Trajectory of adherence to home rehabilitation among older adults with hip fractures and cognitive impairment

Factors associated with change in activities of daily living performance in home health care patients with diabetes

Older adults with diabetes are at risk for impairments in activities of daily living (ADL) performance. Home health (HH) services help patients regain their ability to perform ADLs following hospitalization, but there may be disparities in ADL improvement. We aimed to identify factors associated with change in ADL performance from the start of HH care to discharge in HH patients with diabetes age ≥65. This secondary analysis used Outcome and Assessment Information Set-D data collected by a HH agency. The sample (n = 1350) had a mean age of 76.3 (SD 7.3). Black/African American race and bowel incontinence/ostomy were associated with less ADL improvement. The following factors were associated with greater ADL improvement: having a caregiver who needed training/support, surgical wounds, pain that interfered with activity, confusion, and better scores in prior functioning. Overall, most patients improved their ADL performance while receiving HH care, but there are disparities that should be addressed.

Impact of rehabilitation adherence and depressive symptoms on post-stroke self-care ability and quality of life: a longitudinal study

BACKGROUND

Good rehabilitation adherence leads to effective post-stroke recovery. However, some recovering patients experience post-stroke depressive symptoms, which can affect post-stroke health outcomes. Previous studies have not examined the effect of a combination of rehabilitation adherence and depressive symptoms on recovery after a stroke.

OBJECTIVES

This study explored the combined predictive influence of rehabilitation adherence and post-stroke depressive symptoms on self-care abilities and quality of life in patients with stroke.

METHODS

This prospective longitudinal study analyzed data from 75 stroke patients. We examined rehabilitation adherence (self-reported, five-point scale), post-stroke depressive symptoms (Taiwanese Depression Scale), self-care ability (Chinese versions of the Barthel Index and Lawton - Brody Instrumental Activities of Daily Living Scale), and post-stroke quality of life (World Health Organization Quality of Life-BREF). Patients were followed up for six months after inclusion. The influence of rehabilitation adherence and post-stroke depressive symptoms on post-stroke self-care abilities and quality of life was examined using generalized estimating equations.

RESULTS

The sample's mean age was 60.85 (±12.9) years. Patients with perfect rehabilitation adherence had better self-care abilities and quality of life than those with imperfect rehabilitation adherence. Patients without post-stroke depressive symptoms had a better quality of life than their counterparts. Patients with perfect rehabilitation adherence and no post-stroke depressive symptoms had better self-care abilities and quality of life than those with imperfect rehabilitation adherence and post-stroke depressive symptoms.

CONCLUSION

Both depressive symptoms and rehabilitation adherence behavior impacted the rehabilitation effect among patients who are recovering from a stroke.

Can rehabilitation adherence among stroke patients be measured using a single item?

AIMS AND OBJECTIVES

To assess the concurrent validity between logbooks and a single-item rehabilitation adherence measurement for patients with stroke. Agreement between caregivers and patients and between caregivers and physical therapists regarding a single-item measurement was investigated, and its predictive validity was explored.

BACKGROUND

Adherence to therapy is a primary determinant of treatment success. There are no standard instruments for measuring rehabilitation adherence available for stroke patients.

DESIGN

Prospective longitudinal study.

METHODS

Seventy-five patients with stroke were recruited, measured four times and followed for 6 months. The Strengthening the Reporting of Observational Studies in Epidemiology (STROBE) checklist was used to ensure comprehensive reporting. Adherence was documented in logbooks, and single-item measurements were compared. Predictive validity was explored by assessing associations between adherence levels, self-care ability and health-related quality of life. The Spearman's correlation coefficients, weighted kappa, and generalised estimating equations statistics were used to explore the concurrent validity, measurement agreement, and predictive validity, respectively.

RESULTS

Logbook records had a fair correlation (r_s  = .23, p = .04) with the single-item rehabilitation adherence measurements. There was moderate agreement (kappa = 0.42, p < .001) between caregiver and patient assessments and fair agreement (kappa = 0.29, p = .017) between caregiver and physical therapist assessments of patients' rehabilitation adherence levels. Perfect rehabilitation adherence, based on the logbook and single-item measurements, predicted better scores for self-care ability and quality of life than imperfect rehabilitation adherence during 6 months after inclusion.

CONCLUSIONS

There was fair concurrent validity between logbooks and single-item rehabilitation adherence measurements and moderate and fair adherence measure agreement between caregivers and patients and caregivers and physical therapists, respectively. Logbooks and single-item rehabilitation adherence measurements had adequate predictive validity.

RELEVANCE TO CLINICAL PRACTICE

Single-item rehabilitation adherence measurement is a workable and straightforward method to assess stroke patients' rehabilitation adherence in busy clinical care settings. Caregivers can represent stroke patients regarding their reported rehabilitation adherence.

PATIENT OR PUBLIC CONTRIBUTION

Patients were diagnosed with stroke in the study hospital. Rehabilitation physicians transferred patients to a research nurse who then screened them for the inclusion criteria and invited them and their family caregivers to participate in this study if they met the requirements. We also recruited seven physical therapists responsible for the physical therapy of the study participants. After participants signed informed consent, the research nurse encouraged participants to respond to research questions face to face, including rehabilitation adherence data, daily physical function, and quality of life. Each participant was measured four times at baseline and at 1, 3, and 6 months after inclusion in this study. Physical therapists had to score their patients' rehabilitation adherence levels before discharge.

TRIAL REGISTRATION DETAILS

Not applicable.

Deep learning-based predictions of older adults' adherence to cognitive training to support training efficacy

As the population ages, the number of older adults experiencing mild cognitive impairment (MCI), Alzheimer's disease, and other forms of dementia will increase dramatically over the next few decades. Unfortunately, cognitive changes associated with these conditions threaten independence and quality of life. To address this, researchers have developed promising cognitive training interventions to help prevent or reverse cognitive decline and cognitive impairment. However, the promise of these interventions will not be realized unless older adults regularly engage with them over the long term, and like many health behaviors, adherence to cognitive training interventions can often be poor. To maximize training benefits, it would be useful to be able to predict when adherence lapses for each individual, so that support systems can be personalized to bolster adherence and intervention engagement at optimal time points. The current research uses data from a technology-based cognitive intervention study to recognize patterns in participants' adherence levels and predict their future adherence to the training program. We leveraged the feature learning capabilities of deep neural networks to predict patterns of adherence for a given participant, based on their past behavior. A separate, personalized model was trained for each participant to capture individualistic features of adherence. We posed the adherence prediction as a binary classification problem and exploited multivariate time series analysis using an adaptive window size for model training. Further, data augmentation techniques were used to overcome the challenge of limited training data and enhance the size of the dataset. To the best of our knowledge, this is the first research effort to use advanced machine learning techniques to predict older adults' daily adherence to cognitive training programs. Experimental evaluations corroborated the promise and potential of deep learning models for adherence prediction, which furnished highest mean F-scores of 75.5, 75.5, and 74.6% for the Convolution Neural Network (CNN), Long Short-Term Memory (LSTM) network, and CNN-LSTM models respectively.

A Machine-Learning Based Approach for Predicting Older Adults' Adherence to Technology-Based Cognitive Training

Adequate adherence is a necessary condition for success with any intervention, including for computerized cognitive training designed to mitigate age-related cognitive decline. Tailored prompting systems offer promise for promoting adherence and facilitating intervention success. However, developing adherence support systems capable of just-in-time adaptive reminders requires understanding the factors that predict adherence, particularly an imminent adherence lapse. In this study we built machine learning models to predict participants' adherence at different levels (overall and weekly) using data collected from a previous cognitive training intervention. We then built machine learning models to predict adherence using a variety of baseline measures (demographic, attitudinal, and cognitive ability variables), as well as deep learning models to predict the next week's adherence using variables derived from training interactions in the previous week. Logistic regression models with selected baseline variables were able to predict overall adherence with moderate accuracy (AUROC: 0.71), while some recurrent neural network models were able to predict weekly adherence with high accuracy (AUROC: 0.84-0.86) based on daily interactions. Analysis of the post hoc explanation of machine learning models revealed that general self-efficacy, objective memory measures, and technology self-efficacy were most predictive of participants' overall adherence, while time of training, sessions played, and game outcomes were predictive of the next week's adherence. Machine-learning based approaches revealed that both individual difference characteristics and previous intervention interactions provide useful information for predicting adherence, and these insights can provide initial clues as to who to target with adherence support strategies and when to provide support. This information will inform the development of a technology-based, just-in-time adherence support systems.