A Semi-Supervised Approach to Unobtrusively Predict Abnormality in Breathing Patterns Using Hydraulic Bed Sensor Data in Older Adults Aging-in-place

Shortness of breath is often considered to be a repercussion of aging in older adults due, as such respiratory illnesses like COPD or respiratory illnesses due to heart-related issues are often misdiagnosed or under-diagnosed or ignored at early stages. Continuous health monitoring using ambient sensors has the potential to solve this problem for older adults at aging-in-place facilities. In this work, we leverage continuous respiratory health data collected by using ambient hydraulic bed sensors that were installed in the apartments of older adults in aging-in-place Americare facilities to find the data adaptive indicators related to shortness of breath. We used unlabeled data collected unobtrusively over the span of 3 years from a COPD-diagnosed individual and used data mining to label the data. This labeled data is then used to train the predictive model to make future predictions in older adults related to shortness of breath abnormality. To summarize each day’s predictions we propose an abnormal breathing index (ABI) in this work. To showcase the trajectory of the shortness of breath abnormality over time, we also propose trend analysis on the ABI quarterly and incrementally.