Informatics and machine learning to define the phenotype

Abstract

Introduction For the past decade, the focus of complex disease research has been the genotype. From technological advancements to the development of analysis methods, great progress has been made. However, advances in our definition of the phenotype have remained stagnant. Phenotype characterization has recently emerged as an exciting area of informatics and machine learning. The copious amounts of diverse biomedical data that have been collected may be leveraged with data-driven approaches to elucidate trait-related features and patterns. Areas covered In this review, the authors discuss the phenotype in traditional genetic associations and the challenges this has imposed. The authors address approaches for phenotype refinement that can aid in the more accurate characterization of traits. Further, the authors highlight promising machine learning approaches for establishing a phenotype and the challenges of electronic health record (EHR) derived data. Expert Commentary The authors hypothesize that through unsupervised machine learning, data-driven approaches can be used to define phenotypes rather than relying on expert clinician knowledge, which may be inaccurate. Through the use of machine learning and an unbiased set of features extracted from clinical repositories, researchers will have the potential to further understand complex traits and identify patient subgroups. This knowledge may lead to more preventative and precise clinical care.

Dissecting the Genetics of Osteoporosis using Systems Approaches

“…For example, patterns that classify samples as healthy or diseased can be discerned in multi-omic datasets, facilitating the prediction of diseased individuals from input data, as well as identifying causal determinants of disease, leading to a deeper understanding of the biological networks underlying phenotypes [89]. Similarly, machine learning approaches can also be used to learn patterns in data that lead to the identification of more accurate phenotypes and biomarkers [90]. Deep learning approaches can even be used to predict genetic elements, such as enhancers, from genomic data [91].…”

High-throughput phenotyping with electronic medical record data using a common semi-supervised approach (PheCAP)

“…This goal contrasted with existing rule-based approaches which developed phenotype algorithms one at a time, using project-specific methodologies. It is also important to note that there are several other robust approaches using NLP or machine learning for phenotyping using EMR data [7][8][9][17][18][19] . In this protocol, we describe PheCAP as an option for investigators interested in using a standardized semisupervised input from the clinical expert as part of the approach for phenotyping.…”

Computational Phenotyping of Obstructive Airway Diseases: Protocol for A Systematic Review

“…Generally, disease phenotyping falls into two areas: hypothesis-led approach and data-driven or computational approach. The hypothesis-led phenotyping relies on classifying diseases on the basis of the characteristics of the presenting patient and the general framework has been to rely on the clinical or physiological features, based on speci c triggers and pathobiology of in ammation (11,13). As no standard exists in such classi cations, the clinician relies on the current knowledge of the disease and his own experiences and presumptions; consequently, the hypothesis-led approach is said to be largely subjective and may be potentially biased (14,15).…”

“…The advancement in machine-led computations and novel statistical methods in human diseases has facilitated the progress now being made in datadriven phenotyping of chronic obstructive airway diseases (17). Whilst the traditional clustering technique, like hierarchical clustering and partitioning methods, has remained the most frequently used conventional approach to disease phenotyping, several emerging machine-learning approaches, such as deep learning and probabilistic modelling, are providing advanced avor to the phenotyping exercises (18).…”