Preventive, personalized treatment of biopsychosocial (BPS) functional decline or stagnation in the rehabilitation process requires early prediction of those at risk. Ambulant monitoring of objective physical activity using wearable accelerometers could be a quantitative, noninvasive, and affordable method to gain insight into current and future biopsychosocial functioning.

In this retrospective study, Random Forest Regression was used to predict cross-sectional and longitudinal Functional Ambulation Category (FAC) and Six-item Cognitive Impairment Test (6CIT) after hip fracture using ambulatory accelerometry data. Accelerometry data and BPS functional assessments were available of 49 participants of the HIPCARE study, assessing prognostic determinants of outcome after hip fracture in the elderly.

Overall, cross-sectional FAC scores three months after hip fracture could be predicted with moderately low error, and categorized regression predictions showed high precision and recall. Cross-sectional 6CIT and both longitudinal regression models underperformed, but categorized regression predictions revealed mixed but more promising precision and recall.

It is expected that the predictive performance of models can be improved by increasing participant sample size with balanced samples over population-specific, prevalent ranges of BPS outcome scales and exploring additional machine learning models. In the future, accurate accelerometry-based predictions for individual patients needing rehabilitation could support personalized treatment and improve long-term biopsychosocial functioning.

Introduction:Timely personalized treatment of functional decline depends on early ambulant identification of persons at risk. Regularity of daily body acceleration, quantified by sample entropy (SampEn), is associated with fall risk and is a potential proxy for functional (biopsychosocial) resilience.
Objective: This cross-sectional study associates SampEn of daily life accelerometry with physical (short physical performance battery, SPPB [0 12]) and cognitive functioning (cognitive impairment test, 6 CIT [0-28]).Method: Data was provided from the HIPCARE cohort of 51 community-dwelling adults [81 (75 – 89)] after femur fracture. The SPPB, CIT, and 7 days accelerometry were recorded at three months follow-up after hip surgery. The mean SampEn for different activities was compared between patients with low (<4), moderate (4-9), and high (>9) SPPB and between low (<8) and high (>7) CIT with a significance of p≤0.05Results: Moderate SPPB scores had more regularity (lower SampEn) in complete daily life acceleration signals and during stair-walking than the high SPPB group. In addition, the cognitive impaired group (i.e., high CIT) had more regularity (lower SampEn) than the healthy group during cycling and sitting activities.Discussion and conclusions: More regular accelerations indicate the development of limited physical performance and deterioration of cognitive functions. The findings advocate that acceleration entropy in daily life activities is a promising proxy for physical and mental (biopsychological) functions. A large-scale longitudinal study is needed to examine the potential added value of daily acceleration for the early detection of biopsychosocial functioning.