Joint state estimation prediction that evaluates differences in predicted vs. corresponding received data

Abstract

Systems and methods are provided for reconciling untrusted data of a subject using trusted data pertaining to the subject. Systems and methods are directed to evaluating differences in predicted data with respect to corresponding received data. Systems and methods estimate metabolic states from a combination of trusted and untrusted metabolic inputs, along with optionally using a personalized mathematical model with parameter optimization. Systems and methods provide for reconciled untrusted inputs with their measured impact of the glycemic signals that is consistent with a metabolic model. Estimation of future metabolic states for decision support and automated insulin dosing is enabled. Replay of scenarios with estimated or reconciled data is also provided.

What is claimed is: 
     
         1 . A system comprising:
 a processor; and   a metabolic model,   wherein the processor is configured to receive untrusted user inputs and reconcile the untrusted user inputs with trusted inputs using the metabolic model.   
     
     
         2 . The system of  claim 1 , wherein the processor is further configured to optimize the predictive ability of the metabolic model to predict future glucose levels. 
     
     
         3 . The system of  claim 1 , wherein the processor is further configured to allow a replay of events and outcomes with alternate treatment procedures. 
     
     
         4 . The system of  claim 1 , wherein the processor is further configured to provide real time prediction of future metabolic states. 
     
     
         5 . The system of  claim 1 , wherein the processor is further configured to determine the credibility of the untrusted user inputs. 
     
     
         6 . The system of  claim 5 , wherein the processor is further configured to provide a score corresponding the credibility. 
     
     
         7 . The system of  claim 5 , wherein the processor is further configured to perform a replay analysis directed to at least one replay application. 
     
     
         8 . The system of  claim 7 , wherein the at least one replay application comprises assessment of blood glucose (BG) outcome metrics in the analysis, identification of credible instances of scenarios in the replay analysis, evaluation of data quality, credibility profiles, and data credibility as a function of time of day. 
     
     
         9 . The system of  claim 5 , wherein the processor is further configured to perform a reconciled projection directed to at least one real time application. 
     
     
         10 . The system of  claim 9 , wherein the at least one real time application comprises confidence of medical actions and determination of need to wait before providing advice. 
     
     
         11 . The system of  claim 1 , wherein the untrusted user inputs comprise estimated carbs. 
     
     
         12 . The system of  claim 1 , wherein the untrusted user inputs comprise a time series of uncertain metabolic inputs. 
     
     
         13 . The system of  claim 1 , wherein the trusted inputs comprise CGM and insulin pump readings. 
     
     
         14 . The system of  claim 1 , wherein the trusted inputs comprise a time series of trusted metabolic inputs. 
     
     
         15 . The system of  claim 1 , wherein the processor is further configured to output estimated metabolic states in time series form, final reconciled estimated metabolic states in time series form, and credibility of final estimated metabolic states and reconciled estimated inputs in time series form. 
     
     
         16 . The system of  claim 1 , wherein the processor is comprised within a joint state/input estimator, and the metabolic model is a plugin. 
     
     
         17 . A method comprising:
 receiving estimated metabolic states, reconciled estimated untrusted metabolic inputs, trusted metabolic inputs, and alternative metabolic inputs;   performing replay prediction using the estimated metabolic states, the reconciled estimated untrusted metabolic inputs, the trusted metabolic inputs, and the alternative metabolic inputs; and   outputting replay simulated metabolic states based on the replay prediction.   
     
     
         18 . The method of  claim 17 , wherein the estimated metabolic states, the reconciled estimated untrusted metabolic inputs, and the trusted metabolic inputs each comprise a time series. 
     
     
         19 . The method of  claim 18 , wherein performing the replay prediction comprises estimating metabolic states for a duration of the time series for the estimated metabolic states, the reconciled estimated untrusted metabolic inputs, and the trusted metabolic inputs to generate the replay simulated metabolic states. 
     
     
         20 . A system comprising:
 a processor; and   a metabolic model,   wherein the processor is configured to:
 receive estimated metabolic states, reconciled estimated untrusted metabolic inputs, trusted metabolic inputs, and alternative metabolic inputs; 
 perform replay prediction using the estimated metabolic states, the reconciled estimated untrusted metabolic inputs, the trusted metabolic inputs, and the alternative metabolic inputs; and 
 output replay simulated metabolic states based on the replay prediction. 
   
     
     
         21 . The system of  claim 20 , wherein the estimated metabolic states, the reconciled estimated untrusted metabolic inputs, and the trusted metabolic inputs each comprise a time series. 
     
     
         22 . The system of  claim 21 , wherein performing the replay prediction comprises estimating metabolic states for a duration of the time series for the estimated metabolic states, the reconciled estimated untrusted metabolic inputs, and the trusted metabolic inputs to generate the replay simulated metabolic states. 
     
     
         23 . A method comprising:
 receiving untrusted user inputs; and   reconciling the untrusted user inputs with trusted inputs using a metabolic model.   
     
     
         24 . The method of  claim 23 , further comprising optimizing the predictive ability of the metabolic model to predict future glucose levels. 
     
     
         25 . The method of  claim 23 , further comprising allowing a replay of events and outcomes with alternate treatment procedures. 
     
     
         26 . The method of  claim 23 , further comprising providing real time prediction of future metabolic states. 
     
     
         27 . The method of  claim 23 , further comprising determining the credibility of the untrusted user inputs. 
     
     
         28 . The method of  claim 27 , further comprising providing a score corresponding the credibility. 
     
     
         29 . The method of  claim 27 , further comprising performing a replay analysis directed to at least one replay application. 
     
     
         30 . The method of  claim 29 , wherein the at least one replay application comprises assessment of blood glucose (BG) outcome metrics in the analysis, identification of credible instances of scenarios in the replay analysis, evaluation of data quality, credibility profiles, and data credibility as a function of time of day. 
     
     
         31 . The method of  claim 27 , further comprising performing a reconciled projection directed to at least one real time application. 
     
     
         32 . The method of  claim 31 , wherein the at least one real time application comprises confidence of medical actions and determination of need to wait before providing advice. 
     
     
         33 . The method of  claim 23 , wherein the untrusted user inputs comprise estimated carbs. 
     
     
         34 . The method of  claim 23 , wherein the untrusted user inputs comprise a time series of uncertain metabolic inputs. 
     
     
         35 . The method of  claim 23 , wherein the trusted inputs comprise CGM and insulin pump readings. 
     
     
         36 . The method of  claim 23 , wherein the trusted inputs comprise a time series of trusted metabolic inputs. 
     
     
         37 . The method of  claim 23 , further comprising outputting estimated metabolic states in time series form, final reconciled estimated metabolic states in time series form, and credibility of final estimated metabolic states and reconciled estimated inputs in time series form.