Background
Falls in hospitals are the most common risk factor that affects the safety of inpatients and can result in severe harm. Therefore, preventing falls is one of the most important areas of risk management for health care organizations. However, existing methods for predicting falls are laborious and costly.
Objective
The objective of this study is to verify whether hospital inpatient falls can be predicted through the analysis of a single input—unstructured nursing records obtained from Japanese electronic medical records (EMRs)—using a natural language processing (NLP) algorithm and machine learning.
Methods
The nursing records of 335 fallers and 408 nonfallers for a 12-month period were extracted from the EMRs of an acute care hospital and randomly divided into a learning data set and test data set. The former data set was subjected to NLP and machine learning to extract morphemes that contributed to separating fallers from nonfallers to construct a model for predicting falls. Then, the latter data set was used to determine the predictive value of the model using receiver operating characteristic (ROC) analysis.
Results
The prediction of falls using the test data set showed high accuracy, with an area under the ROC curve, sensitivity, specificity, and odds ratio of mean 0.834 (SD 0.005), mean 0.769 (SD 0.013), mean 0.785 (SD 0.020), and mean 12.27 (SD 1.11) for five independent experiments, respectively. The morphemes incorporated into the final model included many words closely related to known risk factors for falls, such as the use of psychotropic drugs, state of consciousness, and mobility, thereby demonstrating that an NLP algorithm combined with machine learning can effectively extract risk factors for falls from nursing records.
Conclusions
We successfully established that falls among hospital inpatients can be predicted by analyzing nursing records using an NLP algorithm and machine learning. Therefore, it may be possible to develop a fall risk monitoring system that analyzes nursing records daily and alerts health care professionals when the fall risk of an inpatient is increased.
fibrin results in an inflammatory process that effectively damages the capillaries of a capsule, increasing the permeability of the vascular wall and producing bleeding from dilated microvessels beneath the fibrous capsule. In some cases, erosion of microvessels may cause massive hemoptysis. Despite the calcification of the capsule, it seems that a small degree of elasticity exists, which is the reason hematomas usually expand over a long period of time.These lesions are difficult to differentiate from soft-tissue sarcomas or other malignancies because many of them also reveal hemorrhagic and cystic changes on radiology. [2][3][4] The best diagnostic tools are computed tomography and magnetic resonance imaging, including guided fine-needle biopsy.
We have developed the Terumo Capiox centrifugal pump (CXP), which consists of a rotor having a unique straight-path design to reduce pump rotational speed without decreasing hydraulic efficiency. The CXP was tested in vitro for blood trauma with a specially designed test circuit using fresh bovine blood. The Biopump (BP) (Medtronic, Minneapolis, MN. U.S.A.) and the roller pump (RP) were used as controls. The CXP demonstrated the smallest elevation of free plasma hemoglobin cornpared with the BP and the RP. The CXP was then applied to cardiopulmonary bypass (CPB) in 10 patients (CXP group) who underwent elective coronary artery bypass grafiing (CABG), and the results were compared with those for a comparable roller pump group (RP group).Free plasma hemoglobin level, platelet count, and serum P-thromboglobulin (P-TG) level were measured during CPB. There were no CXP-related complications nor hemodynamic abnormalities during CPB. The CXP group demonstrated less hemolysis and less platelet depletion than the RP group. Furthermore, the serum P-TG level was significantly lower in the CXP group than in the RP group. The CXP showed excellent hemodynamic performance with less blood trauma both in vitro and in clinical application to open heart surgery. Thus, the CXP has significant potential to be safely applied to CPB for open heart surgery and circulatory support. Key Words: Centrifugal pump-Hemolysis-Cardiopulmonary bypass-P-Thromboglobulin-Free plasma hemoglobin.
Sjögren's syndrome is one of the major autoimmune diseases, however infective endocarditis associated with Sjögren's syndrome has not previously been reported. A patient with Sjögren's syndrome associated with aortic valve regurgitation due to infective endocarditis, underwent successful aortic valve replacement. Patients with Sjögren's syndrome tend to be at a higher risk of intraoral infections due to diminished secretion of saliva. Particular care must be taken of Sjögren's syndrome patients as they can also be at an increased risk of infective endocarditis.
Background Clinical outcomes and problems following off-pump coronary artery bypass grafting (OPCAB) in elderly patients have not been clarified.
Methods and ResultsThe surgical results of elderly patients aged 75 years or older (n=50; 38 males, mean age, 78.8 years) were reviewed and compared with those of younger patients (n=95; 79 males, mean age, 63.0 years). The EuroSCORE score was 6.9±3.5 in the elderly group and 3.0±2.4 in the younger group (p<0.0001). There were no hospital deaths in either group. There was no significant difference in the postoperative complication rate except for atrial fibrillation (40.0% elderly vs 24.2% younger, p=0.0479). Postoperative intensive care unit and hospital stays did not differ. The frequency of blood transfusion was significantly higher in the elderly group (78.0% elderly vs 37.2% younger, p<0.0001). During the mean follow-up of 18.6±8.8 months, there was 1 sudden death in the elderly group, but no cardiac deaths in either group. The 32-month cardiac event-free and survival rates were similar for the 2 groups. Conclusion OPCAB provides satisfactory clinical outcomes for elderly as well as younger patients. (Circ J 2004; 68: 1184 -1188
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.