首页 | 本学科首页   官方微博 | 高级检索  
     


Phenotype based prediction of exome sequencing outcome using machine learning for neurodevelopmental disorders
Authors:Alexander J.M. Dingemans  Max Hinne  Sandra Jansen  Jeroen van Reeuwijk  Nicole de Leeuw  Rolph Pfundt  Bregje W. van Bon  Anneke T. Vulto-van Silfhout  Tjitske Kleefstra  David A. Koolen  Marcel A.J. van Gerven  Lisenka E.L.M. Vissers  Bert B.A. de Vries
Affiliation:1. Department of Human Genetics, Donders Institute for Brain, Cognition and Behaviour, Radboud University Medical Center, Radboud University, Nijmegen, The Netherlands;2. Department of Artificial Intelligence, Faculty of Social Sciences, Donders Institute for Brain, Cognition and Behaviour, Radboud University Medical Center, Radboud University, Nijmegen, The Netherlands;1. Spectrum Health Helen DeVos Children’s Hospital, Grand Rapids, MI;2. Department of Pediatrics and Human Development, Michigan State University College of Human Medicine, Grand Rapids, MI;3. Center for Bioethics, University of South Carolina, Columbia, SC;4. Department of Social Sciences and Health Policy, Wake Forest School of Medicine, Winston-Salem, NC;5. Wake Forest Institute for Regenerative Medicine, Wake Forest School of Medicine, Winston-Salem, NC;6. Center for Bioethics, Health, and Society, Wake Forest University, Winston-Salem, NC;7. Division of Medical Genetics, Department of Pediatrics, Stanford Medicine, Stanford University, Stanford, CA;8. The Jackson Laboratory for Genomic Medicine, Farmington, CT;9. Invitae Corporation, San Francisco, CA;10. Mountain States Regional Genetics Network, Austin, TX;11. American College of Medical Genetics and Genomics, Bethesda, MD;1. School of Medicine Greenville, University of South Carolina, Greenville, SC;2. Center for Bioethics, University of South Carolina, Columbia, SC;3. Montefiore Medical Center, Albert Einstein College of Medicine, Bronx, NY;4. Vanderbilt University Medical Center, Nashville, TN;5. Phoenix Children’s Hospital, College of Medicine, The University of Arizona, Phoenix, AZ;6. Optum, Eden Prairie, MN;7. Color Genomics, Burlingame, CA;8. Patient Advocate, Greenville, SC;9. GeneDx, Gaithersburg, MD;10. Homer Stryker M.D. School of Medicine, Western Michigan University, Kalamazoo, MI;11. Divisions of Medical Genetics and Molecular Diagnostics, Departments of Pathology & Laboratory Medicine, Pediatrics, and Human Genetics, UCLA School of Medicine, Los Angeles, CA;12. The UCLA Institute for Society and Genetics, Los Angeles, CA;13. American College of Medical Genetics and Genomics, Bethesda, MD;1. Waisman Center, University of Wisconsin-Madison, Madison, WI;2. Department of Biostatistics and Bioinformatics, Duke University School of Medicine, Durham, NC;1. Department of Medical Genetics, School of Clinical Medicine, University of Cambridge, Cambridge, United Kingdom;2. Department of Endocrinology and Diabetes, Birmingham Children''s Hospital, Birmingham Women''s and Children''s NHS Foundation Trust, Birmingham, United Kingdom;3. Institute of Metabolism and Systems Research, College of Medical and Dental Sciences, University of Birmingham, Birmingham, United Kingdom;4. MRC Epidemiology Unit, Institute of Metabolic Science, University of Cambridge School of Clinical Medicine, Cambridge, United Kingdom;5. Department of Paediatrics, School of Clinical Medicine, University of Cambridge, Cambridge, United Kingdom;6. West Midlands Regional Clinical Genetics Service and Birmingham Health Partners, Birmingham Women’s and Children’s NHS Foundation Trust, Birmingham, United Kingdom;7. London North West Regional Genetics Service, St. Mark’s and Northwick Park hospitals, Harrow, Middlesex, United Kingdom;8. Biocruces Bizkaia Health Research Institute, Hospital Universitario Cruces, CIBERDEM, CIBERER, Endo-ERN, University of the Basque Country (UPV-EHU), Bizkaia, Spain;9. Stratified Medicine Core Laboratory NGS Hub, Department of Medical Genetics, University of Cambridge, Cambridge, United Kingdom;10. The Alan Turing Institute, London, United Kingdom;11. MRC Biostatistics Unit, School of Clinical Medicine, University of Cambridge, Cambridge, United Kingdom;12. Cambridge University Hospitals NHS Foundation Trust, Cambridge, United Kingdom;1. National Heart and Lung Institute, Faculty of Medicine, Imperial College London, London, United Kingdom;2. Royal Brompton and Harefield Hospitals, Guy’s and St. Thomas’ NHS Foundation Trust, London, United Kingdom;3. British Heart Foundation Research Accelerator, and Institute of Health Informatics, University College London, London, United Kingdom;4. MRC London Institute of Medical Sciences, Imperial College London, London, United Kingdom;5. Wellcome Centre for Human Genetics, Nuffield Department of Medicine, University of Oxford, Oxford, United Kingdom;6. Bart’s Heart Centre, Barts Health NHS Trust, St. Bartholomew’s Hospital, London, United Kingdom;1. Department of Optometry and Vision Sciences, Melbourne School of Health Sciences, Faculty of Medicine, Dentistry and Health Sciences, University of Melbourne, Parkville, Victoria, Australia;2. Department of Surgery (Ophthalmology), Melbourne Medical School, Faculty of Medicine, Dentistry and Health Sciences, University of Melbourne, Parkville, Victoria, Australia;3. Centre for Eye Research Australia, Royal Victorian Eye and Ear Hospital, Melbourne, Victoria, Australia
Abstract:
PurposeAlthough the introduction of exome sequencing (ES) has led to the diagnosis of a significant portion of patients with neurodevelopmental disorders (NDDs), the diagnostic yield in actual clinical practice has remained stable at approximately 30%. We hypothesized that improving the selection of patients to test on the basis of their phenotypic presentation will increase diagnostic yield and therefore reduce unnecessary genetic testing.MethodsWe tested 4 machine learning methods and developed PredWES from these: a statistical model predicting the probability of a positive ES result solely on the basis of the phenotype of the patient.ResultsWe first trained the tool on 1663 patients with NDDs and subsequently showed that diagnostic ES on the top 10% of patients with the highest probability of a positive ES result would provide a diagnostic yield of 56%, leading to a notable 114% increase. Inspection of our model revealed that for patients with NDDs, comorbid abnormal (lower) muscle tone and microcephaly positively correlated with a conclusive ES diagnosis, whereas autism was negatively associated with a molecular diagnosis.ConclusionIn conclusion, PredWES allows prioritizing patients with NDDs eligible for diagnostic ES on the basis of their phenotypic presentation to increase the diagnostic yield, making a more efficient use of health care resources.
Keywords:Artificial intelligence  Clinical genomics  Exome sequencing  Intellectual disability  Machine learning
本文献已被 ScienceDirect 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号