature were obtained from the GWAS catalog.Information on 731 immune cell properties,such as morphologic parameters,median fluorescence intensity,absolute cellular,and relative cellular,was compiled using publicly available genetic databases.The results'robustness,heterogeneity,and horizontal pleiotropy were confirmed using extensive sensitivity examination.RESULTS Following false discovery rate(FDR)correction,no statistically significant effect of OSAHS on immunophenotypes was observed.However,two lymphocyte subsets were found to have a significant association with the risk of OSAHS:Basophil%CD33dim HLA DR-CD66b-(OR=1.03,95%CI=1.01-1.03,P<0.001);CD38 on IgD+CD24-B cell(OR=1.04,95%CI=1.02-1.04,P=0.019).CONCLUSION This study shows a strong link between immune cells and OSAHS through a gene approach,thus offering direction for potential future medical research.

Integrated causal inference modeling uncovers novel causal factors and potential therapeutic targets of Qingjin Yiqi granules for chronic fatigue syndrome

Objective:Chronic fatigue syndrome(CFS)is a prevalent symptom of post-coronavirus disease 2019(COVID-19)and is associated with unclear disease mechanisms.The herbal medicine Qingjin Yiqi granules(QJYQ)constitute a clinically approved formula for treating post-COVID-19;however,its potential as a drug target for treating CFS remains largely unknown.This study aimed to identify novel causal factors for CFS and elucidate the potential targets and pharmacological mechanisms of action of QJYQ in treating CFS.Methods:This prospective cohort analysis included 4,212 adults aged≥65 years who were followed up for 7 years with 435 incident CFS cases.Causal modeling and multivariate logistic regression analysis were performed to identify the potential causal determinants of CFS.A proteome-wide,two-sample Mendelian randomization(MR)analysis was employed to explore the proteins associated with the identified causal factors of CFS,which may serve as potential drug targets.Furthermore,we performed a virtual screening analysis to assess the binding affinity between the bioactive compounds in QJYQ and CFS-associated proteins.Results:Among 4,212 participants(47.5%men)with a median age of 69 years(interquartile range:69–70 years)enrolled in 2004,435 developed CFS by 2011.Causal graph analysis with multivariate logistic regression identified frequent cough(odds ratio:1.74,95%confidence interval[CI]:1.15–2.63)and insomnia(odds ratio:2.59,95%CI:1.77–3.79)as novel causal factors of CFS.Proteome-wide MR analysis revealed that the upregulation of endothelial cell-selective adhesion molecule(ESAM)was causally linked to both chronic cough(odds ratio:1.019,95%CI:1.012–1.026,P=2.75 e^(−05))and insomnia(odds ratio:1.015,95%CI:1.008–1.022,P=4.40 e^(−08))in CFS.The major bioactive compounds of QJYQ,ginsenoside Rb2(docking score:−6.03)and RG4(docking score:−6.15),bound to ESAM with high affinity based on virtual screening.Conclusions:Our integrated analytical framework combining epidemiological,genetic,and in silico data provides a novel strategy for elucidating complex disease mechanisms,such as CFS,and informing models of action of traditional Chinese medicines,such as QJYQ.Further validation in animal models is warranted to confirm the potential pharmacological effects of QJYQ on ESAM and as a treatment for CFS.

Causal temporal graph attention network for fault diagnosis of chemical processes

Fault detection and diagnosis(FDD)plays a significant role in ensuring the safety and stability of chemical processes.With the development of artificial intelligence(AI)and big data technologies,data-driven approaches with excellent performance are widely used for FDD in chemical processes.However,improved predictive accuracy has often been achieved through increased model complexity,which turns models into black-box methods and causes uncertainty regarding their decisions.In this study,a causal temporal graph attention network(CTGAN)is proposed for fault diagnosis of chemical processes.A chemical causal graph is built by causal inference to represent the propagation path of faults.The attention mechanism and chemical causal graph were combined to help us notice the key variables relating to fault fluctuations.Experiments in the Tennessee Eastman(TE)process and the green ammonia(GA)process showed that CTGAN achieved high performance and good explainability.

Causal genetic regulation of DNA replication on immune microenvironment in colorectal tumorigenesis: Evidenced by an integrated approach of trans-omics and GWAS

The interplay between DNA replication stress and immune microenvironment alterations is known to play a crucial role in colorectal tumorigenesis,but a comprehensive understanding of their association with and relevant biomarkers involved in colorectal tumorigenesis is lacking.To address this gap,we conducted a study aiming to investigate this association and identify relevant biomarkers.We analyzed transcriptomic and proteomic profiles of 904 colorectal tumor tissues and 342 normal tissues to examine pathway enrichment,biological activity,and the immune microenvironment.Additionally,we evaluated genetic effects of single variants and genes on colorectal cancer susceptibility using data from genome-wide association studies(GWASs)involving both East Asian(7062 cases and 195745 controls)and European(24476 cases and 23073 controls)populations.We employed mediation analysis to infer the causal pathway,and applied multiplex immunofluorescence to visualize colocalized biomarkers in colorectal tumors and immune cells.Our findings revealed that both DNA replication activity and the flap structure-specific endonuclease 1(FEN1)gene were significantly enriched in colorectal tumor tissues,compared with normal tissues.Moreover,a genetic variant rs4246215 G>T in FEN1 was associated with a decreased risk of colorectal cancer(odds ratio=0.94,95%confidence interval:0.90–0.97,P_(meta)=4.70×10^(-9)).Importantly,we identified basophils and eosinophils that both exhibited a significantly decreased infiltration in colorectal tumors,and were regulated by rs4246215 through causal pathways involving both FEN1 and DNA replication.In conclusion,this trans-omics incorporating GWAS data provides insights into a plausible pathway connecting DNA replication and immunity,expanding biological knowledge of colorectal tumorigenesis and therapeutic targets.

TCAS-PINN:Physics-informed neural networks with a novel temporal causality-based adaptive sampling method

Physics-informed neural networks(PINNs)have become an attractive machine learning framework for obtaining solutions to partial differential equations(PDEs).PINNs embed initial,boundary,and PDE constraints into the loss function.The performance of PINNs is generally affected by both training and sampling.Specifically,training methods focus on how to overcome the training difficulties caused by the special PDE residual loss of PINNs,and sampling methods are concerned with the location and distribution of the sampling points upon which evaluations of PDE residual loss are accomplished.However,a common problem among these original PINNs is that they omit special temporal information utilization during the training or sampling stages when dealing with an important PDE category,namely,time-dependent PDEs,where temporal information plays a key role in the algorithms used.There is one method,called Causal PINN,that considers temporal causality at the training level but not special temporal utilization at the sampling level.Incorporating temporal knowledge into sampling remains to be studied.To fill this gap,we propose a novel temporal causality-based adaptive sampling method that dynamically determines the sampling ratio according to both PDE residual and temporal causality.By designing a sampling ratio determined by both residual loss and temporal causality to control the number and location of sampled points in each temporal sub-domain,we provide a practical solution by incorporating temporal information into sampling.Numerical experiments of several nonlinear time-dependent PDEs,including the Cahn–Hilliard,Korteweg–de Vries,Allen–Cahn and wave equations,show that our proposed sampling method can improve the performance.We demonstrate that using such a relatively simple sampling method can improve prediction performance by up to two orders of magnitude compared with the results from other methods,especially when points are limited.

Causal association between 731 immunocyte phenotypes and liver cirrhosis: A bidirectional two-sample mendelian randomization analysis

BACKGROUND Liver cirrhosis is a progressive hepatic disease whose immunological basis has attracted increasing attention.However,it remains unclear whether a concrete causal association exists between immunocyte phenotypes and liver cirrhosis.AIM To explore the concrete causal relationships between immunocyte phenotypes and liver cirrhosis through a mendelian randomization(MR)study.METHODS Data on 731 immunocyte phenotypes were obtained from genome-wide assoc-iation studies.Liver cirrhosis data were derived from the Finn Gen dataset,which included 214403 individuals of European ancestry.We used inverse variable weighting as the primary analysis method to assess the causal relationship.Sensitivity analyses were conducted to evaluate heterogeneity and horizontal pleiotropy.RESULTS The MR analysis demonstrated that 11 immune cell phenotypes have a positive association with liver cirrhosis[P<0.05,odds ratio(OR)>1]and that 9 immu-nocyte phenotypes were negatively correlated with liver cirrhosis(P<0.05,OR<1).Liver cirrhosis was positively linked to 9 immune cell phenotypes(P<0.05,OR>1)and negatively linked to 10 immune cell phenotypes(P<0.05;OR<1).None of these associations showed heterogeneity or horizontally pleiotropy(P>0.05).CONCLUSION This bidirectional two-sample MR study demonstrated a concrete causal association between immunocyte phenotypes and liver cirrhosis.These findings offer new directions for the treatment of liver cirrhosis.

Mendelian Randomization Study of Causal Relationship between Inflammatory Factors and Vascular Dementia and Chinese Herbal Medicines Screening for Prevention and Treatment

Objective: This study aims to examine the causal relationship between inflammatory factors and the probability of developing vascular dementia (VD) using Mendelian Randomization (MR) and Chinese herbal medicine prediction method, and to screen potential Chinese herbal medicines for the prevention and treatment of VD. Methods: Single nucleotide polymorphisms (SNPs) that exhibit a strong association with vascular dementia (VD) were identified as instrumental variables from the summary statistics of genome-wide association studies (GWAS). The primary analytical method employed was inverse variance weighting (IVW), while auxiliary analyses included the MR-Egger method, weighted median method, simple model, and weighted model. A two-way Mendelian randomization analysis was conducted to assess the causal relationship between inflammatory factors and the risk of VD, thereby identifying the key inflammatory factors involved. The MR-Egger intercept test and Cochran’s Q test were employed to assess the horizontal polymorphism and heterogeneity of instrumental variables. A sensitivity analysis was conducted by excluding one method at a time. Ultimately, based on key inflammatory factors, predictions for the prevention and treatment using traditional Chinese medicine were made, along with the screening of homologous herbal remedies. Results: Based on the results of the forward MR, the probability of developing VD was elevated when the inflammatory factors CXCL10 and CXCL5 were expressed at higher levels, whereas the probability of developing VD decreased as the expression levels of IL-13 and IL-20RA increased. These findings were supported by the assessment of pleiotropy, heterogeneity, and sensitivity. The results of the reverse MR analysis showed that there was no causal relationship between VD, as an exposure dataset, and these four inflammatory factors. According to the key inflammatory factors, 37 Chinese herbal medicines such as Siraitia grosvenorii were selected. Their characteristics including four natures, five flavors, channel tropism and treatment efficiency were cold, warm, neutral, pungent, sweet, bitter, lung meridian, spleen meridian, liver meridian, kidney meridian and clearing heat. Among them, Siraitia grosvenorii, Poria with hostwood, Perilla frutescens, and Radix Platycodi were all medicine and food homologous Chinese herbal medicines. Conclusions: The increase of CXCL10 and CXCL5 expression levels can increase the risk of VD, and the increase of IL-13 and IL-20 RA expression levels can reduce the risk of VD. Siraitia grosvenorii and other Chinese herbal medicines might be potential sources of therapeutic drugs for the treatment of VD. Medicine and food homologous Chinese herbal medicines, such as Siraitia grosvenorii, Poria with hostwood, Perilla frutescens, and Radix Platycodi, may help the elderly population with corresponding Traditional Chinese Medicine (TCM) constitutions to prevent VD.

Causal association between 25-hydroxyvitamin D status and cataract development:A two-sample Mendelian randomization study

BACKGROUND Vitamin deficiencies are linked to various eye diseases,and the influence of vitamin D on cataract formation has been noted in prior research.However,detailed investigations into the causal relationship between 25-(OH)D status and cataract development remain scarce.AIM To explore a possible causal link between cataracts and vitamin D.METHODS In this study,we explored the causal link between 25-(OH)D levels and cataract development using Mendelian randomization.Our analytical approach included inverse-variance weighting(IVW),MR-Egger,weighted median,simple mode,and weighted mode methods.The primary analyses utilized IVW with random effects,supplemented by sensitivity and heterogeneity tests using both IVW and MR-Egger.MR-Egger was also applied for pleiotropy testing.Additionally,a leave-one-out analysis helped identify potentially impactful single-nucleotide polymorphisms.RESULTS The analysis revealed a positive association between 25-(OH)D levels and the risk of developing cataracts(OR=1.11,95%CI:1.00-1.22;P=0.032).The heterogeneity test revealed that our IVW analysis exhibited minimal heterogeneity(P>0.05),and the pleiotropy test findings confirmed the absence of pleiotropy within our IVW analysis(P>0.05).Furthermore,a search of the human genotype-phenotype association database failed to identify any potentially relevant risk-factor single nucleotide polymorphisms.CONCLUSION There is a potential causal link between 25-(OH)D levels and the development of cataracts,suggesting that greater 25-(OH)D levels may be a contributing risk factor for cataract formation.Further experimental research is required to confirm these findings.

What-If XAI Framework (WiXAI): From Counterfactuals towards Causal Understanding

People learn causal relations since childhood using counterfactual reasoning. Counterfactual reasoning uses counterfactual examples which take the form of “what if this has happened differently”. Counterfactual examples are also the basis of counterfactual explanation in explainable artificial intelligence (XAI). However, a framework that relies solely on optimization algorithms to find and present counterfactual samples cannot help users gain a deeper understanding of the system. Without a way to verify their understanding, the users can even be misled by such explanations. Such limitations can be overcome through an interactive and iterative framework that allows the users to explore their desired “what-if” scenarios. The purpose of our research is to develop such a framework. In this paper, we present our “what-if” XAI framework (WiXAI), which visualizes the artificial intelligence (AI) classification model from the perspective of the user’s sample and guides their “what-if” exploration. We also formulated how to use the WiXAI framework to generate counterfactuals and understand the feature-feature and feature-output relations in-depth for a local sample. These relations help move the users toward causal understanding.

Analysis of causal relationship between blood metabolites and prostate cancer by two-sample Mendelian randomization

Objective:To investigate the causal relationship between blood metabolite levels and the occurrence of prostate cancer by using two-sample Mendelian randomization method.Methods:Pooled data from public databases for genome-wide association analyses of blood metabolites and prostate cancer were selected,and inverse variance weighting(IVW)was used as the primary method for estimating the causal effects,while heterogeneity tests,gene multiplicity tests and sensitivity analyses were performed to assess the stability and reliability of the results.Results:A total of six known metabolites were found to potentially increase the risk of prostate cancer development(P<0.05),namely fructose,allantoin,5-hydroxytryptophan,potassium ketoisocaproate,glycyltryptophan,and 1-heptadecanoyl-glycerol-3-phosphorylcholine,with no heterogeneity or genetic pleiotropy found.Conclusion:Six known blood metabolites may be potential risk factors for prostate cancer development in European populations.

基于差分Causal LSTM模型的气象图像短时预测研究

为解决气象图像序列在短时预测时预测精度低的问题,利用一种具有级联记忆单元的Causal LSTM,将图像梯度差分惩罚因子引入训练过程,来提高预测模型对短时序列动态和突变的建模能力,提出了差分Causal LSTM模型。研究首先通过循环神经网络建立气象图像短时预测模型,然后分析了ConvLSTM模型对气象雷达回波图与卫星云图序列的预测效果,对于ConvLSTM模型预测气象图像存在严重模糊的问题,使用差分Causal LSTM模型进行优化,结果表明改进的模型能够有效改善模糊,提升预测结果的准确性。改进后的差分Causal LSTM模型在HKO-7数据集的测试样本中,关键成功指数(CSI)提高了0.019,在气象云图数据集中提高了0.078,模糊程度有所减弱。

Shared genetics and bidirectional causal relationships between type 2 diabetes and attention-deficit/hyperactivity disorder

Background Type 2 diabetes(T2D)is a chronic metabolic disorder with high comorbidity with mental disorders.The genetic links between attention-deficit/hyperactivity disorder(ADHD)and T2D have yet to be elucidated.Aims We aim to assess shared genetics and potential associations between ADHD and T2D.Methods We performed genetic correlation,two-sample Mendelian randomisation and polygenic overlap analyses between ADHD and T2D.The genome-wide association study(GWAS)summary results of T2D(80154 cases and 853816 controls),ADHD2019(20183 cases and 35191 controls from the 2019 GWAS ADHD dataset)and ADHD2022(38691 cases and 275986 controls from the 2022 GWAS ADHD dataset)were used for the analyses.The T2D dataset was obtained from the DIAGRAM Consortium.The ADHD datasets were obtained from the Psychiatric Genomics Consortium.We compared genome-wide association signals to reveal shared genetic variation between T2D and ADHD using the larger ADHD2022 dataset.Moreover,molecular pathways were constructed based on large-scale literature data to understand the connection between ADHD and T2D.Results T2D has positive genetic correlations with ADHD2019(rg=0.33)and ADHD2022(rg=0.31).Genetic liability to ADHD2019 was associated with an increased risk for T2D(odds ratio(OR):1.30,p<0.001),while genetic liability to ADHD2022 had a suggestive causal effect on T2D(OR:1.30,p=0.086).Genetic liability to T2D was associated with a higher risk for ADHD2019(OR:1.05,p=0.001)and ADHD2022(OR:1.03,p<0.001).The polygenic overlap analysis showed that most causal variants of T2D are shared with ADHD2022.T2D and ADHD2022 have three overlapping loci.Molecular pathway analysis suggests that ADHD and T2D could promote the risk of each other through inflammatory pathways.Conclusions Our study demonstrates substantial shared genetics and bidirectional causal associations between ADHD and T2D.

Causal associations between inflammatory bowel disease and anxiety:A bidirectional Mendelian randomization study

BACKGROUND Anxiety is common in patients with inflammatory bowel disease(IBD),including those with ulcerative colitis(UC)and Crohn’s disease(CD);however,the causal relationship between IBD and anxiety remains unknown.AIM To investigate the causal relationship between IBD and anxiety by using bidirectional Mendelian randomization analysis.METHODS Single nucleotide polymorphisms retrieved from genome-wide association studies(GWAS)of the European population were identified as genetic instrument variants.GWAS statistics for individuals with UC(6968 patients and 20464 controls;adults)and CD(5956 patients and 14927 controls;adults)were obtained from the International IBD Genetics Consortium.GWAS statistics for individuals with anxiety were obtained from the Psychiatric Genomics Consortium(2565 patients and 14745 controls;adults)and FinnGen project(20992 patients and 197800 controls;adults),respectively.Inverse-variance weighted was applied to assess the causal relationship,and the results were strengthened by heterogeneity,pleiotropy and leave-one-out analyses.RESULTS Genetic susceptibility to UC was associated with an increased risk of anxiety[odds ratio:1.071(95%confidence interval:1.009-1.135),P=0.023],while genetic susceptibility to CD was not associated with anxiety.Genetic susceptibility to anxiety was not associated with UC or CD.No heterogeneity or pleiotropy was observed,and the leave-one-out analysis excluded the potential influence of a particular variant.CONCLUSION This study revealed that genetic susceptibility to UC was significantly associated with anxiety and highlighted the importance of early screening for anxiety in patients with UC.

Evaluating the causal relationship between human blood metabolites and gastroesophageal reflux disease

BACKGROUND Gastroesophageal reflux disease(GERD)affects approximately 13% of the global population.However,the pathogenesis of GERD has not been fully elucidated.The development of metabolomics as a branch of systems biology in recent years has opened up new avenues for the investigation of disease processes.As a powerful statistical tool,Mendelian randomization(MR)is widely used to explore the causal relationship between exposure and outcome.AIM To analyze of the relationship between 486 blood metabolites and GERD.METHODS Two-sample MR analysis was used to assess the causal relationship between blood metabolites and GERD.A genome-wide association study(GWAS)of 486 metabolites was the exposure,and two different GWAS datasets of GERD were used as endpoints for the base analysis and replication and meta-analysis.Bonferroni correction is used to determine causal correlation features(P<1.03×10^(-4)).The results were subjected to sensitivity analysis to assess heterogeneity and pleiotropy.Using the MR Steiger filtration method to detect whether there is a reverse causal relationship between metabolites and GERD.In addition,metabolic pathway analysis was conducted using the online database based MetaboAnalyst 5.0 software.RESULTS In MR analysis,four blood metabolites are negatively correlated with GERD:Levulinate(4-oxovalerate),stearate(18:0),adrenate(22:4n6)and p-acetamidophenylglucuronide.However,we also found a positive correlation between four blood metabolites and GERD:Kynurenine,1-linoleoylglycerophosphoethanolamine,butyrylcarnitine and guanosine.And bonferroni correction showed that butyrylcarnitine(odd ratio 1.10,95% confidence interval:1.05-1.16,P=7.71×10^(-5))was the most reliable causal metabolite.In addition,one significant pathways,the"glycerophospholipid metabolism"pathway,can be involved in the pathogenesis of GERD.CONCLUSION Our study found through the integration of genomics and metabolomics that butyrylcarnitine may be a potential biomarker for GERD,which will help further elucidate the pathogenesis of GERD and better guide its treatment.At the same time,this also contributes to early screening and prevention of GERD.However,the results of this study require further confirmation from both basic and clinical real-world studies.

Causal inference using regression-based statistical control: Confusion in Econometrics

Regression is a widely used econometric tool in research. In observational studies, based on a number of assumptions, regression-based statistical control methods attempt to analyze the causation between treatment and outcome by adding control variables. However, this approach may not produce reliable estimates of causal effects. In addition to the shortcomings of the method, this lack of confidence is mainly related to ambiguous formulations in econometrics, such as the definition of selection bias, selection of core control variables, and method of testing for robustness. Within the framework of the causal models, we clarify the assumption of causal inference using regression-based statistical controls, as described in econometrics, and discuss how to select core control variables to satisfy this assumption and conduct robustness tests for regression estimates.

Local-to-Global Causal Reasoning for Cross-Document Relation Extraction

Cross-document relation extraction(RE),as an extension of information extraction,requires integrating information from multiple documents retrieved from open domains with a large number of irrelevant or confusing noisy texts.Previous studies focus on the attention mechanism to construct the connection between different text features through semantic similarity.However,similarity-based methods cannot distinguish valid information from highly similar retrieved documents well.How to design an effective algorithm to implement aggregated reasoning in confusing information with similar features still remains an open issue.To address this problem,we design a novel local-toglobal causal reasoning(LGCR)network for cross-document RE,which enables efficient distinguishing,filtering and global reasoning on complex information from a causal perspective.Specifically,we propose a local causal estimation algorithm to estimate the causal effect,which is the first trial to use the causal reasoning independent of feature similarity to distinguish between confusing and valid information in cross-document RE.Furthermore,based on the causal effect,we propose a causality guided global reasoning algorithm to filter the confusing information and achieve global reasoning.Experimental results under the closed and the open settings of the large-scale dataset Cod RED demonstrate our LGCR network significantly outperforms the state-ofthe-art methods and validate the effectiveness of causal reasoning in confusing information processing.

Exploring the asymmetric effect of COVID‑19 pandemic news on the cryptocurrency market:evidence from nonlinear autoregressive distributed lag approach and frequency domain causality

This paper explores the asymmetric effect of COVID-19 pandemic news,as measured by the coronavirus indices(Panic,Hype,Fake News,Sentiment,Infodemic,and Media Coverage),on the cryptocurrency market.Using daily data from January 2020 to September 2021 and the exponential generalized autoregressive conditional heter-oskedasticity model,the results revealed that both adverse and optimistic news had the same effect on Bitcoin returns,indicating fear of missing out behavior does not prevail.Furthermore,when the nonlinear autoregressive distributed lag model is esti-mated,both positive and negative shocks in pandemic indices promote Bitcoin’s daily changes;thus,Bitcoin is resistant to the SARS-CoV-2 pandemic crisis and may serve as a hedge during market turmoil.The analysis of frequency domain causality supports a unidirectional causality running from the Coronavirus Fake News Index and Sentiment Index to Bitcoin returns,whereas daily fluctuations in the Bitcoin price Granger affect the Coronavirus Panic Index and the Hype Index.These findings may have significant policy implications for investors and governments because they highlight the impor-tance of news during turbulent times.The empirical results indicate that pandemic news could significantly influence Bitcoin’s price.

Performance of Bayesian Propensity Score Adjustment for Estimating Causal Effects in Small Clinical Trials

Propensity score (PS) adjustment can control confounding effects and reduce bias when estimating treatment effects in non-randomized trials or observational studies. PS methods are becoming increasingly used to estimate causal effects, including when the sample size is small compared to the number of confounders. With numerous confounders, quasi-complete separation can easily occur in logistic regression used for estimating the PS, but this has not been addressed. We focused on a Bayesian PS method to address the limitations of quasi-complete separation faced by small trials. Bayesian methods are useful because they estimate the PS and causal effects simultaneously while considering the uncertainty of the PS by modelling it as a latent variable. In this study, we conducted simulations to evaluate the performance of Bayesian simultaneous PS estimation by considering the specification of prior distributions for model comparison. We propose a method to improve predictive performance with discrete outcomes in small trials. We found that the specification of prior distributions assigned to logistic regression coefficients was more important in the second step than in the first step, even when there was a quasi-complete separation in the first step. Assigning Cauchy (0, 2.5) to coefficients improved the predictive performance for estimating causal effects and improving the balancing properties of the confounder.