Could hair predict pulmonary fibrosis?

Skin tissues and hair follicle cross-section.

Health care professionals may one day be able to diagnose pulmonary fibrosis and measure disease progression by analyzing a person’s hair. This is according to a recent proof-of-concept study published in Lung

Symptoms of pulmonary fibrosis can be ambiguous, frequently delaying detection and proper treatment. Typically, high-resolution CT scans are used to diagnose pulmonary fibrosis and frequent lung function tests are conducted to monitor development. Biopsies are the most accurate form of diagnosis, but they are intrusive and costly. 

In this study, a group of multidisciplinary researchers from the University of Louisville tested hair metabolites to find a noninvasive, effective method for identifying fibrotic lung disease. The team collected hair specimens from 56 patients with pulmonary fibrosis and 14 healthy patients, then extracted metabolites and analyzed them using advanced lab technology. Next, the scientists created a machine learning model that was tested and validated. They used this new method to classify patients with and without the disease and organize them by progression.

Study results were encouraging, with data that demonstrated the ability to diagnose pulmonary fibrosis with an average area under the receiver operating characteristic (AUROC)TRAIN of 0.888 and an AUROCTEST of 0.908. The key hair metabolites that were discovered to play a role in diagnosis were ornithine, 4-(methylnitrosamino)-1–3-pyridyl-N-oxide-1-butanol, Thr-Phe, desthiobiotin and proline.

The study also achieved an average AUROCTRAIN of 0.833 and an AUROCTEST of 0.799 when assessing stable versus progressing disease. The primary hair metabolites that correlated with progressive fibrosis were azelaic acid, Thr-Phe, Ala-Tyr, indoleacetyl glutamic acid and cytidine.

“Hair is composed mainly of fibrous proteins, melanin, water, lipids and minerals and provides a highly stable structure that retains endogenous metabolites for long term, providing a useful biological matrix in forensics analyses,” the researchers said. “Since hair has been shown to reflect the serum metabolome over time, it is unsurprising that some amino acids detected in this study are consistent with metabolites previously implicated in ILD [interstitial lung disease].”

Limitations of the study included small sample size and data usage from a single clinic. The researchers summarized that the exploratory study suggested correlations between the hair metabolites’ ability to predict the disease and prognosis but failed to establish causation. It does provide preliminary hypotheses for further research. 

“The use of machine learning to predict the importance of biomarkers and their role in pulmonary fibrosis clinical outcomes is still a relatively unexplored field,” the researchers said. “This proof-of-concept study reveals a novel approach for detection of molecular signatures characteristic of pulmonary fibrosis.”

More in Pulmonary
Page 1 of 16
Next Page