AMELIE 3: Fully Automated Mendelian Patient Reanalysis at Under 1 Alert per Patient per Year

Abstract

BackgroundMany thousands of patients with a suspected Mendelian disease have their exomes/genomes sequenced every year, but only about 30% receive a definitive diagnosis. Since a novel Mendelian gene-disease association is published on average every business day, thousands of undiagnosed patient cases could receive a diagnosis each year if their genomes were regularly compared to the latest literature. With millions of genomes expected to be sequenced for rare disease analysis by 2025, and considering the current publication rate of 1.1 million new articles per annum in PubMed, manually reanalyzing the growing cases of undiagnosed patients is not sustainable.MethodsWe describe a fully automated reanalysis framework for patients with suspected, but undiagnosed, Mendelian disorders. The presented framework was tested by automatically parsing all ∼100,000 newly published peer reviewed papers every month and matching them on genotype and phenotype with all stored undiagnosed patients. If a new article contains a possible diagnosis for an undiagnosed patient, the system provides notification. We test the accuracy of the automatic reanalysis system on 110 patients, including 61 with available trio data.ResultsEven when trained only on older data, our system identifies 80% of reanalysis diagnoses, while sending only 0.5-1 alerts per patient per year, a 100-1,000-fold efficiency gain over manual literature surveillance of equivalent yield.ConclusionWe show that automatic reanalysis of patients with suspected Mendelian disease is feasible and has the potential to greatly streamline diagnosis. Our system is not intended to replace clinical judgment. Rather, clinical diagnostic services could greatly benefit from a modest re-allocation of time from manual literature exploration to review of automated reanalysis alerts. Our system additionally supports a new paradigm for medical IT systems: proactive, continuously learning and consequently able to autonomously identify valuable insights as they emerge in digital health records. We have launched automated patient reanalysis, trained on the latest data, with user accounts and daily literature updates at https://AMELIE.stanford.edu.

Applying Machine Learning on UK Biobank biomarker data empowers case-control discovery yield

“…By using quantitative PheWAS results from Wang et al 2021 2 , we were able to further disentangle 949 gene-disease associations possibly dominated by the most predictive feature learnt by MILTON per disease. Moreover, our nominally significant (p<0.05) and putative novel associations (p<1x10 -8 ) were preferentially enriched among Mantis-ML 39,40 and AMELIE 42,43 predicted gene-disease associations, as two independent sources of additional evidence.…”

“…As an additional assessment, we performed an automated literature search using AMELIE 42,43 (version 3.1.0), integrating nightly updates from the entire PubMED corpus, to estimate gene rankings for disease causality among a candidate gene pool. As part of the evaluation process, AMELIE requires diseases to be organised within the Human Phenotype Ontology (HPO).…”

Evaluation of a whole‐exome sequencing pipeline and benchmarking of causal germline variant prioritizers

“…Its algorithm and the type of WES data of our study could underlie this discrepancy by preventing causal genes to rank in the top positions in our results. Recent studies by Birgmeier et al (2020, 2021) testing a set of empirical WES data from patients with diagnosed developmental disorders report AMELIE demonstrating a 66% rate of correct causal variant ranking. This is a considerably higher estimate compared to our calculation of 47.5% (95% CI: 34.6–60.7).…”

Clinical Exome Reanalysis: Current Practice and Beyond

“…For the purpose of reevaluation of genomic data, AI may draw associations between phenotype and genotype data, as well as knowledge from genomic databases and updated publications, and therefore be able to generate a potential genetic diagnosis. Such methods are already in development, though, to our knowledge, none are part of routine clinical testing workflows [ 35 ]. Ultimately, an AI-based system may have the potential to improve the performance and work efficiency in exome reanalysis.…”