Techniques for evaluating the effectiveness of an intervention for a condition of a plurality of subjects are disclosed. First data can be received from a plurality of activity monitors respectively associated with the plurality of subjects. Each of the activity monitors can measure at least some activity by a respective plurality of subjects over a time period. For each of the plurality of subjects, second data can be received that identifies one or more indicators of a
life stage or a
quality of life condition of each of the plurality of subjects receiving a therapy,
nutrition, or intervention over at least some portion of the time period. The first data and the second data can be input into at least one
machine learning (ML) model that can process the first data and the second data. The ML model can determine that the intervention is relatively effective, or that the intervention is relatively ineffective.