Circulatory shock prediction and diagnosis model

A method for determining a probability of a patient going into shock, the method comprising:

• receiving, at a client device, a first set of vital sign measurements from the patient associated with a first time;
• determining, using a time-variant machine learning model, the probability that the patient will go into shock within a predetermined time period based on the first set of vital sign measurements, the time-variant machine learning model having a first set of parameters associated with the first time, wherein determining the probability of the patient going into shock comprises:
• applying the first set of parameters to a first relationship between a first vital sign measurement and a second vital sign measurement from the first set of vital sign measurements,
• wherein the first vital sign measurement corresponds to a first vital sign, and the second vital sign measurement corresponds to a second vital sign,
• wherein the first set of parameters is selected, by the time-variant machine learning model, for application to the first relationship based on the first time;
• wherein the time-variant machine learning model is trained using a training data set comprising a) historical vital sign measurements of one or more training patients over a plurality of time periods and an indication of whether or not each training patient developed shock, b) a plurality of physiological relationships between subsets of the historical vital sign measurements over the plurality of time periods, and c) a diagnosis buffer accounting for a delay in input of the historical vital sign measurements relative to the indication of training patient shock development;
• receiving, at the client device, a second set of vital sign measurements from the patient associated with a second time;
• updating, using the time-variant machine learning model, the probability that the patient will go into shock within the predetermined time period based on the first set of vital sign measurements and the second set of vital sign measurements, the time-variant machine learning model having a second set of parameters associated with the second time, the second set of parameters differing from the first set of parameters;
• receiving, at the client device, a third set of vital sign measurements from the patient associated with a third time;
• and
• updating, using the time-variant machine learning model, the probability that the patient will go into shock within the predetermined time period based on the first set of vital sign measurements, the second set of vital sign measurements, and the third set of vital sign measurements, the time-variant machine learning model having a third set of parameters associated with the third time, the third set of parameters differing from the first set of parameters and the second set of parameters,
• wherein updating the probability of the patient going into shock comprises:
• applying the second set of parameters to a second relationship between a third vital sign measurement and a fourth vital sign measurement from the second set of vital sign measurements,
• wherein the third vital sign measurement corresponds to the first vital sign, and the fourth vital sign measurement corresponds to the second vital sign,
• wherein the second set of parameters is selected, by the time-variant machine learning model, for application to the second relationship based on the second time, wherein the second relationship differs from the first relationship.

A system for determining a probability of a patient going into shock, the system comprising:

• a body sensor for measuring a plurality of vital sign measurements associated with the patient;
• a time-variable machine learning model for determining the probability of the patient going into shock;
• and
• one or more non-transitory computer-readable media comprising computer-executable instructions that, when executed by at least one processor, perform a method of determining the probability of the patient going into shock, the method comprising:
• receiving a first set of vital sign measurements from the plurality of vital sign measurements associated with a first time;
• determining, using a time-variant machine learning model, the probability of the patient going into shock based on the first set of vital sign measurements, the time-variant machine learning model having a first set of parameters associated with the first time, wherein determining the probability of the patient going into shock comprises:
• applying the first set of parameters to a first relationship between a first vital sign measurement and a second vital sign measurement from the first set of vital sign measurements,
• wherein the first vital sign measurement corresponds to a first vital sign, and the second vital sign measurement corresponds to a second vital sign,
• wherein the first set of parameters is selected, by the time-variant machine learning model, for application to the first relationship based on the first time;
• wherein the time-variant machine learning model is trained using a training data set comprising a) historical vital sign measurements of one or more training patients over a plurality of time periods and an indication of whether or not each training patient developed shock, b) a plurality of physiological relationships between subsets of the historical vital sign measurements over the plurality of time periods, and c) a diagnosis buffer accounting for a delay in input of the historical vital sign measurements relative to the indication of training patient shock development;
• receiving a second set of vital sign measurements from the plurality of vital sign measurements associated with a second time;
• and
• updating, using the time-variant machine learning model, the probability of the patient going into shock based on the second set of vital sign measurements, the time-variant machine learning model having a second set of parameters associated with the second time, the second set of parameters differing from the first set of parameters, wherein updating the probability of the patient going into shock comprises:
• applying the second set of parameters to a second relationship between a third vital sign measurement and a fourth vital sign measurement from the second set of vital sign measurements,
• wherein the third vital sign measurement corresponds to the first vital sign, and the fourth vital sign measurement corresponds to the second vital sign,
• wherein the second set of parameters is selected, by the time-variant machine learning model, for application to the second relationship based on the second time,
• wherein the second relationship differs from the first relationship.