The goal of this study is to extract new indicators that are descriptive of aging-associated decline in reserve and function (frailty) and perform this through an unobtrusive monitoring system aiming to augment the standard geriatric assessment. Extraction of such indicators was performed by fusing information from multiple devices, such as inertial measurement units (IMUs), a games platform and an outdoor monitoring system, and thereby creating a multi-parametric profile of the older person. Principal component analysis (PCA) was applied to remove correlations in the extracted features, followed by locally linear embedding (LLE) to embed the data in a lower dimensional space where unsupervised clustering is feasible. Exploration of the identified clusters revealed patterns of frailty manifestation that were in high accordance with geriatric indices from several domains (medical, cognitive, psychological, etc). Our results highlight the potential of the applied data mining methodology for the extraction of novel frailty indicators.