Personalized Health Risk Assessment For Critical Care

A computer-readable storage medium comprising computer-readable instructions to be executed on a processor of a system for assessing whether a patient is at risk of developing a clinical condition, the instructions when executed cause the processor to:

• receive training data from a database representing a set of patient-related variables for each of a plurality of patients;
• generate model data based on the received training data;
• receive target data representing the set of patient-related variables for a target patient;
• automatically determine a risk level for the target patient of developing the clinical condition, wherein determining the risk level includes causing the processor to perform one or more calculations involving the received target data and the generated model data;
• and
• automatically indicate the risk level of developing the clinical condition,
• wherein
• i) when the clinical condition is a mortality condition, the set of patient-related variables consists of fifteen or fewer variables, and at least three of the fifteen or fewer variables are selected from the group consisting of:
• functional health status prior to surgery, ASA classification, preoperative serum albumin, age, presence of disseminated cancer, preoperative BUN, DNR status, emergent versus non-emergent case, work relative value unit, and presence of ascites, and
• ii) when the clinical condition is a morbidity condition, the set of patient-related variables consists of fifteen or fewer variables, and at least three of the fifteen or fewer variables are selected from the group consisting of:
• ASA classification, work relative value unit, preoperative serum albumin, emergent versus non-emergent case, functional health status prior to surgery, inpatient versus outpatient case, preoperative systemic sepsis, age, steroid use for chronic condition, and weight.

A computer-implemented method of assessing whether a patient is at risk of developing a clinical condition, the method comprising:

• receiving from a database training data representing a set of patient-related variables for each of a plurality of patients, wherein
• i) the set of patient-related variables excludes all variables corresponding to laboratory results,
• ii) the training data excludes all training data collected within a period of at least one year immediately prior to receiving the training data, or
• iii) the set of patient-related variables excludes all variables corresponding to laboratory results and the training data excludes all training data collected within a period of at least one year immediately prior to receiving the training data;
• generating model data via a computer based on the received training data;
• receiving target data representing the set of patient-related variables for a target patient;
• determining via the computer a risk level for the target patient of developing the clinical condition, wherein determining the risk level includes performing one or more calculations involving the received target data and the generated model data;
• and
• indicating the risk level of developing the clinical condition.

A computer-implemented method of assessing whether a patient is at risk of developing a clinical condition, the method comprising:

• receiving from a database training data, wherein the training data represents a plurality of codes corresponding to a plurality of patients;
• receiving target data, wherein the target data represents one or more codes corresponding to a target patient;
• generating model data via a computer based on the received training data, at least in part by utilizing a non-parametric learning method that maps the codes corresponding to the plurality of patients to a linear space;
• determining a risk level corresponding to the target data of developing the clinical condition, wherein:
• determining the risk level includes performing one or more calculations comparing, in the linear space, the one or more codes corresponding to the target patient to the plurality of codes corresponding to the plurality of patients, and
• determining the risk level includes at least one selected from the group consisting of:
• (a) determining via the computer a risk classification corresponding to the target data, and
• (b) determining via the computer a risk score corresponding to the target data;
• and
• indicating the risk level of developing the clinical condition, wherein indicating the risk level includes at least one selected from the group consisting of:
• (a) indicating whether the target patient is at risk of developing the clinical condition, wherein the indication is based at least in part on the risk classification, and
• (b) indicating an extent to which the target patient is at risk of developing the clinical condition, wherein the indication is based at least in part on the risk score.