Psychometric properties of the Chinese version of the Infertility Self-Efficacy Scale

Objective:To translate the English version of Infertility Self-Efficacy Scale into Chinese and to validate the psychometric properties of the Chinese version of the Infertility Self-Efficacy Scale(CISE).Method(s):Participants were recruited from the Gynecology Department of two city hospitals.Five main processes were involved in the formation of CISE[1]:scale translation based on expert consultation[2];pre-test questionnaire development with infertile women's feedback(N=20)[3];factor structure assessed by exploratory and confirmatory factor analysis(N=177)[4];assessment of reliability by internal consistency(N=177)and test-retest reliability(N=21);and[5]assessment of convergent validity with Self-rating Anxiety Scale,Self-rating Depression Scale,and Simplified Coping Style Questionnaire(N=177).Results:This study established a 16-item CISE.Factor analyses confirmed a onecomponent solution,which explained 54.59% of total variances and showed an acceptable model fit.Cronbach's a and test-retest correlation coefficients for the scale were 0.94 and 0.84,respectively.The CISE score was significantly correlated with anxiety(r=0.47),depression(r=0.60),positive coping style(r=0.37),and certain negative coping style items.Conclusion:This 16-item CISE is a reliable and valid measure to evaluate perceived selfefficacy among a sample of Chinese women who underwent infertility treatment.

Predicting Critically Ill Patients Short-Term Mortality Risk Using Routinely Collected Data:Deep Learning Model Development,Validation,and Explanation

This paper aims to develop and validate a deep learning-based short-term mortality risk prediction model for critically ill patients by using routinely collected data in a large Chinese cohort and explore the explainability of the model decision.A total of 10925 critically ill patients between January 2014 and June 2020 are included in this study.Data routinely collected in the electronic health records(EHRs)system are extracted and used to develop a short-term mortality risk prediction model based on a deep artificial neural network(ANN).The features include demographic characteristics,vital signs,laboratory tests,and the daily dose of intravenous medications.The developed deep learning model(AUROC:0.88,AUPRC:0.63,Brier score:0.108)is superior to the model based on APACHEⅡscores(AUROC:0.78,AURPC:0.52,Brier score:0.124)in the prediction of hospital mortality for critically ill patients.Further attribution analysis based on the integrated gradients method shows that measurements observed at a later time seem to have a more significant influence on mortality,while earlier usage of amiodarone or dexmedetomidine contributed to lower mortality.This well-performing and interpretable model may have practical implications for improving the quality of care for critically ill patients.