Kabeshova Anastasiia, Launay Cyrille P, Gromov Vasilii A, Annweiler Cédric, Fantino Bruno, Beauchet Olivier
Department of Neuroscience, Division of Geriatric Medicine, Angers University Hospital, Angers, France; UPRES EA 4336, UNAM, Angers University Hospital, Angers, France; Computational Mathematics and Mathematical Cybernetics Department, Faculty of Applied Mathematics, Oles Honchar Dnepropetrovsk National University Dnepropetrovsk, Ukraine.
Department of Neuroscience, Division of Geriatric Medicine, Angers University Hospital, Angers, France; UPRES EA 4336, UNAM, Angers University Hospital, Angers, France.
J Am Med Dir Assoc. 2015 Apr;16(4):277-81. doi: 10.1016/j.jamda.2014.09.013. Epub 2014 Oct 29.
Identification of the risk of recurrent falls is complex in older adults. The aim of this study was to examine the efficiency of 3 artificial neural networks (ANNs: multilayer perceptron [MLP], modified MLP, and neuroevolution of augmenting topologies [NEAT]) for the classification of recurrent fallers and nonrecurrent fallers using a set of clinical characteristics corresponding to risk factors of falls measured among community-dwelling older adults.
Based on a cross-sectional design, 3289 community-dwelling volunteers aged 65 and older were recruited. Age, gender, body mass index (BMI), number of drugs daily taken, use of psychoactive drugs, diphosphonate, calcium, vitamin D supplements and walking aid, fear of falling, distance vision score, Timed Up and Go (TUG) score, lower-limb proprioception, handgrip strength, depressive symptoms, cognitive disorders, and history of falls were recorded. Participants were separated into 2 groups based on the number of falls that occurred over the past year: 0 or 1 fall and 2 or more falls. In addition, total population was separated into training and testing subgroups for ANN analysis.
Among 3289 participants, 18.9% (n = 622) were recurrent fallers. NEAT, using 15 clinical characteristics (ie, use of walking aid, fear of falling, use of calcium, depression, use of vitamin D supplements, female, cognitive disorders, BMI <21 kg/m(2), number of drugs daily taken >4, vision score <8, use of psychoactive drugs, lower-limb proprioception score ≤5, TUG score >9 seconds, handgrip strength score ≤29 (N), and age ≥75 years), showed the best efficiency for identification of recurrent fallers, sensitivity (80.42%), specificity (92.54%), positive predictive value (84.38), negative predictive value (90.34), accuracy (88.39), and Cohen κ (0.74), compared with MLP and modified MLP.
NEAT, using a set of 15 clinical characteristics, was an efficient ANN for the identification of recurrent fallers in older community-dwellers.
识别老年人反复跌倒的风险很复杂。本研究的目的是使用一组在社区居住的老年人中测量的与跌倒风险因素相对应的临床特征，检验3种人工神经网络（ANN：多层感知器[MLP]、改良MLP和增强拓扑神经进化[NEAT]）对反复跌倒者和非反复跌倒者进行分类的效率。
基于横断面设计，招募了3289名65岁及以上的社区居住志愿者。记录年龄、性别、体重指数（BMI）、每日服用药物数量、精神活性药物使用情况、双膦酸盐、钙、维生素D补充剂和助行器使用情况、跌倒恐惧、远视力评分、定时起立行走（TUG）评分、下肢本体感觉、握力、抑郁症状、认知障碍和跌倒史。根据过去一年发生的跌倒次数，将参与者分为两组：0次或1次跌倒以及2次或更多次跌倒。此外，将总人群分为训练和测试亚组进行ANN分析。
在3289名参与者中，18.9%（n = 622）为反复跌倒者。与MLP和改良MLP相比，NEAT使用15种临床特征（即助行器使用情况、跌倒恐惧、钙的使用、抑郁、维生素D补充剂使用情况、女性、认知障碍、BMI <21 kg/m²、每日服用药物数量>4、视力评分<8、精神活性药物使用情况下肢本体感觉评分≤5、TUG评分>9秒、握力评分≤29（N）以及年龄≥75岁），在识别反复跌倒者方面显示出最佳效率，敏感性（80.42%）、特异性（92.54%）、阳性预测值（84.38）、阴性预测值（90.34）、准确性（88.39）和科恩κ（0.74）。
NEAT使用一组15种临床特征，是识别社区居住老年人反复跌倒者的有效ANN。
