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

2021 ◽  
Vol 13 (1) ◽  
Author(s):  
Francisco M. De La Vega ◽  
Shimul Chowdhury ◽  
Barry Moore ◽  
Erwin Frise ◽  
Jeanette McCarthy ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Candidate Genes ◽  
Language Processing ◽  
Genetic Disease ◽  
Genetic Diseases ◽  
Disease Diagnosis ◽  
Case Review ◽  
Genome Interpretation ◽  
Rare Genetic Diseases ◽  
New Findings

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 expediting genome interpretation. Methods We benchmarked GEM in a retrospective cohort of 119 probands, mostly NICU infants, diagnosed with rare genetic diseases, who received whole-genome or whole-exome sequencing (WGS, WES). We replicated our analyses in a separate cohort of 60 cases collected from five academic medical centers. For comparison, we also analyzed these cases with current state-of-the-art variant prioritization tools. Included in the comparisons were trio, duo, and singleton cases. Variants underpinning diagnoses spanned diverse modes of inheritance and types, including structural variants (SVs). Patient phenotypes were extracted from clinical notes by two means: manually and using an automated clinical natural language processing (CNLP) tool. Finally, 14 previously unsolved cases were reanalyzed. Results GEM ranked over 90% of the causal genes among the top or second candidate and prioritized for review a median of 3 candidate genes per case, using either manually curated or CNLP-derived phenotype descriptions. Ranking of trios and duos was unchanged when analyzed as singletons. In 17 of 20 cases with diagnostic SVs, GEM identified the causal SVs as the top candidate and in 19/20 within the top five, irrespective of whether SV calls were provided or inferred ab initio by GEM using its own internal SV detection algorithm. GEM showed similar performance in absence of parental genotypes. Analysis of 14 previously unsolved cases resulted in a novel finding for one case, candidates ultimately not advanced upon manual review for 3 cases, and no new findings for 10 cases. Conclusions GEM enabled diagnostic interpretation inclusive of all variant types through automated nomination of a very short list of candidate genes and disorders for final review and reporting. In combination with deep phenotyping by CNLP, GEM enables substantial automation of genetic disease diagnosis, potentially decreasing cost and expediting case review.

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

2021 ◽  
Author(s):  
Francisco M. De La Vega ◽  
Shimul Chowdhury ◽  
Barry Moore ◽  
Erwin Frise ◽  
Jeanette McCarthy ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Language Processing ◽  
Genetic Variants ◽  
Genetic Disease ◽  
Genetic Diseases ◽  
Disease Diagnosis ◽  
Case Review ◽  
Support Tool ◽  
Rare Genetic Diseases ◽  
New Findings

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 interpretation by comprehensively evaluating genetic variants for pathogenicity in the context of the growing knowledge of genetic disease. We assess the diagnostic performance of GEM, a new, AI-based, clinical decision support tool, compared with expert manual interpretation. We benchmarked GEM in a retrospective cohort of 119 probands, mostly NICU infants, diagnosed with rare genetic diseases, who received whole genome sequencing (WGS) at Rady Children's Hospital. We also performed a replication study in a separate cohort of 60 cases diagnosed at five additional academic medical centers. For comparison, we also analyzed these cases with commonly used variant prioritization tools (Phevor, Exomiser, and VAAST). Included in the comparisons were WGS and whole exome sequencing (WES) as trios, duos, and singletons. Variants underpinning diagnoses spanned diverse modes of inheritance and types, including structural variants (SVs). Patient phenotypes were extracted either manually or by automated clinical natural language processing (CNLP) from clinical notes. Finally, 14 previously unsolved cases were re-analyzed. GEM ranked >90% of causal genes among the top or second candidate, using manually curated or CNLP derived phenotypes, and prioritized a median of 3 genes for review per case. Ranking of trios and duos was unchanged when analyzed as singletons. In 17 of 20 cases with diagnostic SVs, GEM identified the causal SVs as the top or second candidate irrespective of whether SV calls where provided or inferred ab initio by GEM when absent. Analysis of 14 previously unsolved cases provided novel findings in one, candidates ultimately not advanced in 3, and no new findings in 10, demonstrating the utility of GEM for reanalysis. GEM enables automated diagnostic interpretation of WES and WGS for all types of variants, including SVs, nominating a very short list of candidate genes and disorders for final review and reporting. In combination with deep phenotyping by CNLP, GEM enables substantial automation of genetic disease diagnosis, potentially decreasing the cost and speeding case review.

scholarly journals New Diagnostic Approaches for Undiagnosed Rare Genetic Diseases

2020 ◽  
Vol 21 (1) ◽  
pp. 351-372 ◽  
Author(s):  
Taila Hartley ◽  
Gabrielle Lemire ◽  
Kristin D. Kernohan ◽  
Heather E. Howley ◽  
David R. Adams ◽  
...  
Keyword(s):  
Molecular Diagnosis ◽  
Genetic Disease ◽  
New Technologies ◽  
Genetic Diseases ◽  
Well Being ◽  
Accurate Diagnosis ◽  
Diagnostic Odyssey ◽  
Rare Genetic Disease ◽  
Rare Genetic Diseases ◽  
Diagnostic Approaches

Accurate diagnosis is the cornerstone of medicine; it is essential for informed care and promoting patient and family well-being. However, families with a rare genetic disease (RGD) often spend more than five years on a diagnostic odyssey of specialist visits and invasive testing that is lengthy, costly, and often futile, as 50% of patients do not receive a molecular diagnosis. The current diagnostic paradigm is not well designed for RGDs, especially for patients who remain undiagnosed after the initial set of investigations, and thus requires an expansion of approaches in the clinic. Leveraging opportunities to participate in research programs that utilize new technologies to understand RGDs is an important path forward for patients seeking a diagnosis. Given recent advancements in such technologies and international initiatives, the prospect of identifying a molecular diagnosis for all patients with RGDs has never been so attainable, but achieving this goal will require global cooperation at an unprecedented scale.

scholarly journals Barriers and Considerations for Diagnosing Rare Diseases in Indigenous Populations

2020 ◽  
Vol 8 ◽  
Author(s):  
Carla S. D'Angelo ◽  
Azure Hermes ◽  
Christopher R. McMaster ◽  
Elissa Prichep ◽  
Étienne Richer ◽  
...  
Keyword(s):  
Rare Disease ◽  
Genetic Diseases ◽  
Disease Diagnosis ◽  
Indigenous Populations ◽  
Genomic Research ◽  
Medical Attention ◽  
Genomic Technologies ◽  
Rare Genetic Diseases ◽  
Research Consortium ◽  
Multi Stakeholder

Advances in omics and specifically genomic technologies are increasingly transforming rare disease diagnosis. However, the benefits of these advances are disproportionately experienced within and between populations, with Indigenous populations frequently experiencing diagnostic and therapeutic inequities. The International Rare Disease Research Consortium (IRDiRC) multi-stakeholder partnership has been advancing toward the vision of all people living with a rare disease receiving an accurate diagnosis, care, and available therapy within 1 year of coming to medical attention. In order to further progress toward this vision, IRDiRC has created a taskforce to explore the access barriers to diagnosis of rare genetic diseases faced by Indigenous peoples, with a view of developing recommendations to overcome them. Herein, we provide an overview of the state of play of current barriers and considerations identified by the taskforce, to further stimulate awareness of these issues and the passage toward solutions. We focus on analyzing barriers to accessing genetic services, participating in genomic research, and other aspects such as concerns about data sharing, the handling of biospecimens, and the importance of capacity building.

scholarly journals RDmap: A Map for Exploring Rare Diseases

2021 ◽  
Author(s):  
Jian Yang ◽  
Cong Dong ◽  
Huilong Duan ◽  
Qiang Shu ◽  
Haomin Li
Keyword(s):  
Rare Disease ◽  
Rare Diseases ◽  
Genetic Diseases ◽  
Distance Matrix ◽  
Disease Diagnosis ◽  
Human Phenotype ◽  
Pathogenic Genes ◽  
Disease Information ◽  
Rare Genetic Diseases ◽  
Interactive Map

Abstract Background: The complexity of the phenotypic characteristics and molecular bases of many rare human genetic diseases makes the diagnosis of such diseases a challenge for clinicians. A map for visualizing, locating and navigating rare diseases based on similarity will help clinicians and researchers understand and easily explore these diseases. Methods: A distance matrix of rare diseases included in Orphanet was measured by calculating the quantitative distance among phenotypes and pathogenic genes based on Human Phenotype Ontology (HPO) and Gene Ontology (GO), and each disease was mapped into Euclidean space. A rare disease map, enhanced by clustering classes and disease information, was developed based on ECharts. Results: A rare disease map called RDmap was published at http://rdmap.nbscn.org. Total 3,287 rare diseases are included in the phenotype-based map, and 3,789 rare genetic diseases are included in the gene-based map; 1,718 overlapping diseases are connected between two maps. RDmap works similarly to the widely used Google Map service and supports zooming and panning. The phenotype similarity base disease location function performed better than traditional keyword searches in an in silico evaluation, and 20 published cases of rare diseases also demonstrated that RDmap can assist clinicians in seeking the rare disease diagnosis. Conclusion: RDmap is the first user-interactive map-style rare disease knowledgebase. It will help clinicians and researchers explore the increasingly complicated realm of rare genetic diseases.

scholarly journals RDmap: a map for exploring rare diseases

2021 ◽  
Vol 16 (1) ◽  
Author(s):  
Jian Yang ◽  
Cong Dong ◽  
Huilong Duan ◽  
Qiang Shu ◽  
Haomin Li
Keyword(s):  
Rare Disease ◽  
Rare Diseases ◽  
Genetic Diseases ◽  
Distance Matrix ◽  
Disease Diagnosis ◽  
Human Phenotype ◽  
Pathogenic Genes ◽  
Disease Information ◽  
Rare Genetic Diseases ◽  
Interactive Map

Abstract Background The complexity of the phenotypic characteristics and molecular bases of many rare human genetic diseases makes the diagnosis of such diseases a challenge for clinicians. A map for visualizing, locating and navigating rare diseases based on similarity will help clinicians and researchers understand and easily explore these diseases. Methods A distance matrix of rare diseases included in Orphanet was measured by calculating the quantitative distance among phenotypes and pathogenic genes based on Human Phenotype Ontology (HPO) and Gene Ontology (GO), and each disease was mapped into Euclidean space. A rare disease map, enhanced by clustering classes and disease information, was developed based on ECharts. Results A rare disease map called RDmap was published at http://rdmap.nbscn.org. Total 3287 rare diseases are included in the phenotype-based map, and 3789 rare genetic diseases are included in the gene-based map; 1718 overlapping diseases are connected between two maps. RDmap works similarly to the widely used Google Map service and supports zooming and panning. The phenotype similarity base disease location function performed better than traditional keyword searches in an in silico evaluation, and 20 published cases of rare diseases also demonstrated that RDmap can assist clinicians in seeking the rare disease diagnosis. Conclusion RDmap is the first user-interactive map-style rare disease knowledgebase. It will help clinicians and researchers explore the increasingly complicated realm of rare genetic diseases.

scholarly journals ClinPhen extracts and prioritizes patient phenotypes directly from medical records to accelerate genetic disease diagnosis

2018 ◽  
Author(s):  
Cole A. Deisseroth ◽  
Johannes Birgmeier ◽  
Ethan E. Bodle ◽  
Jonathan A. Bernstein ◽  
Gill Bejerano
Keyword(s):  
Genetic Disease ◽  
Medical Records ◽  
Genetic Diseases ◽  
Disease Diagnosis ◽  
High Accuracy ◽  
Substantial Contribution ◽  
Optimal Care ◽  
Gene Ranking ◽  
Clinical Notes ◽  
Diagnostic Odyssey

AbstractPurposeSevere genetic diseases affect 7 million births per year, worldwide. Diagnosing these diseases is necessary for optimal care, but it can involve the manual evaluation of hundreds of genetic variants per case, with many variants taking an hour to evaluate. Automatic gene-ranking approaches shorten this process by reporting which of the genes containing variants are most likely to be causing the patient’s symptoms. To use these tools, busy clinicians must manually encode patient phenotypes, which is a cumbersome and imprecise process. With 60 million patients expected to be sequenced in the next 7 years, a fast alternative to manual phenotype extraction from the clinical notes in patients’ medical records will become necessary.MethodsWe introduce ClinPhen: a fast, high-accuracy tool that automatically converts the clinical notes into a prioritized list of patient symptoms using HPO terms.ResultsClinPhen shows superior accuracy to existing phenotype extractors, and when paired with a gene-ranking tool it significantly improve the latter’s performance.ConclusionCompared to manual phenotype extraction, ClinPhen saves more than 5 hours per case in Mendelian diagnosis alone. Summing over millions of forthcoming cases whose medical notes await phenotype encoding, ClinPhen makes a substantial contribution towards ending all patients’ diagnostic odyssey.

scholarly journals Genetic disease in the family: trajectories and experiences in public health services

2020 ◽  
Vol 24 (1) ◽  
Author(s):  
Laura Helena Gerber Franciscatto ◽  
Mara Regina Santos da Silva ◽  
Alessandro Marques dos Santos ◽  
Adriane Maria Netto de Oliveira ◽  
Keterlin Salvador
Keyword(s):  
Health Services ◽  
Genetic Disease ◽  
Genetic Diseases ◽  
Disease Diagnosis ◽  
Northern Region ◽  
Public Health Services ◽  
Health Care Networks ◽  
Organization And Management ◽  
The Family ◽  
The Individual

Abstract Objective: To identify the trajectories and experiences of families of children with genetic diseases in health services. Method: A qualitative study, with data collected through interviews with 15 families and caregivers of children with Genetic Disease, living in the northern region of Rio Grande do Sul. Interviews were conducted from March to May 2018. Data analysis was based on thematic analysis. Results: A genetic disease diagnosis led to families' changes due to the demands of treatment, and also the needs of the child for being met by health services. To access specialized services, some families needed to travel to referral centers in larger cities. Families experienced difficulties such as unprepared health professionals, lack of organization of services, judicialization of resources, and need for structured Health Care Networks. Conclusion: The professional has the fundamental role of providing families with access to information and are responsible for decision making and for the organization and management of health and nursing services to meet the demands imposed on the individual and the family by the genetic disease.

scholarly journals The Road Map From Artificial Intelligence, Machine Learning, Deep Learning Techniques Towards Image Captioning System.

2021 ◽  
Author(s):  
revathi B. S. ◽  
A. Meena Kowshalya
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Deep Learning ◽  
Language Processing ◽  
Research Area ◽  
Language Models ◽  
Image Captioning ◽  
Road Map ◽  
New Findings ◽  
Visually Impaired Persons

Abstract Image Captioning is the process of generating textual descriptions of an image. These descriptions need to be syntactically and semantically correct. Image Captioning has potential advantages in many applications like image indexing techniques, devices for visually impaired persons, social media and several other natural language processing applications. Image Captioning is a popular research area where numerous scopes for new findings exist in preparation of datasets, generating language models, developing the models and evaluating the same. This paper extensively surveys very early literature that includes the advent of Artificial Intelligence, the Machine Learning pathway, the photography era, the early Deep Learning and the current Deep Learning methodology for image Captioning. This survey will definitely help novice researchers to understand the roadmap to current techniques.

scholarly journals Genetic and pharmacological causes of germline hypermutation

2021 ◽  
Author(s):  
Joanna Kaplanis ◽  
Benjamin Ide ◽  
Rashesh Sanghvi ◽  
Matthew Neville ◽  
Petr Danecek ◽  
...  
Keyword(s):  
Genetic Variation ◽  
Genetic Disease ◽  
De Novo ◽  
Genetic Diseases ◽  
Chemotherapeutic Agents ◽  
Single Nucleotide Variants ◽  
Mutational Signatures ◽  
Rare Genetic Diseases ◽  
Primary Determinant ◽  
Clinical Records

Mutation in the germline is the source of all evolutionary genetic variation and a cause of genetic disease. Previous studies have shown parental age to be the primary determinant of the number of new germline mutations seen in an individual's genome. Here we analysed the genome-wide sequences of 21,879 families with rare genetic diseases and identified 12 hypermutated individuals with between two and seven times more de novo single nucleotide variants (dnSNVs) than expected. In most of these families (9/12) the excess mutations could be attributed to the father. We determined that two of these families had genetic drivers of germline hypermutation, with the fathers carrying damaging genetic variation in known DNA repair genes, causing distinctive mutational signatures. For five families, by analysing clinical records and mutational signatures, we determined that paternal exposure to chemotherapeutic agents prior to conception was a key driver of hypermutation. Our results suggest that the germline is well protected from mutagenic effects, hypermutation is rare and relatively modest in degree and that most hypermutated individuals will not have a genetic disease.

Reports of the Workshops Held at the 2019 AAAI Conference on Artificial Intelligence

AI Magazine ◽  
2019 ◽  
Vol 40 (3) ◽  
pp. 67-78
Author(s):  
Guy Barash ◽  
Mauricio Castillo-Effen ◽  
Niyati Chhaya ◽  
Peter Clark ◽  
Huáscar Espinoza ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Language Processing ◽  
Cyber Security ◽  
Question Answering ◽  
Intent Recognition ◽  
Affective Content ◽  
Learning Plan ◽  
Dialog System ◽  
Affective Content Analysis ◽  
Games And Simulations

The workshop program of the Association for the Advancement of Artificial Intelligence’s 33rd Conference on Artificial Intelligence (AAAI-19) was held in Honolulu, Hawaii, on Sunday and Monday, January 27–28, 2019. There were fifteen workshops in the program: Affective Content Analysis: Modeling Affect-in-Action, Agile Robotics for Industrial Automation Competition, Artificial Intelligence for Cyber Security, Artificial Intelligence Safety, Dialog System Technology Challenge, Engineering Dependable and Secure Machine Learning Systems, Games and Simulations for Artificial Intelligence, Health Intelligence, Knowledge Extraction from Games, Network Interpretability for Deep Learning, Plan, Activity, and Intent Recognition, Reasoning and Learning for Human-Machine Dialogues, Reasoning for Complex Question Answering, Recommender Systems Meet Natural Language Processing, Reinforcement Learning in Games, and Reproducible AI. This report contains brief summaries of the all the workshops that were held.

Sign in / Sign up

Export Citation Format

Share Document