Prediction of fall events during admission using eXtreme gradient boosting: a comparative validation study.

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.

Do Emergency Nurses Spend Enough Time on Nursing Activities? The Relationship Between Actual and Expected Patient Care Nursing Time.

BACKGROUND: The overcrowded environments of emergency departments (EDs) lead to increased clinical workloads for nurses and infl uences the quality of patient care. This study aimed to evaluate whether the quality of patient care meets the expectations of emergency nurses in Taiwan by measuring the amount of time nurses spend on patient care activities. METHODS: The direct observation study was conducted in one suburban academic hospital with approximately 80,000 annual ED visits. This study observed emergency nurses and the time they spent on their nursing activities. The directly measured times and nurse expected patient care nursing times were compared. RESULTS: For all 88 types of nursing activities recorded, each measured nursing time was less than the expected nursing time. On average, the measured nursing time was 82% less than the expected nursing time (2.0 ± 0.3 minutes vs. 11.6 ± 1.5 minutes, p < 0.01). Among the 88 types of nursing activities recorded, the average measured time spent on 76 types (86%) was less than 3 minutes. The nursing activity on which the longest time was spent was cerebrospinal fl uid study nursing (7 minutes). The most frequent nursing activity was documentation. CONCLUSION: The nursing time spent on patient-care activities in EDs was much less than the nurses expected. The results may provide a basis for nursing quality measurements and manpower calculations for EDs.

Symptom management tasks and behaviors related to chemotherapy in Taiwanese outpatients with breast cancer.

PURPOSE: There are many challenges that patients face when dealing with the side effects of chemotherapy. The purpose of this study was to describe the key tasks and behaviors that contribute to symptom management and the difficulties relating to self-care in the context of chemotherapy in Taiwanese outpatients with breast cancer. METHOD: This qualitative study included a purposive sample of 17 women with breast cancer, aged 30-64 years, and who had undergone chemotherapy. Data were collected via face-to-face semi-structured tape-recorded interviews. Qualitative content analysis was performed for the identified themes. RESULTS: Four main categories of tasks were identified that reflected the patient's experience with the behaviors required for chemotherapy symptom management. These task domains included communicating chemotherapy-related concerns, managing chemotherapy-related symptoms, managing emotional and interpersonal disturbances, and acquiring relevant resources. In particular, the results indicated many challenges with behaviors related to self-management under these tasks. CONCLUSIONS: Systematic information regarding symptoms relating to chemotherapy and self-management strategies should be put into practice at the beginning of chemotherapy and following assessment, in addition to the individual support of patients during their treatment.

Development and Preliminary Evaluation of Psychometric Properties of Symptom-Management Self-Efficacy Scale for Breast Cancer Related to Chemotherapy.

PURPOSE: The purpose of this study was to develop and preliminarily evaluate the reliability and validity of the Symptom-Management Self-Efficacy Scale-Breast Cancer (SMSES-BC) related to chemotherapy. METHODS: The study included three stages. This paper presents the results of stage 2 and stage 3. In total, 34 items in the SMSES-BC were found during stage 1 from qualitative findings, a literature review, and expert suggestions; the 34 items were used for the psychometric properties test. Test-retest reliability and Cronbach α were assessed in the first sample, which included 45 participants for the pilot test (stage 2). The second sample, which included 152 patients, was used to assess the construct validity and concurrent validity (stage 3). RESULTS: The pilot test results revealed a test-retest reliability of .73 (p < .001) and Cronbach α coefficient of .96 for the total scale. Three factors (managing chemotherapy-related symptoms, acquiring problem solving, and managing emotional and interpersonal disturbances) were identified from exploratory factor analysis. Correlation coefficient r was .40 (p < .001), which supported the association between SMSES-BC and the General Self-Efficacy Scale for concurrent validity. CONCLUSIONS: The study results demonstrate acceptable reliability and validity for the SMSES-BC that was developed for measuring symptom-management self-efficacy related to chemotherapy for patients with breast cancer. This study suggests further research to validate the construct of the SMSES-BC.