Heart failure event detection using multi-level categorical fusion

Abstract

Systems and methods for detecting a present, or predicting a future, target physiologic event such as worsening heart failure (HF) are described. A system can comprise a patient information receiver circuit, at least two categorical risk analyzer circuits, and a categorical fusion circuit. The patient information receiver circuit receives physiologic signals and generates signal trends. The categorical risk analyzer circuit receives a category-specific input selected from the signal trends according to an associative physiologic condition indicative or correlative of the target event. The categorical risk analyzer circuit produces a signal trend metric indicating relative change in signal strength over time. The categorical risk analyzer circuit calculates a categorical risk index that indicates likelihood of the patient developing or presenting the associative physiologic condition. The categorical fusion circuit uses the categorical risk indices to generate a composite risk indicator indicating likelihood of the patient developing the target physiologic event.