Causal Inference Research Articles

Key Factors Influencing Sustainable Population Growth: A DEMATEL-ANP Combined Approach

This study highlights the importance of sustainable social demographic growth. It uses a model that combines the Decision-making Trial and Evaluation Laboratory (DEMATEL) with the Analytic Network Process (ANP) to examine key factors affecting this growth and their interactions. The analysis focuses on six critical factors: economic development, education and gender equality, health services, environmental sustainability, immigration policies, and technological advancement. Experiments using government and international organization databases include comparative experiments with deep learning prediction models, ensemble learning models, Causal Inference Models, complex network analysis models, and agent-based models. Comparison metrics cover accuracy, precision, recall, and F1 score. The results indicate that, with a data volume of 4000, the optimized model achieves an accuracy of 0.973, precision of 0.981, recall of 0.969, and an F1 score of 0.89, demonstrating the model's superior performance. The DEMATEL method analyzes the direct relationships among the factors. The results show that economic development and technological advancement have impact scores of 3.91 and 3.43, respectively, indicating their strong influence on other factors and their role in promoting sustainable demographic growth. Education and gender equality, health services, and technological advancement each have impact scores of 3.39, meaning they are significantly affected by other factors and are sensitive in the growth process. Finally, the ANP method is used to calculate the weights of each factor, determining their relative importance in sustainable social demographic growth. The results highlight that economic development level and technological advancement and innovation are core factors influencing sustainable social demographic growth, with significant direct and indirect impacts on other factors and a crucial role in the overall system. These findings provide a scientific basis for formulating relevant policies and interventions, particularly in prioritizing and strengthening economic and technological development strategies. This study offers valuable insights for research in demography, sustainable development, and social policy formulation.

Impact of a pilot advanced provider-based comprehensive management program to support patients with immunotoxicity-related adverse events in a cancer care setting.

31 Background: Immune checkpoint inhibitors (ICIs) have revolutionized the treatment of many types of cancers. Despite the clinical benefits of the targeted therapy, its use is associated with a spectrum of autoimmune side effects known as immune-related adverse events (irAEs). Toxicities are distinct from those associated with standard chemotherapy, and, if unrecognized and not managed aggressively, can become life-threatening. Early recognition and management of these toxicities, as well as approaches toward cautious retreatment following resolution is essential in clinical practice. Methods: As part of larger effort to provide efficient and proactive care to patients, advanced provider-based comprehensive management program was established in an academic hospital ambulatory setting to identify and manage the full spectrum of unique toxicities of patients receiving standard-of-care ICIs. The goal of the program was to manage patients with severe toxicity including seamless transitions of care between outpatient and inpatient settings to obviate the need for future acute care utilizations. The program provided real-time guidance to providers with clinical questions on use of ICIs, actively navigated patients with suspected immunotherapy toxicity and assessed ongoing education needs for both outpatient and inpatient services. A retrospective analysis of 2-year post implementation of the program was performed with inpatient to outpatient referrals as primary outcome and median length of stay and 30-day readmission rate as secondary outcomes. Results: A total of 388 inpatient admissions (222 Year-1 and 166 Year-2) were included. Preliminary analysis revealed a 25% decrease in immunotoxicity related inpatient admissions (admission rate decreased from 2.8 to 1.9) while patients treated with immunotherapy increased by 7%. The number of ambulatory encounters with the navigator increased by 40% (362 vs 509). The median length of stay for those on the dedicated program decreased by 27.3% (5.5 vs. 4 days) and the 30-day readmission rate decreased by 15.8% (24.3 vs. 20.5) from Year 1 to Year 2. Conclusions: Preliminary analysis suggests the program improved patient care, provided timelier follow-up and management, and reduced the delay to return to anti-cancer treatment. The ambulatory program provided proactive intervention, diagnosis, and management of immunotherapy related toxicities, preventing hospitalization and readmission to the hospital. Although initial findings suggest improved preliminary outcomes, further analysis is required to make any causal inference on the true and sustainable impact of the intervention.

The intention-to-treat effect of changes in planned participation on injury risk in adolescent ice hockey players: A target trial emulation

ObjectivesTarget trial emulation is a framework for conducting causal inference using observational data. We employ this framework to estimate the effect of changing planned participation duration, measured using the acute:chronic workload ratio (ACWR), on injury risk among adolescent ice hockey players without recent injuries. DesignProspective cohort study designed to emulate a hypothetical randomized trial. MethodsWe used data from a 5-year cohort study (2013–2018) of ice hockey players aged 13–17 years in Alberta and British Columbia. We estimated injury risks associated with different planned changes in hockey participation duration (e.g. half [ACWR = 0.5], no change [ACWR = 1], two-fold [ACWR = 2], three-fold [ACWR = 3], and five-fold [ACWR = 5]) relative to participation in the previous 4 weeks. Outcomes were modeled using generalized additive models. We conducted secondary analyses restricted to concussions, and stratified by league bodychecking status. ResultsThere were 2633 eligible participants, contributing 115,821 player-trials. Injury risk was 1.9 % (95 % CI: 1.7 %–2.3 %) for no change in participation (ACWR = 1). Injury risk ratios (RRs) were 0.43 at ACWR = 0.5 (95 % CI: 0.31–0.54), 1.62 (95 % CI: 1.33–1.98) at ACWR = 2, 1.91 at ACWR = 3 (95 % CI: 1.52–2.48) and 2.35 at ACWR = 5 (95 % CI: 1.68–3.26). Patterns were similar by league bodychecking status. Concussion RRs were stable between ACWR = 1 and 1.5, but RRs were greater than for any injury past ACWR = 2. ConclusionsWithin the assumptions of this target trial emulation, injury risk increases consistently (no sweet spots) for increases in planned changes in participation duration relative to the previous 4 weeks among adolescent ice hockey players without recent injuries. Injuries in injury risk are less than expected for the increased exposure time at risk, suggesting beneficial effects of increasing participation that partially counteract the increased exposure time.

The role of single case experimental designs in evidence creation in rehabilitation.

Randomized controlled trials (RCTs) are considered the gold standard of evidence guiding intervention selection in rehabilitation. However, conduct of sufficiently powered RCTs in rehabilitation can be expensive, pose ethical and attrition concerns when participants are assigned to ineffective treatment as usual conditions, and are infeasible with low-incidence populations. Single-case experimental designs (SCEDs), including N-of-1 RCTs are causal inference studies for small numbers of participants and not necessarily one participant as the name implies. These designs are increasingly used to evaluate the effectiveness of rehabilitation interventions in diverse clinical settings and employ design features including but not limited to randomization and each participant serving as their own control. These and other internal validity enhancements can increase the confidence in study results coming from these designs. This manuscript discusses the expanded application of SCEDs in rehabilitation contexts to answer everyday clinical rehabilitation research questions with emphasis on strategies to use: 1) to maximize internal validity of this family of designs; 2) improve utility, effectiveness, and acceptability of these designs for rehabilitation end-users (clinicians, policymakers, and participants); 3) build evidence bases in areas of rehabilitation where RCTs are uncommonly used. Primary considerations for situating SCEDs within the continuum of experimental designs include increasing internal validity within designs, improving transparency in conduct and reporting of these studies, and increasing access to advanced research methods training for rehabilitation professionals.

Association of watching sports games with subsequent health and well-being among adults in Japan: An outcome-wide longitudinal approach

ObjectiveAlthough the health benefits of playing sports are well-known, the association between watching sports and health is not well understood. We examined the longitudinal association of watching sports with 20 different health and well-being outcomes. MethodsThree-wave cohort data from 6327 adults (4851 workers) in the Meiji Yasuda LifeStyle study were used to draw causal inferences. We assessed the frequency of watching sports games on media or in-person using a self-reported questionnaire in 2018. Outcomes, including health behaviors, physical, mental, and work-related outcomes, were evaluated in 2019. In 2017, sociodemographic factors, prior exposure, and outcome values were evaluated and used as covariates. Three different statistical models (logistic, modified Poisson, or linear regression) were used according to the nature of the outcome variable. ResultsWatching sports on media had a favorable dose-response association with a lower risk of becoming physically inactive and skipping breakfast, as well as higher happiness (p for trend < 0.05). Conversely, watching sports on media had an adverse dose-response association with higher body mass index and increased risks of developing hypertension and diabetes (p for trend < 0.05). Watching sports in-person had a dose-response association with lower risks of exhibiting the precontemplation stage of health behavior change, moderate/severe psychological distress, and dyslipidemia (p for trend < 0.05). ConclusionsDespite the observed detrimental association between watching sports and cardiometabolic health, which should be interpreted cautiously and studied further, the study findings suggest that watching sports could be a new modifiable protective factor for developing healthy lifestyles and improving mental well-being.

Methods in Causal Inference Part 2: Interaction, Mediation, and Time-Varying Treatments

Abstract The analysis of ‘moderation’, ‘interaction’, ‘mediation’, and ‘longitudinal growth’ is widespread in the human sciences, yet subject to confusion. To clarify these concepts, it is essential to state causal estimands, which requires specifying counterfactual contrasts for a target population on an appropriate scale. Once causal estimands are defined, we must consider their identification. I employ causal directed acyclic graphs (causal DAGs) and Single World Intervention Graphs to elucidate identification workflows. I show that when multiple treatments exist, common methods for statistical inference, such as multi-level regressions and statistical structural equation models, cannot typically recover the causal quantities we seek. By properly framing and addressing causal questions of interaction, mediation, and time-varying treatments, we can expose the limitations of popular methods and guide researchers to a clearer understanding of the phenomena that animate our interests.

Exploring Therapeutic Effects of Continuous Kidney Replacement Therapy in Patients with Severe Acidosis Using Deep Learning-Based Causal Inference

Exploring Therapeutic Effects of Continuous Kidney Replacement Therapy in Patients with Severe Acidosis Using Deep Learning-Based Causal Inference

Contract Contingencies and Uncertainty: Evidence from Product Market Contracts

We study contingencies written in firms’ material product market contracts, focusing on the theoretical prediction of uncertainty as an important determinant. We identify contract contingencies from firms’ public regulatory filings and examine the effects of general business uncertainty and specific innovation-related uncertainty. To enhance causal inference, we utilize two major business shocks (i.e., the 2008 Financial Crisis and the COVID pandemic) and the diffusion of 29 disruptive innovation shocks (Bloom et al. 2021). We also explore the effects of re-negotiation costs and writing costs. Overall, our empirical results are consistent with predictions from dynamic models of incomplete contracting.

Association between parental phubbing and short-form video addiction: A moderated mediation analysis among Chinese adolescents

BackgroundShort-form video applications have spread rapidly and gained popularity among adolescents for their interactivity, sociality, and personalization. However, excessive and uncontrolled use has also caused some adolescents to develop short-form video addiction (SFVA). Although parental phubbing has been shown to be a risk factor for SFVA in adolescents, its intermediate mechanisms, particularly the emotional mediation mechanisms, remain unclear. Therefore, this study aims to explore the relationships among parental phubbing, SFVA, symptoms of depression and anxiety, and neuroticism in adolescents. MethodsAdolescents aged 13–19 (N = 5785) were recruited from Shandong Province, China, as participants in 2023. Participants were asked to complete five self-report questionnaires, including the Parental Phubbing Behavior Questionnaire (PPBQ), Short-Form Video Addiction (SFVA) Scale, The Center for Epidemiological Studies Depression Scale (CESD20), Generalized Anxiety Disorder 7-item (GAD-7) Scale, and Chinese Big Five Personality Inventory (Brief Version) (CBF-PI-B). ResultsThe results indicate that the influence of parental phubbing on short-form video addiction among adolescents is mediated by symptoms of depression and anxiety. Additionally, neuroticism moderates the association between parental phubbing and symptoms of depression and anxiety. LimitationsCross-sectional design limits causal inferences. Reliance on self-report scales. ConclusionsThese findings contribute to a better understanding of the systemic impact mechanisms of negative family interactions on SFVA. Moreover, prevention and intervention strategies targeting high neuroticism and symptoms of depression and anxiety may help prevent the developmental pathway from parental phubbing to SFVA.

Transdiagnostic white matter controllability deficits across patients with affective and anxiety spectrum disorders

BackgroundAffective and anxiety disorders including major depression disorder (MDD), post-traumatic stress disorder (PTSD), and social anxiety disorder (SAD) are characterized by network dysconnectivity. Network controllability quantifies the capability of specific brain regions to impact functional dynamics based on the underlying structural connectome. This study aimed to investigate transdiagnostic and illness-specific network controllability alterations across these three disorders. Materials and methodsThe study enrolled 233 currently untreated and non-comorbid subjects, including 68 MDD patients, 51 PTSD patients, 46 SAD patients, and 68 healthy controls (HCs). White matter network controllability was compared among the four groups, and its associations with symptom severity and duration of untreated illness were evaluated. ResultsCompared with HCs, patients with PTSD, MDD and SAD exhibited reduced average controllability in the somatomotor, subcortical, and default mode network, notably in brain regions such as the superior frontal gyrus, postcentral gyrus, paracentral gyrus, pallidum, posterior cingulate, and putamen. MDD and SAD patients exhibited reduced average controllability in the left lateral occipital gyrus and bilateral accumbens. SAD patients showed reduced average controllability in the dorsal attention network. These controllability changes did not correlate with illness duration or symptom severity. LimitationsThe cross-sectional design limits causal inference, and adjusting for age and sex differences may not completely eliminate their influence on the results. ConclusionThe present study revealed shared and specific alterations of network controllability in MDD, PTSD, and SAD, suggesting reduced ability of specific brain regions/networks in driving the brain system into different functional states across these disorders.

An optimized instrument variable selection approach to improve causality estimation in association studies

Mendelian randomization (MR) is an emerging tool for inferring causality in genetic epidemiology. MR studies suffer bias from weak genetic instrument variables (IVs) and horizontal pleiotropy. We introduce a robust integrative framework strictly adhering with STROBE-MR guidelines to improve causality inference through MR studies. We implemented novel t-statistics-based criteria to improve the reliability of selected IVs followed by various MR methods. Further, we include sensitivity analyses to remove horizontal-pleiotropy bias. For functional validation, we perform enrichment analysis of identified causal SNPs. We demonstrate effectiveness of our proposed approach on 5 different MR datasets selected from diverse populations. Our pipeline outperforms its counterpart MR analyses using default parameters on these datasets. Notably, we found a significant association between total cholesterol and coronary artery disease (P = 1.16 × 10−71) in a single-sample dataset using our pipeline. Contrarily, this same association was deemed ambiguous while using default parameters. Moreover, in a two-sample dataset, we uncover 13 new causal SNPs with enhanced statistical significance (P = 1.06 × 10−11) for liver-iron-content and liver-cell-carcinoma. Likewise, these SNPs remained undetected using the default parameters (P = 7.58 × 10−4). Furthermore, our analysis confirmed previously known pathways, such as hyperlipidemia in heart diseases and gene ME1 in liver cancer. In conclusion, we propose a robust and powerful framework to infer causality across diverse populations and easily adaptable to different diseases.

Causal inference using genome-wide association study results of Hanwoo carcass traits: Mendelian randomization analysis

Causal inference using genome-wide association study results of Hanwoo carcass traits: Mendelian randomization analysis

Statistical challenges and solutions in multidisciplinary clinical research: Bridging the gap between

This paper delves into the intricate challenges and innovative solutions in applying statistical methodologies within clinical research, aiming to bridge the gap between biostatistics and medicine. The study meticulously examines fundamental biostatistical concepts, addressing the complexities of modern clinical trials and observational studies. Through a comprehensive review of advanced regression models, causal inference techniques, and machine learning algorithms, the paper illuminates the evolving landscape of biostatistics in handling high-dimensional data and confounding variables. The methods employed in this study involve an extensive analysis of current literature, case studies, and practical applications that demonstrate the utility of these advanced methodologies. Key findings reveal that traditional statistical approaches often fall short in capturing the complexities of clinical data, necessitating the adoption of more sophisticated techniques. The integration of non-linear regression models, robust causal inference methods, and machine learning has significantly enhanced the accuracy and reliability of research outcomes, offering deeper insights into patient outcomes and treatment efficacy. Conclusions drawn from this study underscore the critical need for a paradigm shift in clinical research, moving beyond the rigid reliance on p-values towards a more holistic approach that emphasizes effect sizes, confidence intervals, and practical significance. The paper recommends continued innovation in statistical methodologies, particularly the integration of big data analytics and machine learning, to address the growing complexities of biomedical data. Furthermore, it advocates for interdisciplinary collaboration and ethical considerations in the application of these advanced techniques to ensure that biostatistics continues to contribute meaningfully to the advancement of medical science.

Evaluating deep neural networks in optimizing drug discovery and precision medicine: A review

Introduction/Background: Deep neural networks have shown great promise in advancing drug discovery and precision medicine. By leveraging large amounts of complex biomedical and chemical data, deep learning approaches can identify novel targets, predict drug-target and drug-drug interactions, generate new molecular structures, and assist in personalized treatment selection and development. However, fully utilizing deep learning techniques for optimization across the drug development pipeline remains an ongoing challenge. Materials and Methods: A comprehensive literature review was conducted using major bibliographic databases including PubMed, Web of Science, and Scopus. Search terms included combinations of "deep learning", "drug discovery", "precision medicine", "biomedical data", and "neural networks". Over 200 papers published between 2010-2023 related to deep learning applications in pharmacology and genomics were identified and reviewed. Results: Deep learning has been widely applied at various stages of the drug discovery process including target identification/prioritization, lead generation/optimization, and prediction of molecular properties. Convolutional neural networks are commonly used for the representation and classification of biological sequence and image data for tasks such as gene expression analysis and pathogen detection from microscopy images. Graph neural networks effectively model compound structures and interactome networks to predict molecular bindings and disease associations. Multi-modal neural networks integrate diverse data types for personalized treatment response prediction and biomarker discovery. Challenges remain around data and model interpretation, generalization to new targets/diseases, and integration across domains. Discussion: While deep learning has shown promise, rigorous benchmarking and validation on real-world clinical endpoints are still needed to establish usefulness in decision-making. Data and model transparency must be improved to enable scientific insights. Privacy and security risks accompanying "real world" biomedical big data will require ethical practices. Standardization and sharing of resources/protocols could accelerate progress by enabling comparison of techniques. Combining deep learning with other AI paradigms like causal inference may further improve utility in drug discovery and precision healthcare. Conclusion: Deep neural networks demonstrate potential for optimizing drug development and precision medicine applications. Continued advancement relies on addressing challenges around data, models, validation, and ethics. Multi-disciplinary collaborations integrating machine learning, molecular biology, medicine, and other domains are needed to fully realize benefits to patients.

AteMeVs: An R package for the estimation of the average treatment effect with measurement error and variable selection for confounders.

In causal inference, the estimation of the average treatment effect is often of interest. For example, in cancer research, an interesting question is to assess the effects of the chemotherapy treatment on cancer, with the information of gene expressions taken into account. Two crucial challenges in this analysis involve addressing measurement error in gene expressions and handling noninformative gene expressions. While analytical methods have been developed to address those challenges, no user-friendly computational software packages seem to be available to implement those methods. To close this gap, we develop an R package, called AteMeVs, to estimate the average treatment effect using the inverse-probability-weighting estimation method to handle data with both measurement error and spurious variables. This developed package accommodates the method proposed by Yi and Chen (2023) as a special case, and further extends its application to a broader scope. The usage of the developed R package is illustrated by applying it to analyze a cancer dataset with information of gene expressions.

Role of human plasma metabolites in prediabetes and type 2 diabetes from the IMI-DIRECT study.

Type 2 diabetes is a chronic condition that is caused by hyperglycaemia. Our aim was to characterise the metabolomics to find their association with the glycaemic spectrum and find a causal relationship between metabolites and type 2 diabetes. As part of the Innovative Medicines Initiative - Diabetes Research on Patient Stratification (IMI-DIRECT) consortium, 3000 plasma samples were measured with the Biocrates AbsoluteIDQ p150 Kit and Metabolon analytics. A total of 911 metabolites (132 targeted metabolomics, 779 untargeted metabolomics) passed the quality control. Multivariable linear and logistic regression analysis estimates were calculated from the concentration/peak areas of each metabolite as an explanatory variable and the glycaemic status as a dependent variable. This analysis was adjusted for age, sex, BMI, study centre in the basic model, and additionally for alcohol, smoking, BP, fasting HDL-cholesterol and fasting triacylglycerol in the full model. Statistical significance was Bonferroni corrected throughout. Beyond associations, we investigated the mediation effect and causal effects for which causal mediation test and two-sample Mendelian randomisation (2SMR) methods were used, respectively. In the targeted metabolomics, we observed four (15), 34 (99) and 50 (108) metabolites (number of metabolites observed in untargeted metabolomics appear in parentheses) that were significantly different when comparing normal glucose regulation vs impaired glucose regulation/prediabetes, normal glucose regulation vs type 2 diabetes, and impaired glucose regulation vs type 2 diabetes, respectively. Significant metabolites were mainly branched-chain amino acids (BCAAs), with some derivatised BCAAs, lipids, xenobiotics and a few unknowns. Metabolites such as lysophosphatidylcholine a C17:0, sum of hexoses, amino acids from BCAA metabolism (including leucine, isoleucine, valine, N-lactoylvaline, N-lactoylleucine and formiminoglutamate) and lactate, as well as an unknown metabolite (X-24295), were associated with HbA1c progression rate and were significant mediators of type 2 diabetes from baseline to 18 and 48 months of follow-up. 2SMR was used to estimate the causal effect of an exposure on an outcome using summary statistics from UK Biobank genome-wide association studies. We found that type 2 diabetes had a causal effect on the levels of three metabolites (hexose, glutamate and caproate [fatty acid (FA) 6:0]), whereas lipids such as specific phosphatidylcholines (PCs) (namely PC aa C36:2, PC aa C36:5, PC ae C36:3 and PC ae C34:3) as well as the two n-3 fatty acids stearidonate (18:4n3) and docosapentaenoate (22:5n3) potentially had a causal role in the development of type 2 diabetes. Our findings identify known BCAAs and lipids, along with novel N-lactoyl-amino acid metabolites, significantly associated with prediabetes and diabetes, that mediate the effect of diabetes from baseline to follow-up (18 and 48 months). Causal inference using genetic variants shows the role of lipid metabolism and n-3 fatty acids as being causal for metabolite-to-type 2 diabetes whereas the sum of hexoses is causal for type 2 diabetes-to-metabolite. Identified metabolite markers are useful for stratifying individuals based on their risk progression and should enable targeted interventions.

Relationship between serum vitamin D levels and thyroid- and parathyroid-related diseases: a Mendelian randomisation study.

Previous studies have indicated an association between vitamin D and thyroid- and parathyroid-related diseases. However, it remains unclear whether it is a cause of the disease, a side effect of treatment or a consequence of the disease. The Mendelian randomisation (MR) study strengthens the causal inference by controlling for non-heritable environmental confounders and reverse causation. In this study, a two-sample bidirectional MR analysis was conducted to investigate the causal relationship between serum vitamin D levels and thyroid- and parathyroid-related diseases. Inverse variance weighted, weighted median and MR-Egger methods were performed, the Cochran Q test was used to evaluate the heterogeneity and the MR-PRESSO and MR-Egger intercepts were utilised to assess the possibility of pleiotropy. The Bonferroni-corrected significance threshold was 0·0038. At the Bonferroni-corrected significance level, we found that vitamin D levels suggestively decreased the risk of benign parathyroid adenoma (OR = 0·244; 95 % CI 0·074, 0·802; P = 0·0202) in the MR analyses. In the reverse MR study, a genetically predicted risk of thyroid cancer suggestively increased the risk of elevated vitamin D (OR = 1·007; 95 % CI 1·010, 1·013; P = 0·0284), chronic thyroiditis significantly increased the risk of elevated vitamin D (OR = 1·007; 95 % CI 1·002, 1·011; P = 0·0030) and thyroid nodules was significantly decreased the vitamin D levels (OR = 0·991; 95 % CI 0·985, 0·997; P = 0·0034). The findings might be less susceptible to horizontal pleiotropy and heterogeneity (P > 0·05). This study from a gene perspective indicated that chronic thyroiditis and thyroid nodules may impact vitamin D levels, but the underlying mechanisms require further investigation.

A Causal Inference Approach to Mediation Analysis in Vitreomacular Traction: How Much Does Traction Resolution Mediate Functional Outcomes?

Modern mediation analysis techniques supplement the primary intention-to-treat analysis with the aim to shed light onto the treatment mechanism. We investigate to what extent the anatomic marker vitreomacular adhesion resolution (VMAR) mediates vision benefits, comparing ocriplasmin vs. a sham regimen. A causal mediation analysis is applied to randomized trial data including 218 participants with vitreomacular traction. Logistic regression models are used to estimate the total treatment effect (TTE) on binary outcomes. Outcomes, assessed at month 24, included visual acuity improvement (VA-I): ≥2-line increase in VA; visual function questionnaire improvement (VFQ-I): ≥5-point increase in the 25-item visual function questionnaire composite score (VFQ-25cs); visual function improvement (VF-I): defined as either a VA-I or a clinically meaningful improvement in the VFQ-25cs. Quantity of interest is the breakdown of TTE into an indirect (through VMAR) and direct effect to estimate the extent to which the TTE is transmitted through the mediating variable (VMAR) vs. other pathways. Causal effects are expressed as risk differences. Indirect effects for VFQ-I, VA-I, and VF-I are 5.7%, 11.8%, and 5.2%, respectively, representing the increase in the probability of a vision improvement if VMAR status were changed for each participant to the extent that it is affected by ocriplasmin. The direct effects are 8.3%, 12.1%, and 24.1% respectively, capturing the effect of treatment on the probability of a vision improvement if ocriplasmin left each participant's VMAR status unchanged. The relative treatment effect of ocriplasmin on the functional outcome VA-I is to a large extent the result of its effect on VMAR, while an improvement in the patient-reported outcomes VFQ-I or VF-I was only partially mediated by VMAR.

Assessing the Operational Characteristics of the Individual Causal Association as a Metric of Surrogacy in the Binary Continuous Setting.

In a causal inference framework, a new metric has been proposed to quantify surrogacy for a continuous putative surrogate and a binary true endpoint, based on information theory. The proposed metric, termed the individual causal association (ICA), was quantified using a joint causal inference model for the corresponding potential outcomes. Due to the non-identifiability inherent in this type of models, a sensitivity analysis was introduced to study the behavior of the ICA as a function of the non-identifiable parameters characterizing the aforementioned model. In this scenario, to reduce uncertainty, several plausible yet untestable assumptions like monotonicity, independence, conditional independence or homogeneous variance-covariance, are often incorporated into the analysis. We assess the robustness of the methodology regarding these simplifying assumptions via simulation. The practical implications of the findings are demonstrated in the analysis of a randomized clinical trial evaluating an inactivated quadrivalent influenza vaccine.

A Moderated Mediation Model of Entrepreneurship Education, Competence, and Environmental Dynamics on Entrepreneurial Performance

This study explores the relationship between entrepreneurship education, entrepreneurial competence, and entrepreneurial performance, focusing on the moderating role of environmental dynamics under conditions of high and low environmental dynamics. Using SPSS 21.0 and Smart PLS 4.0 software, this quantitative research analyzed survey data from 424 college students in China who have started their own businesses. The results indicate that entrepreneurship education has a significant positive impact on entrepreneurial performance. Furthermore, environmental dynamics moderate the indirect effect of entrepreneurship education on entrepreneurial performance through entrepreneurial competence, with the indirect effect being stronger when environmental dynamics are high. The study also underscores the need for the sustainable development of entrepreneurship education, ensuring that educational programs evolve continuously to meet the changing demands of entrepreneurial environments. The findings highlight the importance of entrepreneurship education in fostering entrepreneurial competence and enhancing entrepreneurial performance. However, due to the cross-sectional design and self-reported nature of the data, the ability to draw causal inferences is limited. Future research should adopt longitudinal designs and objective performance measures to further investigate these relationships.