Detecting changes in health and daily activities using environmental and electricity sensors and machine learning.

Purpose: The purpose of this feasibility study was to test whether changes in the indoor environment and electricity usage can be used to detect changes in occupant activities that reflect changes in health. Methods: Temperature, relative humidity, carbon dioxide and electrical current were measured over 14+ months in 36 single-occupant homes. Data regarding health and household activities were collected via frequent optional surveys. Characteristics were extracted from the sensor data, including descriptive statistics, timings of peaks and troughs, frequency, deviations from average and modelled values (long short-term memory neural network). Machine learning was used to map these characteristics to occupant responses about health and activities, using a multilayer regressor neural network. Models were trained using all participant data together and separately on data from individual participants. Results: Detection of an existing health condition being worse than normal gave a balanced accuracy of 62%, with 95% of the models having performance above chance. For individual participants, highest performance for detecting worse health was 75% balanced accuracy. Models trained on this participant's data generally gave the highest performance detecting specific reasons for worse health, with 80% for an existing health condition, 87% for mental health, and 84% for physical pain. Conclusions: Overall, the results from this feasibility study provide evidence that data from environmental and electrical-power sensors could be useful in monitoring health and supporting independent living at home. When indicators of worsening health are detected, interventions could be made, providing external support from service providers, or prompting behavioural change, in advance of the issue worsening. Supplementary Information: The online version contains supplementary material available at 10.1007/s12553-026-01082-x.