Oklahoma City – September 16, 2026 -- Acarix AB announced that a peer-reviewed study published in PLOS Digital Health found its seismocardiography (SCG) technology can detect heart failure with diagnostic accuracy comparable to NT-proBNP, the current standard blood test, while producing significantly fewer false positives.
SCG algorithm matches blood test accuracy with far higher specificity
Researchers at Aalborg University Hospital, Aarhus University Hospital and Odense University Hospital enrolled 218 patients, including 198 referred by general practitioners for suspected heart failure and 20 with previously confirmed HFrEF. Using machine learning, the team built two SCG-based scores: an 'AnyHF-score' to flag heart failure of any type, and an 'HFrEF-score' targeting the more severe reduced-ejection-fraction form of the condition.
The HFrEF-score achieved 92.9% AUC versus 94.7% for NT-proBNP, with specificity of 92% compared to 68.8% for the blood test (p0.001) and a positive predictive value of 57.7% versus 27.1% (p=0.007). The AnyHF-score detected heart failure of any type with 90.9% sensitivity and an 87.5% negative predictive value.
Algorithm could cut unnecessary echocardiogram referrals by half
Among 139 patients referred for suspected heart failure who ultimately did not have the condition, the SCG-based scores classified 71 patients (51%) as "minimal risk,