Explainable machine learning using perioperative serial laboratory results to predict postoperative mortality in patients with peritonitis-induced sepsis

Purpose@#Sepsis is one of the most common causes of death after surgery. Several conventional scoring systems have been developed to predict the outcome of sepsis; however, their predictive power is insufficient. The present study applies explainable machine-learning algorithms to improve the accuracy of predicting postoperative mortality in patients with sepsis caused by peritonitis. @*Methods@#We performed a retrospective analysis of data from demographic, clinical, and laboratory analyses, including the delta neutrophil index (DNI), WBC and neutrophil counts, and CRP level. Laboratory data were measured before surgery, 12–36 hours after surgery, and 60–84 hours after surgery. The primary study output was the probability of mortality.The areas under the receiver operating characteristic curves (AUCs) of several machine-learning algorithms using the Sequential Organ Failure Assessment (SOFA) and Simplified Acute Physiology Score (SAPS) 3 models were compared.‘SHapley Additive exPlanations’ values were used to indicate the direction of the relationship between a variable and mortality. @*Results@#The CatBoost model yielded the highest AUC (0.933) for mortality compared to SAPS3 and SOFA (0.860 and 0.867, respectively). Increased DNI on day 3, septic shock, use of norepinephrine therapy, and increased international normalized ratio on day 3 had the greatest impact on the model’s prediction of mortality. @*Conclusion@#Machine-learning algorithms increase the accuracy of predicting postoperative mortality in patients with sepsis caused by peritonitis.

Factors Affecting Subjective Quality of Life of Hospice Volunteers / 한국호스피스완화의료학회지

PURPOSE: This study tested a model of hospice volunteer's motivations and outcomes to encourage more volunteer workers to participate in hospice care. METHODS: This included 200 volunteers who attended the Autumn Conference in 2007 and 132 volunteers from five hospice organizations. RESULTS: Volunteers' existential well-being affected an endogenous variable of volunteers' participation in volunteer activities. The durability of volunteer activity was affected by value motivation, the level of participation in volunteer activities and the level of job satisfaction. For volunteers' job satisfaction level, valid endogenous variables included existential well-being, social motivation, understanding motivation and value motivation. The durability of volunteer activities was indirectly affected through three different paths. Volunteers' existential well-being determined the level of their participation in volunteer activities, which in turn affected the durability of such activities. Social motivation influenced volunteers' job satisfaction, and then the durability of volunteer activities. Volunteers' understanding of motivation also influenced their job satisfaction, and then the durability of volunteer activities. CONCLUSION: Based on these results, this study proposes that the durability of volunteers activities could be improved by developing a program to improve volunteers' well-being and by providing volunteers with education on altruistic values, encouraging them to seek intellectual growth, and advocating them to continue volunteer activities based on close relationships with other volunteers.

Developing Job Description for Dietitians Working in Public Health Nutrition Areas / 대한지역사회영양학회지

The purpose of this study was to develop a standardized job description for dietitians working in the public health nutrition area. Work-oriented job analysis methodology was employed for the study purpose. Subjects of 38 dietitians currently working at health centers in 2002 were recruited. Based on the focus group interview with 7 public health nutritionists and 7 professors, information about task elements was collected. Questionnaires measuring work performance and self-perception of importance of the selected task elements were administered. Reliability and validity of this instrument were tested by Chronbach's alpha and factor analysis. SAS PC package program was used for the statistical analysis. The final developed job description for public health nutritionists included 5 duties, 20 tasks and 93 task elements. The results of this study can be summarized as follows; 1) 5 duty areas are A. plan and evaluation of public health nutrition services, B. developing nutrition education materials, C. implementing nutrition services, D. networking community, and E. self development. 2) Each duty area from A to E was composed with 6, 2, 6, 4, 2 tasks, respectively. 3) Each duty area from A to E was composed with 24, 8, 38, 14, 9, and 2 task elements, respectively.