Abstract:More than 4,000 genes have been associated with recognizable Mendelian/monogenic diseases. When faced with a new diagnosis of a rare genetic disorder, health care providers increasingly turn to internet resources for information to understand the disease and direct care. Unfortunately, it can be challenging to find information concerning treatment for rare diseases as key details are scattered across a number of authoritative websites and numerous journal articles. The website and associated mobile device appl… Show more
“…2 , 3 , Supplementary Data 1 ). They were identified by a survey of our clinical rWGS experience in ~3500 cases, and from expanded newborn screening lists developed by several groups 2 – 7 , 10 – 16 , 18 , 28 , 63 – 67 . Fig.…”
While many genetic diseases have effective treatments, they frequently progress rapidly to severe morbidity or mortality if those treatments are not implemented immediately. Since front-line physicians frequently lack familiarity with these diseases, timely molecular diagnosis may not improve outcomes. Herein we describe Genome-to-Treatment, an automated, virtual system for genetic disease diagnosis and acute management guidance. Diagnosis is achieved in 13.5 h by expedited whole genome sequencing, with superior analytic performance for structural and copy number variants. An expert panel adjudicated the indications, contraindications, efficacy, and evidence-of-efficacy of 9911 drug, device, dietary, and surgical interventions for 563 severe, childhood, genetic diseases. The 421 (75%) diseases and 1527 (15%) effective interventions retained are integrated with 13 genetic disease information resources and appended to diagnostic reports (https://gtrx.radygenomiclab.com). This system provided correct diagnoses in four retrospectively and two prospectively tested infants. The Genome-to-Treatment system facilitates optimal outcomes in children with rapidly progressive genetic diseases.
“…2 , 3 , Supplementary Data 1 ). They were identified by a survey of our clinical rWGS experience in ~3500 cases, and from expanded newborn screening lists developed by several groups 2 – 7 , 10 – 16 , 18 , 28 , 63 – 67 . Fig.…”
While many genetic diseases have effective treatments, they frequently progress rapidly to severe morbidity or mortality if those treatments are not implemented immediately. Since front-line physicians frequently lack familiarity with these diseases, timely molecular diagnosis may not improve outcomes. Herein we describe Genome-to-Treatment, an automated, virtual system for genetic disease diagnosis and acute management guidance. Diagnosis is achieved in 13.5 h by expedited whole genome sequencing, with superior analytic performance for structural and copy number variants. An expert panel adjudicated the indications, contraindications, efficacy, and evidence-of-efficacy of 9911 drug, device, dietary, and surgical interventions for 563 severe, childhood, genetic diseases. The 421 (75%) diseases and 1527 (15%) effective interventions retained are integrated with 13 genetic disease information resources and appended to diagnostic reports (https://gtrx.radygenomiclab.com). This system provided correct diagnoses in four retrospectively and two prospectively tested infants. The Genome-to-Treatment system facilitates optimal outcomes in children with rapidly progressive genetic diseases.
“…These testing methods allow more precise diagnosis and have changed the approach to phenotyping ( Hennekam and Biesecker, 2012 ). However, access to these testing technologies is uneven, and it remains important to be able to quickly recognize patients who may be affected by certain conditions, especially those with near-term management implications ( Solomon et al, 2013 ; Bick et al, 2021 ). For example, people with WS are prone to infantile electrolyte abnormalities and immunologic dysfunction, and people with 22q may be affected by endocrine, immunologic, cardiovascular, and other sequelae that require immediate attention ( Campbell et al, 2018 ; Morris et al, 2020 ).…”
Background: In medical genetics, one application of neural networks is the diagnosis of genetic diseases based on images of patient faces. While these applications have been validated in the literature with primarily pediatric subjects, it is not known whether these applications can accurately diagnose patients across a lifespan. We aimed to extend previous works to determine whether age plays a factor in facial diagnosis as well as to explore other factors that may contribute to the overall diagnostic accuracy.Methods: To investigate this, we chose two relatively common conditions, Williams syndrome and 22q11.2 deletion syndrome. We built a neural network classifier trained on images of affected and unaffected individuals of different ages and compared classifier accuracy to clinical geneticists. We analyzed the results of saliency maps and the use of generative adversarial networks to boost accuracy.Results: Our classifier outperformed clinical geneticists at recognizing face images of these two conditions within each of the age groups (the performance varied between the age groups): 1) under 2 years old, 2) 2–9 years old, 3) 10–19 years old, 4) 20–34 years old, and 5) ≥35 years old. The overall accuracy improvement by our classifier over the clinical geneticists was 15.5 and 22.7% for Williams syndrome and 22q11.2 deletion syndrome, respectively. Additionally, comparison of saliency maps revealed that key facial features learned by the neural network differed with respect to age. Finally, joint training real images with multiple different types of fake images created by a generative adversarial network showed up to 3.25% accuracy gain in classification accuracy.Conclusion: The ability of clinical geneticists to diagnose these conditions is influenced by the age of the patient. Deep learning technologies such as our classifier can more accurately identify patients across the lifespan based on facial features. Saliency maps of computer vision reveal that the syndromic facial feature attributes change with the age of the patient. Modest improvements in the classifier accuracy were observed when joint training was carried out with both real and fake images. Our findings highlight the need for a greater focus on age as a confounder in facial diagnosis.
“…For ve patients in the TRANSLATE-NAMSE cohort a molecular diagnosis personalized treatments, or therapies directed against the mechanism of the disease could be initiated. 54 A patient with metachromatic leukodystrophy (MLD) due to pathogenic variants in arylsulfatase alpha (ARSA) was treated with autologous CD34 + cells that were transduced ex vivo using a lentiviral vector encoding ARSA 55 . The gene therapeutic approach with atidarsagene autotemcel has been authorized by EMA in the EU since 17 December 2020.…”
Most individuals with rare diseases first contact primary care physicians. Although efficient diagnostic routines exist for a subset of rare diseases, ultra-rare entities often require expert clinical knowledge or comprehensive genetic diagnostics, which poses structural challenges to public healthcare systems. To address these challenges, a novel structured diagnostic concept based on the presence of multidisciplinary expertise at centers for rare diseases (CRDs) that have been established at German university hospitals in recent years, was evaluated in a prospective study (TRANSLATE-NAMSE). Between January 2018 and December 2020, 5652 patients were enrolled in the study and were comprehensively assessed by multidisciplinary teams (MDTs) at ten CRDs. Exome sequencing (ES) was initiated for 268 adult and 1309 pediatric patients and partially complemented by additional molecular tests. Conclusive diagnoses were established in 494 individuals, covering 400 diagnostic-grade genes, suggesting ultra-rare disorders were enriched in this cohort. In addition, we describe 56 novel gene-phenotype associations, mainly in individuals with neurodevelopmental delay. A subcohort of 211 individuals was analyzed with the artificial intelligence–based PEDIA protocol, which integrates next-generation phenotyping on medical imaging and sequencing data. With the entire cohort data, we developed a tool to predict the diagnostic yield from the clinical features of a patient if advanced molecular testing strategies are applied.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
