Multi-omics AI model boosts preterm birth prediction accuracy to nearly 90%
Peer-Reviewed Publication
Updates every hour. Last Updated: 13-Jan-2026 14:12 ET (13-Jan-2026 19:12 GMT/UTC)
A recent study developed a highly accurate risk prediction framework for preterm birth (PTB) that could broaden the potential of AI-driven multi-omics applications in precision obstetrics and biomedical research.
The model, deeply integrating genomics, transcriptomics, and large language models (LLMs) for the first time for PTB risk prediction, has shown its effectiveness and clinical application prospects.
The research was conducted by a collaborative team led by BGI Genomics, together with Professor Huang Hefeng's team, Shenzhen Longgang Maternal and Child Health Hospital, Fujian Maternity and Child Health Hospital, and OxTium Technology. The research was published in npj Digital Medicine on August 20th.
The non-coding genome, once dismissed as "junk DNA", is now recognized as a fundamental regulator of gene expression and a key player in understanding complex diseases. Following the landmark achievements of the Human Genome Project (HGP), scientists have increasingly focused on deciphering the non-coding regions of the human genome, which comprise approximately 98% of the genetic material. These regions, long overlooked due to their non-protein-coding nature, are now known to harbor regulatory elements crucial for cell function and disease progression.
Prostate cancer remains a global health challenge, ranking as the second most common malignancy among men. While early-stage disease can be effectively managed, advanced forms—particularly metastatic castration-resistant prostate cancer (mCRPC)—pose significant therapeutic hurdles. A growing body of evidence highlights the pivotal role of SOX transcription factors, with SOX2 emerging as a central driver in tumor growth, spread, and resistance to therapy.
Air pollution from oil and gas is causing 91,000 premature deaths and hundreds of thousands of health issues across the United States annually, with Black, Asian, Native American and Hispanic groups consistently the most affected, finds a major new study led by researchers at UCL and the Stockholm Environment Institute (SEI).
While 42 states require public school students to take a sexual education course that covers at least one topic within this subject between kindergarten and high school, only 19 states mandate that this instruction be medically accurate—and 5 of those states only require medical accuracy for specific topics, according to a new study in the American Journal of Public Health. The study also found that 34 states that mandate sexual education in public schools require instruction on abstinence, a method that has consistently proven to be ineffective or harmful to adolescent sexual health, but continues to be embraced and funded by the federal government. Thirty-four states also allow parents to opt their children out of receiving any sexual education instruction, while five states require parents to opt in for their children to receive this instruction.