Automated programs can identify which sick infants in a neonatal intensive care unit (NICU) have sepsis hours before clinicians recognize the life-threatening condition. A team of data researchers and physician-scientists tested machine-learning models in a NICU population, drawing only on routinely collected data available in electronic health records (EHRs).
The human genome contains approximately 20,000 genes, and exome analysis focuses on about 7,000 genes known in medical literature to be clinically associated with a disease. Currently, up to 70 percent of exome test reports are negative or inconclusive. But suppose at a later date a researcher discovers a gene that could be causative of the disease?