Accelerometry-Based Activity Recognition and Assessment in Rheumatic and Musculoskeletal Diseases

被引:9
作者
Billiet, Lieven [1 ,2 ]
Swinnen, Thijs Willem [3 ,4 ,5 ]
Westhovens, Rene [3 ,4 ]
de Vlam, Kurt [3 ,4 ]
Van Huffel, Sabine [1 ,2 ]
机构
[1] Katholieke Univ Leuven, Dept Elect Engn ESAT, STADIUS Ctr Dynam Syst Signal Proc & Data Analyt, Kasteelpk Arenberg 10 Box 2446, B-3001 Leuven, Belgium
[2] iMinds, Med IT, B-3001 Leuven, Belgium
[3] Univ Hosp Leuven, Div Rheumatol, Herestr 49 Box 7003, B-3000 Leuven, Belgium
[4] Katholieke Univ Leuven, Dept Dev & Regenerat, Skeletal Biol & Engn Res Ctr, Herestr 49 Box 7003, B-3000 Leuven, Belgium
[5] Katholieke Univ Leuven, Dept Rehabil Sci, Musculoskeletal Rehabil Res Unit, Tervuursevest 101 Box 1501, B-3001 Leuven, Belgium
基金
欧洲研究理事会;
关键词
accelerometry; activity capacity; activity performance; activity recognition; interpretable medical scoring systems; physical activity; physical therapy; monitoring; PHYSICAL FUNCTION; FEATURE-SELECTION; SENSORS; CLASSIFICATION; SCORE; PAIN;
D O I
10.3390/s16122151
中图分类号
O65 [分析化学];
学科分类号
070302 [分析化学];
摘要
One of the important aspects to be considered in rheumatic and musculoskeletal diseases is the patient's activity capacity (or performance), defined as the ability to perform a task. Currently, it is assessed by physicians or health professionals mainly by means of a patient-reported questionnaire, sometimes combined with the therapist's judgment on performance-based tasks. This work introduces an approach to assess the activity capacity at home in a more objective, yet interpretable way. It offers a pilot study on 28 patients suffering from axial spondyloarthritis (axSpA) to demonstrate its efficacy. Firstly, a protocol is introduced to recognize a limited set of six transition activities in the home environment using a single accelerometer. To this end, a hierarchical classifier with the rejection of non-informative activity segments has been developed drawing on both direct pattern recognition and statistical signal features. Secondly, the recognized activities should be assessed, similarly to the scoring performed by patients themselves. This is achieved through the interval coded scoring (ICS) system, a novel method to extract an interpretable scoring system from data. The activity recognition reaches an average accuracy of 93.5%; assessment is currently 64.3% accurate. These results indicate the potential of the approach; a next step should be its validation in a larger patient study.
引用
收藏
页数:19
相关论文
共 43 条
[1]
Support vector machines combined with feature selection for breast cancer diagnosis [J].
Akay, Mehmet Fatih .
EXPERT SYSTEMS WITH APPLICATIONS, 2009, 36 (02) :3240-3247
[2]
Using Accelerometer and Gyroscopic Measures to Quantify Postural Stability [J].
Alberts, Jay L. ;
Hirsch, Joshua R. ;
Koop, Mandy Miller ;
Schindler, David D. ;
Kana, Daniel E. ;
Linder, Susan M. ;
Campbell, Scott ;
Thota, Anil K. .
JOURNAL OF ATHLETIC TRAINING, 2015, 50 (06) :578-588
[3]
Estimating Energy Expenditure Using Body-Worn Accelerometers: A Comparison of Methods, Sensors Number and Positioning [J].
Altini, Marco ;
Penders, Julien ;
Vullers, Ruud ;
Amft, Oliver .
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2015, 19 (01) :219-226
[4]
A PRACTICAL SCORE FOR THE EARLY DIAGNOSIS OF ACUTE APPENDICITIS [J].
ALVARADO, A .
ANNALS OF EMERGENCY MEDICINE, 1986, 15 (05) :557-564
[5]
[Anonymous], 2010, 23 INT C ARCH COMP S
[6]
Physical Human Activity Recognition Using Wearable Sensors [J].
Attal, Ferhat ;
Mohammed, Samer ;
Dedabrishvili, Mariam ;
Chamroukhi, Faicel ;
Oukhellou, Latifa ;
Amirat, Yacine .
SENSORS, 2015, 15 (12) :31314-31338
[7]
Billiet Lieven, 2016, Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods (ICPRAM 2016), P33
[8]
Billiet L., 2016, P 3 INT WORKSH SENS
[9]
Bishop C., 2006, Pattern recognition and machine learning, P423
[10]
Evaluation of a threshold-based tri-axial accelerometer fall detection algorithm [J].
Bourke, A. K. ;
O'Brien, J. V. ;
Lyons, G. M. .
GAIT & POSTURE, 2007, 26 (02) :194-199