The influence of informal caregivers on the rehabilitation of the elderly in the postoperative period of proximal femoral fracture

A machine learning-based prediction model pre-operatively for functional recovery after 1-year of hip fracture surgery in older people

Background

Machine learning (ML) has been widely utilized for constructing high-performance prediction models. This study aimed to develop a preoperative machine learning-based prediction model to identify functional recovery one year after hip fracture surgery.

Methods

We collected data from 176 elderly hip fracture patients admitted to the Department of Orthopaedics and Oncology at Shenzhen Second People's Hospital between May 2019 and December 2019, who met the inclusion criteria. Patient's functional recovery was monitored for one year after surgery. We selected 26 factors, comprising 12 preoperative indicators, 8 surgical indicators, and 6 postoperative indicators. Eventually, 77 patients were included based on the exclusion criteria. Random allocation divided them into the training set (70%) and test set (30%) for internal validation. The Lasso method was employed to screen prognostic variables. We conducted comparisons among various common machine learning classifiers to determine the best prediction model. Prediction performance was evaluated using the area under the receiver operating characteristic curve (ROC), calibration curve, and decision curve analysis. To identify the importance of the predictor variables, we performed the recursive feature elimination (RFE) algorithm based on Shapley Additive Explanations (SHAP) values.

Results

The AUCs for the testing dataset were as follows: logistic regression (Logit) model = 0.934, k-nearest neighbors (KNN) model = 0.930, support vector machine (SVM) model = 0.910, Gaussian naive Bayes (GNB) model = 0.926, decision tree (DT) model = 0.730, random forest (RF) model = 0.957, and Extreme Gradient Boosting (XGB) model = 0.902. Among the seven ML-based models tested, the RF model demonstrated the best prediction performance, incorporating four features: postoperative rehabilitation compliance, marital status, age-adjusted Charlson comorbidity score (aCCI), and clinical frailty scale (CFS).

Conclusion

We developed a prediction model for the functional recovery following hip fracture surgery in elderly patients after one year, based on the Random Forest (RF) algorithm. This model exhibited superior prediction performance (ROC) compared to other models. The software application is available for use. External validation in a larger patient cohort or diverse hospital settings is necessary to assess the clinical utility of this tool.

Family Caregivers' Experiences with Tele-Rehabilitation for Older Adults with Hip Fracture

Background: There is a knowledge gap for implementing tele-rehabilitation (telerehab) after hip fracture. We recently conducted a clinical trial (ClinicalTrials.gov Identifier: NCT02968589) to test a novel online family caregiver-supported rehabilitation program for older adults with hip fracture, called @ctivehip. In this qualitative substudy, our objective was to use semi-structured interviews to explore family caregivers experience with the telerehab program. Methods: Twenty-one family caregivers were interviewed between three and six months after the older adults completed @ctivehip. One occupational therapist with research and clinical experience, but not involved in the main trial, conducted and transcribed the interviews. We conducted a multi-step content analysis, and two authors completed one coding cycle and two recoding cycles. Results: Family caregivers who enrolled in @ctivehip were satisfied with the program, stated it was manageable to use, and perceived benefits for older adults’ functional recovery after hip fracture. They also suggested improvements for the program content, such as more variety with exercises, and increased monitoring by health professionals. Conclusions: This work extends existing literature and generates research hypotheses for future studies to test telerehab content and program implementation.

Effects of Tele-Rehabilitation Compared with Home-Based in-Person Rehabilitation for Older Adult's Function after Hip Fracture

This study aimed to examine the effect of a multidisciplinary tele-rehabilitation program on functional recovery of older adults with hip fracture compared with home-based in-person rehabilitation. In this single-blinded, non-randomized clinical trial, we included older with hip fracture. The tele-rehabilitation group received a 12-week tele-rehabilitation program (supervised by their family caregivers). The control group received the usual postoperative rehabilitation provided by the Andalusian health system (Spain). The primary outcome was the patient-reported functional status assessed with the Functional Independence Measure. We also measured performance-based functional recovery using the Timed Up and Go Test and Short Physical Performance Battery. We performed both a per-protocol (62 participants; 28 tele-rehabilitation and 34 control groups) and an intention-to-treat analysis (71 participants; 35 tele-rehabilitation and 36 control groups). Participants who used the tele-rehabilitation program had higher Functional Independence Measure scores (high effect size: 0.98 Cohen’s d; p < 0.001) and better performance in the Timed Up and Go Test (medium effect size: 0.63 Cohen’s d; p = 0.025) compared with the control group. Differences between groups post-intervention were not statistically significant in the Short Physical Performance Battery. The tele-rehabilitation intervention proposed in this study is a valuable treatment option in the recovery process for older adults with hip fracture. ClinicalTrials.gov Identifier: NCT02968589.

Needs of Chinese patients undergoing home-based rehabilitation after hip replacement: A qualitative study

Background

The needs of Chinese patients undergoing home-based rehabilitation after hip replacement surgery remain unclear. In this study, we qualitatively investigated the needs of Chinese patients undergoing home-based rehabilitation after hip replacement surgery.

Methods

A total of 21 participants undergoing home-based rehabilitation after hip replacement surgery were included in this study. Individual semi-structured interviews involving all participants were performed to determine the needs and experiences of this patient population during home-based rehabilitation. Data were subjected to qualitative content analysis.

Results

The patients had numerous needs during rehabilitation. Three substantive themes, namely, the need to obtain health-related knowledge, the need to obtain care and support, and the needs of those who cannot perform self-care, were identified from the qualitative data. The participants shared valuable insights into their needs during home-based rehabilitation after hip replacement and provided potential suggestions.

Conclusions

Patients undergoing home-based rehabilitation after hip replacement have several strong needs and lack proper guidance. The initial and continuous engagement of rehabilitation professionals and the establishment of related policies based on patient’s needs are potential approaches for improving the effectiveness of home-based rehabilitation after hip replacement.

Comfort level of caregivers of cancer patients receiving palliative care

Objective:

To verify the association between the level of comfort of the caregiver and socio-demographic variables related to caregiving, and the patient’s functional status and symptoms.

Method:

Cross-sectional study with non-probabilistic intentional sample. The instruments Palliative Performance Scale (score 0 to 100%), Edmonton Symptom Assessment Scale (symptom scores from zero to ten) and Holistic Comfort Questionnaire (total score ranging from 49 to 294 and mean score from 1 to 6) were used. The relationship between comfort scores and independent variables was calculated by multiple linear regression.

Results:

Fifty informal caregivers participated in the study - 80% were female, 32% were 60 years old or older, 36% were children of the patient, 58% had paid work and 60% did not have help in the care. The mean overall comfort was 4.52 points. A better functional status of the patients was associated with higher levels of comfort of the caregivers. Older caregivers who received helped in the care activities presented higher comfort scores.

Conclusion:

The level of comfort of caregivers of cancer patients receiving palliative care was associated with socio-demographic variables and patients’ functional status and symptoms.

Predictive factors for thirty day mortality in geriatric patients with hip fractures: a prospective study

PURPOSE

The study aims to analyze the incidence of 30-day mortality in elderly patients who underwent surgery for hip fractures and its associated factors.

METHODS

A prospective multicentric study was performed. All patients aged ≥ 65 years, with fragility hip fractures, consecutively admitted in two Italian hospitals were included. Patients with periprosthetic or pathological fractures were excluded. Logistic regression was used to identify patient and patient care variables that independently influenced the 30-day mortality and receiver operating characteristic (ROC) curve analysis to assess their predictive capacity on the outcome.

RESULTS

Of the patients, 728 met the inclusion criteria, of whom approximately 5% died within 30 days after admission. The 45.7% of the deceased patients died while hospitalized. Multivariate analysis showed that advancing age was the only independent predictor of 30-day mortality (OR = 1.084, 95% CI = 1.024-1.147), while a higher presence of informal caregivers was a protective factor (OR = 0.988, 95% CI = 0.979-0.997). The area under the ROC curve of the model was 0.723 (CI95% 0.676-0.770) for 30-day mortality in elderly hip fractures patients.

CONCLUSIONS

Patients with an advanced age need careful follow-up, especially within 30 days following operation for hip fracture; at the same time, the presence of informal caregivers at the patient's bedside should be promoted.