Diagnosis of genetic diseases in seriously ill children by rapid whole-genome sequencing and automated phenotyping and interpretation

Automated phenotyping and interpretation of rapid whole-genome sequencing improve time to diagnosis of genetic diseases in hospitalized children. A streamlined genetic diagnosis pipeline When treating seriously ill children, time is of the essence. Clark et al. built an automated pipeline to analyze EHR data and genome sequencing data from dried blood spots to deliver a potential diagnosis for hospitalized, often critically ill, children with suspected genetic diseases. Their pipeline required minimal user intervention, increasing usability and shortening time to diagnosis, delivering a provisional finding in a median time of less than 24 hours. Although this pipeline would need to be adapted for use at different hospital systems, such an automated tool could aid clinicians to expedite an accurate genetic disease diagnosis, potentially hastening lifesaving changes to patient care. By informing timely targeted treatments, rapid whole-genome sequencing can improve the outcomes of seriously ill children with genetic diseases, particularly infants in neonatal and pediatric intensive care units (ICUs). The need for highly qualified professionals to decipher results, however, precludes widespread implementation. We describe a platform for population-scale, provisional diagnosis of genetic diseases with automated phenotyping and interpretation. Genome sequencing was expedited by bead-based genome library preparation directly from blood samples and sequencing of paired 100-nt reads in 15.5 hours. Clinical natural language processing (CNLP) automatically extracted children’s deep phenomes from electronic health records with 80% precision and 93% recall. In 101 children with 105 genetic diseases, a mean of 4.3 CNLP-extracted phenotypic features matched the expected phenotypic features of those diseases, compared with a match of 0.9 phenotypic features used in manual interpretation. We automated provisional diagnosis by combining the ranking of the similarity of a patient’s CNLP phenome with respect to the expected phenotypic features of all genetic diseases, together with the ranking of the pathogenicity of all of the patient’s genomic variants. Automated, retrospective diagnoses concurred well with expert manual interpretation (97% recall and 99% precision in 95 children with 97 genetic diseases). Prospectively, our platform correctly diagnosed three of seven seriously ill ICU infants (100% precision and recall) with a mean time saving of 22:19 hours. In each case, the diagnosis affected treatment. Genome sequencing with automated phenotyping and interpretation in a median of 20:10 hours may increase adoption in ICUs and, thereby, timely implementation of precise treatments.