Methods and systems for mitigating sensor error propagation

A processor-implemented method comprising:

• identifying an error metric associated with an input variable influenced by electrical signals provided by a glucose sensing element, the electrical signals being influenced by a glucose level in a body of a patient;
• determining modulated values for the input variable using the error metric;
• determining a reference output glucose value of a translation model using reference input values for the input variable, wherein the reference output glucose value of the translation model is influenced by the reference input values and a weighting applied to the input variable;
• determining a simulated output glucose value of the translation model using the modulated values for the input variable, wherein the simulated output glucose value of the translation model is influenced by the modulated values for the input variable and the weighting;
• when a difference between the simulated output glucose value and the reference output glucose value is greater than a threshold, updating, by one or more processors, the translation model with a reduced weighting applied to the input variable, resulting in an updated translation model which mitigates error associated with the input variable;
• and
• providing the updated translation model to a device monitoring the glucose level in the body of the patient using the glucose sensing element, wherein the device generates an output glucose value of the updated translation model based on one or more subsequent values for the input variable derived from one or more subsequent electrical signals output by the glucose sensing element in response to the glucose level in the body of the patient, wherein the device provides a notification pertaining to a glucose level in the body of the patient, the notification generated based at least in part on the output glucose value of the updated translation model.

A system comprising:

• a database configured to store historical measurement data corresponding to instances of a sensing element influenced by a glucose level in a body of a patient;
• and
• a server coupled to the database, the server configured to identify an error metric associated with an input variable to a translation model based at least in part on the historical measurement data, identify reference input values for the input variable using the historical measurement data, determine modulated values for the input variable based on the reference input values using the error metric, determine a reference output glucose value of the translation model by providing the reference input values for the input variable to the translation model, determine a simulated output glucose value of the translation model by providing the modulated values for the input variable to the translation model, update the translation model to reduce a weighting applied to the input variable when a difference between the simulated output glucose value and the reference output glucose value is greater than a threshold, the updated translation model mitigating error associated with the input variable, provide an output glucose value of the updated translation model based on one or more subsequent values for the input variable derived from one or more electrical signals output by an instance of the sensing element, and providing a notification pertaining to a glucose level in the body of the patient, wherein the notification is generated based at least in part on the output glucose value of the updated translation model.