Adapting data collection in clinical research and digital therapeutics
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for managing and adapting monitoring programs. In some implementations, a system communicates with a set of remote devices involved in a monitoring program that involves collection of data from the remote devices over a communication network. The system determines a set of attributes associated with an outcome or condition that has occurred for multiple of the remote devices. The system generates parameters to adapt the monitoring program, and the system selects a second group of remote devices to involve in the adapted monitoring program based on profiles or sets of attributes of users associated with the remote devices. The system configures the remote devices in the selected second group to perform monitoring for the adapted monitoring program, including acquiring data for the adapted monitoring program and providing the acquired data to a server over the communication network.
1 . A method performed by one or more computers, the method comprising:
communicating, by one or more computers, with a group of remote devices involved in a monitoring program that involves collection of data from the remote devices over a communication network, each of the remote devices corresponding to a different participant in a set of multiple participants for the monitoring program, wherein communicating with the remote devices comprises receiving, from each of the remote devices over the communication network, a series of messages including monitoring data collected by the remote device at different times for first types of data specified by the monitoring program;
based on the monitoring data collected from the remote devices, determining, by the one or more computers, that an outcome or condition indicated by the monitoring data to have occurred for each of multiple participants in the set of participants has a prevalence among the set of participants that satisfies one or more criteria:
determining, by the one or more computers and based on the monitoring data collected from the remote devices, a set of attributes associated with the outcome or condition that has occurred for multiple participants in the monitoring program;
generating, by the one or more computers, parameters to adapt the monitoring program, the parameters including (i) selection criteria to select additional devices or participants that are associated with the set of attributes to provide data in the adapted monitoring program or (ii) second types of data to collect in the adapted monitoring program;
selecting, by the one or more computers, a second group of remote devices to involve in the adapted monitoring program based on profiles or sets of attributes of users associated with the remote devices; and
configuring, by the one or more computers, the remote devices in the selected second group to perform monitoring for the adapted monitoring program, including acquiring data for the adapted monitoring program and providing the acquired data to a server over the communication network, wherein the remote devices in the second selected group are configured to perform monitoring for the adapted monitoring program based on the determination that the outcome or condition has a prevalence among the set of participants that satisfies the one or more criteria.
2 . The method of claim 1 , comprising:
analyzing, by the one or more computers, the data collected from the remote devices in the first group to identify a pattern or similarity among monitoring data collected from a subset of the remote devices involved in the monitoring program; and
determining, by the one or more computers, attributes associated with the respective devices in the subset;
wherein the selection criteria are based on the attributes associated with the respective devices in the subset.
3 . The method of claim 2 , wherein the attributes are attributes of users of the devices.
4 . The method of claim 2 , wherein the attributes are attributes specified in a profile for a device or for a user of the device.
5 . The method of claim 2 , wherein determining the selection criteria based on the attributes associated with the respective devices in the subset comprises:
determining, for a particular attribute, a range of attribute values based on a range or distribution of attribute values for the particular attribute among the attributes associated with the respective devices in the subset; and
determining the selection criteria to include devices or users having attribute values for the particular attribute in the determined range.
6 . The method of claim 1 , wherein configuring the one or more devices comprises distributing, to the one or more devices, a software module or configuration data that cause the one or more devices to initiate collection of the second types of data.
7 . The method of claim 1 , wherein the second types of data comprise measurements made using one or more sensors of the one or more devices or of devices communicatively coupled to the one or more devices.
8 . The method of claim 7 , wherein the measurements comprise one or more physiological or behavioral measurements.
9 . The method of claim 1 , comprising:
providing, to a client device of a researcher associated with the monitoring program, program data for display on a user interface of the client device, the program data indicating characteristics of the second monitoring program, including at least one of the selection criteria, data indicating the members of the second monitoring group or characteristics of the second monitoring group, or the second types of data to be collected; and
after providing the program data for display, receiving, from the client device, confirmation data indicating user input confirming that the second monitoring program should be conducted; and
wherein configuring the remote devices in the selected second group is performed in response to receiving the confirmation data.
10 . A system comprising:
one or more computers; and
one or more computer-readable media storing instructions that are operable, when executed by the one or more computers, to cause the system to perform operations comprising:
communicating, by one or more computers, with a group of remote devices involved in a monitoring program that involves collection of data from the remote devices over a communication network, each of the remote devices corresponding to a different participant in a set of multiple participants for the monitoring program, wherein communicating with the remote devices comprises receiving, from each of the remote devices over the communication network, a series of messages including monitoring data collected by the remote device at different times for first types of data specified by the monitoring program;
based on the monitoring data collected from the remote devices, determining, by the one or more computers, that an outcome or condition indicated by the monitoring data to have occurred for each of multiple participants in the set of participants has a prevalence among the set of participants that satisfies one or more criteria;
determining, by the one or more computers and based on the monitoring data collected from the remote devices, a set of attributes associated with the outcome or condition that has occurred for multiple participants in the monitoring program;
generating, by the one or more computers, parameters to adapt the monitoring program, the parameters including (i) selection criteria to select additional devices or participants that are associated with the set of attributes to provide data in the adapted monitoring program or (ii) second types of data to collect in the adapted monitoring program;
selecting, by the one or more computers, a second group of remote devices to involve in the adapted monitoring program based on profiles or sets of attributes of users associated with the remote devices; and
configuring, by the one or more computers, the remote devices in the selected second group to perform monitoring for the adapted monitoring program, including acquiring data for the adapted monitoring program and providing the acquired data to a server over the communication network, wherein the remote devices in the second selected group are configured to perform monitoring for the adapted monitoring program based on the determination that the outcome or condition has a prevalence among the set of participants that satisfies the one or more criteria.
11 . The system of claim 10 , comprising:
analyzing, by the one or more computers, the data collected from the remote devices in the first group to identify a pattern or similarity among monitoring data collected from a subset of the remote devices involved in the monitoring program; and
determining, by the one or more computers, attributes associated with the respective devices in the subset;
wherein the selection criteria are based on the attributes associated with the respective devices in the subset.
12 . The system of claim 11 , wherein the attributes are attributes of users of the devices.
13 . The system of claim 11 , wherein the attributes are attributes specified in a profile for a device or for a user of the device.
14 . The system of claim 11 , wherein determining the selection criteria based on the attributes associated with the respective devices in the subset comprises:
determining, for a particular attribute, a range of attribute values based on a range or distribution of attribute values for the particular attribute among the attributes associated with the respective devices in the subset; and
determining the selection criteria to include devices or users having attribute values for the particular attribute in the determined range.
15 . The system of claim 10 , wherein configuring the one or more devices comprises distributing, to the one or more devices, a software module or configuration data that cause the one or more devices to initiate collection of the second types of data.
16 . One or more non-transitory computer-readable media storing instructions that are operable, when executed by one or more computers, to cause the one or more computers to perform operations comprising:
communicating, by one or more computers, with a group of remote devices involved in a monitoring program that involves collection of data from the remote devices over a communication network, each of the remote devices corresponding to a different participant in a set of multiple participants for the monitoring program, wherein communicating with the remote devices comprises receiving, from each of the remote devices over the communication network, a series of messages including monitoring data collected by the remote device at different times for first types of data specified by the monitoring program;
based on the monitoring data collected from the remote devices, determining, by the one or more computers, that an outcome or condition indicated by the monitoring data to have occurred for each of multiple participants in the set of participants has a prevalence among the set of participants that satisfies one or more criteria:
determining, by the one or more computers and based on the monitoring data collected from the remote devices, a set of attributes associated with the outcome or condition that has occurred for multiple participants in the monitoring program;
generating, by the one or more computers, parameters to adapt the monitoring program, the parameters including (i) selection criteria to select additional devices or participants that are associated with the set of attributes to provide data in the adapted monitoring program or (ii) second types of data to collect in the adapted monitoring program;
selecting, by the one or more computers, a second group of remote devices to involve in the adapted monitoring program based on profiles or sets of attributes of users associated with the remote devices; and
configuring, by the one or more computers, the remote devices in the selected second group to perform monitoring for the adapted monitoring program, including acquiring data for the adapted monitoring program and providing the acquired data to a server over the communication network, wherein the remote devices in the second selected group are configured to perform monitoring for the adapted monitoring program based on the determination that the outcome or condition has a prevalence among the set of participants that satisfies the one or more criteria.
17 . The method of claim 1 , wherein determining that the outcome or condition has a prevalence of among the set of participants that satisfies one or more criteria comprises determining that a measure of the prevalence the outcome or condition among the set of participants satisfies a threshold.
18 . The method of claim 1 , wherein determining that the outcome or condition has a prevalence among the set of participants that satisfies one or more criteria comprises:
determining a percentage of the set of participants that experienced the outcome or condition; and
determining that the percentage satisfies a threshold.
19 . The method of claim 1 , wherein the set of participants is a research study cohort; and
wherein determining that the outcome or condition has a prevalence among the set of participants that satisfies one or more criteria comprises comparing (i) measures of health characteristics for the participants that the monitoring data indicates have experienced the outcome or condition with (ii) aggregate measures for the research study cohort.
20 . The method of claim 1 , comprising storing adaptation rules that indicate multiple different conditions for triggering adaptation of monitoring programs; and
wherein determining that the outcome or condition has a prevalence among the set of participants that satisfies one or more criteria comprises determining that the prevalence of the outcome or condition among the set of participants satisfies one of the multiple different conditions for triggering adaptation of monitoring programs.
21 . The method of claim 1 , comprising storing pattern signatures representing sets of monitoring program characteristics that are appropriate for adaptation;
wherein determining that the outcome or condition has a prevalence among the set of participants that satisfies one or more criteria comprises determining that characteristics of the monitoring program match or are within a threshold level of similarity to one of the pattern signatures.