Ambient Monitoring of Gait and Machine Learning Models for Dynamic and Short-Term Falls Risk Assessment in People With Dementia

被引:10
作者
Adeli, Vida [1 ,2 ]
Korhani, Navid [1 ,3 ]
Sabo, Andrea [1 ,2 ]
Mehdizadeh, Sina [1 ]
Mansfield, Avril [1 ,4 ,5 ]
Flint, Alastair [1 ,6 ,7 ]
Iaboni, Andrea [1 ,6 ,7 ]
Taati, Babak [2 ,3 ,8 ]
机构
[1] Univ Hlth Network, Toronto Rehabil Inst, KITE, Toronto, ON M5G 2C4, Canada
[2] Univ Toronto, Inst Biomed Engn, Toronto, ON M5S 1A1, Canada
[3] Univ Toronto, Dept Comp Sci, Toronto, ON M5S 1A1, Canada
[4] Univ Toronto, Dept Phys Therapy, Toronto, ON M5S 1A1, Canada
[5] Sunnybrook Res Inst, Hurvitz Brain Sci Program, Evaluat Clin Sci, Toronto, ON M4N 3M5, Canada
[6] Univ Toronto, Dept Psychiat, Toronto, ON M5S 1A1, Canada
[7] Univ Hlth Network, Ctr Mental Hlth, Toronto, ON M5G 2C4, Canada
[8] UHN, Toronto Rehabil Inst, KITE, Toronto, ON M5G 2C4, Canada
基金
加拿大自然科学与工程研究理事会;
关键词
Fall risk assessment; fall prediction; dementia; gait analysis; machine learning; computer vision; OLDER-ADULTS; MOBILITY ASSESSMENT; ASSESSMENT TOOL; PERFORMANCE; PREDICTION; RESIDENTS; CHALLENGES; INPATIENTS; STRATIFY;
D O I
10.1109/JBHI.2023.3267039
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Falls are a leading cause of morbidity and mortality in older adults with dementia residing in long-term care. Having access to a frequently updated and accurate estimate of the likelihood of a fall over a short time frame for each resident will enable care staff to provide targeted interventions to prevent falls and resulting injuries. To this end, machine learning models to estimate and frequently update the risk of a fall within the next 4 weeks were trained on longitudinal data from 54 older adult participants with dementia. Data from each participant included baseline clinical assessments of gait, mobility, and fall risk at the time of admission, daily medication intake in three medication categories, and frequent assessments of gait performed via a computer vision-based ambient monitoring system. Systematic ablations investigated the effects of various hyperparameters and feature sets and experimentally identified differential contributions from baseline clinical assessments, ambient gait analysis, and daily medication intake. In leave-one-subject-out cross-validation, the best performing model predicts the likelihood of a fall over the next 4 weeks with a sensitivity and specificity of 72.8 and 73.2, respectively, and achieved an area under the receiver operating characteristic curve (AUROC) of 76.2. By contrast, the best model excluding ambient gait features achieved an AUROC of 56.2 with a sensitivity and specificity of 51.9 and 54.0, respectively. Future research will focus on externally validating these findings to prepare for the implementation of this technology to reduce fall and fall-related injuries in long-term care.
引用
收藏
页码:3599 / 3609
页数:11
相关论文
共 60 条
[1]   A survey on spatio-temporal framework for kinematic gait analysis in RGB videos [J].
Amsaprabhaa, M. ;
Jane, Nancy Y. ;
Nehemiah, Khanna H. .
JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2021, 79 (79)
[2]   The prevalence, assessment and associations of falls in dementia with Lewy bodies and Alzheimer's disease [J].
Ballard, CG ;
Shaw, F ;
Lowery, K ;
McKeith, I ;
Kenny, R .
DEMENTIA AND GERIATRIC COGNITIVE DISORDERS, 1999, 10 (02) :97-103
[3]  
Beauchet Olivier, 2008, Neuropsychiatr Dis Treat, V4, P155
[4]  
Berg R. L, 1992, 2 50 YEARS PROMOTING
[5]   Fall detection and fall risk assessment in older person using wearable sensors: A systematic review [J].
Bet, Patricia ;
Castro, Paula C. ;
Ponti, Moacir A. .
INTERNATIONAL JOURNAL OF MEDICAL INFORMATICS, 2019, 130
[6]   Too much or too little step width variability is associated with a fall history in older persons who walk at or near normal gait speed [J].
Brach J.S. ;
Berlin J.E. ;
VanSwearingen J.M. ;
Newman A.B. ;
Studenski S.A. .
Journal of NeuroEngineering and Rehabilitation, 2 (1)
[7]   Predictors of Serious Consequences of Falls in Residential Aged Care: Analysis of More Than 70,000 Falls From Residents of Bavarian Nursing Homes [J].
Buechele, Gisela ;
Becker, Clemens ;
Cameron, Ian D. ;
Koenig, Hans-Helmut ;
Robinovitch, Stephen ;
Rapp, Kilian .
JOURNAL OF THE AMERICAN MEDICAL DIRECTORS ASSOCIATION, 2014, 15 (08) :559-563
[8]   Risk factors for falls in older people with cognitive impairment living in the community: Systematic review and meta-analysis [J].
Chantanachai, Thanwarat ;
Sturnieks, Daina L. ;
Lord, Stephen R. ;
Payne, Narelle ;
Webster, Lyndell ;
Taylor, Morag E. .
AGEING RESEARCH REVIEWS, 2021, 71
[9]   SMOTE: Synthetic minority over-sampling technique [J].
Chawla, Nitesh V. ;
Bowyer, Kevin W. ;
Hall, Lawrence O. ;
Kegelmeyer, W. Philip .
2002, American Association for Artificial Intelligence (16)
[10]   Factors Affecting Caregivers' Acceptance of the Use of Wearable Devices by Patients With Dementia: An Extension of the Unified Theory of Acceptance and Use of Technology Model [J].
Dai, Baozhen ;
Larnyo, Ebenezer ;
Tetteh, Ebenezer Ababio ;
Aboagye, Abigail Konadu ;
Ibn Musah, Abdul-Aziz .
AMERICAN JOURNAL OF ALZHEIMERS DISEASE AND OTHER DEMENTIAS, 2020, 35