AI Tool Detects Early Signs of Blood Mutations Linked to Cancer and Heart Disease

Deep inside the body, clusters of mutated blood cells can slowly form without symptoms, affecting about one in five older adults. This condition, known as clonal hematopoiesis of indeterminate potential (CHIP), increases the likelihood of leukemia more than tenfold and raises the risk of heart disease up to fourfold. Because it often goes undetected for years, finding CHIP earlier could allow for proactive monitoring or preventive care to reduce risk. Now, an artificial intelligence (AI) tool can find early signs of blood mutations linked to cancer and heart disease.

The AI tool called UNISOM—short for UNIfied SOmatic calling and Machine learning—has been developed by researchers at Mayo Clinic (Rochester, MN, USA) to identify CHIP-related mutations in standard genetic datasets. Unlike earlier methods that required advanced sequencing, this innovation allows clinicians and scientists to uncover subtle DNA changes using existing data, broadening research and potential clinical use.

UNISOM was evaluated in a study published in Genomics, Proteomics & Bioinformatics. The tool successfully detected nearly 80% of CHIP mutations using whole-exome sequencing, which focuses on protein-coding DNA. It also identified mutations present in fewer than 5% of blood cells when tested on whole-genome sequencing data from the Mayo Clinic Biobank, outperforming conventional techniques that often miss such small but significant changes.

By detecting CHIP at its earliest molecular stages, the approach offers a powerful new way to study disease progression and guide patient care. The researchers emphasized that integrating this tool into larger and more diverse datasets could strengthen predictions, enabling earlier detection of high-risk individuals and more precise treatment decisions in the clinic.

"We're engineering a path from genomic discovery to clinical decision-making," said Shulan Tian, Ph.D., the co-senior author and a bioinformatician at Mayo Clinic. "It's rewarding to help bring these discoveries closer to clinical care, where they can inform decisions and support more precise treatment."