| Zdroj: |
Rangarajan, S, Lee, Y, Johnson, V, Schorger, K, Lee, H, Nguyen, D, Behfar, M H, Jansson, E, Rekilä, J, Hiltunen, J, Vin, E & Obraczka, K 2022, A Novel IoT System For Patient-Centric Pressure Ulcer Prevention Using Sensor Embedded Dressings . in 2022 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events, PerCom Workshops 2022 . IEEE Institute of Electrical and Electronic Engineers, pp. 42-45, 2022 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events, PerCom Workshops 2022, Pisa, Italy, 21/03/22 . https://doi.org/10.1109/PerComWorkshops53856.2022.9767294 |
| Popis: |
Pressure ulcers/injuries (PU/Is) are localized damage to the skin and/or underlying tissue caused by prolonged pressure to an area of the body. PU/Is affect over 2.5 million individuals in the United States annually, are associated with increased morbidity and mortality, and incur a cost of approximately $11 billion to the US healthcare system. Mitigating PU/Is continues to be a challenging task using traditional methods due to their time-and labor-intensive nature, and existing technological solutions tend to be prohibitively expensive, inefficiently implemented, or ineffective. Thus, there is a clear unmet need for a holistic, end-to-end, hospital-integrated, patient-centric system for PU/I prevention. Such a system can monitor pressure at high-risk areas and uses real-time sensor data, analysis, and visualization to guide clinicians and caregivers to perform effective preventative measures. In this paper, we describe a proof of concept of this system, which integrates: (A) a prototype "smart wound dressing"capable of detecting of changes in interface pressure and patient angle over time, including during routine patient repositioning maneuvers; and (B) an open software infrastructure that collects pressure-over-time data, stores, analyzes, and displays them to clinicians and caregivers. We present preliminary results obtained using our current prototype which uses machine learning algorithms to infer a patient's current position based on data from the pressure sensor. |
