No abstract

Background: Trauma is a serious medical and economic problem worldwide, and patients with trauma injuries have a poor survival rate following cardiac arrest. This study aimed to create a prediction model specific to prehospital trauma care and to achieve greater accuracy with techniques of machine learning.Methods: This retrospective observational study investigated data of patients who had blunt trauma injuries due to traffic accident and fall trauma from January 1, 2018, to December 31, 2019, using the National Emergency Medical Services Information System, which stores emergency medical service activity records nationwide in the United States. Random forest was used to develop a machine learning model. Results:Per the prediction model, the area under the curve of the predictive model was 0.95 and negative predictive value was 0.99. The feature importance of the predictive model was the highest for the AVPU scale (an acronym from "Alert, Verbal, Pain, Unresponsive"), followed by oxygen saturation (SpO2). Among patients who were progressing to cardiac arrest, the cutoff value was 89% for SpO2 in unalert patients.Conclusions: Patients whose conditions did not progress to cardiac arrest could be identified with high accuracy by machine learning model techniques.

No abstract

Background: It is difficult to predict vancomycin trough concentrations in critically ill patients as their pharmacokinetics change with the progression of both organ failure and medical intervention. This study aims to develop a model to predict vancomycin trough concentration using machine learning (ML) and to compare its prediction accuracy with that of the population pharmacokinetic (PPK) model. Methods: A single-center retrospective observational study was conducted. Patients who had been admitted to the intensive care unit, received intravenous vancomycin, and had undergone therapeutic drug monitoring between 2013 and 2020,were included. Thereafter, ML models were developed with random forest, LightGBM, and ridge regression using 42 features. Mean absolute errors (MAE) were compared and important features were shown using LightGBM. Results: Among 335 patients, 225 were included as training data and 110 were used for test data. A significant difference was identified in the MAE by each ML model compared with PPK;4.13 ± 3.64 for random forest, 4.18 ± 3.37 for LightGBM, 4.29 ± 3.88 for ridge regression, and 6.17 ± 5.36 for PPK. The highest importance features were pH, lactate, and serum creatinine. Conclusion: This study concludes that ML may be able to more accurately predict vancomycin trough concentrations than the currently used PPK model in ICU patients.

Objective. In general, there are many CO 2-abatement measures including renewable energy utilization. However, we might have to consider the reduction of the indirect CO 2 emission, e.g., behavior and/or preference etc., on life cycle assessment (LCA) basis. For elderly people, there are surely difficulties in reducing CO 2 emission. That is, they would not be able to take the specific countermeasures such as promotion of PV system and/or eco-car, because of their limited incomes. For them, somewhat reasonable motivation without any obligation might have to be provided. In this paper, we investigated the relationship between the specific CO 2 emission and salt content of the cooking for the elderly who worry about their health condition, and they would try to pay more attention to the high-blood pressure problem. Due to this fact, a good motivation for their behavior of CO 2 emission abatement would be accrued. Results and Discussion. Here, we selected the 171 menus for elderly people from the cooking database of "Bob & Angie". The selected menus are satisfied with the condition of their calorie intake per day of 1800 kcal/day. At the same time, the numerical data of salt content of each menu was provided in the cooking database. For all of the menus, we estimated the life cycle CO 2 emission in the functional unit of g-CO 2 /kcal. From the results, we estimated the correlation between the CO 2 emission and salt content based on the four categories: the category of main and side dishes and/or soup, that of food preparations of boiling, steaming and grilling etc., that of food materials of meat, fish and vegetable, that of different cuisines of Japanese, Western and Chinese dishes. As a result, the coefficient of correlation between the CO 2 emission and salt content for the category of main and side dishes and/or soup was the highest of 0.996. The average CO 2 emissions for the category were 1.115 g-CO 2 /kcal in the main dish, 1.801 g-CO 2 /kcal in the side dish and 2.907 g-CO 2 /kcal in the soup. In the other categories, the coefficients of correlation were between 0.905 and 0.986. Conclusions. In this paper, we were able to find out the evidence that there would be the specific correlation between CO 2 emission and salt content in cooking for elderly people. Due to their efforts to reduce the risks of illness, that is, their desires to remain physically healthy, it implies that the CO 2 emissions for their dietary behavior are mitigated.