Devices that monitor seniors for safety are appealing to worried loved ones and underresourced home care agencies. It was January of 2026 in North Seattle, and my 86-year-old father was struggling to move around his house. "I'm stumbling around here," my 86-year-old father told a guest in his home this past January. "Oooh, ooh, careful," the guest replied. "Yeah, I almost fell down."

Recent work in machine learning for healthcare has raised concerns about patient privacy and algorithmic fairness. For example, previous work has shown that patient self-reported race can be predicted from medical data that does not explicitly contain racial information. However, the extent of data identification is unknown, and we lack ways to develop models whose outcomes are minimally affected by such information. Here we systematically investigated the ability of time-series electronic health record data to predict patient static information. We found that not only the raw time-series data, but also learned representations from machine learning models, can be trained to predict a variety of static information with area under the receiver operating characteristic curve as high as 0.851 for biological sex, 0.869 for binarized age and 0.810 for self-reported race. Such high predictive performance can be extended to a wide range of comorbidity factors and exists even when the model was trained for different tasks, using different cohorts, using different model architectures and databases. Given the privacy and fairness concerns these findings pose, we develop a variational autoencoder-based approach that learns a structured latent space to disentangle patient-sensitive attributes from time-series data. Our work thoroughly investigates the ability of machine learning models to encode patient static information from time-series electronic health records and introduces a general approach to protect patient-sensitive attribute information for downstream tasks.

As the world grows older, issues surrounding elderly care abound: who's taking care of our elderly relatives, are they doing it well, and how do we keep track of well-being and safety in a sensitive way? Israeli startup Sensi.AI thinks it may have the solution with a smart, AI-powered auditory system that monitors a person's daily routine, environment and well-being, which it claims can provide better caregiver retention and quality-of-care assurance– not only for the elderly, but also for babies, special-needs kids and others. "The idea for it came out of my own personal place, to do with my daughter," says Sensi.AI CEO Romi Gubes. "I understood this whole world of caregiving for the helpless, and how much the element of transparency is lacking in order to prevent future problems." This lack of transparency, she explains, is the result of the often-silent population that requires caregiving and can lead to blind spots in the treatment process that inhibit improvement.