No abstract

No abstract

Detailed information about a home's occupancy is necessary to implement many advanced energy-efficiency optimizations. However, monitoring occupancy directly is intrusive, typically requiring the deployment of multiple environmental sensors, e.g., motion, acoustic, CO2, etc. In this paper, we explore the potential for Non-Intrusive Occupancy Monitoring (NIOM) by using electricity data from smart meters to infer occupancy. We first observe that a home's pattern of electricity usage generally changes when occupants are present due to their interact with electrical loads. We empirically evaluate these interactions by monitoring ground truth occupancy in two homes, then correlating it with changes in statistical metrics of smart meter data, such as power's mean and variance, over short intervals. In particular, we use each metric's maximum value at night as a proxy for its maximum value in an unoccupied home, and then signal occupancy whenever the daytime value exceeds it. Our results highlight NIOM's potential and its challenges.

Objective Health care providers increasingly rely upon predictive algorithms when making important treatment decisions, however, evidence indicates that these tools can lead to inequitable outcomes across racial and socio-economic groups. In this study, we introduce a bias evaluation checklist that allows model developers and health care providers a means to systematically appraise a model’s potential to introduce bias. Materials and Methods Our methods include developing a bias evaluation checklist, a scoping literature review to identify 30-day hospital readmission prediction models, and assessing the selected models using the checklist. Results We selected 4 models for evaluation: LACE, HOSPITAL, Johns Hopkins ACG, and HATRIX. Our assessment identified critical ways in which these algorithms can perpetuate health care inequalities. We found that LACE and HOSPITAL have the greatest potential for introducing bias, Johns Hopkins ACG has the most areas of uncertainty, and HATRIX has the fewest causes for concern. Discussion Our approach gives model developers and health care providers a practical and systematic method for evaluating bias in predictive models. Traditional bias identification methods do not elucidate sources of bias and are thus insufficient for mitigation efforts. With our checklist, bias can be addressed and eliminated before a model is fully developed or deployed. Conclusion The potential for algorithms to perpetuate biased outcomes is not isolated to readmission prediction models; rather, we believe our results have implications for predictive models across health care. We offer a systematic method for evaluating potential bias with sufficient flexibility to be utilized across models and applications.

Shifts in environment between development and deployment cause classical supervised learning to produce models that fail to generalize well to new target distributions. Recently, many solutions which find invariant predictive distributions have been developed. Among these, graph-based approaches do not require data from the target environment and can capture more stable information than alternative methods which find stable feature sets. However, these approaches assume that the data generating process is known in the form of a full causal graph, which is generally not the case. In this paper, we propose I-SPEC, an end-to-end framework that addresses this shortcoming by using data to learn a partial ancestral graph (PAG). Using the PAG we develop an algorithm that determines an interventional distribution that is stable to the declared shifts; this subsumes existing approaches which find stable feature sets that are less accurate. We apply I-SPEC to a mortality prediction problem to show it can learn a model that is robust to shifts without needing upfront knowledge of the full causal DAG.