Urine output as one of the most important features in differentiating in-hospital death among patients receiving extracorporeal membrane oxygenation: a random forest approach.

BACKGROUND: It is common to support cardiovascular function in critically ill patients with extracorporeal membrane oxygenation (ECMO). The purpose of this study was to identify patients receiving ECMO with a considerable risk of dying in hospital using machine learning algorithms. METHODS: A total of 1342 adult patients on ECMO support were randomly assigned to the training and test groups. The discriminatory power (DP) for predicting in-hospital mortality was tested using both random forest (RF) and logistic regression (LR) algorithms. RESULTS: Urine output on the first day of ECMO implantation was found to be one of the most predictive features that were related to in-hospital death in both RF and LR models. For those with oliguria, the hazard ratio for 1 year mortality was 1.445 (p < 0.001, 95% CI 1.265-1.650). CONCLUSIONS: Oliguria within the first 24 h was deemed especially significant in differentiating in-hospital death and 1 year mortality.

A cloud system for mobile medical services of traditional Chinese medicine.

Many medical centers in Taiwan have started to provide Traditional Chinese Medicine (TCM) services for hospitalized patients. Due to the complexity of TCM modality and the increasing need for providing TCM services for patients in different wards at distantly separate locations within the hospital, it is getting difficult to manage the situation in the traditional way. A computerized system with mobile ability can therefore provide a practical solution to the challenge presented. The study tries to develop a cloud system equipped with mobile devices to integrate electronic medical records, facilitate communication between medical workers, and improve the quality of TCM services for the hospitalized patients in a medical center. The system developed in the study includes mobile devices carrying Android operation system and a PC as a cloud server. All the devices use the same TCM management system developed by the study. A website of database is set up for information sharing. The cloud system allows users to access and update patients' medical information, which is of great help to medical workers for verifying patients' identification and giving proper treatments to patients. The information then can be wirelessly transmitted between medical personnel through the cloud system. Several quantitative and qualitative evaluation indexes are developed to measure the effectiveness of the cloud system on the quality of the TCM service. The cloud system is tested and verified based on a sample of hospitalized patients receiving the acupuncture treatment at the Lukang Branch of Changhua Christian Hospital (CCH) in Taiwan. The result shows a great improvement in operating efficiency of the TCM service in that a significant saving in labor time can be attributable to the cloud system. In addition, the cloud system makes it easy to confirm patients' identity through taking a picture of the patient upon receiving any medical treatment. The result also shows that the cloud system achieves significant improvement in the acupuncture treatment. All the acupuncture needles now can be removed at the time they are expected to be removed. Furthermore, through the cloud system, medical workers can access and update patients' medical information on-site, which provides a means of effective communication between medical workers. These functions allow us to make the most use of the portability feature of the acupuncture service. The result shows that the contribution made by the cloud system to the TCM service is multi-dimensional: cost-effective, environment-protective, performance-enhancing etc. Developing and implementing such a cloud system for the TCM service in Taiwan symbolizes a pioneering effort. We believe that the work we have done here can serve as a stepping-stone toward advancing the TCM service quality in the future.