Application of Decision Tree to Classify Fall Risk Using Inertial Measurement Unit Sensor Data and Clinical Measurements
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Background: While efforts have been made to differentiate fall risk in older adults using wearable devices and clinical methodologies, technologies are still infancy. We applied a decision tree (DT) algorithm using inertial measurement unit (IMU) sensor data and clinical measurements to generate high performance classification models of fall risk of older adults. Objects: This study aims to develop a classification model of fall risk using IMU data and clinical measurements in older adults. Methods: Twenty-six older adults were assessed and categorized into high and low fall risk groups. IMU sensor data were obtained while walking from each group, and features were extracted to be used for a DT algorithm with the Gini index (DT1) and the Entropy index (DT2), which generated classification models to differentiate high and low fall risk groups. Model’s performance was compared and presented with accuracy, sensitivity, and specificity. Results: Accuracy, sensitivity and specificity were 77.8%, 80.0%, and 66.7%, respectively, for DT1; and 72.2%, 91.7%, and 33.3%, respectively, for DT2. Conclusion: Our results suggest that the fall risk classification using IMU sensor data obtained during gait has potentials to be developed for practical use. Different machine learning techniques involving larger data set should be warranted for future research and development.
Abstract
Background: While efforts have been made to differentiate fall risk in older adults using wearable devices and clinical methodologies, technologies are still infancy. We applied a decision tree (DT) algorithm using inertial measurement unit (IMU) sensor data and clinical measurements to generate high performance classification models of fall risk of older adults. Objects: This study aims to develop a classification model of fall risk using IMU data and clinical measurements in older adults. Methods: Twenty-six older adults were assessed and categorized into high and low fall risk groups. IMU sensor data were obtained while walking from each group, and features were extracted to be used for a DT algorithm with the Gini index (DT1) and the Entropy index (DT2), which generated classification models to differentiate high and low fall risk groups. Model’s performance was compared and presented with accuracy, sensitivity, and specificity. Results: Accuracy, sensitivity and specificity were 77.8%, 80.0%, and 66.7%, respectively, for DT1; and 72.2%, 91.7%, and 33.3%, respectively, for DT2. Conclusion: Our results suggest that the fall risk classification using IMU sensor data obtained during gait has potentials to be developed for practical use. Different machine learning techniques involving larger data set should be warranted for future research and development.
참고문헌 (49)
- Tinetti ME, "Factors associated with serious injury during falls by ambulatory nursing home residents", J Am Geriatr Soc, 35(7), pp.644~648 (1987)
- Karlsson MK, "Prevention of falls in the elderly--a review", Osteoporos Int, 24(3), pp.747~762 (2013)
- Fingerhut LA, "Injury chartbook. Health, United States, 1996–97" (1997), National Center for Health Statistics
- Burns ER, "Primary care providers’ discussion of fall prevention approaches with their older adult patients-DocStyles, 2014", Prev Med Rep, 9, pp.149~152 (2018)
- Robinovitch SN, "Video capture of the circumstances of falls in elderly people residing in long-term care : an observational study", Lancet, 381(9860), pp.47~54 (2013)
- Overstall PW, "Falls in the elderly related to postural imbalance", Br Med J, 1(6056), pp.261~264 (1977)
- Overstall PW, "Instability and falls in the elderly", Age Ageing, (Suppl), pp.92~96 (1978)
- Fletcher PC, "Risk factors for serious falls among community-based seniors : results from the national population health survey", Can J Aging, 21(1), pp.103~116 (2002)
- Chen LK, "Asian working group for sarcopenia : 2019 consensus update on sarcopenia diagnosis and treatment", J Am Med Dir Assoc, 21(3), pp.300~307 (2020)
- Sánchez-Rodríguez D, "Does gait speed contribute to sarcopenia case-finding in a postacute rehabilitation setting?", Arch Gerontol Geriatr, 61(2), pp.176~181 (2015)
- Kim M, "Sarcopenia is associated with cognitive impairment mainly due to slow gait speed : results from the Korean frailty and aging cohort study(KFACS)", Int J Environ Res Public Health, 16(9), pp.1491~ (2019)
- Bet P, "Fall detection and fall risk assessment in older person using wearable sensors : a systematic review", Int J Med Inform, 130, pp.103946~ (2019)
- Brodie MA, "Eight-week remote monitoring using a freely worn device reveals unstable gait patterns in older fallers", IEEE Trans Biomed Eng, 62(11), pp.2588~2594 (2015)
- Zakaria NA, "Quantitative analysis of fall risk using TUG test", Comput Methods Biomech Biomed Engin, 18(4), pp.426~437 (2015)
- Rivolta MW, "Evaluation of the Tinetti score and fall risk assessment via accelerometry-based movement analysis", Artif Intell Med, 95, pp.38~47 (2019)
- Lima CA, "The Berg balance scale as a clinical screening tool to predict fall risk in older adults : a systematic review", Physiotherapy, 104(4), pp.383~394 (2018)
- Liu TW, "Assessing the fall risks of communitydwelling stroke survivors using the short-form physiological profile assessment(S-PPA)", PLoS One, 14(5), pp.e0216769~ (2019)
- Castellini G, "Fall prevention:is the STRATIFY tool the right instrument in Italian Hospital inpatient? A retrospective observational study", BMC Health Serv Res, 17(1), pp.656~ (2017)
- Oliver D, "Development and evaluation of evidence based risk assessment tool(STRATIFY)to predict which elderly inpatients will fall : casecontrol and cohort studies", BMJ, 315(7115), pp.1049~1053 (1997)
- Lord SR, "A physiological profile approach to falls risk assessment and prevention", Phys Ther, 83(3), pp.237~252 (2003)
- Senden R, "Accelerometry-based gait analysis, an additional objective approach to screen subjects at risk for falling", Gait Posture, 36(2), pp.296~300 (2012)
- Smee DJ, "Association between berg balance, physiological profile assessment and physical activity, physical function and body composition: a cross-sectional study", J Frailty Aging, 5(1), pp.20~26 (2016)
- Brodie MA, "Comparison between clinical gait and dailylife gait assessments of fall risk in older people", Geriatr Gerontol Int, 17(11), pp.2274~2282 (2017)
- Simon SR, "Quantification of human motion : gait analysisbenefits and limitations to its application to clinical problems", J Biomech, 37(12), pp.1869~1880 (2004)
- Brodie MA, "Wearable pendant device monitoring using new wavelet-based methods shows daily life and laboratory gaits are different", Med Biol Eng Comput, 54(4), pp.663~674 (2016)
- Tao W, "Gait analysis using wearable sensors", Sensors(Basel), 12(2), pp.2255~2283 (2012)
- Ponti M, "Better than counting seconds : Identifying fallers among healthy elderly using fusion of accelerometer features and dual-task Timed Up and Go", PLoS One, 12(4), pp.e0175559~ (2017)
- Engin M, "Recent developments and trends in biomedical sensors", Measurement, 37(2), pp.173~188 (2005)
- Bonato P, "Wearable sensors", systems and their impact on biomedical engineering, 2003, pp.22(3), 18~20
- Muro-de-la-Herran A, "Gait analysis methods : an overview of wearable and nonwearable systems, highlighting clinical applications", Sensors(Basel), 14(2), pp.3362~3394 (2014)
- Hori K, "Inertial measurement unit-based estimation of foot trajectory for clinical gait analysis", Front Physiol, 10, pp.1530~ (2020)
- Adachi W, "Calculation of joint reaction force and joint moments using by wearable walking analysis system", Annu Int Conf IEEE Eng Med Biol Soc, 2012, pp.507~510 (2012)
- Saadeh W, "A patient-specific single sensor IoT-based wearable fall prediction and detection system", IEEE Trans Neural Syst Rehabil Eng, 27(5), pp.995~1003 (2019)
- Santhiranayagam B, "Support vector machines for young and older gait classification using inertial sensor kinematics at minimum toe clearance", EAI Endorsed Trans Pervasive Health Technol, 16(7), pp.e2~ (2015)
- Aziz O, "An analysis of the accuracy of wearable sensors for classifying the causes of falls in humans", IEEE Trans Neural Syst Rehabil Eng, 19(6), pp.670~676 (2011)
- Drover D, "Faller classification in older adults using wearable sensors based on turn and straight-walking accelerometer-based features", Sensors(Basel), 17(6), pp.1321~ (2017)
- Berg K, "Measuring balance in the elderly : development and validation of an instrument", Doctoral, pp.1992
- Liston RA, "Reliability and validity of measures obtained from stroke patients using the Balance Master", Arch Phys Med Rehabil, 77(5), pp.425~430 (1996)
- Podsiadlo D, "The timed"Up & Go" : a test of basic functional mobility for frail elderly persons", J Am Geriatr Soc, 39(2), pp.142~148 (1991)
- Yardley L, "Development and initial validation of the Falls Efficacy Scale-International(FES-I)", Age Ageing, 34(6), pp.614~619 (2005)
- Salarian A, "Gait assessment in Parkinson’s disease : toward an ambulatory system for long-term monitoring", IEEE Trans Biomed Eng, 51(8), pp.1434~1443 (2004)
- Bertsimas D, "Optimal classification trees", Mach Learn, 106(7), pp.1039~1082 (2017)
- Doupe P, "Machine learning for health services researchers", Value Health, 22(7), pp.808~815 (2019)
- Trabassi D, "Machine learning approach to support the detection of Parkinson’s disease in IMU-based gait analysis", Sensors(Basel), 22(10), pp.3700~ (2022)
- Veronese N, "Epidemiology and social costs of hip fracture", Injury, 49(8), pp.1458~1460 (2018)
- Sucerquia A, "SisFall : a fall and movement dataset", Sensors(Basel), 17(1), pp.198~ (2017)
- Aziz O, "A comparison of accuracy of fall detection algorithms (threshold-based vs. machine learning) using waist-mounted tri-axial accelerometer signals from a comprehensive set of falls and non-fall trials", Med Biol Eng Comput, 55(1), pp.45~55 (2017)
- Aziz O, "Validation of accuracy of SVM-based fall detection system using real-world fall and non-fall datasets", PLoS One, 12(7), pp.e0180318~ (2017)
- 임기택, "Feature Extraction and Evaluation for Classification Models of Injurious Falls Based on Surface Electromyography", 한국전문물리치료학회지, 28(2), pp.123~131 (2021), 한국전문물리치료학회[DOI]