Dynamic bayesian networks: representation, inference and learning
Dynamic bayesian networks: representation, inference and learning
A novel emergency telemedicine system based on wireless communication technology-AMBULANCE
IEEE Transactions on Information Technology in Biomedicine
A mobile teletrauma system using 3G networks
IEEE Transactions on Information Technology in Biomedicine
A multimodal sensing system for detection of traumatic brain injury
WH '10 Wireless Health 2010
| Hi-index | 0.00 |
We propose to develop a portable, handheld, noninvasive solution for accurate screening and real-time monitoring of traumatic brain injury (BI) in ambulatory/emergency response scenarios. A layered sensing concept that unifies alternate modalities such as a) ultrasound (US), b) near infrared spectroscopy (NIRS), c) tonometry (IOP), to predict BI, their severity and mode of recommendations for emergency medical service (EMS) personnel is offered. Specifically, we aim to determine i) novel 3D morphometric parameters of optic nerve sheath that can predict elevated intracranial pressure from US data, ii) incidence of intracranial hematomas using NIRS, iii) intraocular pressure using a tonometer, iv) cerebral blood flow and blood oxygen content using other auxiliary non-invasive sensing modes and v) finally provide a sensor fused outcome of all i)-iv) combined. This decision-support system (DSS) will improve BI detection by incorporating accurate on-site measurements that accounts for individual baseline variations and monitors temporal manifestation of the injury. The data collected and the preliminary analysis performed by the DSS will be sent to an emergency department (ED) physician stationed at a nearby trauma center via a wireless 3G network. Based on the available bandwidth, either all the data including the preliminary analysis (US video, images, 1D measurements, etc) or only the refined signals (feature vector extracted during screening) along with the DSS diagnosis will be sent to the physician. If the DSS determined output is agreeable to the physician then the screening can be terminated and the physician/ED staff can prepare to perform advanced interventions (intubation, cerebralspinal fluid (CSF) drainage, etc). If not, the on-call physician can inform the medic to repeat the scans/take additional measurements to obtain a more concrete outcome via the DSS. In summary, such a knowledge-driven system will equip a novice or a trained medic with an easy-to-use tool to detect traumatic BI and reduce the diagnosis time involved (i.e., computed tomography (CT) scan, clinical evaluation) in ED before performing advanced interventions and thereby improve the prognosis.