Johns Hopkins Kimmel Cancer Center researchers introduced plasmaCHORD, a machine learning approach intended to improve mutation identification accuracy from liquid biopsy samples. The tool is designed to enhance the precision of mutation calling in circulating blood-based assays, targeting common limitations in detecting genetic alterations from low-input specimens. The researchers said the model’s improved diagnostic performance could support clinical decision-making by strengthening the reliability of ctDNA findings for precision oncology. The work signals continued movement toward AI-enhanced analytics for liquid biopsy platforms, where data quality and interpretation remain key constraints. While the summary materials did not provide regulatory status or deployment timelines, the approach described positions plasmaCHORD as a potential step-change in how clinicians translate liquid biopsy results into actionable therapeutic selection.