Artificial intelligence (AI) has enabled researchers to intercept microbial messages bearing clinically useful information about of a variety of respiratory disorders. The organisms that comprise our microbiome communicate via the release of tiny, biomolecule-laden membrane bubbles called ‘extracellular vesicles’ (EVs) into the bloodstream. EVs are also influenced by human disease. South Korean researchers led by Yoon-Keun Kim of MD Healthcare, Seoul, and Young-Koo Jee of Dankook University College of Medicine, Cheonan, have used an AI algorithm to assemble EV-based profiles that can discriminate between healthy people and those with conditions like asthma or lung cancer. Their analysis of 1727 patient serum samples revealed microbial signatures that enabled accurate diagnosis of several respiratory disorders. Preliminary experiments in mice suggest that certain dietary changes could help shift the microbiome of high-risk individuals towards a healthier profile.