Phenotypic homogeneity in childhood epilepsies evolves in gene-specific patterns across 3251 patient-years of clinical data

Abstract

While genetic studies of epilepsies can be performed in thousands of individuals, phenotyping remains a manual, non-scalable task. A particular challenge is capturing the evolution of complex phenotypes with age. Here, we present a novel approach, applying phenotypic similarity analysis to a total of 3251 patient-years of longitudinal electronic medical record data from a previously reported cohort of 658 individuals with genetic epilepsies. After mapping clinical data to the Human Phenotype Ontology, we determined the phenotypic similarity of individuals sharing each genetic etiology within each 3-month age interval from birth up to a maximum age of 25 years. 140 of 600 (23%) of all 27 genes and 3-month age intervals with sufficient data for calculation of phenotypic similarity were significantly higher than expect by chance. 11 of 27 genetic etiologies had significant overall phenotypic similarity trajectories. These do not simply reflect strong statistical associations with single phenotypic features but appear to emerge from complex clinical constellations of features that may not be strongly associated individually. As an attempt to reconstruct the cognitive framework of syndrome recognition in clinical practice, longitudinal phenotypic similarity analysis extends the traditional phenotyping approach by utilizing data from electronic medical records at a scale that is far beyond the capabilities of manual phenotyping. Delineation of how the phenotypic homogeneity of genetic epilepsies varies with age could improve the phenotypic classification of these disorders, the accuracy of prognostic counseling, and by providing historical control data, the design and interpretation of precision clinical trials in rare diseases.

Enriching Representation Learning Using 53 Million Patient Notes through Human Phenotype Ontology Embedding

“…Future iterations including temporal components [11] or inclusion of additional data such as medication and procedure information may further improve phenotype embeddings and exceed the currently available frameworks.…”

“…When compared to randomly assigned term frequencies, the inclusion of term frequencies in the embedding allows for more closely related phenotypes to be “drawn in” and more distantly related phenotypes to be “pushed out.” This exemplifies how additional information incorporated in the embedding technique such as term frequency can provide more specificity and nuance in the connections between phenotypes. Future iterations including temporal components [11] or inclusion of additional data such as medication and procedure information may further improve phenotype embeddings and exceed the currently available frameworks.…”

“…However, it can be reasoned that these higher-level terms are often essential as they may capture large groups of individuals with phenotypically broad but clinically or biologically important similarities. Accordingly, we performed a method referred to as "propagation" that we have used extensively in past work [6,25,[41][42][43][44][45]. In brief, for each individual's set of explicitly annotated HPO terms, we add all HPO terms that can be inferred as applicable by taking the union of all those terms encountered following all possible paths along "is a" relationships to the root of the HPO.…”

“…We have contributed to HPO terminology since 2010 [4][5][6][7]. The HPO has been widely used for harmonization of clinical features in various studies, including, but not limited to, semantic unification of common and rare diseases [8], genetic discoveries in pediatric epilepsy [9,10], and delineation of longitudinal phenotypes [11,12]. In addition, the HPO is commonly used for genomic studies and allows for analyses of clinical data at a scale that is required by current and future initiatives.…”

Computational analysis of neurodevelopmental phenotypes: Harmonization empowers clinical discovery

“…We have previous examined longitudinal phenotypic data by extracting features from EMR (Ganesan et al, 2020; D. Lewis‐Smith, Ganesan, et al, 2021; Xian et al, 2021). The widespread adoption of EMR mandated by the American Recovery and Reinvestment Act of 2009 is an unprecedented opportunity to leverage clinical data generated as a byproduct of healthcare for genomic research.…”