RESUMEN

Background@#Worldwide, sepsis is the leading cause of death in hospitals. If mortality rates in patients with sepsis can be predicted early, medical resources can be allocated efficiently. We constructed machine learning (ML) models to predict the mortality of patients with sepsis in a hospital emergency department. @*Methods@#This study prospectively collected nationwide data from an ongoing multicenter cohort of patients with sepsis identified in the emergency department. Patients were enrolled from 19 hospitals between September 2019 and December 2020. For acquired data from 3,657 survivors and 1,455 deaths, six ML models (logistic regression, support vector machine, random forest, extreme gradient boosting [XGBoost], light gradient boosting machine, and categorical boosting [CatBoost]) were constructed using fivefold cross-validation to predict mortality. Through these models, 44 clinical variables measured on the day of admission were compared with six sequential organ failure assessment (SOFA) components (PaO 2 /FIO 2 [PF], platelets (PLT), bilirubin, cardiovascular, Glasgow Coma Scale score, and creatinine).The confidence interval (CI) was obtained by performing 10,000 repeated measurements via random sampling of the test dataset. All results were explained and interpreted using Shapley’s additive explanations (SHAP). @*Results@#Of the 5,112 participants, CatBoost exhibited the highest area under the curve (AUC) of 0.800 (95% CI, 0.756–0.840) using clinical variables. Using the SOFA components for the same patient, XGBoost exhibited the highest AUC of 0.678 (95% CI, 0.626–0.730). As interpreted by SHAP, albumin, lactate, blood urea nitrogen, and international normalization ratio were determined to significantly affect the results. Additionally, PF and PLTs in the SOFA component significantly influenced the prediction results. @*Conclusion@#Newly established ML-based models achieved good prediction of mortality in patients with sepsis. Using several clinical variables acquired at the baseline can provide more accurate results for early predictions than using SOFA components. Additionally, the impact of each variable was identified.

RESUMEN

This study was performed to investigate the effects of very low calorie diet (VLCD) using meal replacements that contain the wild grass extracts based on Samul-tang ingredients on psychological factors and quality of life in the obese women (BMI > or = 25 kg/m2) for four weeks. Seventy five women (20 < or = age < 26) participated in this experiment. Subjects were randomly classified three groups: 1) General diet group (GD group, n = 27) consumed 3 regular meals within 600 kcal/day 2) Meal replacements group (MR group, n = 27) consumed 1 regular meal and 2 meal replacements within 600 kcal/day 3) Herbal Meal replacements group (HMR group, n = 27) consumed 1 regular meal and 2 meal replacements within 600 kcal/day. Physical factors (weight, BMI, fat(%)) of the HMR group significantly decreased more than those of GD and MR groups. Moreover, binge eating habit and environmental factors (surrounding support, emotional reaction, expression of opinion) of the HMR group significantly decreased more than those of GD and MR groups. Psychological factor and quality of life were no significant differences among three groups during the experimental period, because both were significantly decreased in all groups after 4 weeks. Therefore, very low calorie diet using meal replacements that contain the wild grass extracts based on Samul-tang ingredients for 4 weeks was effective on improvement of psychological factor and quality of life as well as weight reduction in the obese premenopausal women.

Asunto(s)

RESUMEN

This study was performed to investigate the effects of very low calorie diet (VLCD) using newly meal replacements that contain the wild grass extracts based on Samul-tang ingredients on weight reduction and health in the obese adult women (BMI > or = 25 kg/m2) for four weeks. Seventy five women participated in this experiment. Subjects were randomly classified three groups: 1) General Diet group (GD group, n = 25) consumed 3 regular meals within 600 kcal/day, 2) Meal replacements group (MR group, n = 25) consumed 1 regular meal and 2 meal replacements within 600 kcal/ day, 3) Herbal Meal replacements group (HMR group, n = 25) consumed 1 regular meal and 2 meal replacements within 600 kcal/day. Anthropometric measurements, body composition, biochemical measurements and body symptoms were assessed before (the initial) and after (the 4th week) the study. Anthropometry measurements such as weight, waist and hip circumference, and BMI and body composition such as body fat percent, fat mass significantly decreased in all groups after diet intervention. Anthropometric measurements and body composition of the HMR group significantly more than those of GD and MR groups. Serum Total cholesterol was significantly decreased in all groups. However, there was no significant difference among three groups during the experimental period. HMR group had significantly less felt a pain than GD and MR groups in body symptoms such as anemia, powerlessness, vomiting, constipation and dryness of skin during the experimental period. Therefore, very low calorie diet (VLCD) using meal replacements that contain the wild grass extracts based on Samul-tang ingredients was very effective on weight reduction and health in the obese adult women.

Asunto(s)