Phenotype driven molecular genetic test recommendation for diagnosing pediatric rare disorders

Fangyi Chen; Priyanka Ahimaz; Quan M Nguyen; Rachel Lewis; Wendy K Chung; Casey N Ta; Katherine M Szigety; Sarah E Sheppard; Ian M Campbell; Kai Wang; Chunhua Weng; Cong Liu

doi:10.1038/s41746-024-01331-1

Phenotype driven molecular genetic test recommendation for diagnosing pediatric rare disorders

NPJ Digit Med. 2024 Nov 21;7(1):333. doi: 10.1038/s41746-024-01331-1.

Authors

Fangyi Chen¹, Priyanka Ahimaz^{2

3}, Quan M Nguyen^{4

5}, Rachel Lewis², Wendy K Chung⁶, Casey N Ta¹, Katherine M Szigety⁷, Sarah E Sheppard⁷, Ian M Campbell⁷, Kai Wang⁴, Chunhua Weng^#⁸, Cong Liu^#⁹

Affiliations

¹ Department of Biomedical Informatics, Columbia University, New York, NY, USA.
² Department of Pediatrics, Columbia University, New York, NY, USA.
³ Institute of Genomic Medicine, Columbia University, New York, NY, USA.
⁴ Raymond G. Perelman Center for Cellular and Molecular Therapeutics, Children's Hospital of Philadelphia, Philadelphia, PA, USA.
⁵ Department of Bioengineering, University of Pennsylvania, Philadelphia, PA, USA.
⁶ Division of Genetics and Genomics, Department of Pediatrics, Boston Children's Hospital, Harvard Medical School, Boston, MA, USA.
⁷ Division of Human Genetics, Department of Pediatrics, Children's Hospital of Philadelphia, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA.
⁸ Department of Biomedical Informatics, Columbia University, New York, NY, USA. [email protected].
⁹ Division of Genetics and Genomics, Department of Pediatrics, Boston Children's Hospital, Harvard Medical School, Boston, MA, USA. [email protected].

^# Contributed equally.

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.

Abstract

Grants and funding