Asthma is a common disease that affects people of all ages; however, it remains underdiagnosed. Researchers have recently identified a genetic biomarker of asthma that can be tested for using a nasal brush and basic follow-up data analysis.
in Scientific Reports
applied machine learning algorithms to the genetic (RNA) data retrieved from nasal brushes of patients with and without asthma. This collection of data resulted in the identification of a 90-gene biomarker of a patient’s asthma status.
“Mild to moderate asthma can be difficult to diagnose because symptoms change over time and can be complicated by other respiratory conditions,” Supinda Bunyavanich, MD, physician and researcher at the Icahn School of Medicine said in a statement
. “Our nasal brush test takes seconds to collect. For time-strapped clinicians, particularly primary care providers at the front lines of asthma diagnosis, this could greatly improve patient outcomes through early and accurate diagnosis.”
According to the study, the 90-gene classifier performed with strong predictive value and sensitivity during 8 test sets including:
- A test set of independent asthmatic and control subjects profiled by RNA sequencing
- Independent case-control cohorts of asthma profiled by microarray
- Five cohorts with other respiratory conditions (allergic rhinitis, upper respiratory infection, cystic fibrosis, smoking) where the classifier had a low to zero misclassification rate
One of the most exciting components of this study is demonstrating the power of machine learning when applied to biomedical data,” said Gaurav Pandey, PhD, who led data science efforts to develop the biomarker. “We have the power of many insights we didn’t have in the past, and that opens a window to an entirely new world of diagnostic tools and treatments.”
Other similar genetic biomarker tests are already being used in other disease areas, such as MammaPrint and Oncotype DX, which is used for certain types of breast cancer prognosis. These tests demonstrate the positive impact biomarkers have and set the example for further diagnostic tools based on the use and identification of biomarkers.
Specifically, this study’s use of the nasal brush-based classifier acts as the first step to future nasal biomarkers for asthma care. The researchers emphasized how this may lead to the development of a nasal biomarker that can predict endotypes and treatment response so that every asthma treatment can be specifically targeted and personalized.
“We’re hopeful that further studies can help bring this test into primary care settings, transforming the ease and accuracy of diagnosing asthma and our ability as doctors to appropriately treat our patients,” concluded Bunyavanich.
Pandey G, Pandey OP, Rogers AJ, et al. A nasal brush-based classified of asthma identified by machine learning analysis of nasal RNA sequence data. [published online June 18, 2018]. Sci Rep
. doi: 10.1038/s41598-018-27189-4.