Prediction of Physical Activity Patterns in Older Patients Rehabilitating After Hip Fracture Surgery: Exploratory Study.

BACKGROUND: Building up physical activity is a highly important aspect in an older patient's rehabilitation process after hip fracture surgery. The patterns of physical activity during rehabilitation are associated with the duration of rehabilitation stay. Predicting physical activity patterns early in the rehabilitation phase can provide patients and health care professionals an early indication of the duration of rehabilitation stay as well as insight into the degree of patients' recovery for timely adaptive interventions. OBJECTIVE: This study aims to explore the early prediction of physical activity patterns in older patients rehabilitating after hip fracture surgery at a skilled nursing home. METHODS: The physical activity of patients aged ≥70 years with surgically treated hip fracture was continuously monitored using an accelerometer during rehabilitation at a skilled nursing home. Physical activity patterns were described in our previous study, and the 2 most common patterns were used in this study for pattern prediction: the upward linear pattern (n=15) and the S-shape pattern (n=23). Features from the intensity of physical activity were calculated for time windows with different window sizes of the first 5, 6, 7, and 8 days to assess the early rehabilitation moment in which the patterns could be predicted most accurately. Those features were statistical features, amplitude features, and morphological features. Furthermore, the Barthel Index, Fracture Mobility Score, Functional Ambulation Categories, and the Montreal Cognitive Assessment score were used as clinical features. With the correlation-based feature selection method, relevant features were selected that were highly correlated with the physical activity patterns and uncorrelated with other features. Multiple classifiers were used: decision trees, discriminant analysis, logistic regression, support vector machines, nearest neighbors, and ensemble classifiers. The performance of the prediction models was assessed by calculating precision, recall, and F1-score (accuracy measure) for each individual physical activity pattern. Furthermore, the overall performance of the prediction model was calculated by calculating the F1-score for all physical activity patterns together. RESULTS: The amplitude feature describing the overall intensity of physical activity on the first day of rehabilitation and the morphological features describing the shape of the patterns were selected as relevant features for all time windows. Relevant features extracted from the first 7 days with a cosine k-nearest neighbor model reached the highest overall prediction performance (micro F1-score=1) and a 100% correct classification of the 2 most common physical activity patterns. CONCLUSIONS: Continuous monitoring of the physical activity of older patients in the first week of hip fracture rehabilitation results in an early physical activity pattern prediction. In the future, continuous physical activity monitoring can offer the possibility to predict the duration of rehabilitation stay, assess the recovery progress during hip fracture rehabilitation, and benefit health care organizations, health care professionals, and patients themselves.

Patterns of physical activity over time in older patients rehabilitating after hip fracture surgery: a preliminary observational study.

BACKGROUND: To investigate patterns of continuously monitored physical activity in older patients rehabilitating after hip fracture surgery and the association with patient characteristics. METHODS: Physical activity of surgically treated hip fracture patients aged 70 years or older, who were rehabilitating at a skilled nursing home, was continuously monitored using a tri-axial accelerometer. The intensity of physical activity per day was calculated from the accelerometer signals to describe the daily physical activity levels of the enrolled patients. The patterns of three different aspects of physical activity were investigated: overall physical activity, overall variability, and day-to-day variability. Two experts in the geriatric rehabilitation field helped identifying unique physical activity patterns for each aspect based on visual analysis. Eighteen healthcare professionals independently classified each patient in one of the predefined patterns for each aspect. Differences between physical activity patterns and patient characteristics were assessed using a Kruskal-Wallis or Fisher's Exact Test. RESULTS: Physical activity data from 66 older patients were used in this preliminary study. A total of six unique patterns were identified for overall physical activity and overall variability, and five unique patterns for the day-to-day variability. The most common pattern found for the overall physical activity and day-to-day variability had a S-shape, which first slowly increased, then steeply increased, and subsequently flattened (n = 23, 34.8%). A N-shape pattern was found the most common pattern for overall variability, which first slowly increased, then steeply increased, then decreased and lastly increased (n = 14, 21.2%). The functionality at admission to rehabilitation, measured with the Barthel Index, and the duration of rehabilitation stay differed between the patterns of physical activity. CONCLUSIONS: Multiple patterns of physical activity among older patients during hip fracture rehabilitation were found in this preliminary study. The functionality at admission to rehabilitation and the duration of rehabilitation stay were associated with the different patterns found in this study. Results of this study highlight the importance of personalized hip fracture treatment.

Transparency in hip fracture recovery over institutional boundaries: The transmural monitoring pathway.

OBJECTIVES: To develop a transmural pathway for healthcare professionals across institutions to monitor the recovery of hip fracture patients. The secondary objectives were to evaluate the pathway's feasibility and initial outcomes. DESIGN: Prospective cohort study. METHOD: Stakeholders of the hospital and geriatric rehabilitation institutions implemented a transmural monitoring pathway in which different geriatric health domains were monitored during three phases: The in-hospital, inpatient rehabilitation, and outpatient follow-up phase. The outcomes for the first 291 patients and the feasibility of the pathway were evaluated. If the outcomes of the clinimetrics significantly improved over time, progress in functional recovery was assumed. Feasibility was assessed according to the rate of adherence to the clinimetric tests. RESULTS: During the in-hospital phase, patients showed a decline in functional level (the Katz index of independence in Activities of Daily Living (Katz-ADL) pre-fracture vs. discharge: 0 (0-2) vs. 4 (4-5), P < 0.001). Patients, in which 78.6% (n = 140) had cognitive impairment and 41.2% had malnutrition, showed the most progress (Katz-ADL 2 (1-3)) during the inpatient rehabilitation phase. In the outpatient follow-up phase, recovery remained ongoing, but most patients had not returned to their pre-fracture functional levels (Katz-ADL 1 (1-3)). The pathway feasibility during the first phase was excellent (>85%), whereas room for improvement existed during other phases (<85%). CONCLUSION: The transmural monitoring pathway provides insight into the entire recovery process for all involved healthcare professionals. Patients showed the most progress during the rehabilitation phase. The pathway feasibility was excellent during the in-hospital phase, but improvements could be made during other phases.

Early Predictors for Discharge to Geriatric Rehabilitation after Hip Fracture Treatment of Older Patients.

OBJECTIVE: To investigate early predictors for discharge to a geriatric rehabilitation department at a skilled nursing home in older patients after hospitalization for hip fracture surgery. DESIGN: Retrospective cohort study. SETTING AND PARTICIPANTS: Data from 21,176 patients with hip fracture aged ≥70 years, who were registered in the Dutch Hip Fracture Audit database between January 1, 2017, and December 31, 2019, were included. METHODS: Patients were categorized into 3 discharge groups: home (n=7326), rehabilitation (n=11,738), and nursing home (n=2112). Age, gender, Pre-Fracture Mobility Score (PFMS), premorbid Katz index of independence in Activities of Daily Living (Katz-ADL), history of dementia, American Society of Anesthesiologists physical status classification (ASA score), type of anesthesia, fracture type, surgical treatment, and cotreatment by a geriatrician were gathered. Multinomial regression analysis was used to assess for early predictors. RESULTS: Higher age, poor premorbid mobility, lower premorbid Katz-ADL, no history of dementia, ASA score 3-5, general anesthesia, intramedullary implant, and cotreatment by a geriatrician were independent predictors for discharge to geriatric rehabilitation vs discharge home. Identical predictors were found for discharge to a nursing home vs discharge home. History of dementia and premorbid Katz-ADL were distinguishing factors; a higher premorbid Katz-ADL and a history of dementia were associated with a higher risk of discharge to a nursing home vs discharge home. The multinomial regression model correctly predicted 86%, 38.6%, and 2.4% of the patients in the rehabilitation group, home group, and nursing home group, respectively. CONCLUSIONS AND IMPLICATIONS: This study showed that age, PFMS, premorbid Katz-ADL, surgical treatment, ASA score, type of anesthesia, history of dementia, and cotreatment by a geriatrician were independent early predictors for discharge to geriatric rehabilitation vs discharge home in older patients after hip fracture surgery. Identical predictors were found as predictors for discharge to a nursing home vs discharge home, except for history of dementia and premorbid Katz-ADL.

Breath analysis in detecting epilepsy.

The aim of this proof of concept study is to investigate if an electronic nose (eNose) is able to make a distinction between breath profiles of diagnosed epilepsy patients and epilepsy-free control subjects. An eNose is a non-invasive device, with a working mechanism that is based on the presence of volatile organic compounds (VOCs) in exhaled breath. These VOCs interact with the sensors of the eNose, and the eNose has to be trained to distinguish between breath patterns from patients with a specific disease and control subjects without that disease. During the measurement participants were asked to breathe through the eNose for five minutes via a disposable mouthpiece. Seventy-four epilepsy patients and 110 control subjects were measured to train the eNose and create a classification model. To assess the effects of anti-epileptic drugs (AEDs) usage on the classification, additional test groups were measured: seven patients who (temporarily) did not use AEDs and 11 patients without epilepsy who used AEDs. The results show that an eNose is able to make a distinction between epilepsy and control subjects with a sensitivity of 76%, a specificity of 67%, and an accuracy of 71%. The results of the two additional groups of subjects show that the created model classifies one out of seven epilepsy patients without AEDs and six out of 13 patients without epilepsy but with AEDs correctly. In this proof of concept study, the AeonoseTM is able to differentiate between epilepsy patients and control subjects. However, the number of false positives and false negatives is still high, which suggests that this first model is still mainly based on the usage of various AEDs.