New Machine Learning Framework Improves Respiratory Sound Classification Across Different Recording Conditions
Researchers have proposed QLung, a machine learning framework that adaptively adjusts training margins based on recording quality to classify respiratory sounds more accurately. The system derives a no-reference audio quality measure from spectral entropy and root-mean-square energy, scaling angular margins accordingly to handle noisy or low-quality recordings. The work addresses a key challenge in clinical AI: building models that generalize reliably across different recording environments and equipment.
QLung is a quality-adaptive angular-margin learning framework designed to improve the classification of respiratory sounds, such as those used in diagnosing lung conditions. The core innovation is a no-reference audio quality metric—computed from spectral entropy and RMS energy—that dynamically scales angular margins during training, penalizing the model more for errors on higher-quality recordings. The framework also introduces a log-scaled angular margin to stabilize training under severe class imbalance, a common problem in medical audio datasets. An angular classifier normalizes both features and class weights, ensuring consistent margin enforcement on the unit hypersphere. On the widely used ICBHI benchmark dataset, QLung achieves a 2.46% improvement over a cross-entropy baseline, and it outperforms prior state-of-the-art methods on the SPRSound out-of-distribution test set, suggesting stronger generalization. The paper has been accepted to Interspeech 2026, and code has been made publicly available.
What's missing
Limitations regarding dataset diversity, real-world deployment conditions, and computational cost of the quality estimation step are not discussed in the abstract.
What different sources said
- arXiv cs.AICenter
Quality Adaptive Angular Margin Learning for Respiratory Sound Classification
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.