Machine learning algorithm brings long-read sequencing to the clinic
Peer-Reviewed Publication
This month, we’re focusing on artificial intelligence (AI), a topic that continues to capture attention everywhere. Here, you’ll find the latest research news, insights, and discoveries shaping how AI is being developed and used across the world.
Updates every hour. Last Updated: 6-Nov-2025 16:11 ET (6-Nov-2025 21:11 GMT/UTC)
SAVANA uses a machine learning algorithm to identify cancer-specific structural variations and copy number aberrations in long-read DNA sequencing data.
The complex structure of cancer genomes means that standard analysis tools give false-positive results, leading to erroneous clinical interpretations of tumour biology. SAVANA significantly reduces such errors.
SAVANA offers rapid and reliable genomic analysis to better analyse clinical samples, thereby informing cancer diagnosis and therapeutic interventions.
According to the National Center on Birth Defects and Developmental Disabilities, approximately 1 in 6 children in the United States have developmental disabilities which include physical, learning, language or behavior-related disabilities. Students with disabilities often receive accommodations (how students access and learn the same content as their classmates) at school, but teachers rarely explain them to typically-developing classmates. Children with disabilities are increasingly included in general education classrooms alongside typically-developing classmates. Accommodations such as an adult helper to work one-on-one with the student, preferential seating, or extra time to navigate the school between classes ensure the success of many children with disabilities in these settings. When teachers do not discuss accommodations or their purpose with typically-developing classmates, those classmates may have to make sense of the accommodations themselves. The findings showed that with increasing age, children evaluated disability-related accommodations as increasingly fair. Older children also demonstrated greater understanding of how specific accommodations help to address specific needs, which might account for why they judged accommodations as fairer. The research was featured in a new Child Development article with authors from Vanderbilt University, in the United States.
First-of-its-kind platform for molecular diagnostics shows exactly how AI-generated PCR results are achieved - delivering transparency, trust, and CE-IVDR compliance. Diagnostics.ai has launched the first CE-IVDR certified transparent AI platform for molecular diagnostics, aligned with the EU's May 26 regulatory deadline. Backed by over 15 years of experience processing millions of samples, the PCR.AI platform offers real-time model monitoring, per-test auditability and algorithm transparency, empowering laboratories to meet compliance demands with clinically proven >99.9% diagnostic accuracy. Now available to clinical labs and manufacturers across Europe.
Artificial intelligence isn’t always a reliable source of information: large language models (LLMs) like Llama and ChatGPT can be prone to “hallucinating” and inventing bogus facts. But what if AI could be used to detect mistaken or distorted claims, and help people find their way more confidently through a sea of potential distortions online and elsewhere?
Researchers at the Icahn School of Medicine at Mount Sinai have developed a machine learning tool that can help doctors manage blood sugar levels in patients recovering from heart surgery, a critical but often difficult task in the intensive care unit (ICU). The findings were reported in the May 27 online issue of NPJ Digital Medicine. After cardiac surgery, patients are at risk for both high and low blood sugar, which can lead to serious complications. Managing these fluctuations requires careful insulin dosing, but existing protocols often fall short due to the unpredictable nature of ICU care and differences among patients, say the investigators.
A multi-university team with heavy involvement from industry leaders plans to infuse artificial intelligence into the design process for radio frequency integrated circuits to reduce the difficulty of making these important chips.
Neurons deep in the brain not only help to initiate movement—they also actively suppress it, and with astonishing precision. This is the conclusion of a new study by researchers at the University of Basel and the Friedrich Miescher Institute for Biomedical Research (FMI), published in the journal “Nature”. The findings are especially relevant for better understanding neurological disorders such as Parkinson’s disease.