Systems and methods to support medical therapy decisions

Abstract

Systems and methods for supporting medical therapy decisions are disclosed that utilize predictive models and electronic medical records (EMR) data to provide predictions of health conditions over varying time horizons. Embodiments also determine a 0-100 health risk index value that represents the “risk” for a patient to acquire a health condition based on a combination of real-time and predicted EMR data. The systems and methods receive EMR data and use the predictive models to predict one or more data values from the EMR data as diagnostic criteria. In some embodiments, the health condition trying to be avoided is Sepsis and the health risk index is a Sepsis Risk Index (SRI). In some embodiments, the predictive models are neural network models such as time delay neural networks.

We claim: 
     
         1 . A processor based method of generating an alert for improving a treatment outcome of a patient, the method comprising:
 receiving electronic medical record (EMR) data;   computing an overall risk index for a current patient; and   generating alerts for a directive recommendation.   
     
     
         2 . The processor based method of  claim 1  wherein the overall risk index comprises a Sepsis Risk Index (SRI) of a current patient state. 
     
     
         3 . The processor based method of  claim 1  wherein the EMR data comprises one or more selected from the group of data consisting of:
 a heart rate; 
 a respiration rate; 
 a systolic blood pressure; 
 a mean arterial pressure; 
 a temperature; and 
 a urine output. 
 
     
     
         4 . The processor based method of  claim 3  wherein the EMR data further comprises one or more selected from the group of data consisting of:
 a blood glucose level; 
 a white blood cell count; 
 a creatinine level; 
 a platelet count; and 
 a lactate level. 
 
     
     
         5 . The processor based method of  claim 1  wherein the directive recommendation comprises utilizing a Self-Organizing Feature Map (SOFM). 
     
     
         6 . The processor based method of  claim 1  wherein the directive recommendation comprises utilizing a Self-Organizing Feature Map (SOFM) wherein an input vector node based on the current patient state is mapped to a closest vector node of the SOFM to define the directive recommendation. 
     
     
         7 . The processor based method of  claim 1  wherein the alert for improving a treatment outcome of a patient comprises one or more alert required for an optimal antibiotic therapy and infection management. 
     
     
         8 . The processor based method of  claim 7  wherein the alerts for improving an outcome of a patient is one or more alerting mechanism selected from the group of alerting mechanism consisting of:
 a visual alert; and 
 an auditory alert. 
 
     
     
         9 . The processor based method of  claim 1  wherein the treatment outcome of the patient comprises one or more treatment outcome selected from the group of treatment outcomes consisting of:
 a reduction in ICU length of stay; 
 a reduction in hospital length of stay; 
 a reduction in-hospital mortality; 
 a reduction in thirty day mortality; 
 a reduction in six month mortality; 
 a reduction in one year mortality; and 
 a reduction in two year mortality.