P2022WKABN - Frailty status in hospitalized persons: artificial intelligence-based detection and technology-assisted home-based empowerment (ART.I.DE.)

Frailty is defined as a clinically recognizable state in which the ability of people to cope with everyday or acute stressors is compromised by an increased vulnerability brought by age-associated declines in physiological reserve and function across multiple organ systems [1]. Frailty is characterized by multisystem dysregulations, leading to a loss of dynamic homeostasis, reduced physiological reserve and greater vulnerability to subsequent morbidity and mortality. This is often manifested by maladaptive response to stressors, leading to a vicious cycle that results in functional decline and other serious adverse health outcomes [1,2]. Frequent not exclusive components of the biological substratum underlying frailty include a pro-inflammatory state, sarcopenia, anemia, relative deficiencies in anabolic hormones and excessive exposure to catabolic ones, insulin resistance, compromised or altered immune function, micronutrient deficiencies and oxidative stress [1,2]. Frail people are exposed to a significant 50% increase in mortality risk compared to non-frail peers, with a very low 5-year survival rate [3], and also to a higher risk for hospitalizations and falls [3,4] with high burden for families and care-givers. From an economic perspective, literature shows that frailty is the strongest predictor of formal social care costs. In Europe, mean social care costs for frail are tentimes higher compared with individuals without frailty. It has been calculated that for every 1% of nonfrail people not transitioning to frailty, a savings of 4.4 million pounds in annual expenditures on formal social care in England are expected [vb]. Worldwide, in adults greater than 50 years old, the prevalence of frailty ranges from 12 to 24% [5], with the percentage that increases to more than 50% in elderlies hospitalized for any cause [5]. Unfortunately a wide heterogeneity reported is principally due to the huge amount of methods to assess frailty [5]. Up-to-date, more than 75 different methods of measuring frailty are validated in literature covering the physical, physiological, biochemical and psychological aspects. In addition, the number of tools is continuously increasing, and unfortunately, literature reports that there is no agreement on how to best measure it [6]. Two of the mostre used methods to assess frailty are the frailty phenotype (FP) also known as Fried et al.’s definition, and the frailty index (FI). In the first one, Fried et al. operationalized a frailty syndrome when three or more of the following five phenotypic criteria were present: 1. weakness measured by low grip strength; 2. slowness measured by decreased walking speed; 3. low level of physical activity; 4. low energy or self-reported exhaustion; 5. unintentional weight loss [1,2]. The FI on the other hand, proposed by Mitnitski et al., follows a different approach [7]. Being based on an arithmetical assumption, it measures frailty in terms of an age-related accumulation of “deficits” in relation to the expected health status. In recent years, the growing accessibility of low-cost technology hasve contributed to the proliferation of tools, mainly organized intotriaxial accelerometers, wrist or ankle sensors and, force sensors, which that have been successfully employed to measure frailty [4,8-11]. Once more, a wide variety of instruments is available with different sites of application, time of data collection, analyses and interpretation of the results [8-11]. Another cornerstone in frailty, in addition to its precise detection, is the early proactive identification of frail people in the community to provide their empowerment to prevent or delay functional loss [1]. To this end, physical activity/exercise is considered one of the main strategies to counteract frailty-related physical impairment in the elderly. Exercise reduces age-related oxidative damage and chronic inflammation, improves mitochondrial