{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T00:07:09Z","timestamp":1780445229971,"version":"3.54.1"},"reference-count":32,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2018,5,22]],"date-time":"2018-05-22T00:00:00Z","timestamp":1526947200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Early detection of high fall risk is an essential component of fall prevention in older adults. Wearable sensors can provide valuable insight into daily-life activities; biomechanical features extracted from such inertial data have been shown to be of added value for the assessment of fall risk. Body-worn sensors such as accelerometers can provide valuable insight into fall risk. Currently, biomechanical features derived from accelerometer data are used for the assessment of fall risk. Here, we studied whether deep learning methods from machine learning are suited to automatically derive features from raw accelerometer data that assess fall risk. We used an existing dataset of 296 older adults. We compared the performance of three deep learning model architectures (convolutional neural network (CNN), long short-term memory (LSTM) and a combination of these two (ConvLSTM)) to each other and to a baseline model with biomechanical features on the same dataset. The results show that the deep learning models in a single-task learning mode are strong in recognition of identity of the subject, but that these models only slightly outperform the baseline method on fall risk assessment. When using multi-task learning, with gender and age as auxiliary tasks, deep learning models perform better. We also found that preprocessing of the data resulted in the best performance (AUC = 0.75). We conclude that deep learning models, and in particular multi-task learning, effectively assess fall risk on the basis of wearable sensor data.<\/jats:p>","DOI":"10.3390\/s18051654","type":"journal-article","created":{"date-parts":[[2018,5,23]],"date-time":"2018-05-23T03:14:24Z","timestamp":1527045264000},"page":"1654","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":165,"title":["Deep Learning to Predict Falls in Older Adults Based on Daily-Life Trunk Accelerometry"],"prefix":"10.3390","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8966-9736","authenticated-orcid":false,"given":"Ahmed","family":"Nait Aicha","sequence":"first","affiliation":[{"name":"Department of Computer Science, Amsterdam University of Applied Sciences, 1091 GM Amsterdam, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gwenn","family":"Englebienne","sequence":"additional","affiliation":[{"name":"Human Media Interaction, University of Twente, 7522 NH Enschede, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0902-8440","authenticated-orcid":false,"given":"Kimberley S.","family":"Van Schooten","sequence":"additional","affiliation":[{"name":"Neuroscience Research Australia, University of New South Wales, Sydney 2031, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8416-2602","authenticated-orcid":false,"given":"Mirjam","family":"Pijnappels","sequence":"additional","affiliation":[{"name":"Department of Human Movement Sciences, Vrije Universiteit Amsterdam, 1081 HV Amsterdam, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1237-0618","authenticated-orcid":false,"given":"Ben","family":"Kr\u00f6se","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Amsterdam University of Applied Sciences, 1091 GM Amsterdam, The Netherlands"},{"name":"Informatics Institute, University of Amsterdam, 1098 XH Amsterdam, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2018,5,22]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1016\/j.maturitas.2013.02.009","article-title":"Risk factors for falls among older adults: A review of the literature","volume":"75","author":"Ambrose","year":"2013","journal-title":"Maturitas"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"ii37","DOI":"10.1093\/ageing\/afl084","article-title":"Falls in older people: Epidemiology, risk factors and strategies for prevention","volume":"35","author":"Rubenstein","year":"2006","journal-title":"Age Ageing"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"658","DOI":"10.1097\/EDE.0b013e3181e89905","article-title":"Review Article: Risk Factors for Falls in Community-dwelling Older People: A Systematic Review and Meta-analysis","volume":"21","author":"Deandrea","year":"2010","journal-title":"Epidemiology"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"142","DOI":"10.1111\/j.1532-5415.1991.tb01616.x","article-title":"The Timed Up & Go: A Test of Basic Functional Mobility for Frail Elderly Persons","volume":"39","author":"Podsiadlo","year":"1991","journal-title":"J. Am. Geriatr. Soc."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1111\/j.1532-5415.1986.tb05480.x","article-title":"Performance-Oriented Assessment of Mobility Problems in Elderly Patients","volume":"34","author":"Tinetti","year":"1986","journal-title":"J. Am. Geriatr. Soc."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"304","DOI":"10.3138\/ptc.41.6.304","article-title":"Measuring balance in the elderly: Validation of an instrument","volume":"41","author":"Berg","year":"1989","journal-title":"Physiother. Can."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Barry, E., Galvin, R., Keogh, C., Horgan, F., and Fahey, T. (2014). Is the Timed Up and Go test a useful predictor of risk of falls in community dwelling older adults: A systematic review and meta-analysis. BMC Geriatr., 14.","DOI":"10.1186\/1471-2318-14-14"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1109\/MPRV.2014.52","article-title":"Bayesian Inference in Hidden Markov Models for In-Home Activity Recognition","volume":"13","author":"Ordonez","year":"2014","journal-title":"IEEE Pervasive Comput."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Nait Aicha, A., Englebienne, G., and Kr\u00f6se, B. (2017). Continuous measuring of the indoor walking speed of older adults living alone. J. Ambient Intell. Hum. Comput., 1\u201311.","DOI":"10.1007\/s12652-017-0456-x"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1186\/1743-0003-10-91","article-title":"Review of fall risk assessment in geriatric populations using inertial sensors","volume":"10","author":"Howcroft","year":"2013","journal-title":"J. Neuroeng. Rehabil."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"608","DOI":"10.1093\/gerona\/glu225","article-title":"Ambulatory fall-risk assessment: Amount and quality of daily-life gait predict falls in older adults","volume":"70","author":"Pijnappels","year":"2015","journal-title":"J. Gerontol. Ser. A Biomed. Sci. Med. Sci."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1177\/1545968314532031","article-title":"Identification of fall risk predictors in daily life measurements: Gait characteristics\u2019 reliability and association with self-reported fall history","volume":"29","author":"Rispens","year":"2015","journal-title":"Neurorehabil. Neural Repair"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"742","DOI":"10.1177\/1545968313491004","article-title":"Does the evaluation of gait quality during daily life provide insight into fall risk? A novel approach using 3-day accelerometer recordings","volume":"27","author":"Weiss","year":"2013","journal-title":"Neurorehabil. Neural Repair"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1102","DOI":"10.1093\/gerona\/glw019","article-title":"Continuous monitoring of turning mobility and its association to falls and cognitive function: A pilot study","volume":"71","author":"Mancini","year":"2016","journal-title":"J. Gerontol. Ser. A Biol. Sci. Med. Sci."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"843","DOI":"10.1109\/TBME.2002.800763","article-title":"Measurement of stand-sit and sit-stand transitions using a miniature gyroscope and its application in fall risk evaluation in the elderly","volume":"49","author":"Najafi","year":"2002","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Ord\u00f3nez, F.J., and Roggen, D. (2016). Deep convolutional and lstm recurrent neural networks for multimodal wearable activity recognition. Sensors, 16.","DOI":"10.3390\/s16010115"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1016\/j.jbiomech.2018.01.005","article-title":"Machine learning algorithms based on signals from a single wearable inertial sensor can detect surface-and age-related differences in walking","volume":"71","author":"Hu","year":"2018","journal-title":"J. Biomech."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1016\/0022-3956(75)90026-6","article-title":"Mini-mental state: A practical method for grading the cognitive state of patients for the clinician","volume":"12","author":"Folstein","year":"1975","journal-title":"J. Psychiatr. Res."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"e4","DOI":"10.2196\/resprot.3931","article-title":"Do extreme values of daily-life gait characteristics provide more information about fall risk than median values?","volume":"4","author":"Rispens","year":"2015","journal-title":"JMIR Res. Protoc."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1093\/ageing\/afp249","article-title":"Detection of gait and postures using a miniaturised triaxial accelerometer-based system: Accuracy in community-dwelling older adults","volume":"39","author":"Dijkstra","year":"2010","journal-title":"Age Ageing"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Van Schooten, K.S., Pijnappels, M., Rispens, S.M., Elders, P.J.M., Lips, P., Daffertshofer, A., Beek, P.J., and van Die\u00ebn, J.H. (2016). Daily-life gait quality as predictor of falls in older people: A 1-year prospective cohort study. PLoS ONE, 11.","DOI":"10.1371\/journal.pone.0158623"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Abdel-Hamid, O., Mohamed, A.R., Jiang, H., and Penn, G. (2012, January 25\u201330). Applying convolutional neural networks concepts to hybrid NN-HMM model for speech recognition. Proceedings of the 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Kyoto, Japan.","DOI":"10.1109\/ICASSP.2012.6288864"},{"key":"ref_24","unstructured":"Krizhevsky, A., Sutskever, I., and Hinton, G.E. (2012, January 3\u20136). Imagenet classification with deep convolutional neural networks. Proceedings of the 25th International Conference on Neural Information Processing Systems, Lake Tahoe, NV, USA."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Toshev, A., and Szegedy, C. (2014, January 24\u201327). Deeppose: Human pose estimation via deep neural networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.","DOI":"10.1109\/CVPR.2014.214"},{"key":"ref_26","unstructured":"Sutskever, I., Vinyals, O., and Le, Q.V. (2014, January 8\u201313). Sequence to sequence learning with neural networks. Proceedings of the Advances in Neural Information Processing Systems, Montreal, QC, Canada."},{"key":"ref_27","unstructured":"Graves, A. (arXiv, 2013). Generating sequences with recurrent neural networks, arXiv."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1109\/MC.2016.127","article-title":"A Medium-Scale Distributed System for Computer Science Research: Infrastructure for the Long Term","volume":"49","author":"Bal","year":"2016","journal-title":"Computer"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1109\/72.279181","article-title":"Learning long-term dependencies with gradient descent is difficult","volume":"5","author":"Bengio","year":"1994","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long Short-Term Memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Caruana, R. (1993, January 27\u201329). Multitask Learning: A Knowledge-Based Source of Inductive Bias. Proceedings of the Tenth International Conference on Machine Learning, Amherst, MA, USA.","DOI":"10.1016\/B978-1-55860-307-3.50012-5"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Van Kasteren, T.L., Englebienne, G., and Kr\u00f6se, B.J. (2011, January 16\u201318). Hierarchical activity recognition using automatically clustered actions. Proceedings of the International Joint Conference on Ambient Intelligence, Amsterdam, The Netherlands.","DOI":"10.1007\/978-3-642-25167-2_9"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/18\/5\/1654\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T15:05:21Z","timestamp":1760195121000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/18\/5\/1654"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5,22]]},"references-count":32,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2018,5]]}},"alternative-id":["s18051654"],"URL":"https:\/\/doi.org\/10.3390\/s18051654","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,5,22]]}}}