As the performance of current fall risk assessment tools is limited, clinicians face significant challenges in identifying patients at risk of falling. This study proposes an automatic fall risk prediction model based on eXtreme gradient boosting (XGB), using a data-driven approach to the standardized medical records. This study analyzed a cohort of 639 participants (297 fall patients and 342 controls) from Chang Gung Memorial Hospital, Chiayi Branch, Taiwan. A derivation cohort of 507 participants (257 fall patients and 250 controls) was collected for constructing the prediction model using the XGB algorithm. A comparative validation of XGB and the Morse Fall Scale (MFS) was conducted with a prospective cohort of 132 participants (40 fall patients and 92 controls). The areas under the curves (AUCs) of the receiver operating characteristic (ROC) curves were used to compare the prediction models. This machine learning method provided a higher sensitivity than the standard method for fall risk stratification. In addition, the most important predictors found (Department of Neuro-Rehabilitation, Department of Surgery, cardiovascular medication use, admission from the Emergency Department, and bed rest) provided new information on in-hospital fall event prediction and the identification of patients with a high fall risk.
The purpose of this study was to evaluate the longitudinal incidence, severity, pattern of changes or predictors of oxaliplatin‐induced peripheral neuropathy (OXAIPN) in Taiwanese patients with colorectal cancer. A longitudinal repeated measures study design was employed, and 77 participants were recruited from the colorectal and oncology departments of two teaching medical centres in Taiwan. Physical examinations were performed, and self‐reports regarding adverse impacts of OXAIPN and quality of life were obtained at five time points throughout 12 cycles of chemotherapy (C/T). The incidence of OXAIPN increased with C/T cycles (31.1%–81.9%), and the upper limb numbness and cold sensitivity were most significant acute OXAIPN symptoms (29.9%–73.6%). Findings also documented significant increases in overall severity, symptom distress, interference and physical results associated with OXAIPN over the course of C/T. Predictors of OXAIPN severity varied by treatment cycle, including younger patient, higher cumulative dose of oxaliplatin, greater body surface area, receipt of chemotherapy in winter and the occurrence of OXAIPN during prior C/T cycles. The results from this study might help healthcare providers to recognise the symptom characteristics, degree of influences, trends and high‐risk group of OXAIPN, facilitating early evaluation and potential interventions to mitigate or prevent negative effects of OXAIPN on patients.
As caregivers undertake caregiving responsibilities over a long period of time, the burdens placed on them could lead to undue stress and affect their health. This correlation study examined the current situations and relationships among caregiver burden, health status, and learned resourcefulness (LR) of older caregivers who care for disabled older adults, and predicted the important factors that affect their caregiver burden. In all, 108 older caregivers were recruited from home care services of two hospitals. Structured questionnaire interviews were applied to collect data: the Caregiver Burden Scale, the SF-36 Health Survey (SF-36), and the Rosenbaum's Self-Control Schedule. Results indicated that the caregiver burden was negatively correlated with physical health, mental health, and LR. Physical and mental health were positively correlated with LR. The predictors of caregiver burden included LR, health status, economic status, and activities of daily living, which accounted for 58.60% of the total caregiver burden variance.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.