Fast Causal Inference Research Articles

Causal Inference Thinking of Elementary School Teacher Professional Education Program Students in Determining Digital Strategies to Solve Mathematical Problems

This research aims to examine the causal inference thinking of PPG PGSD students in solving mathematical problems. This research uses a qualitative approach with a case study type. The subjects of this research were four pre-service PPG students from PGSD UM. The instruments for this research include researchers, indicator rubrics, validation sheets, researcher notes, mathematical problems, internet networks, laptops, and handphones. Research subjects as data sources produce data that is analyzed in the form of written answers and recorded interviews. The qualitative data analysis technique used in this research is the interactive model. The results of this research show that fast causal inference thinking is characterized by expressing familiarity with mathematical problem solving, expressing familiarity with accessing digital platforms to solve mathematical problems, accessing digital platforms with keywords, correlating the characteristics of information with specific digital platforms, and Accessing specific digital platforms spontaneously. Slow Causal Inference Thinking is characterized by accessing more than one digital platform to understand a piece of information and read the math problem text repeatedly. The digital platforms that the subjects considered to be a solution were the Google and YouTube platforms.

Mixed-variable graphical modeling framework towards risk prediction of hospital-acquired pressure injury in spinal cord injury individuals

Developing machine learning (ML) methods for healthcare predictive modeling requires absolute explainability and transparency to build trust and accountability. Graphical models (GM) are key tools for this but face challenges like small sample sizes, mixed variables, and latent confounders. This paper presents a novel learning framework addressing these challenges by integrating latent variables using fast causal inference (FCI), accommodating mixed variables with predictive permutation conditional independence tests (PPCIT), and employing a systematic graphical embedding approach leveraging expert knowledge. This method ensures a transparent model structure and an explainable feature selection and modeling approach, achieving competitive prediction performance. For real-world validation, data of hospital-acquired pressure injuries (HAPI) among individuals with spinal cord injury (SCI) were used, where the approach achieved a balanced accuracy of 0.941 and an AUC of 0.983, outperforming most benchmarks. The PPCIT method also demonstrated superior accuracy and scalability over other benchmarks in causal discovery validation on synthetic datasets that closely resemble our real dataset. This holistic framework effectively addresses the challenges of mixed variables and explainable predictive modeling for disease onset, which is crucial for enabling transparency and interpretability in ML-based healthcare.

Age-associated proteins explain the role of medial temporal lobe networks in Alzheimer's disease.

The structural connectivity (SC) of the medial temporal lobe and its associated cortical anterior temporal and posterior medial networks (MTL-AT-PM) is linked to pathologies and memory decline in Alzheimer's disease (AD). However, neuroimaging analyses cannot tell us how SC changes occur in AD at the molecular level and do not provide a means of intervening to slow/prevent pathology-related changes in MTL-AT-PM SC. The current study aimed to understand how and where AD-related changes occur within MTL-AT-PM using proteomics. We used a 4-step approach in 101 older adults froma local sample, aiming to understand how proteins and SC in combination at the multivariate level predict AD pathology, and to identify specific proteins related to SC and AD pathology. Separately, we validated the discovered proteins in relation to SC and AD pathology using ADNI sample. We identified 12 latent factors linking proteins and SC; five showed significant relationships with AD pathology and/or episodic memory. Insulin-like growth factor binding proteins and tumor necrosis factor receptors, and hippocampal/parahippocampal edges contributed most to AD-related latent factors. Fast causal inference found protein-protein, protein-SC, and protein-pathology pathways, with seven proteins showing directional links to SC and AD-related neurodegeneration. We validated these results by identifying significant relationships between six available proteins with SC and amyloid-beta and phosphorylated tau in ADNI. We identified multivariate relationships between proteins and MTL-AT-PM networks that add to our understanding of AD pathology and suggest specific non-pathological proteins that warrant further study in relation to brain networks and AD pathology as possible therapeutic targets.

An exploratory study of the relationship between pulse transit time and blood pressure based on causal inference

Aim: We propose to examine the causal relationship between the noninvasive features represented by pulse transit time (PTT) and blood pressure (BP), with the aim of mitigating the impact of confounding factor(s) and thus improving the performance of BP estimation. Methods: We identified the causal graph of BP and the important noninvasive features extracted from electrocardiogram (ECG) and photoplethysmogram (PPG) via fast causal inference (FCI) algorithm, with the orientations of the edges in the causal graph being determined by the causal generative neural networks (CGNN) algorithm. With the knowledge obtained from the causal graph, we further used hierarchical regression model to estimate BP, and validated the proposed method on 17 subjects. Results: We found that the obtained causal graph was almost consistent with the prior knowledge, and heart rate (HR) was one of the main confounding factors of PTT and BP. Incorporating HR into the hierarchical regression model to eliminate its confounding effect on the PTT-based BP estimation, the mean value of SBP and DBP estimation was improved by 1.27 and 1.89 mmHg, respectively, and the mean absolute difference (MAD) was improved by 2.28 and 3.60 mmHg, respectively. Conclusion: Causal inference-based method has the potential to clarify the causal relationship between BP and related wearable noninvasive features, which can further shed light on developing new methods for cuffless BP with acceptable accuracy.

Determining causality in travel mode choice

This article presents one of the pioneering studies on causal modeling in travel mode choice decision-making using causal discovery algorithms. These models are a major advancement from conventional correlation-based techniques. We propose a novel methodology that combines causal discovery with structural equation modeling (SEM). This modeling approach overcomes some of the limitations of SEM by combining the strengths of both causal discovery and SEM. Causal discovery algorithms determine causal graphs from observational data and domain knowledge, and SEMs estimate direct causal effects and test the performance of causal discovery algorithms. In this study, we test four causal discovery algorithms: Peter-Clark (PC), Fast Causal Inference (FCI), Fast Greedy Equivalence Search (FGES), and Direct Linear Non-Gaussian Acyclic Models (DirectLiNGAM). The results show that DirectLiNGAM based SEM model best captures causality in mode choice behavior. It passes several goodness-of-fit tests, including Root Mean Square Error of Approximation (RMSEA) and Goodness-of-Fit Index (GFI), and it achieves the lowest Bayesian Information Criterion (BIC) value. The analyses are conducted on data collected from the 2017 National Household Travel Survey in the New York Metropolitan area.

Discovering causal models for structural, construction and defense-related engineering phenomena

Causality, the science of cause and effect, has made it possible to create a new family of models. Such models are often referred to as causal models. Unlike those of mathematical, numerical, empirical, or machine learning (ML) nature, causal models hope to tie the cause(s) to the effect(s) pertaining to a phenomenon (i.e., data generating process) through causal principles. This paper presents one of the first works at creating causal models in the area of structural and construction engineering. To this end, this paper starts with a brief review of the principles of causality and then adopts four causal discovery algorithms, namely, PC (Peter-Clark), FCI (fast causal inference), GES (greedy equivalence search), and GRaSP (greedy relaxation of the sparsest permutation), have been used to examine four phenomena, including predicting the load-bearing capacity of axially loaded members, fire resistance of structural members, shear strength of beams, and resistance of walls against impulsive (blast) loading. Findings from this study reveal the possibility and merit of discovering complete and partial causal models. Finally, this study also proposes two simple metrics that can help assess the performance of causal discovery algorithms.

Factors and pathways of non-suicidal self-injury in children: insights from computational causal analysis.

Non-suicidal self-injury (NSSI) has become a significant public health issue, especially prevalent among adolescents. The complexity and multifactorial nature of NSSI necessitate a comprehensive understanding of its underlying causal factors. This research leverages the causal discovery methodology to explore these causal associations in children. An observational dataset was scrutinized using the causal discovery method, particularly employing the constraint-based approach. By integrating machine learning and causal inference techniques, the study aimed to determine direct causal relationships associated with NSSI. The robustness of the causal relationships was evaluated using three methods to construct and validate it: the PC (Peter and Clark) method, Fast Causal Inference (FCI) method, and the GAE (Graphical Autoencoder) method. Analysis identified nine nodes with direct causal relationships to NSSI, including life satisfaction, depression, family dysfunction, sugary beverage consumption, PYD (positive youth development), internet addiction, COVID-19 related PTSD, academic anxiety, and sleep duration. Four principal causal pathways were identified, highlighting the roles of lockdown-induced lifestyle changes, screen time, positive adolescent development, and family dynamics in influencing NSSI risk. An in-depth analysis of the factors leading to Non-Suicidal Self-Injury (NSSI), highlighting the intricate connections among individual, family, and pandemic-related influences. The results, derived from computational causal analysis, underscore the critical need for targeted interventions that tackle these diverse causative factors.

Causal discovery to understand hot corrosion

AbstractGas turbine superalloys experience hot corrosion, driven by factors including corrosive deposit flux, temperature, gas composition, and component material. The full mechanism still needs clarification and research often focuses on laboratory work. As such, there is interest in causal discovery to confirm the significance of factors and identify potential missing causal relationships or codependencies between these factors. The causal discovery algorithm fast causal inference (FCI) has been trialled on a small set of laboratory data, with the outputs evaluated for their significance to corrosion propagation, and compared to existing mechanistic understanding. FCI identified salt deposition flux as the most influential corrosion variable for this limited data set. However, HCl was the second most influential for pitting regions, compared to temperature for more uniformly corroding regions. Thus, FCI generated causal links aligned with literature from a randomised corrosion data set, while also identifying the presence of two different degradation modes in operation.

The discovery of a data-driven causal diagram of sport participation in children and adolescents with heart disease: a pilot study

The interventions aimed at improving the levels of physical activity (PA) in children and adolescents diagnosed with heart disease did not produce the expected outcomes. Safe participation in sport activities proposed based on actual recommendations could be a solution to promote PA in this population. The aims of this study were to discover a causal diagram of sport participation in children and youth with heart disease and establish the factors that affect and are affected thereof through the use of questionnaires. Furthermore, the study aims to qualitatively assess the reliability of the constructed diagram in comparison with existing medical knowledge. The Greedy Fast Causal Inference method was employed to conduct a data-driven search of the directed acyclic graph that represents the causal relationships within the provided observational data. This causal discovery was performed using the Tetrad software. The analysis involved a cohort of 121 Caucasian patients (50 females) diagnosed with heart disease. The age range of the patients included in the study was 8–17 years. The study findings indicate that the participants engaged in sports presented significantly higher values of health-related quality of life (QoL) and motives for participating in physical and leisure activities. Age appears to be a cause of sport participation. Sport participation appears to be a cause of participation in physical education classes, which in turn appears to be a cause of higher enjoyment. Higher enjoyment appears to be a cause of other motives for participating in physical and leisure activities, as well as a higher score in terms of physical health. The causal diagram provided a graphical representation of the causal relationship between sport participation and better QoL with potential confounders for children and adolescents with heart disease that nearly coincided with the existing literature. Clinical trials should be designed to validate clinical utility of the presented causal diagram.

Key Influencing Factors Identification in Complex Systems Based on Heuristic Causal Inference

In complex systems constrained by multiple factors, it is very important to identify the key influencing factors for mastering the evolution and development law of a system and for obtaining scientific decision-making suggestions or schemes. At present, the method based on experimental simulation is limited by the difficulty of system model construction; DEMATEL (Factual Decision Trial and Evaluation Laboratory) is inevitably influenced by subjective factors. In view of this, we propose a novel model based on heuristic causal inference. By combining the network analysis in complex network science, the model defines the global/local causal pathway and the causal pathway’s length in the causal network and takes the causal pathway contribution degree as an indicator to measure the approximate causal effects. The model includes steps such as causal network learning, causal pathway contribution degree calculation, and key influencing factor identification. The model uses the Fast Causal Inference (FCI) algorithm with prior knowledge to learn the global causal network of the complex system and uses the heuristic causal inference to calculate the causal pathway contribution degree. The heuristic method draws on the idea of complex network topology analysis and measures the influence degree between variables by the number and distance of causal pathways. The key influencing factors are finally identified according to the causal pathway contribution degree. Based on the SECOM dataset, we carried out simulation experiments and demonstrated the feasibility and effectiveness of the proposed method.

Causal Structural Learning via Local Graphs.

We consider the problem of learning causal structures in sparse high-dimensional settings that may be subject to the presence of (potentially many) unmeasured confounders, as well as selection bias. Based on structure found in common families of large random networks, we propose a new local notion of sparsity for structure learning in the presence of latent and selection variables, and develop a new version of the Fast Causal Inference (FCI) algorithm, which we refer to as local FCI (lFCI). Under the new sparsity condition and an additional assumption that ensures that conditional dependencies can be determined locally, lFCI is consistent and offers reduced computational and sample complexity when compared to standard FCI algorithms. The new notion of sparsity allows the presence of highly connected hub nodes, which are common in real-world networks, but problematic for existing methods. Our numerical experiments indicate that the lFCI algorithm achieves state-of-the-art performance across many classes of large random networks, and its performance is superior to that of existing methods for networks containing hub nodes.

Causal inference based cuffless blood pressure estimation: A pilot study

Enabled by wearable sensing, e.g., photoplethysmography (PPG) and electrocardiography (ECG), and machine learning techniques, study on cuffless blood pressure (BP) measurement with data-driven methods has become popular in recent years. However, causality has been overlooked in most of current studies. In this study, we aim to examine the feasibility of causal inference for cuffless BP estimation. We first attempt to detect wearable features that are causally related, rather than correlated, to BP changes by identifying causal graphs of interested variables with fast causal inference (FCI) algorithm. With identified causal features, we then employ time-lagged link to integrate the mechanism of causal inference into the BP estimated model. The proposed method was validated on 62 subjects with their continuous ECG, PPG and BP signals being collected. We found new causal features that can better track BP changes than pulse transit time (PTT). Further, the developed causal-based estimation model achieved an estimation error of mean absolute difference (MAD) being 5.10 mmHg and 2.85 mmHg for SBP and DBP, respectively, which outperformed traditional model without consideration of causality. To the best of our knowledge, this work is the first to study the causal inference for cuffless BP estimation, which can shed light on the mechanism, method and application of cuffless BP measurement.

Toward a causal model of chronic back pain: Challenges and opportunities.

Chronic low back pain (cLBP) afflicts 8. 2% of adults in the United States, and is the leading global cause of disability. Neuropsychiatric co-morbidities including anxiety, depression, and substance abuse- are common in cLBP patients. In particular, cLBP is a risk factor for opioid addiction, as more than 50% of opioid prescriptions in the United States are for cLBP. Misuse of these prescriptions is a common precursor to addiction. While associations between cLBP and neuropsychiatric disorders are well established, causal relationships for the most part are unknown. Developing effective treatments for cLBP, and associated co-morbidities, requires identifying and understanding causal relationships. Rigorous methods for causal inference, a process for quantifying causal effects from observational data, have been developed over the past 30 years. In this review we first discuss the conceptual model of cLBP that current treatments are based on, and how gaps in causal knowledge contribute to poor clinical outcomes. We then present cLBP as a "Big Data" problem and identify how advanced analytic techniques may close knowledge gaps and improve clinical outcomes. We will focus on causal discovery, which is a data-driven method that uses artificial intelligence (AI) and high dimensional datasets to identify causal structures, discussing both constraint-based (PC and Fast Causal Inference) and score-based (Fast Greedy Equivalent Search) algorithms.

Causal determinants of postoperative length of stay in cardiac surgery using causal graphical learning

ObjectiveWe aimed to learn the causal determinants of postoperative length of stay in cardiac surgery patients undergoing isolated coronary artery bypass grafting or aortic valve replacement surgery. MethodsFor patients undergoing isolated coronary artery bypass grafting or isolated aortic valve replacement surgeries between 2011 and 2016, we used causal graphical modeling on electronic health record data. The Fast Causal Inference (FCI) algorithm from the Tetrad software was used on data to estimate a Partial Ancestral Graph (PAG) depicting direct and indirect causes of postoperative length of stay, given background clinical knowledge. Then, we used the latent variable intervention-calculus when the directed acyclic graph is absent (LV-IDA) algorithm to estimate strengths of causal effects of interest. Finally, we ran a linear regression for postoperative length of stay to contrast statistical associations with what was learned by our causal analysis. ResultsIn our cohort of 2610 patients, the mean postoperative length of stay was 219 hours compared with the Society of Thoracic Surgeons 2016 national mean postoperative length of stay of approximately 168 hours. Most variables that clinicians believe to be predictors of postoperative length of stay were found to be causes, but some were direct (eg, age, diabetes, hematocrit, total operating time, and postoperative complications), and others were indirect (including gender, race, and operating surgeon). The strongest average causal effects on postoperative length of stay were exhibited by preoperative dialysis (209 hours); neuro-, pulmonary-, and infection-related postoperative complications (315 hours, 89 hours, and 131 hours, respectively); reintubation (61 hours); extubation in operating room (–47 hours); and total operating room duration (48 hours). Linear regression coefficients diverged from causal effects in magnitude (eg, dialysis) and direction (eg, crossclamp time). ConclusionsBy using retrospective electronic health record data and background clinical knowledge, causal graphical modeling retrieved direct and indirect causes of postoperative length of stay and their relative strengths. These insights will be useful in designing clinical protocols and targeting improvements in patient management.

Generalizability challenges of mortality risk prediction models: A retrospective analysis on a multi-center database.

Modern predictive models require large amounts of data for training and evaluation, absence of which may result in models that are specific to certain locations, populations in them and clinical practices. Yet, best practices for clinical risk prediction models have not yet considered such challenges to generalizability. Here we ask whether population- and group-level performance of mortality prediction models vary significantly when applied to hospitals or geographies different from the ones in which they are developed. Further, what characteristics of the datasets explain the performance variation? In this multi-center cross-sectional study, we analyzed electronic health records from 179 hospitals across the US with 70,126 hospitalizations from 2014 to 2015. Generalization gap, defined as difference between model performance metrics across hospitals, is computed for area under the receiver operating characteristic curve (AUC) and calibration slope. To assess model performance by the race variable, we report differences in false negative rates across groups. Data were also analyzed using a causal discovery algorithm "Fast Causal Inference" that infers paths of causal influence while identifying potential influences associated with unmeasured variables. When transferring models across hospitals, AUC at the test hospital ranged from 0.777 to 0.832 (1st-3rd quartile or IQR; median 0.801); calibration slope from 0.725 to 0.983 (IQR; median 0.853); and disparity in false negative rates from 0.046 to 0.168 (IQR; median 0.092). Distribution of all variable types (demography, vitals, and labs) differed significantly across hospitals and regions. The race variable also mediated differences in the relationship between clinical variables and mortality, by hospital/region. In conclusion, group-level performance should be assessed during generalizability checks to identify potential harms to the groups. Moreover, for developing methods to improve model performance in new environments, a better understanding and documentation of provenance of data and health processes are needed to identify and mitigate sources of variation.

Willingness to vaccinate against SARS-CoV-2: The role of reasoning biases and conspiracist ideation

Backgr1oundWidespread vaccine hesitancy and refusal complicate containment of the SARS-CoV-2 pandemic. Extant research indicates that biased reasoning and conspiracist ideation discourage vaccination. However, causal pathways from these constructs to vaccine hesitancy and refusal remain underspecified, impeding efforts to intervene and increase vaccine uptake. Method554 participants who denied prior SARS-CoV-2 vaccination completed self-report measures of SARS-CoV-2 vaccine intentions, conspiracist ideation, and constructs from the Health Belief Model of medical decision-making (such as perceived vaccine dangerousness) along with tasks measuring reasoning biases (such as those concerning data gathering behavior). Cutting-edge machine learning algorithms (Greedy Fast Causal Inference) and psychometric network analysis were used to elucidate causal pathways to (and from) vaccine intentions. ResultsResults indicated that a bias toward reduced data gathering during reasoning may cause paranoia, increasing the perceived dangerousness of vaccines and thereby reducing willingness to vaccinate. Existing interventions that target data gathering and paranoia therefore hold promise for encouraging vaccination. Additionally, reduced willingness to vaccinate was identified as a likely cause of belief in conspiracy theories, subverting the common assumption that the opposite causal relation exists. Finally, perceived severity of SARS-CoV-2 infection and perceived vaccine dangerousness (but not effectiveness) were potential direct causes of willingness to vaccinate, providing partial support for the Health Belief Model’s applicability to SARS-CoV-2 vaccine decisions. ConclusionsThese insights significantly advance our understanding of the underpinnings of vaccine intentions and should scaffold efforts to prepare more effective interventions on hesitancy for deployment during future pandemics.

Causal pathways to social and occupational functioning in the first episode of schizophrenia: uncovering unmet treatment needs.

We aimed to identify unmet treatment needs for improving social and occupational functioning in early schizophrenia using a data-driven causal discovery analysis. Demographic, clinical, and psychosocial measures were obtained for 276 participants from the Recovery After an Initial Schizophrenia Episode Early Treatment Program (RAISE-ETP) trial at baseline and 6-months, along with measures of social and occupational functioning from the Quality of Life Scale. The Greedy Fast Causal Inference algorithm was used to learn a partial ancestral graph modeling causal relationships across baseline variables and 6-month functioning. Effect sizes were estimated using a structural equation model. Results were validated in an independent dataset (N = 187). In the data-generated model, greater baseline socio-affective capacity was a cause of greater baseline motivation [Effect size (ES) = 0.77], and motivation was a cause of greater baseline social and occupational functioning (ES = 1.5 and 0.96, respectively), which in turn were causes of their own 6-month outcomes. Six-month motivation was also identified as a cause of occupational functioning (ES = 0.92). Cognitive impairment and duration of untreated psychosis were not direct causes of functioning at either timepoint. The graph for the validation dataset was less determinate, but otherwise supported the findings. In our data-generated model, baseline socio-affective capacity and motivation are the most direct causes of occupational and social functioning 6 months after entering treatment in early schizophrenia. These findings indicate that socio-affective abilities and motivation are specific high-impact treatment needs that must be addressed in order to promote optimal social and occupational recovery.

The psychological determinants of internet gaming disorder: Vulnerability to stress, psychological well-being, and comorbidity

IntroductionA variety of psychological determinants, such as vulnerability to stress, low levels of psychological well-being and several comorbidities, have been hypothesized to play a role in the development, and maintenance of Internet Gaming Disorder (IGD). However, evidence has been insufficient to sustain an overarching model of the causal pathways leading to IGD.Objectives. This study aimed to depict a model of the causal links between vulnerability to stress, psychological well-being, and symptoms of common mental disorders (e.g., depression, generalized anxiety, phobic anxiety, obsessive-compulsive disorder, somatization, and hostility).Methods. A community-based sample of Portuguese gamers (N = 153; Mage = 21.92; 15.29% female) completed measures of IGD (IGDS9-SF), mental health (SCL-90-R), psychological well-being (EBEP), and vulnerability to stress (23QVS). A machine learning algorithm – Greedy Fast Causal Inference – was used to infer a model of the causal pathways linking those psychological determinants to IGD.Results. Hostility and psychological well-being were directly involved with a subgroup of IGD symptoms (i.e., gaming used as escape, tolerance, withdrawal, and loss of control). Stress vulnerability and symptoms of mental disorders were only indirectly implicated in the causal pathways leading to IGD.Conclusions. It is likely that several psychological factors implicated in the causal pathways leading to IGD, have not been yet identified. Future research should directly test specific models of the causal pathways involved in the development and maintenance of IGD symptoms.DisclosureNo significant relationships.

Willingness to Vaccinate Against SARS-CoV-2: The Role of Reasoning Biases and Conspiracist Ideation

Background: Widespread vaccine hesitancy and refusal complicate containment of the SARS-CoV-2 pandemic. Extant research indicates that biased reasoning and conspiracist ideation discourage vaccination. However, causal pathways from these constructs to vaccine hesitancy and refusal remain underspecified, impeding efforts to intervene and increase vaccine uptake. Method: 554 participants who denied prior SARS-CoV-2 vaccination completed self-report measures of SARS-CoV-2 vaccine intentions, conspiracist ideation, and constructs from the Health Belief Model of medical decision-making (such as perceived vaccine dangerousness) along with tasks measuring reasoning biases (such as those concerning data gathering behavior). Cutting-edge machine learning algorithms (Greedy Fast Causal Inference) and psychometric network analysis were used to elucidate causal pathways to (and from) vaccine intentions.Results: Results indicated that a bias toward reduced data gathering during reasoning may cause paranoia, increasing the perceived dangerousness of vaccines and thereby reducing willingness to vaccinate. Existing interventions that target data gathering and paranoia therefore hold promise for encouraging vaccination. Additionally, reduced willingness to vaccinate was identified as a likely cause of belief in conspiracy theories, subverting the common assumption that the opposite causal relation exists. Finally, perceived severity of SARS-CoV-2 infection and perceived vaccine dangerousness (but not effectiveness) were potential direct causes of willingness to vaccinate, providing partial support for the Health Belief Model’s applicability to SARS-CoV-2 vaccine decisions.Conclusions: These insights significantly advance our understanding of the underpinnings of vaccine intentions and should scaffold efforts to prepare more effective interventions on hesitancy for deployment during future pandemics.

Causal Discovery in Radiographic Markers of Knee Osteoarthritis and Prediction for Knee Osteoarthritis Severity With Attention-Long Short-Term Memory.

The goal of this study is to build a prognostic model to predict the severity of radiographic knee osteoarthritis (KOA) and to identify long-term disease progression risk factors for early intervention and treatment. We designed a long short-term memory (LSTM) model with an attention mechanism to predict Kellgren/Lawrence (KL) grade for knee osteoarthritis patients. The attention scores reveal a time-associated impact of different variables on KL grades. We also employed a fast causal inference (FCI) algorithm to estimate the causal relation of key variables, which will aid in clinical interpretability. Based on the clinical information of current visits, we accurately predicted the KL grade of the patient's next visits with 90% accuracy. We found that joint space narrowing was a major contributor to KOA progression. Furthermore, our causal structure model indicated that knee alignments may lead to joint space narrowing, while symptoms (swelling, grinding, catching, and limited mobility) have little impact on KOA progression. This study evaluated a broad spectrum of potential risk factors from clinical data, questionnaires, and radiographic markers that are rarely considered in previous studies. Using our statistical model, providers are able to predict the risk of the future progression of KOA, which will provide a basis for selecting proper interventions, such as proceeding to joint arthroplasty for patients. Our causal model suggests that knee alignment should be considered in the primary treatment and KOA progression was independent of clinical symptoms.