Computer methods and programs in biomedicine
-
Comput Methods Programs Biomed · Jun 2017
Predicting return visits to the emergency department for pediatric patients: Applying supervised learning techniques to the Taiwan National Health Insurance Research Database.
Return visits (RVs) to the emergency department (ED) consume medical resources and may represent a patient safety issue. The occurrence of unexpected RVs is considered a performance indicator for ED care quality. Because children are susceptible to medical errors and utilize considerable ED resources, knowing the factors that affect RVs in pediatric patients helps improve the quality of pediatric emergency care. ⋯ We identified several factors which are associated with RVs to the ED in pediatric patients. The knowledge of these factors may help assess risk of RVs in the ED and guide physicians to reevaluate and provide interventions to children belonging to the high risk groups before ED discharge.
-
Comput Methods Programs Biomed · Mar 2017
A novel end-to-end classifier using domain transferred deep convolutional neural networks for biomedical images.
Highly accurate classification of biomedical images is an essential task in the clinical diagnosis of numerous medical diseases identified from those images. Traditional image classification methods combined with hand-crafted image feature descriptors and various classifiers are not able to effectively improve the accuracy rate and meet the high requirements of classification of biomedical images. The same also holds true for artificial neural network models directly trained with limited biomedical images used as training data or directly used as a black box to extract the deep features based on another distant dataset. In this study, we propose a highly reliable and accurate end-to-end classifier for all kinds of biomedical images via deep learning and transfer learning. ⋯ We propose a robust automated end-to-end classifier for biomedical images based on a domain transferred deep convolutional neural network model that shows a highly reliable and accurate performance which has been confirmed on several public biomedical image datasets.
-
Comput Methods Programs Biomed · Mar 2017
Computational simulation of passive leg-raising effects on hemodynamics during cardiopulmonary resuscitation.
The passive leg-raising (PLR) maneuver has been used for patients with circulatory failure to improve hemodynamic responsiveness by increasing cardiac output, which should also be beneficial and may exert synergetic effects during cardiopulmonary resuscitation (CPR). However, the impact of the PLR maneuver on CPR remains unclear due to difficulties in monitoring cardiac output in real-time during CPR and a lack of clinical evidence. ⋯ We developed a CPR-PLR model and demonstrated the effects of PLR on hemodynamics by investigating changes in CO, SPP, and CPP under different compression rates and angles of leg raising. Our computational model will facilitate study of PLR effects during CPR and the development of an advanced model combined with circulatory disorders, which will be a valuable asset for further studies.
-
Comput Methods Programs Biomed · Mar 2017
Determinants and development of a web-based child mortality prediction model in resource-limited settings: A data mining approach.
Improving child health and reducing child mortality rate are key health priorities in developing countries. This study aimed to identify determinant sand develop, a web-based child mortality prediction model in Ethiopian local language using classification data mining algorithm. ⋯ In this study, nearly accurate results were obtained by employing decision tree and rule induction techniques. Determinants are identified and a web-based child mortality prediction model in Ethiopian local language is developed. Thus, the result obtained could support child health intervention programs in Ethiopia where trained human resource for health is limited. Advanced classification algorithms need to be tested to come up with optimal models.
-
Comput Methods Programs Biomed · Jul 2016
Numerical simulations of the 10-year-old head response in drop impacts and compression tests.
Studies on traumatic injuries of children indicate that impact to the head is a major cause of severe injury and high mortality. However, regulatory and ethical concerns very much limit development and validation of computer models representing the pediatric head. The purpose of this study was to develop a child head finite element model with high-biofidelity to be used for studying pediatric head injury mechanisms. ⋯ Based on the results of the injury analyses, the following conclusions can be drawn: (1) ICP cannot be used to accurately predict the locations of brain injury, but it may reflect the overall energy level of the impact event. (2) The brain regions predicted by the model to have high σv coincide with the locations of subdural hematoma with transtentorial herniation and the impact position of an actual injury. (3) The brain regions with high εp predicted by the model coincide with locations commonly found where diffuse axonal injuries (DAI) due to blunt-impact and rapid acceleration have taken place.