Methods and systems for adverse event prediction using pump operating data
The present disclosure provides for each of a method of characterizing divergence of a monitored flow rate of blood through an implantable blood pump, and a method of predicting an upcoming adverse cardiac event using operating data of the blood pump, such as the characterized divergence data. Predicting an upcoming adverse cardiac event may be further based on similar operating data from a plurality of other implantable blood pumps.
1. A method of characterizing divergence of a monitored flow rate of blood through an implantable blood pump, comprising a control circuit repeatedly performing over time:
determining a flow rate of blood through the pump at a then-current time,
calculating an average flow rate of blood through the pump over a first period of time preceding the then-current time,
repeatedly calculating a plurality of divergence values, which is representative of a difference between the average flow rate and the determined then-current flow rate, wherein the divergence of flow rate is characterized based on a sum of the calculated plurality of divergence values,
compiling the summed plurality of divergence values into a waveform,
predicting the adverse event based on a plurality of features of the waveform, and
generating a notification representative of a predicted adverse event based on the sum of the plurality of divergence values, the adverse event being one of a group consisting of a cerebrovascular accident and a thrombus.
2. A method as recited in claim 1 , wherein for a given then-current time, the summed plurality of divergence values are the divergence values calculated over a second period of time immediately preceding the then-current time.
3. A method as recited in claim 2 , wherein the second period of time is shorter than the first period of time.
4. A method as recited in claim 2 , wherein the second period of time is about three hours, and wherein the first period of time is about three days.
5. A method as recited in claim 1 , wherein the calculated average flow rate is a moving average, and wherein the first period of time immediately precedes the then-current time.
6. A method of predicting an adverse event based on flow rate data from an implantable blood pump, the method comprising the method of characterizing divergence of a monitored flow rate recited in claim 1 , wherein each of the summed plurality of divergence values is associated with its corresponding then-current time.
7. A method as recited in claim 6 , wherein the waveform is a time-domain waveform.
8. A method of predicting an adverse event based on flow rate data from an implantable blood pump, the method comprising the method of characterizing divergence of a monitored flow rate recited in claim 1 , wherein each of the summed plurality of divergence values is associated with its corresponding then-current time, and further comprising sorting the summed plurality of divergence values by magnitude, and predicting the adverse event based on the highest magnitude summed plurality of divergence values.