Non-linear missing data imputation for healthcare data via index-aware autoencoders.

The availability of data in the healthcare domain provides great opportunities for the discovery of new or hidden patterns in medical data, which can eventually lead to improved clinical decision making. Predictive models play a crucial role in extracting this unknown information from data. However, medical data often contain missing values that can degrade the performance of predictive models. Autoencoder models have been widely used as non-linear functions for the imputation of missing data in fields such as computer vision, transportation, and finance. In this study, we assess the shortcomings of autoencoder models for data imputation and propose modified models to improve imputation performance. To evaluate, we compare the performance of the proposed model with five well-known imputation techniques on six medical datasets and five classification methods. Through extensive experiments, we demonstrate that the proposed non-linear imputation model outperforms the other models for all degrees of missing ratios and leads to the highest disease classification accuracy for all datasets.

Effects of Stress on Critical Care Nurses: A National Cross-Sectional Study.

BACKGROUND:: Health care is a demanding field, with a high level of responsibility and exposure to emotional and physical danger. High levels of stress may result in depression, anxiety, burnout syndrome, and in extreme cases, post-traumatic stress disorder. The aim of this study was to determine which personal, professional, and organizational variables are associated with greater perceived stress among critical care nurses for purposes of developing integrative solutions to decrease stress in the future. METHODS:: We conducted a correlation research survey using a cross-sectional design and an in-person survey method. The questionnaire consisted of 2 parts: (1) socioeconomic, professional, and institutional variables and (2) work stressors. Surveys were conducted between January 1, 2011, and December 1, 2015. Multistage cluster random sampling was utilized for data collection. Inclusion criteria were (1) age ≥18 years, (2) registered nurse, (3) works in the intensive care unit (ICU), and (4) willing and able to complete the survey. RESULTS:: We surveyed 21 767 ICU nurses in Iran and found that male sex, lower levels of peer collaboration, working with a supervisor in the unit, nurse-patient ratios, and working in a surgical ICU were positively associated with greater stress levels. Increasing age and married status were negatively associated with stress. Intensive care unit type (semi-closed vs open), ICU bed number, shift time, working on holidays, education level, and demographic factors including body mass index, and number of children were not significantly associated with stress levels. CONCLUSION:: As the largest study of its kind, these findings support those found in various European, North, and South American studies. Efforts to decrease workplace stress of ICU nurses by focusing on facilitating peer collaboration, improving resource availability, and staffing ratios are likely to show the greatest impact on stress levels.

Predictive models for charitable giving using machine learning techniques.

Private giving represents more than three fourths of all U.S. charitable donations, about 2% of total Gross Domestic Product (GDP). Private giving is a significant factor in funding the nonprofit sector of the U.S. economy, which accounts for more than 10% of total GDP. Despite the abundance of data available through tax forms and other sources, it is unclear which factors influence private donation, and a reliable predictive mechanism remains elusive. This study aims to develop predictive models to accurately estimate future charitable giving based on a set of potentially influential factors. We have selected several factors, including unemployment rate, household income, poverty level, population, sex, age, ethnicity, education level, and number of vehicles per household. This study sheds light on the relationship between donation and these variables. We use Stepwise Regression to identify the most influential variables among the available variables, based on which predictive models are developed. Multiple Linear Regression (MLR) and machine learning techniques, including Artificial Neural Networks (ANN) and Support Vector Regression (SVR) are used to develop the predictive models. The results suggest that population, education level, and the amount of charitable giving in the previous year are the most significant, independent variables. We propose three predictive models (MLR, ANN, and SVR) and validate them using 10-fold cross-validation method, then evaluate the performance using 9 different measuring criteria. All three models are capable of predicting the amount of future donations in a given region with good accuracy. Based on the evaluation criteria, using a test data set, ANN outperforms SVR and MLR in predicting the amount of charitable giving in the following year.