TY - GEN
T1 - WANDA
T2 - 3rd Conference on Wireless Health 2012, WH 2012
AU - Lan, Mars
AU - Samy, Lauren
AU - Alshurafa, Nabil
AU - Suh, Myung Kyung
AU - Ghasemzadeh, Hassan
AU - MacAbasco-O'Connell, Aurelia
AU - Sarrafzadeh, Majid
PY - 2012
Y1 - 2012
N2 - Recent advances in wireless sensors, mobile technologies, and cloud computing have made continuous remote monitoring of patients possible. In this paper, we introduce the design and implementation of WANDA, an end-to-end remote health monitoring and analytics system designed for heart failure patients. The system consists of a smartphone-based data collection gateway, an Internet-scale data storage and search system, and a backend analytics engine for diagnostic and prognostic purposes. The system supports the collection of data from a wide range of sensory devices that measure patients' vital signs as well as self-reported questionnaires. The main objective of the analytics engine is to predict future events by examining physiological readings of the patients. We demonstrate the efficiency of the proposed analytics engine using the data gathered from a pilot study of 18 heart failure patients. In particular, our results show that the advanced analytic algorithms used in our system are capable of predicting the worsening of patients' heart failure symptoms with up to 74% accuracy while improving the sensitivity performance by more than 45% compared to the commonly used thresholding algorithm based on daily weight change. Moreover, the accuracy attained by our system is only 9% lower than the theoretical upper bound. The proposed framework is currently deployed in a large ongoing heart failure study that targets 1500 congestive heart failure patients.
AB - Recent advances in wireless sensors, mobile technologies, and cloud computing have made continuous remote monitoring of patients possible. In this paper, we introduce the design and implementation of WANDA, an end-to-end remote health monitoring and analytics system designed for heart failure patients. The system consists of a smartphone-based data collection gateway, an Internet-scale data storage and search system, and a backend analytics engine for diagnostic and prognostic purposes. The system supports the collection of data from a wide range of sensory devices that measure patients' vital signs as well as self-reported questionnaires. The main objective of the analytics engine is to predict future events by examining physiological readings of the patients. We demonstrate the efficiency of the proposed analytics engine using the data gathered from a pilot study of 18 heart failure patients. In particular, our results show that the advanced analytic algorithms used in our system are capable of predicting the worsening of patients' heart failure symptoms with up to 74% accuracy while improving the sensitivity performance by more than 45% compared to the commonly used thresholding algorithm based on daily weight change. Moreover, the accuracy attained by our system is only 9% lower than the theoretical upper bound. The proposed framework is currently deployed in a large ongoing heart failure study that targets 1500 congestive heart failure patients.
KW - Machine learning
KW - Medical data mining
KW - Remote health monitoring
KW - Wireless health
UR - http://www.scopus.com/inward/record.url?scp=84876261502&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84876261502&partnerID=8YFLogxK
U2 - 10.1145/2448096.2448105
DO - 10.1145/2448096.2448105
M3 - Conference contribution
AN - SCOPUS:84876261502
SN - 9781450317603
T3 - Proceedings - Wireless Health 2012, WH 2012
BT - Proceedings - Wireless Health 2012, WH 2012
Y2 - 23 October 2012 through 25 October 2012
ER -