New Machine Learning Method Improves Analysis of Rare Disease Data in Electronic Health Records
Researchers have proposed a spectral-based unsupervised learning method to extract meaningful low-dimensional representations of clinical concepts and patients from electronic health records in rare disease cohorts. The approach addresses the core challenge of rare disease data — high dimensionality combined with small sample sizes — by borrowing structured information from larger, related patient populations. The method could improve downstream clinical analyses and machine learning tasks for conditions where data scarcity has historically limited model performance.
A new machine learning framework described in a preprint submitted to arXiv aims to improve how clinical data from rare disease patients is represented computationally. The method uses spectral embedding — a technique that reduces high-dimensional data to lower-dimensional structures — and augments it with a 'knowledge matrix' derived from a broader, more data-rich patient population that partially overlaps with the rare disease cohort. Crucially, the approach relaxes a common assumption in prior work that signals in the target and source datasets must align one-to-one, instead allowing for more flexible, partial sharing of structure. A two-step procedure first filters out irrelevant components from the external knowledge source, then separately recovers shared and disease-specific signals. Validation through simulations and a real-world multiple sclerosis cohort demonstrated that the method outperformed competing approaches, especially when shared signals between populations were weak or only partially aligned — conditions typical of rare disease settings.
What's missing
The study is a preprint and has not yet undergone peer review. Key open questions include how the method performs across a wider range of rare diseases beyond multiple sclerosis, how sensitive results are to the choice of the external knowledge population, and whether the approach scales to very large EHR systems with heterogeneous data quality.
What different sources said
- arXiv cs.LGCenter
Enhancing Spectral Embedding through Robust and Flexible Knowledge Transfer in Electronic Health Records
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.