Using machine learning in prediction of ICU admission, mortality, and length of stay in the early stage of admission of COVID-19 patients

The recent COVID-19 pandemic has affected health systems across the world. Especially, Intensive Care Units (ICUs) have played a pivotal role in the treatment of critically-ill patients. At the same time however, the increasing number of admissions due to the vast prevalence of the virus have caused several problems for ICU wards such as overburdening of staff and shortages of medical resources. These issues might have affected the quality of healthcare services provided directly impacting a patient’s survival. The objective of this research is to leverage Machine Learning (ML) on hospital data in order to support hospital managers and practitioners with the treatment of COVID-19 patients. This is accomplished by providing more detailed inference about a patient’s likelihood of ICU admission, mortality and in case of hospitalization the length of stay (LOS). In this pursuit, the outcome variables are in three separate models predicted by five different ML algorithms: eXtreme Gradient Boosting (XGB), K-Nearest Neighbor (KNN), Random Forest (RF), bagged-CART (b-CART), and LogitBoost (LB). With the exception of KNN, the studied models show good predictive capabilities when evaluating relevant accuracy scores, such as area under the curve. By implementing an ensemble stacking approach (either a Neural Net or a General Linear Model) on top of the aforementioned ML algorithms the performance is further boosted. Ultimately, for the prediction of admission to the ICU, the ensemble stacking via a Neural Net achieved the best result with an accuracy of over 95%. For mortality at the ICU, the vanilla XGB performed slightly better (1% difference with the meta-model). To predict large length of stays both ensemble stacking approaches yield comparable results. Besides it direct implications for managing COVID-19 patients, the approach presented serves as an example how data can be employed in future pandemics or crises.

Association between health locus of control and perceived stress in college student during the COVID-19 outbreak: a cross-sectional study in Iran.

BACKGROUND: The COVID-19 pandemic as a global mental health crisis has affected everyone, including students. The present study aimed to determine and investigate the relationship between health locus of control and perceived stress in students of Bushehr University of Medical Sciences (southern Iran) during the outbreak of COVID-19. METHODS: The present cross-sectional study examined 250 students of Bushehr University of Medical Sciences. We performed simple random sampling and utilized the demographic information form, Multidimensional Health Locus of Control scale (MHLCS) by Wallston, and Perceived Stress Scale (PSS) by Cohen to collect data. We analyzed data using the SPSS, Pearson correlation coefficient, and the hierarchical regression model with an error level of 5%. RESULTS: The mean perceived stress was 30.74 ± 8.09, and 92.4% of the students had moderate and high stress levels. Among the components of the health locus of control, the internal health locus of control (IHLC) had the highest mean in students (27.55 ± 3.81). Furthermore, the internal health locus of control (R = - 0.30, P < 0.001) had a significant inverse relationship, with perceived stress and the chance health locus of control (CHLC) (R = 0.30, P < 0.001) had a significant direct relationship. In the final regression model, the health locus of control and all the variables predicted 22.7% of the perceived stress variation in students during the COVID-19 period. CONCLUSION: The results indicated that the internal health locus of control was associated with a reduction of perceived stress, and the powerful others health locus of control (PHLC) was related to its increase in students during the COVID-19 pandemic. Given the uncertain future, in the present work, universities are suggested to design web-based educational interventions alongside the curriculum to further strengthen the internal health locus of control and thus help reduce their perceived stress.

The association between moral distress and mental health among nurses working at selected hospitals in Iran during the COVID-19 pandemic.

BACKGROUND: In the event of an epidemic outbreak, the mental health of medical staff, including nurses who serve on the frontlines of hospitals, can be affected; thus, the identification of factors affecting nurses' mental health is of importance. OBJECTIVE: This study aimed to examine the association between moral distress and the mental health of nurses working at four selected hospitals in Iran during the coronavirus disease 2019 (COVID-19) pandemic. METHODS: A cross-sectional questionnaire survey was conducted on 296 nurses working at the selected hospitals in Bushehr and Shiraz (south of Iran) at the time of the COVID-19 outbreak. The collected data were analyzed via logistic regression analysis. RESULTS: The mean scores for nurses' moral distress were low (54.31±24.84). The results of this study indicated more symptoms of mental issues among nurses (73.60%). Moreover, a significant association was observed between mental health and moral distress. Among the examined demographic variables, only gender had a significant association with mental health (p-value = 0.014). CONCLUSION: The results of this study indicated that an increase in moral distress would lead to a significant increase in mental health issues of the examined nurses. Nurse managers and hospital policymakers should develop strategies to enhance nurses' level of mental health, as well as providing adequate emotional and family support for nurses. Considering the intensifying role of gender in this association, timely interventions are necessary to reduce the negative effects of workplace pressure/stress on female nurses.

The relationship between professional self-concept and work-related quality of life of nurses working in the wards of patients with COVID-19.

BACKGROUND: Nurses are at the forefront of providing health care services and their performance is largely determinant of the quality of health care. This study aims to investigate associations between professional self-concept (PSC) and WRQoL among nurses from selected hospitals in Bushehr and Shiraz cities (south of Iran), during the period of COVD-19 pandemic. METHOD: This study is designed as a cross-sectional study. Available sampling was performed among active nurses in the care wards of patients with Covid-19 in public hospitals in Bushehr and Shiraz. Data were collected using demographic information form, along with the work-related quality of life and professional self-concept questionnaires. SPSS software and univariate and multivariate linear regression statistical methods with a significance level of 0.05 were used to analyze the data. RESULTS: The mean scores of the PSC and the WRQoL Scale in nurses were respectively 202.32 ± 38.19 and 68.81 ± 19.12. There was also a significant direct relationship between PSC and WRQoL. PSC together with work location and working experience could thus explain 34.6% of the variance in WRQoL, which was 26.5% for PSC. CONCLUSION: Considering the confirmation of the predictive role of nurses' PSC in their WRQoL in terms of planning and designing interventions to boost their WRQoL, attention to internal factors such as PSC is of utmost importance.