Counterfactual analysis of differential comorbidity risk factors in Alzheimer's disease and related dementias

Genetic variants for Alzheimer's disease and comorbid conditions

BACKGROUND

Alzheimer's disease and related dementias (ADRD) frequently co-occur with comorbidities such as diabetes and cardiovascular diseases in elderly populations.

OBJECTIVE

Utilize a life-course approach to identify genetic variants that are associated with the co-occurrence of ADRD and another comorbid condition.

METHODS

Research data from African American participants of the Indianapolis-Ibadan Dementia Project (IIDP) linked with electronic medical record (EMR) data and genome-wide association study (GWAS) data were utilized. The age of onset for ADRD was obtained from longitudinal follow-up of the IIDP study. Age of onset for comorbid conditions was obtained from EMR. The analysis included 1177 African Americans, among whom 174 were diagnosed with ADRD. A semi-parametric marginal bivariate survival model was used to examine the influence of single nucleotide polymorphisms (SNPs) on dual time-to-event outcomes while adjusting for sex, years of education, and the first principal component of GWAS data.

RESULTS

Targeted analysis of 20 SNPs that were reported to be associated with ADRD revealed that six were significantly associated with dual-disease outcomes, specifically congestive heart failure and cancer. In addition, eight novel SNPs were identified for associations with both ADRD and a comorbid condition.

CONCLUSIONS

Using a bivariate survival model approach, we identified genetic variants associated not only with ADRD, but also with comorbid conditions. Our utilization of dual-disease models represents a novel analytic strategy for uncovering shared genetic variants for multiple disease phenotypes.

Self-Explainable Graph Neural Network for Alzheimer Disease and Related Dementias Risk Prediction: Algorithm Development and Validation Study

BACKGROUND

Alzheimer disease and related dementias (ADRD) rank as the sixth leading cause of death in the United States, underlining the importance of accurate ADRD risk prediction. While recent advancements in ADRD risk prediction have primarily relied on imaging analysis, not all patients undergo medical imaging before an ADRD diagnosis. Merging machine learning with claims data can reveal additional risk factors and uncover interconnections among diverse medical codes.

OBJECTIVE

The study aims to use graph neural networks (GNNs) with claim data for ADRD risk prediction. Addressing the lack of human-interpretable reasons behind these predictions, we introduce an innovative, self-explainable method to evaluate relationship importance and its influence on ADRD risk prediction.

METHODS

We used a variationally regularized encoder-decoder GNN (variational GNN [VGNN]) integrated with our proposed relation importance method for estimating ADRD likelihood. This self-explainable method can provide a feature-important explanation in the context of ADRD risk prediction, leveraging relational information within a graph. Three scenarios with 1-year, 2-year, and 3-year prediction windows were created to assess the model's efficiency, respectively. Random forest (RF) and light gradient boost machine (LGBM) were used as baselines. By using this method, we further clarify the key relationships for ADRD risk prediction.

RESULTS

In scenario 1, the VGNN model showed area under the receiver operating characteristic (AUROC) scores of 0.7272 and 0.7480 for the small subset and the matched cohort data set. It outperforms RF and LGBM by 10.6% and 9.1%, respectively, on average. In scenario 2, it achieved AUROC scores of 0.7125 and 0.7281, surpassing the other models by 10.5% and 8.9%, respectively. Similarly, in scenario 3, AUROC scores of 0.7001 and 0.7187 were obtained, exceeding 10.1% and 8.5% than the baseline models, respectively. These results clearly demonstrate the significant superiority of the graph-based approach over the tree-based models (RF and LGBM) in predicting ADRD. Furthermore, the integration of the VGNN model and our relation importance interpretation could provide valuable insight into paired factors that may contribute to or delay ADRD progression.

CONCLUSIONS

Using our innovative self-explainable method with claims data enhances ADRD risk prediction and provides insights into the impact of interconnected medical code relationships. This methodology not only enables ADRD risk modeling but also shows potential for other image analysis predictions using claims data.

Reporting of Observational Studies Explicitly Aiming to Emulate Randomized Trials: A Systematic Review

Importance

Observational (nonexperimental) studies that aim to emulate a randomized trial (ie, the target trial) are increasingly informing medical and policy decision-making, but it is unclear how these studies are reported in the literature. Consistent reporting is essential for quality appraisal, evidence synthesis, and translation of evidence to policy and practice.

Objective

To assess the reporting of observational studies that explicitly aimed to emulate a target trial.

Evidence Review

We searched Medline, Embase, PsycINFO, and Web of Science for observational studies published between March 2012 and October 2022 that explicitly aimed to emulate a target trial of a health or medical intervention. Two reviewers double-screened and -extracted data on study characteristics, key predefined components of the target trial protocol and its emulation (eligibility criteria, treatment strategies, treatment assignment, outcome[s], follow-up, causal contrast[s], and analysis plan), and other items related to the target trial emulation.

Findings

A total of 200 studies that explicitly aimed to emulate a target trial were included. These studies included 26 subfields of medicine, and 168 (84%) were published from January 2020 to October 2022. The aim to emulate a target trial was explicit in 70 study titles (35%). Forty-three studies (22%) reported use of a published reporting guideline (eg, Strengthening the Reporting of Observational Studies in Epidemiology). Eighty-five studies (43%) did not describe all key items of how the target trial was emulated and 113 (57%) did not describe the protocol of the target trial and its emulation.

Conclusion and Relevance

In this systematic review of 200 studies that explicitly aimed to emulate a target trial, reporting of how the target trial was emulated was inconsistent. A reporting guideline for studies explicitly aiming to emulate a target trial may improve the reporting of the target trial protocols and other aspects of these emulation attempts.

Inferring Personalized Treatment Effect of Antihypertensives on Alzheimer's Disease Using Deep Learning

Alzheimer's disease (AD) is one of the leading causes of death in the United States, especially among the elderly. Recent studies have shown how hypertension is related to cognitive decline in elderly patients, which in turn leads to increased mortality as well as morbidity. There have been various studies that have looked at the effect of antihypertensive drugs in reducing cognitive decline, and their results have proved inconclusive. However, most of these studies assume the treatment effect is similar for all patients, thus considering only the average treatment effects of antihypertensive drugs. In this paper, we assume that the effect of antihypertensives on the onset of AD depends on patient characteristics. We develop a deep learning method called LASSO-Dragonnet to estimate the individualized treatment effects of each patient. We considered six antihypertensive drugs, and each of the six models considered one of the drugs as the treatment and the remaining as control. Our studies showed that although many antihypertensives have a positive impact in delaying AD onset on average, the impact varies from individual to individual, depending on their various characteristics. We also analyzed the importance of various covariates in such an estimation. Our results showed that the individualized treatment effects of each patient could be estimated accurately using a deep learning method, and that the importance of various covariates could be determined.

Scalable Causal Structure Learning: Scoping Review of Traditional and Deep Learning Algorithms and New Opportunities in Biomedicine

BACKGROUND

Causal structure learning refers to a process of identifying causal structures from observational data, and it can have multiple applications in biomedicine and health care.

OBJECTIVE

This paper provides a practical review and tutorial on scalable causal structure learning models with examples of real-world data to help health care audiences understand and apply them.

METHODS

We reviewed traditional (combinatorial and score-based) methods for causal structure discovery and machine learning-based schemes. Various traditional approaches have been studied to tackle this problem, the most important among these being the Peter Spirtes and Clark Glymour algorithms. This was followed by analyzing the literature on score-based methods, which are computationally faster. Owing to the continuous constraint on acyclicity, there are new deep learning approaches to the problem in addition to traditional and score-based methods. Such methods can also offer scalability, particularly when there is a large amount of data involving multiple variables. Using our own evaluation metrics and experiments on linear, nonlinear, and benchmark Sachs data, we aimed to highlight the various advantages and disadvantages associated with these methods for the health care community. We also highlighted recent developments in biomedicine where causal structure learning can be applied to discover structures such as gene networks, brain connectivity networks, and those in cancer epidemiology.

RESULTS

We also compared the performance of traditional and machine learning-based algorithms for causal discovery over some benchmark data sets. Directed Acyclic Graph-Graph Neural Network has the lowest structural hamming distance (19) and false positive rate (0.13) based on the Sachs data set, whereas Greedy Equivalence Search and Max-Min Hill Climbing have the best false discovery rate (0.68) and true positive rate (0.56), respectively.

CONCLUSIONS

Machine learning-based approaches, including deep learning, have many advantages over traditional approaches, such as scalability, including a greater number of variables, and potentially being applied in a wide range of biomedical applications, such as genetics, if sufficient data are available. Furthermore, these models are more flexible than traditional models and are poised to positively affect many applications in the future.