Systems and methods for identifying markers using a reconfigurable system
Systems and methods for using a reconfigurable multi-manager observer system to identify markers are provided. The system allows for easy collaboration among users of the system and with subjects. Systems and methods may comprise receiving subject data, selecting predictor and outcome variable classes based on the data, generating a predictor score based on the data and a predictor rule, generating an outcome score based on the data and an outcome rule, generating a marker score based on the predictor score and a marker rule, generating a marker metric based on the outcome score, the marker score, and a marker relationship, and, optionally, taking an action based on the predictor score, the outcome score, the marker score, or the marker metric.
1. A system comprising:
one or more memory units storing instructions; and
one or more processors for executing the instructions to perform operations comprising:
receiving, from one or more devices, first data associated with a subject, the first data including data collected according to one or more data collection parameters;
selecting a predictor variable class based on the first data;
generating a predictor score associated with the predictor variable class based on the first data and a predictor rule;
selecting an outcome variable class based on the first data;
generating an outcome score associated with the outcome variable class based on the first data and an outcome rule;
generating a marker rule comprising an expression to generate a marker score based on the predictor score and at least one other predictor score;
generating a marker score based on the predictor score and the marker rule;
generating a marker metric based on the outcome score, the marker score, and a marker relationship between the marker score and the outcome score;
sending, based on at least one of the predictor score, the outcome score, the marker score, or the marker metric, a command to at least one of the one or more devices to update at least one of the one or more data collection parameters;
causing at least one of the one or more devices to collect second data according to the updated one or more data collection parameters; and
receiving the second data from the one or more devices.
2. The system of claim 1 , wherein the command comprises a command to change at least one of a rate of data collection, a type of data collection, or a device setting.
3. The system of claim 2 , wherein the command to change the rate of data collection comprises instructions to stop data collection.
4. The system of claim 1 , wherein the device is a personal device, a portable or embedded device, a personal wearable device, an invisible device, or an extended network device.
5. The system of claim 1 , wherein the instructions further comprise instructions for applying a machine learning algorithm to determine at least one of the predictor rule, the outcome rule, or the marker rule.
6. The system of claim 1 , wherein the instructions further comprise instructions for applying a machine learning algorithm to determine the marker relationship.
7. The system of claim 1 , wherein the instructions further comprise instructions for determining the marker metric satisfies a criterion before sending the command to update at least one of the one or more data collection parameters.
8. The system of claim 7 , wherein determining the marker metric satisfies a criterion comprises comparing the marker metric to a previously determined marker metric.
9. The system of claim 1 , wherein:
the instructions further comprise instructions for determining if the marker metric satisfies a criterion before sending the command to update at least one of the one or more data collection parameters, wherein:
when the criterion is satisfied, the command comprises a first command,
when the criterion is not satisfied, the command comprises a second command, and
the first command is different from the second command.
10. A computer-implemented method comprising:
receiving, from one or more devices, first data associated with a subject, the first data including data collected according to one or more data collection parameters;
selecting a predictor variable class based on the first data;
generating a predictor score associated with the predictor variable class based on the first data and a predictor rule;
selecting an outcome variable class based on the data;
generating an outcome score associated with the outcome variable class based on the first data and an outcome rule;
generating a marker rule comprising an expression to generate a marker score based on the predictor score and at least one other predictor score;
generating a marker score based on the predictor score and the marker rule;
generating a marker metric based on the outcome score, the marker score, and a marker relationship between the marker score and the outcome score;
sending, based on at least one of the predictor score, the outcome score, the marker score, or the marker metric, a command to at least one of the one or more devices to update at least one of the one or more data collection parameters;
causing at least one of one or more devices to collect second data according to the updated one or more data collection parameters; and
receiving the second data from the one or more devices.
11. The method of claim 10 , wherein the command comprises a command to change at least one of a rate of data collection, a type of data collection, or a device setting.
12. The method of claim 11 , wherein the command to change the rate of data collection comprises instructions to stop data collection.
13. The method of claim 10 , further comprising applying a machine learning algorithm to determine at least one of the predictor rule, the outcome rule, or the marker rule.
14. The method of claim 10 , further comprising applying a machine learning algorithm to determine the marker relationship.
15. The method of claim 10 , further comprising determining the marker metric satisfies a criterion before sending the command to update at least one of the one or more data collection parameters.
16. The method of claim 15 , wherein determining the marker metric satisfies a criterion comprises comparing the marker metric to a previously determined marker metric.
17. The method of claim 10 , further comprising:
determining the marker metric fails to satisfy a criterion before sending the command to update at least one of the one or more data collection parameters.
18. A non-transitory computer readable medium comprising instructions that, when executed by one or more processors, cause the one or more processors to:
receive, from one or more devices, first data associated with a subject, the first data including data collected according to one or more data collection parameters;
select a predictor variable class based on the first data;
generate a predictor score associated with the predictor variable class based on the first data and a predictor rule;
select an outcome variable class based on the data;
generate an outcome score associated with the outcome variable class based on the first data and an outcome rule;
generate a marker rule comprising an expression to generate a marker score based on the predictor score and at least one other predictor score;
generate a marker score based on the predictor score and the marker rule;
generate a marker metric based on the outcome score, the marker score, and a marker relationship between the marker score and the outcome score;
send, based on at least one of the predictor score, the outcome score, the marker score, or the marker metric, a command to at least one of the one or more devices to update at least one of the one or more data collection parameters;
cause at least one of one or more devices to collect second data according to the updated one or more data collection parameters; and
receive the second data from the one or more devices.
19. The non-transitory computer readable medium of claim 18 , wherein the instructions further cause the one or more processors to apply a machine learning algorithm to determine at least one of the predictor rule, the outcome rule, the marker rule, or the marker relationship.
20. The non-transitory computer readable medium of claim 18 , wherein:
the instructions further cause the one or more processors to determine if the marker metric satisfies a criterion before sending the command to update the at least one of the one or more data collection parameters, wherein:
when the criterion is satisfied, the command comprises a first command,
when the criterion is not satisfied, the command comprises a second command, and
the first command is different from the second command.