LwTool: A data processing toolkit for building a real-time pressure mapping smart textile software system

2022 ◽  
pp. 101540
Author(s):  
Tao Guo ◽  
Zhixin Huang ◽  
Jingyuan Cheng
2021 ◽  
Vol 42 (Supplement_1) ◽  
pp. S28-S28
Author(s):  
Leen El Eter ◽  
Pooja S Yesantharao ◽  
Vidhi Javia ◽  
Emily h Werthman ◽  
Carrie A Cox ◽  
...  

Abstract Introduction Real-time pressure mapping devices may help prevent hospital-acquired pressure injury (HAPI) in Burn ICU (BICU) patients who are at a high baseline risk for HAPIs. While prior studies have demonstrated the utility of pressure monitoring devices in preventing pressure injuries, there has been little investigation into using pressure mapping data to better understand HAPI development, and to determine specific predictors of HAPIs. Such data could help risk stratify patients upon admission to the BICU and result in improved patient care as well as cost savings. This study retrospectively investigated the utility of pressure mapping data in predicting/preventing pressure injury among BICU patients, and estimated HAPI-related cost savings associated with the implementation of pressure monitoring. Methods This was a retrospective chart review of real-time pressure mapping in the BICU. Incidence of HAPIs and costs of HAPI-related care were determined through clinical record review, before and after implementation of pressure mapping. Multivariable-adjusted logistic regression was used to determine predictors of HAPIs, in the context of pressure mapping recordings. Results In total, 122 burn ICU patients met inclusion criteria during the study period, of whom 57 (47%) were studied prior to implementation of pressure mapping, and 65 (53%) were studied after implementation. The HAPI rate was 18% prior to implementation of pressure monitoring, which declined to 8% after implementation (chi square: p=0.10). HAPIs were more likely to be less severe in the post-implementation cohort (p< 0.0001). Upon multivariable-adjusted regression accounting for known predictors of HAPIs in burn patients (BMI, length of stay, co-morbidities, age, total body surface area burned, mobility), having had at least 12 hours of sustained pressure loading in one area significantly increased odds of developing a pressure injury in that area (odds ratio 1.3, 95%CI 1.0–1.5, p=0.04). When comparing patients who developed HAPIs to those who did not, pressure mapping demonstrated that patients who developed HAPIs were significantly more likely to have had unsuccessful repositioning efforts prior to HAPI development, defined as persistent high pressure in the at-risk area (60% versus 17%, respectively; p=0.02). Finally, implementation of pressure mapping resulted in significant cost savings ($2,063 prior to implementation, versus $1,082 after implementation, p=0.008). Conclusions The use of real-time pressure mapping decreased incidence of HAPIs in the burn ICU patients and resulted in significant cost savings.


2020 ◽  
Vol 6 (1) ◽  
Author(s):  
Juan Tao ◽  
Ming Dong ◽  
Li Li ◽  
Chunfeng Wang ◽  
Jing Li ◽  
...  

Author(s):  
Pooja S Yesantharao ◽  
Leen El Eter ◽  
Vidhi Javia ◽  
Emily Werthman ◽  
Carrie Cox ◽  
...  

Abstract Although prior studies have demonstrated the utility of real-time pressure mapping devices in preventing pressure ulcers, there has been little investigation of their efficacy in burn intensive care unit (BICU) patients, who are at especially high risk for these hospital-acquired injuries. This study retrospectively reviewed clinical records of BICU patients to investigate the utility of pressure mapping data in determining the incidence, predictors and associated costs of hospital-acquired pressure injuries. Of 122 patients, 57 (47%) were studied prior to implementation of pressure mapping and 65 (53%) were studied after implementation. The hospital-acquired pressure injury rate was 18% prior to implementation of pressure monitoring, which declined to 8% post-implementation (chi square: p=0.10). Hospital acquired pressure injuries were less likely to be stage 3 or worse in the post-implementation cohort (p<0.0001). Upon multivariable-adjusted regression accounting for known predictors of hospital-acquired pressure injuries in burn patients, having had at least 12 hours of sustained pressure loading in one area significantly increased odds of developing a pressure injury in that area (odds ratio 1.3, 95%CI 1.0-1.5, p=0.04). Patients who developed hospital-acquired pressure injuries were significantly more likely to have had unsuccessful repositioning efforts in comparison to those who did not (p=0.02). Finally, implementation of pressure mapping resulted in significant cost savings - $6,750 (standard deviation: $1008) for HAPI-related care prior to implementation, versus $3,800 (standard deviation: $923) after implementation, p=0.008. In conclusion, the use of real-time pressure mapping decreased the morbidity and costs associated with hospital-acquired pressure injuries in BICU patients.


Sensor Review ◽  
2011 ◽  
Vol 31 (2) ◽  
pp. 101-105 ◽  
Author(s):  
Richard Bloss

2020 ◽  
Vol 14 ◽  
pp. 174830262096239 ◽  
Author(s):  
Chuang Wang ◽  
Wenbo Du ◽  
Zhixiang Zhu ◽  
Zhifeng Yue

With the wide application of intelligent sensors and internet of things (IoT) in the smart job shop, a large number of real-time production data is collected. Accurate analysis of the collected data can help producers to make effective decisions. Compared with the traditional data processing methods, artificial intelligence, as the main big data analysis method, is more and more applied to the manufacturing industry. However, the ability of different AI models to process real-time data of smart job shop production is also different. Based on this, a real-time big data processing method for the job shop production process based on Long Short-Term Memory (LSTM) and Gate Recurrent Unit (GRU) is proposed. This method uses the historical production data extracted by the IoT job shop as the original data set, and after data preprocessing, uses the LSTM and GRU model to train and predict the real-time data of the job shop. Through the description and implementation of the model, it is compared with KNN, DT and traditional neural network model. The results show that in the real-time big data processing of production process, the performance of the LSTM and GRU models is superior to the traditional neural network, K nearest neighbor (KNN), decision tree (DT). When the performance is similar to LSTM, the training time of GRU is much lower than LSTM model.


2006 ◽  
Author(s):  
Mike Parker ◽  
Robert N. Bradford ◽  
Laurence Ward Corbett ◽  
Robin Noel Heim ◽  
Christina Leigh Isakson ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document