Development of a Predictive Model for Survival Over Time in Patients With Out-of-Hospital Cardiac Arrest Using Ensemble-Based Machine Learning.

As of now, a model for predicting the survival of patients with out-of-hospital cardiac arrest has not been established. This study aimed to develop a model for identifying predictors of survival over time in patients with out-of-hospital cardiac arrest during their stay in the emergency department, using ensemble-based machine learning. A total of 26 013 patients from the Korean nationwide out-of-hospital cardiac arrest registry were enrolled between January 1 and December 31, 2019. Our model, comprising 38 variables, was developed using the Survival Quilts model to improve predictive performance. We found that changes in important variables of patients with out-of-hospital cardiac arrest were observed 10 minutes after arrival at the emergency department. The important score of the predictors showed that the influence of patient age decreased, moving from the highest rank to the fifth. In contrast, the significance of reperfusion attempts increased, moving from the fourth to the highest rank. Our research suggests that the ensemble-based machine learning model, particularly the Survival Quilts, offers a promising approach for predicting survival in patients with out-of-hospital cardiac arrest. The Survival Quilts model may potentially assist emergency department staff in making informed decisions quickly, reducing preventable deaths.

Perioperative risk factors for new-onset postoperative atrial fibrillation among patients after isolated coronary artery bypass grafting: A retrospective study.

AIMS: Incidence of atrial fibrillation is considerably high after open heart surgery, which may prolong hospitalization and increase mortality. The aim of the present study is to investigate the perioperative risk factors for the occurrence of new-onset atrial fibrillation following isolated coronary artery bypass grafting. DESIGN: A retrospective study. METHODS: A total of 327 Korean patients recorded to have undergone first-time isolated coronary artery bypass grafting and no preoperative history of atrial fibrillation were included. The data were obtained from electronic health record from January 2010 to December 2019 at a tertiary care hospital. Predictors of new-onset atrial fibrillation after the surgery were identified by multivariate logistic regression analysis. RESULTS: The incidence rate of new-onset atrial fibrillation after coronary artery bypass grafting was approximately 28.4%, and the highest occurrence rate was 44.1% on postoperative day 2. Our main finding showed that advanced age was the strongest predictor of atrial fibrillation after coronary artery bypass grafting. In addition, history of stroke and depression, chronic obstructive pulmonary disease and intraoperative use of intra-aortic balloon pump were shown to be the risk factors. CONCLUSION: Our findings showed that approximately 28% patients had new-onset atrial fibrillation after the surgery. Healthcare professionals should proactively assess risk factors for postoperative atrial fibrillation and focus more on older adults with pre-existing comorbidities, such as stroke, depression and chronic obstructive pulmonary disease. IMPACT: Older adults with history of stroke, depression and comorbid chronic obstructive pulmonary disease should be carefully monitored closely during perioperative period. The study highlights that early assessment of new-onset postoperative atrial fibrillation can contribute to promote the quality of nursing care and frontline nurses may be a vital role in timely detection of atrial fibrillation after surgery. Prospective studies are required to identify the mechanisms connecting perioperative risk factors for atrial fibrillation after cardiac surgery.

The effects of a 24-week interactive text message-based mobile health intervention for enhancing self-care behaviours of patients with heart failure: A quasi-experimental study.

AIMS: The aim of this study was to identify the effects of a 24-week interactive text message-based mobile health intervention (called) on enhancing the self-care behaviours of patients with heart failure. BACKGROUND: Whether text message-based mobile health intervention can be used to improve long-term adherence to self-care behaviours among heart failure patients remains unclear. DESIGN: A quasi-experimental study with a pretest-post-test design and repeated measures. METHODS: Data from 100 patients (mean age, 58.78 years; 83.0% men) were analysed. The intervention group (n = 50) used the program over 24 weeks, which consisted of weekly goal setting and interactive text messaging, while the control group (n = 50) received usual care. Trained research assistants collected data using self-reported Likert questionnaires. Primary (self-care behaviours) and secondary (health literacy, eHealth literacy, and disease knowledge) outcome variables were measured at baseline and at 1, 3 and 6 months after intervention for follow-up. RESULTS: The findings showed that the intervention group demonstrated significantly better self-care behaviours than the control group during the 6 months. Notably, the trajectory of self-care behaviours of the patients in the intervention group showed a steep rise between the first- and third-month follow-up, followed by high stability between the third- and sixth-month follow-up. In addition, the intervention group had significantly higher disease knowledge than the control group at the first- and sixth-month follow-up. CONCLUSIONS: We found that the program, as an interactive text messaging service, may be an optimal strategy for improving long-term adherence to self-care behaviours through motivating and providing social support. RELEVANCE TO THE NURSING PRACTICE: The WithUs program can help nurses and other healthcare professionals to track patients' health indicators such as symptom severity, diet and physical activity. In addition, nurses can take an important role in evaluating the efficacy of the app in relation to patients' health outcome. PATIENT OR PUBLIC CONTRIBUTION: Patients have completed a self-reported questionnaire after providing informed consent.