Phenotype driven molecular genetic test recommendation for diagnosing pediatric rare disorders
Open Access
- 21 November 2024
- journal article
- research article
- Published by Springer Nature in npj Digital Medicine
- Vol. 7 (1) , 1-12
Abstract
Patients with rare diseases often experience prolonged diagnostic delays. Ordering appropriate genetic tests is crucial yet challenging, especially for general pediatricians without genetic expertise. Recent American College of Medical Genetics (ACMG) guidelines embrace early use of exome sequencing (ES) or genome sequencing (GS) for conditions like congenital anomalies or developmental delays while still recommend gene panels for patients exhibiting strong manifestations of a specific disease. Recognizing the difficulty in navigating these options, we developed a machine learning model trained on 1005 patient records from Columbia University Irving Medical Center to recommend appropriate genetic tests based on the phenotype information. The model achieved a remarkable performance with an AUROC of 0.823 and AUPRC of 0.918, aligning closely with decisions made by genetic specialists, and demonstrated strong generalizability (AUROC:0.77, AUPRC: 0.816) in an external cohort, indicating its potential value for general pediatricians to expedite rare disease diagnosis by enhancing genetic test ordering.Keywords
All Related Versions
Funding Information
- U.S. Department of Health & Human Services | NIH | National Human Genome Research Institute (R01HG012655, R01HG012655)
- U.S. Department of Health & Human Services | NIH | National Center for Advancing Translational Sciences (UL1TR001873, UL1TR001873)
This publication has 62 references indexed in Scilit:
- Clinical whole-exome sequencing: are we there yet?Genetics in Medicine, 2014
- Systematic comparison of phenome-wide association study of electronic medical record data and genome-wide association study dataNature Biotechnology, 2013
- Genetic medicine and incidental findings: it is more complicated than deciding whether to disclose or notGenetics in Medicine, 2013
- Improved exome prioritization of disease genes through cross-species phenotype comparisonGenome Research, 2013
- Relationship Between Nursing Documentation and Patients' MortalityAmerican Journal of Critical Care, 2013
- “Reading between the lines” of flow sheet data: nurses' optional documentation associated with cardiac arrest outcomesApplied Nursing Research, 2012
- Implementing the Learning Health System: From Concept to ActionAnnals of Internal Medicine, 2012
- “I'm fine; I'm just waiting for my disease”Neurology, 2011
- The Human Phenotype Ontology: A Tool for Annotating and Analyzing Human Hereditary DiseaseThe American Journal of Human Genetics, 2008
- McKusick's Online Mendelian Inheritance in Man (OMIM(R))Nucleic Acids Research, 2008