Applications of artificial intelligence in clinical laboratory genomics

Abstract

The transition from analog to digital technologies in clinical laboratory genomics is ushering in an era of “big data” in ways that will exceed human capacity to rapidly and reproducibly analyze those data using conventional approaches. Accurately evaluating complex molecular data to facilitate timely diagnosis and management of genomic disorders will require supportive artificial intelligence methods. These are already being introduced into clinical laboratory genomics to identify variants in DNA sequencing data, predict the effects of DNA variants on protein structure and function to inform clinical interpretation of pathogenicity, link phenotype ontologies to genetic variants identified through exome or genome sequencing to help clinicians reach diagnostic answers faster, correlate genomic data with tumor staging and treatment approaches, utilize natural language processing to identify critical published medical literature during analysis of genomic data, and use interactive chatbots to identify individuals who qualify for genetic testing or to provide pre‐test and post‐test education. With careful and ethical development and validation of artificial intelligence for clinical laboratory genomics, these advances are expected to significantly enhance the abilities of geneticists to translate complex data into clearly synthesized information for clinicians to use in managing the care of their patients at scale.

Rates and Classification of Variants of Uncertain Significance in Hereditary Disease Genetic Testing

“…As genetic testing increases, tracking VUSs across millions of individuals will require advanced computational methods, including those incorporating machine learning. Algorithms for evaluating variant effects with high prognostic values and quantitative approaches for scoring evidence types can enhance accuracy in classifying variants . Laboratories could also develop methods to highlight which additional evidence types might resolve VUSs and thereby guide clinicians on follow-up.…”

“…Algorithms for evaluating variant effects with high prognostic values and quantitative approaches for scoring evidence types can enhance accuracy in classifying variants. 37 Laboratories could also develop methods to highlight which additional evidence types might resolve VUSs and thereby guide clinicians on follow-up. Together, these approaches would accelerate the adoption of a quantitative system for variant classification, 38 enabling laboratories and clinicians to explain genetic testing results better to patients and resolve VUSs sooner.…”

Pathophysiology of human hearing loss associated with variants in myosins

“…From a technical point of view, more flexible approaches, such as artificial intelligence and machine learning, may be useful to handle large and often unformatted data. Artificial intelligence has already been introduced into clinical genomics laboratories and utilized to predict the pathogenicity and phenotypic consequence of variants ( Aradhya et al, 2023 ). With the ability to handle large data, these novel tools may assist hearing researchers to discover correlations between variants and phenotypes and to identify variants of high priority.…”

Rapid genomic sequencing for genetic disease diagnosis and therapy in intensive care units: a review

“…As URGS, RGS, and RES are implemented in NICUs without prior experience, such tools will be important in achievement of high diagnostic rates. With appropriate training, generative AI can also be used to alleviate the burden of pre- and post-test genetic counseling 167 , 168 . Further work is needed to define best practices for genetic counseling in high acuity settings.…”