2021
DOI: 10.1186/s13073-021-00965-0
|View full text |Cite
|
Sign up to set email alerts
|

Artificial intelligence enables comprehensive genome interpretation and nomination of candidate diagnoses for rare genetic diseases

Abstract: Background Clinical interpretation of genetic variants in the context of the patient’s phenotype is becoming the largest component of cost and time expenditure for genome-based diagnosis of rare genetic diseases. Artificial intelligence (AI) holds promise to greatly simplify and speed genome interpretation by integrating predictive methods with the growing knowledge of genetic disease. Here we assess the diagnostic performance of Fabric GEM, a new, AI-based, clinical decision support tool for e… Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
68
0
2

Year Published

2022
2022
2024
2024

Publication Types

Select...
7
1

Relationship

2
6

Authors

Journals

citations
Cited by 71 publications
(76 citation statements)
references
References 111 publications
0
68
0
2
Order By: Relevance
“…A multidisciplinary, collaborative approach exploring additional variants based on prior genotype-phenotype relationships helps maximise diagnostic yield from WGS [ 50 ]. Advances in clinical decision support tools, such as machine learning/artificial intelligence models, will also facilitate variant classification and accelerate rare disease diagnoses [ 51 , 52 ].…”
Section: Discussionmentioning
confidence: 99%
“…A multidisciplinary, collaborative approach exploring additional variants based on prior genotype-phenotype relationships helps maximise diagnostic yield from WGS [ 50 ]. Advances in clinical decision support tools, such as machine learning/artificial intelligence models, will also facilitate variant classification and accelerate rare disease diagnoses [ 51 , 52 ].…”
Section: Discussionmentioning
confidence: 99%
“…FABRIC GEM works as a complete variant prioritization platform and has been shown to perform better than other solutions such as VAAST [ 39 ], Phevor [ 40 ] and Exomizer [ 41 ]. It has also sped up the interpretation by reducing the time taken to clinically review pathogenic variants within genes by reducing the number of genes in review to an average of just two genes per case instead of tens of genes in the case of competing tools [ 9 , 42 ].…”
Section: Reanalysis Methodologies Using Machine Learningmentioning
confidence: 99%
“…Although the diagnostic rate has improved due to HTS, because of these challenges, there are vast troves of underexplored genomic datasets, leading to an expensive non-diagnosis and lack of actionable insights for patients. Therefore, more efforts are being made to solve previously unsolved rare diseases by reanalyzing previously generated sequencing data using new methodologies [ 9 , 10 ]. One of the first reanalysis studies showed an increase in diagnostic yield by 18% (absolute diagnostic yield increased from 25.4 to 31.4%) [ 11 ], indicating the possibility of gathering new insights into the underpinnings of rare diseases.…”
Section: Introductionmentioning
confidence: 99%
“…Our clinical dataset consisted of 293 probands who underwent rWGS at Rady Children’s Hospital in San Diego (RCHSD), 84 of which received a molecular diagnosis of Mendelian disorder. The diagnosed individuals represent a real-world population comprised of different Mendelian conditions resulting from diverse modes of disease inheritance and disease-causing genotypes 3,5,14 . To this cohort, we added every NICU admission at RCHSD in the year 2018.…”
Section: Methodsmentioning
confidence: 99%
“…Natural Language Processing (NLP) is a class of computational methods for generating structured data from unstructured free text. Recent work has begun to explore the utility of using Clinical Natural Language Processing technologies (CNLP) to automatically generate descriptions directly from clinical notes, with several groups demonstrating that rWGS diagnosis rates using CNLP derived descriptions can equal or exceed those obtained using manually compiled ones 12,14 . This is a significant step towards scalability and automation.…”
Section: Introductionmentioning
confidence: 99%