Search

Sequential model synchronisation is the task of propagating changes from one model to another correlated one to restore consistency. It is challenging to perform this propagation in a least-changing way that avoids unnecessary deletions (which might cause information loss). From a theoretical point of view, so-called short-cut (SC) rules have been developed that enable provably correct propagation of changes while avoiding information loss. However, to be able to react to every possible change, an infinite set of such rules might be necessary. Practically, only small sets of pre-computed basic SC rules have been used, severely restricting the kind of changes that can be propagated without loss of information. In this work, we close that gap by developing an approach to compute more complex required SC rules on-the-fly during synchronisation. These higher-order SC rules allow us to cope with more complex scenarios when multiple changes must be handled in one step. We implemented our approach in the model transformation tool eMoflon. An evaluation shows that the overhead of computing higher-order SC rules on-the-fly is tolerable and at times even improves the overall performance. Above that, completely new scenarios can be dealt with without the loss of information.

Abstract Purpose Real world evidence is crucial to understanding the diffusion of new oncologic therapies, monitoring cancer outcomes, and detecting unexpected toxicities. In practice, real world evidence is challenging to collect rapidly and comprehensively, often requiring expensive and time‐consuming manual case‐finding and annotation of clinical text. In this Review, we summarise recent developments in the use of artificial intelligence to collect and analyze real world evidence in oncology. Methods We performed a narrative review of the major current trends and recent literature in artificial intelligence applications in oncology. Results Artificial intelligence (AI) approaches are increasingly used to efficiently phenotype patients and tumors at large scale. These tools also may provide novel biological insights and improve risk prediction through multimodal integration of radiographic, pathological, and genomic datasets. Custom language processing pipelines and large language models hold great promise for clinical prediction and phenotyping. Conclusions Despite rapid advances, continued progress in computation, generalizability, interpretability, and reliability as well as prospective validation are needed to integrate AI approaches into routine clinical care and real‐time monitoring of novel therapies.

Abstract Understanding patterns of drug‐gene interactions (DGIs) is important for advancing the clinical implementation of pharmacogenetics (PGx) into routine practice. Prior studies have estimated the prevalence of DGIs, but few have confirmed DGIs in patients with known genotypes and prescriptions, nor have they evaluated clinician characteristics associated with DGI‐prescribing. This retrospective chart review assessed prevalence of DGI, defined as a medication prescription in a patient with a PGx phenotype that has a clinical practice guideline recommendation to adjust therapy or monitor drug response, for patients enrolled in a research genetic biorepository linked to electronic health records (EHRs). The prevalence of prescriptions for medications with pharmacogenetic (PGx) guidelines, proportion of prescriptions with DGI, location of DGI prescription, and clinical service of the prescriber were evaluated descriptively. Seventy‐five percent (57,058/75,337) of patients had a prescription for a medication with a PGx guideline. Up to 60% (n = 26,067/43,647) of patients had at least one DGI when considering recommendations to adjust or monitor therapy based on genotype. The majority (61%) of DGIs occurred in outpatient prescriptions. Proton pump inhibitors were the most common DGI medication for 11 of 12 clinical services. Almost 25% of patients (n = 10,706/43,647) had more than one unique DGI, and, among this group of patients, 61% had a DGI with more than one gene. These findings can inform future clinical implementation by identifying key stakeholders for initial DGI prescriptions, helping to inform workflows. The high prevalence of multigene interactions identified also support the use of panel PGx testing as an implementation strategy.

Genetic variation in ANGPTL4 is associated with lipid traits. Here, the authors find that predicted loss-of-function variants in ANGPTL4 are associated with glucose homeostasis and reduced risk of type 2 diabetes and that Angptl4 −/− mice on a high-fat diet show improved insulin sensitivity.

Aortic valve stenosis (AS) is the most common valvular heart disease. Here the authors identify two new AS loci that also associate with bicuspid aortic valve, aortic root diameter and/or coronary artery disease implicating both developmental abnormalities and atherosclerosis-like processes in AS.

Bicuspid aortic valve (BAV) is the most common human congenital cardiovascular malformation. Here, the authors perform a genome-wide association study for BAV and identify risk variants in the gene region of cardiac-specific transcription factor GATA4 and implicate GATA4 in heart valve development.