Causal Analysis Methods Research Articles

Investigating the causal relationship between immune factors and ankylosing spondylitis: insights from a Mendelian Randomization study

BackgroundDespite previous studies indicating a close relationship between immune system and ankylosing spondylitis (AS), the causal relationship between them remains unclear.MethodsGenome-wide association data were utilized to explore the causal link between 731 immune cells and AS using a bidirectional two-sample MR approach. The data included immune cell data from Orrù et al.’s study and AS data from the FinnGen consortium. Cochran’s Q test and leave-one-out checked instrument variable (IV) heterogeneity. IVW was the primary method for causal analysis, with MR-Egger and MR-PRESSO addressing horizontal pleiotropy. FDR correction was applied to both analysis directions to rectify multiple testing errors.ResultsIn our study, 22 immune phenotypes out of 731 were casually linked to AS. After excluding 5 less robust features, 17 immune factors remained, with 4 being protective and the rest posing risks. Through FDR correction, we found a significant causal relationship between HLA DR on CD14- CD16+ monocyte and AS (OR (95%CI) = 0.70(0.60 ~ 0.83), P = 2.06*10−5). In the reverse analysis with AS as exposure, potential effects on 34 immune features were discovered. After correction, we confirmed significant causal relationships between AS and two immune features, namely CD20- B cell %lymphocyte (OR (95%CI) = 1.16(1.08–1.25), P = 1.91*10−5) and CD20- B cell %B cell (OR (95%CI) = 1.17(1.09–1.26), P = 1.50*10−5).ConclusionsOur study identified various features associated with AS in different types of immune cells. These findings provide important clues and a theoretical basis for further understanding the pathogenesis of AS, guiding clinical treatment, and drug design.

Analyzing the causal role of blood cells in aging: a Mendelian randomization study.

Blood cells are crucial components of the human body, closely linked to the aging process. This study aims to explore the causal relationship between 91 blood cell phenotypes and aging through Mendelian randomization (MR) analysis. Exposure data from genome-wide association studies (GWAS) was extracted from the GWAS of blood cell perturbation phenotypes in 2,600 European individuals. Initial analysis utilized GWAS data related to aging from the GWAS Catalog database GCST90014288, with inverse-variance weighting as the primary method for causal analysis. Sensitivity analyses included Cochran's Q test, MR-Egger intercept test, MR-PRESSO, and leave-one-out analysis. For significant associations, replication and meta-analysis were conducted using independent aging GWAS data from GCST90014300. Initial analysis revealed that environmental peroxide-impacted red blood cells and ciprofloxacin-impacted reticulocytes accelerated aging. Additionally, elevated neutrophil levels were found to accelerate aging, while LiCl-impacted neutrophils reduced aging risk. Replication and meta-analysis showed consistent results: ciprofloxacin-impacted reticulocytes and elevated neutrophil levels increased the risk of aging, while LiCl-impacted neutrophils reduced the risk. RBCs showed no significant impact on aging progression. Sensitivity analyses confirmed the robustness and reliability of these positive findings. Our study provides evidence of a causal relationship between three blood cell disturbance phenotypes and human aging.

Factors influencing COVID-19 vaccination intentions and mediating effects among older adults in Southwest China

This study examines the factors influencing COVID-19 vaccination intentions among Chinese residents over the age of 60, with a focus on the mediating roles of Health Beliefs and Cues to Vaccination Action in the relationship between vaccine knowledge and vaccination intentions. We conducted a cross-sectional online survey involving 1,305 participants from Southwest China. Multiple logistic regression analysis identified potential determinants of vaccination intention, including socioeconomic characteristics, knowledge, health beliefs, and cues to vaccination action. Furthermore, mediation analysis using the causal mediation analysis method explored the mediating effects within the knowledge-to-intention pathway. Vaccination intention and its related factors: among the 1212 elderly people included in the study, 92.9% expressed willingness to receive the COVID-19 vaccine. Main factors influencing their vaccination willingness included Residency (urban vs. rural, OR = 0.47, p < 0.01), Age (75 + vs. others, OR = 0.41, p < 0.05), Marital status (OR = 0.36, p < 0.01), Occupation ( business/service vs. others, OR = 0.33, p < 0.05), Awareness of vaccine effectiveness (OR = 1.23, p < 0.01), Cues to vaccination action (OR = 1.31, p < 0.01) and COVID-19 related knowledge (OR = 1.06, p < 0.01). The analysis revealed two significant mediators—Health Beliefs and Cues to Vaccination Action. These mediators (p<0.05 for both natural indirect effect and natural direct effect) acted along two key pathways: (1) From Knowledge of COVID-19 to Health Beliefs to Vaccination Intention: Natural Direct Effects (NDE) ranged from 0.012 to 0.016, with Natural Indirect Effects (NIE) from 0.001 to 0.003, indicating that mediators accounted for 4% to 18% of the total effect. (2) From Knowledge of COVID-19 to Cues of Vaccination Action to Vaccination Intention: NDE ranged from 0.012 to 0.016 and NIE from 0.002 to 0.003, with mediators accounting for 9% to 20% of the effect. The intention to vaccinate against COVID-19 among older adults varies significantly based on socioeconomic and health belief factors. The study identifies health beliefs and cues to action not only as direct contributors but also as crucial mediators in the pathway from knowledge to vaccination intention among older individuals. These findings can extend our understanding of the impact of sociodemographic factors and health beliefs on the COVID-19 vaccination willingness among older adults.

Цифровизация закупочного процесса как элемент управления медицинской организации

In modern conditions, digital technologies are penetrating into all spheres of life, and the healthcare industry is no exception. It is not individual medical services that compete in the market, but financial models. Therefore, those medical institutions that are able to quickly search, test and implement appropriate changes win. Digitalization tools and approaches help you learn to speak the language of value that is created for different target audiences, and regularly update the financial model of a medical institution. A significant stage in the activities of a public health institution is the procurement process. The purpose of the study is to identify the main aspects of building the procurement process of a public health institution through the prism of digitalization of this process within a medical institution. Materials and methods. The study includes the identification of factors that must be taken into account when forming a model of the procurement process; the stages of creating a digital model of the procurement process; the principles of implementing the procurement process project; substantiation of design decisions on information and software for the procurement process of a public health institution; the stages of developing an information system. Methods of structural, functional, information process, causal analysis and modeling are used. Results. The paper identified the main problems associated with the procurement process in medical institutions, including shortcomings in the regulatory framework, the lack of a clear distribution of responsibility between the participants in the process and the inefficiency of management decisions. To improve procurement monitoring and management, a proposal has been developed to optimize the procurement process through the use of digital technologies. Conclusions. The conducted research made it possible to identify the optimization of the procurement process in public medical institutions, which is associated with the use of a digital model of the procurement process. The scope of the results. The results of the work can be used in public medical institutions of various levels to develop and implement a system of digitalization of procurement activities within a medical organization. And also, when optimizing the procurement process in public medical institutions, when using a digital financial model of the procurement process, which has a number of beneficial advantages.

Variable‐weight combined forecasting model with causal analysis and clustering for refined oil sales forecasting

AbstractForecasting refined oil sales is essential in energy supply chain management. However, accurate forecasting is limited by several factors, including multiple influences of external features, heterogeneity of different gasoline stations, and difficulty in balancing linear and nonlinear forecasting. To address these issues, we propose a novel variable‐weight combined forecasting model. In the first stage, the model incorporates causal analysis and clustering methods to provide a quantitative description of multiple effects of external features and highly correlated aggregation of homogeneous data. Subsequently, based on the patterns of external feature influences learned from historical data, variable‐weight combined forecasting is realized to balance linear and nonlinear forecasting dynamically. Experiments based on real sales data procured from several regions demonstrate that the proposed model outperforms other benchmark and widely used models in terms of forecasting accuracy and statistical significance. The ablation experimental results confirm the significance of causal analysis, clustering, and variable‐weight combined forecasting in improving the balance between linear and nonlinear forecasting. Moreover, our results indicate that improving the quality of clustering can yield greater benefits than improving the amount of training data. Finally, we also explore whether the forecasting superiority translates into better inventory control, and our results show that the proposed optimization model can effectively balance inventory cost and service level, while also better suppress the bullwhip effect.

The effect of IT governance on business resilience with intellectual capital as mediating variable

Micro, Small, and Medium Enterprises (MSMEs) must continue to adapt in today's rapidly changing digital business climate to become resilient organizations and maintain their competitive advantage. This study examines the relationship between IT governance (ITG), intellectual capital (IC), and business resilience (BR). Data were collected from 100 MSMEs in Banyumas, Central Java. Specifically, the researcher investigated how IC mediates the effect of ITG on business resilience. The study used a causal step analysis method. The results showed that ITG has a positive effect on business resilience. ITG can improve IC and strengthen business resilience. This mediation suggests that building intellectual capital can increase the benefits of IT and make companies stronger. This knowledge is valuable for MSME managers and policy makers to improve organizational resilience through ITG strategies and IC development.

Modified local Granger causality analysis based on Peter‐Clark algorithm for multivariate time series prediction on IoT data

AbstractClimate data collected through Internet of Things (IoT) devices often contain high‐dimensional, nonlinear, and auto‐correlated characteristics, and general causality analysis methods obtain quantitative causality analysis results between variables based on conditional independence tests or Granger causality, and so forth. However, it is difficult to capture dynamic properties between variables of temporal distribution, which can obtain information that cannot be obtained by the mean detection method. Therefore, this paper proposed a new causality analysis method based on Peter‐Clark (PC) algorithm and modified local Granger causality (MLGC) analysis method, called PC‐MLGC, to reveal the causal relationships between variables and explore the dynamic properties on temporal distribution. First, the PC algorithm is applied to compute the relevant variables of each variable. Then, the results obtained in the previous stage are fed into the modified local Granger causality analysis model to explore causalities between variables. Finally, combined with the quantitative causality analysis results, the dynamic characteristic curves between variables can be obtained, and the accuracy of the causal relationship between variables can be further verified. The effectiveness of the proposed method is further demonstrated by comparing it with standard Granger causality analysis and a two‐stage causal network learning method on one benchmark dataset and two real‐world datasets.

Deep‐Learning Based Causal Inference: A Feasibility Study Based on Three Years of Tectonic‐Climate Data From Moxa Geodynamic Observatory

AbstractHighly sensitive laser strainmeters at Moxa Geodynamic Observatory (MGO) measure motions of the upper Earth's crust. Since the mountain overburden of the laser strainmeters installed in the gallery of the observatory is relatively low, the recorded time series are strongly influenced by local meteorological phenomena. To estimate the nonlinear effect of the meteorological variables on strain measurements in a non‐stationary environment, advanced methods capable of learning the nonlinearity and discovering causal relationships in the non‐stationary multivariate tectonic‐climate time series are needed. Methods for causal inference generally perform well in identifying linear causal relationships but often struggle to retrieve complex nonlinear causal structures prevalent in real‐world systems. This work presents a novel model invariance‐based causal discovery (CDMI) method that utilizes deep networks to model nonlinearity in a multivariate time series system. We propose to use the theoretically well‐established Knockoffs framework to generate in‐distribution, uncorrelated copies of the original data as interventional variables and test the model invariance for causal discovery. To deal with the non‐stationary behavior of the tectonic‐climate time series recorded at the MGO, we propose a regime identification approach that we apply before causal analysis to generate segments of time series that possess locally consistent statistical properties. First, we evaluate our method on synthetically generated time series by comparing it to other causal analysis methods. We then investigate the hypothesized effect of meteorological variables on strain measurements. Our approach outperforms other causality methods and provides meaningful insights into tectonic‐climate causal interactions.

Causal effects of neuroticism on postpartum depression: a bidirectional mendelian randomization study.

Postpartum depression (PPD) brings adverse and serious consequences to both new parents and newborns. Neuroticism affects PPD, which remains controversial for confounding factors and reverse causality in cross-sectional research. Therefore, mendelian randomization (MR) study has been adopted to investigate their causal relationship. This study utilized large-scale genome-wide association study genetic pooled data from three major databases: the United Kingdom Biobank, the European Bioinformatics Institute, and the FinnGen databases. The causal analysis methods used inverse variance weighting (IVW). The weighted median, MR-Egger method, MR-PRESSO test, and the leave-one-out sensitivity test have been used to examine the results' robustness, heterogeneity, and horizontal pleiotropy. The fixed effect model yielded the results of meta-analysis. In the IVW model, a meta-analysis of the MR study showed that neuroticism increased the risk of PPD (OR, 1.17; 95% CI, 1.11-1.25, p < 0.01). Reverse analysis showed that PPD could not genetically predict neuroticism. There was no significant heterogeneity or horizontal pleiotropy bias in this result. Our study suggests neuroticism is the risk factor for PPD from a gene perspective and PPD is not the risk factor for neuroticism. This finding may provide new insights into prevention and intervention strategies for PPD according to early detection of neuroticism.

The asymmetric correlation and causality between the European Union carbon market and fossil energy markets caused by COVID-19

The carbon and fossil energy markets have been significantly affected by the COVID-19 pandemic. This article examines the nonlinear correlation and the spillover effect between the global fossil energy markets and the European Union carbon market prior to and following COVID-19. The nonlinear correlation is captured by the localized Gaussian correlation approach, and the spillover effect is evaluated using a quantile-based Granger causality analysis method. Empirical evidence demonstrates that COVID-19 strengthens the correlation between the carbon and oil markets. Conversely, the correlation between the carbon and coal markets is weakened by COVID-19. Furthermore, COVID-19 only resulted in the contagion between the carbon and Texas gas markets. Finally, the spillover effect between the European Union carbon market and fossil energy markets changes from unidirectional to bidirectional. This article provides inspiration for investors to adjust their portfolios to reduce investment risks and meaningful information for policymakers to maintain market stability.

ANALYSIS OF TOURIST ATTRACTION ON TOURIST VISITING INTEREST IN PERLANG TOURISM VILLAGE CENTRAL BANGKA

This research is motivated by the growing development of Indonesian tourism, one of which is a tourist village. Tourism villages are cultural diversity to tourist destinations owned by each region. The existence of interesting things contained in the tourist village makes tourists interested in visiting Perlang Tourism Village. In this study, it was found that Perlang Tourism Village was included in the top 50 best tourism villages nominated by ADWI and third place in the digital and creative categories. Therefore, the purpose of this study is to provide input to managers on what attractiveness can be developed to become an advantage for Perlang Tourism Village. This research is entitled "Analysis of Tourism Attractiveness of Tourist Visiting Interest in Perlang Village, Central Bangka". This study used a causal analysis method with a quantitative approach. Data collection techniques through observation, interviews, and questionnaires, with 100 research samples selected using non-probability methods and purposive sampling techniques. Data analysis was performed using simple linear regression test, descriptive (mean) test, t test, F test, and R2 analysis. The results of the t test showed that partially the Attraction &amp; Ancillary dimension had a significant influence on visiting interest, while the Amenities &amp;; Accessibility dimension did not have a significant influence. Test F shows that simultaneously, all four dimensions of tourist attraction affect visiting interest. In conclusion, attractiveness has a positive and significant influence on partial interest in visiting. Therefore, this destination must maintain the attractiveness it already has.

ANALYSIS OF TOURIST ATTRACTION ON TOURIST INTEREST IN VISITING KERANGGAN TOURISM VILLAGE SOUTH TANGGERANG

This research is motivated by the development of tourist destinations today so as to increase competitiveness between tourist destinations. Tourism Attraction is the most important factor and the main driver in tourism activities, because tourist attraction is a determining factor to make tourists have an interest in visiting a tourist destination. This study intends to see the influence of tourist attraction on interest in visiting Keranggan Tourism Village. This study used a causal analysis method with a quantitative approach. Data collection techniques by observation, interviews and questionnaires. The sample in this study was tourists who had visited 100 people based on the non-probability method with purposive sampling techniques. The analytical techniques used in this study are validity tests, reliability tests, classical assumption tests, simple linear regression, description (average) t tests, and R2 analysis. The results of this study explain that: 1). Tourism Attraction 4A has a significant effect on Interest in Visiting Keranggan Tourism Village Destinations.

Mendelian randomization study reveals causal effects of specific gut microbiota on the risk of interstitial cystitis/bladder pain syndrome (IC/BPS)

Evidence from previous studies have demonstrated that gut microbiota are closely associated with occurrence of interstitial cystitis/bladder pain syndrome (IC/BPS), yet the causal link between the two is not well known. In this study, we performed a two-sample Mendelian randomization (MR) analysis to determine the possible causal association between gut microbiota with IC/BPS. Gut microbiota summary level data were derived from the genome-wide association study (GWAS) conducted by MiBioGen and the IC/BPS GWAS summary level data were obtained from the GWAS Catalog. Next, we performed an MR study to investigate the causal link between gut microbiota and IC/BPS. The primary method for causal analysis was the inverse variance weighted (IVW), and the MR results were validated through multiple sensitivity analyses. A positive association was found between IC/BPS and eight gut microbial taxa, including genus Bacteroides, genus Haemophilus, genus Veillonella, genus Coprococcus1, genus Butyricimonas, family Bacteroidaceae, family Christensenellaceae, and order Lactobacillales. Sensitivity analysis revealed lack of significant pleiotropy or heterogeneity in the obtained results. This MR analysis reveals that a causal association exists between some gut microbiota with IC/BPS. This finding may is expected to guide future research and development of IC/BPS preventions and treatments based on the bladder-gut axis. However, given the clinical complexity and diagnostic challenges of IC/BPS, along with the limitations of using large-scale GWAS summary data for analysis, our MR results require further validation through additional research.

Path-specific causal decomposition analysis with multiple correlated mediator variables.

A causal decomposition analysis allows researchers to determine whether the difference in a health outcome between two groups can be attributed to a difference in each group's distribution of one or more modifiable mediator variables. With this knowledge, researchers and policymakers can focus on designing interventions that target these mediator variables. Existing methods for causal decomposition analysis either focus on one mediator variable or assume that each mediator variable is conditionally independent given the group label and the mediator-outcome confounders. In this article, we propose a flexible causal decomposition analysis method that can accommodate multiple correlated and interacting mediator variables, which are frequently seen in studies of health behaviors and studies of environmental pollutants. We extend a Monte Carlo-based causal decomposition analysis method to this setting by using a multivariate mediator model that can accommodate any combination of binary and continuous mediator variables. Furthermore, we state the causal assumptions needed to identify both joint and path-specific decomposition effects through each mediator variable. To illustrate the reduction in bias and confidence interval width of the decomposition effects under our proposed method, we perform a simulation study. We also apply our approach to examine whether differences in smoking status and dietary inflammation score explain any of the Black-White differences in incident diabetes using data from a national cohort study.

Causal inference with hidden mediators

Summary Proximal causal inference was recently proposed as a framework to identify causal effects from observational data in the presence of hidden confounders for which proxies are available. In this paper, we extend the proximal causal inference approach to settings where identification of causal effects hinges upon a set of mediators that are not observed, yet error prone proxies of the hidden mediators are measured. Specifically, (i) we establish causal hidden mediation analysis, which extends classical causal mediation analysis methods for identifying natural direct and indirect effects under no unmeasured confounding to a setting where the mediator of interest is hidden, but proxies of it are available; (ii) we establish a hidden front-door criterion, criterion to allow for hidden mediators for which proxies are available; (iii) we show that the identification of a certain causal effect called the population intervention indirect effect remains possible with hidden mediators in settings where challenges in (i) and (ii) might co-exist. We view (i)–(iii) as important steps towards the practical application of front-door criteria and mediation analysis as mediators are almost always measured with error and, thus, the most one can hope for in practice is that the measurements are at best proxies of mediating mechanisms. We propose identification approaches for the parameters of interest in our considered models. For the estimation aspect, we propose an influence function-based estimation method and provide an analysis for the robustness of the estimators.

A new transfer entropy method for measuring directed connectivity from complex-valued fMRI data.

Inferring directional connectivity of brain regions from functional magnetic resonance imaging (fMRI) data has been shown to provide additional insights into predicting mental disorders such as schizophrenia. However, existing research has focused on the magnitude data from complex-valued fMRI data without considering the informative phase data, thus ignoring potentially important information. We propose a new complex-valued transfer entropy (CTE) method to measure causal links among brain regions in complex-valued fMRI data. We use the transfer entropy to model a general non-linear magnitude-magnitude and phase-phase directed connectivity and utilize partial transfer entropy to measure the complementary phase and magnitude effects on magnitude-phase and phase-magnitude causality. We also define the significance of the causality based on a statistical test and the shuffling strategy of the two complex-valued signals. Simulated results verified higher accuracy of CTE than four causal analysis methods, including a simplified complex-valued approach and three real-valued approaches. Using experimental fMRI data from schizophrenia and controls, CTE yields results consistent with previous findings but with more significant group differences. The proposed method detects new directed connectivity related to the right frontal parietal regions and achieves 10.2-20.9% higher SVM classification accuracy when inferring directed connectivity using anatomical automatic labeling (AAL) regions as features. The proposed CTE provides a new general method for fully detecting highly predictive directed connectivity from complex-valued fMRI data, with magnitude-only fMRI data as a specific case.

THE EFFECT OF ELECTRONIC WORD OF MOUTH AND PRICE ON PURCHASING DECISIONS WITH TRUST AS AN INTERVENING VARIABLE IN SHOPEE E-COMMERCE

This study aims to analyze the factors that influence purchasing decisions for Scarlett Whitening products in Shopee e-commerce, where the factors for making product purchasing decisions are Electronic Word Of Mouth, Price, and Trust.The data type is primary data, obtained from distributing questionnaires to consumers who have purchased Scarlett Whitening products in Shopee e-commerce, using non-probability purposive sampling so that the total sample is 155 respondents. This study uses the Causal Associative Analysis method with a qualitative approach and data analysis techniques using the Structural Equation Modeling (SEM) AMOS version 26.0 program.The results showed that electronic word of mouth has a significant effect on trust, price has a significant effect on trust, trust has no significant effect on purchasing decisions, electronic word of mouth has a significant effect on purchasing decisions, and price has a significant effect on purchasing decisions.

The relationship between the Istanbul Stock Market and Türkiye’s foreign trade

International trade is a significant indicator determining all countries' competitiveness and welfare levels, whether developed or developing. Stock markets are indicators of capital markets and economies. In this context, it may be significant to determine the relationship levels of international trade and the stock market. Purpose of the study: To examine the relationship and level between international trade potential in Türkiye and the BIST 100 Index (XU100) in the period 2013:01-2023:12. For this purpose, the reflection of Türkiye's exports and imports on BIST 100 was evaluated using Johansen Cointegral and Granger Causality Analysis methods. According to the findings, it has been determined that exports and imports are related to BIST 100 performance in the short and long term and cause BIST 100 performance. Exports positively affect BIST 100 performance in the short and long term, while imports negatively affect BIST 100 performance in the short and long term.

A Bayesian high-dimensional mediation analysis for multilevel genome-wide epigenetic data

Causal mediation analysis has increasingly become a popular practice in various clinical trials and epidemiological applications to evaluate whether an intermediate variable is on the pathway between the exposure of interest and a response. Previous mediation analyses in the literature mainly focused on settings with a single or low-dimensional mediators and single-level data. In this article, we propose a Bayesian causal mediation analysis method that can handle our multilevel intergenerational epigenetic mechanisms study (IEMS) with high-dimensional mediators. Specifically, we develop a Bayesian hierarchical model for data with such complexity, and then employ the Bayesian spike-and-slab priors on the exposure-mediator-outcome effect pathway to identify active mediators involved in mediation. We derive the natural indirect and direct effects based on our hierarchical model and provide statistical inference based on Markov chain Monte Carlo (MCMC) methods. Our simulation study demonstrates that our proposed Bayesian method outperforms other alternative methods in various scenarios. We further illustrate the utility of our method to IEMS to assess the causal mechanisms between maternal exposure to climate extremes and offspring's growth outcomes through DNA methylation.

Causal Mediation Analysis with the Parallel Process Latent Growth Curve Mediation Model

In parallel process latent growth curve mediation models, the mediation pathways from treatment to the intercept or slope of outcome through the intercept or slope of mediator are often of interest. In this study, we developed causal mediation analysis methods for these mediation pathways. Particularly, we provided causal definitions and identification results for the interventional indirect effects via the mediator intercept (or slope) alone and due to their mutual dependence. For estimation, we proposed an interaction model that incorporates interactions among the mediator intercept/slope and treatment, coupled with a Bayesian method. We evaluated the studied methods through simulations, and illustrated their applications using an empirical example.