BCG-FM: New Foundation Model Enables Contactless Cardiac Health Monitoring Through Bed Sensors
Researchers have introduced BCG-FM, the first foundation model trained on ambient mechanical biosignals captured passively by a piezoelectric sensor embedded in a bed surface. The model was pretrained on 2.75 million hours of nightly ballistocardiography (BCG) recordings from nearly 146,000 individuals, making it the largest raw-waveform biosignal pretraining corpus to date. The work is significant because it demonstrates that health-relevant AI models can be built from signals requiring no deliberate user action, potentially lowering barriers to continuous cardiac monitoring.
BCG-FM is a foundation model designed for ballistocardiography, a technique that measures the mechanical forces produced by the heartbeat and recorded passively through a sensor embedded in a bed. Unlike existing wearable biosignal models that require users to wear a device or visit a clinical setting, BCG-FM operates entirely in the background during normal sleep. The model was pretrained using participant-level contrastive learning on 2.75 million hours of nightly recordings from 145,985 individuals. Frozen embeddings from the pretrained model achieved a mean absolute error of 3.26 years on biological age estimation, the lowest reported for any ambient or contactless modality. The model also demonstrated clinically relevant discrimination across 15 self-reported health conditions and generalized to three independent external cohorts. Notably, representations derived from just 500 labeled participants outperformed a fully supervised baseline trained on 3,372, and model quality scaled log-linearly with contrastive batch size. The authors argue these results establish ambient, longitudinal mechanical biosignals as a viable and underexplored modality for health foundation models.
What's missing
As a preprint, BCG-FM has not yet undergone peer review. Key limitations not fully addressed include: whether the 15 health conditions were validated against clinical diagnoses or relied solely on self-report, the demographic composition and geographic diversity of the 145,985-person training cohort, and whether the bed-sensor hardware is commercially available or standardized across study sites. Long-term longitudinal performance and real-world deployment considerations (e.g., sensor drift, varying sleep environments) are also not discussed.
What different sources said
- arXiv cs.AICenter
BCG-FM: A Foundation Model for Ambient Cardiac Health Sensing
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.