Evaluation of Effectiveness of Brace Treatment in Scoliosis Patients

Scoliosis;Brace treatment;Pervasive monitoring;Context aware sensing;Activity identification;Power density spectrum;Electrical engineering;Biomedical engineering;Computer science;Electrical Engineering, College of Engineering & Computer Science

Bache, Bhavani AnantapurShaout, Adnan ;

University of Michigan

关键词: Scoliosis;    Brace treatment;    Pervasive monitoring;    Context aware sensing;    Activity identification;    Power density spectrum;    Electrical engineering;    Biomedical engineering;    Computer science;    Electrical Engineering, College of Engineering & Computer Science;   

Others  :  https://deepblue.lib.umich.edu/bitstream/handle/2027.42/145482/bhavaniThesisWordFormat25Aug.pdf?sequence=1&isAllowed=y

瑞士|英语

来源: The Illinois Digital Environment for Access to Learning and Scholarship

【 摘 要 】

Scoliosis is a medical condition which occurs in adolescents, where an individual;;s spine develops curvature. Monitoring the effectiveness of brace treatment of scoliosis is an ongoing challenge that many physicians face today. A Thoracolumbosacral orthosis (TLSO) is a type of brace used to control the lateral curvature of the spine in scoliosis. It is a non-surgical treatment with the goal of preventing curve progression in patients with idiopathic scoliosis. To successfully monitor compliance with brace treatment, a wearable multi-modal sensor solution is embedded into the patient;;s brace. The custom-designed hardware consists of a sensor board, a force sensor, an accelerometer and a gyroscope. The force sensor collects the force being exerted on the patient;;s back, while the accelerometer and gyroscope generate cues to determine the patient;;s activities and lifestyle. In this dissertation, a novel data-mining method is proposed, to identify patient activities and evaluate the effectiveness of the brace treatment pervasively based on fusion of continuous force and inertial motion recordings. The proposed method evaluates three main factors: 1) The compliance to the brace treatment or duration of brace wear through the process of segmentation, 2) The level of tightness of brace by estimating the baseline force per segment and 3) The quality of brace fit in the presence of different activities including sitting, standing, climbing, walking, running and lying. The aim is to design a context-aware remote monitoring system for ubiquitous evaluation and enhancement of brace treatment compliance of adolescent idiopathic scoliosis patients. Two experimental scenarios have been investigated: 1) Semi-supervised scenario in which, the patient performs a series of pre-defined activities at home during day long segments of brace wear, and 2) Unsupervised scenario in which, there is no knowledge of the patient;;s activities and other circumstances during pervasive sensor data recordings. The experimental results demonstrated that we achieved an overall accuracy of a 100% for activity detection. The level of tightness of brace-fit reduced gradually over a period of 4 weeks by 33%. Initially, at the beginning of the treatment, patients were instructed to wear the brace for 2 hours, and the compliance with the brace treatment was 7.8%. The duration of the brace wear increased gradually during the period of 4 weeks. At the end of week 4, the compliance reached 80%.