{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T03:05:39Z","timestamp":1765422339053,"version":"build-2065373602"},"reference-count":48,"publisher":"MDPI AG","issue":"22","license":[{"start":{"date-parts":[[2023,11,15]],"date-time":"2023-11-15T00:00:00Z","timestamp":1700006400000},"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>Injury, hospitalization, and even death are common consequences of falling for elderly people. Therefore, early and robust identification of people at risk of recurrent falling is crucial from a preventive point of view. This study aims to evaluate the effectiveness of an interpretable semi-supervised approach in identifying individuals at risk of falls by using the data provided by ankle-mounted IMU sensors. Our method benefits from the cause\u2013effect link between a fall event and balance ability to pinpoint the moments with the highest fall probability. This framework also has the advantage of training on unlabeled data, and one can exploit its interpretation capacities to detect the target while only using patient metadata, especially those in relation to balance characteristics. This study shows that a visual-based self-attention model is able to infer the relationship between a fall event and loss of balance by attributing high values of weight to moments where the vertical acceleration component of the IMU sensors exceeds 5 m\/s\u00b2 during an especially short period. This semi-supervised approach uses interpretable features to highlight the moments of the recording that may explain the score of balance, thus revealing the moments with the highest risk of falling. Our model allows for the detection of 71% of the possible falling risk events in a window of 1 s (500 ms before and after the target) when compared with threshold-based approaches. This type of framework plays a paramount role in reducing the costs of annotation in the case of fall prevention when using wearable devices. Overall, this adaptive tool can provide valuable data to healthcare professionals, and it can assist them in enhancing fall prevention efforts on a larger scale with lower costs.<\/jats:p>","DOI":"10.3390\/s23229194","type":"journal-article","created":{"date-parts":[[2023,11,16]],"date-time":"2023-11-16T08:19:43Z","timestamp":1700122783000},"page":"9194","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["CNN-Based Self-Attention Weight Extraction for Fall Event Prediction Using Balance Test Score"],"prefix":"10.3390","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5433-2332","authenticated-orcid":false,"given":"Youness","family":"El Marhraoui","sequence":"first","affiliation":[{"name":"CLI Department, University of Paris 8, 93200 Saint-Denis, France"},{"name":"Laboratoire Analyse, G\u00e9om\u00e9trie et Applications, University of Sorbonne Paris Nord, 93430 Villetaneuse, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"St\u00e9phane","family":"Bouilland","sequence":"additional","affiliation":[{"name":"Fondation Hopale, 62608 Berck, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mehdi","family":"Boukallel","sequence":"additional","affiliation":[{"name":"Laboratory for Integration of Systems and Technology, CEA, 91120 Palaiseau, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Margarita","family":"Anastassova","sequence":"additional","affiliation":[{"name":"Laboratory for Integration of Systems and Technology, CEA, 91120 Palaiseau, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mehdi","family":"Ammi","sequence":"additional","affiliation":[{"name":"CLI Department, University of Paris 8, 93200 Saint-Denis, France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,11,15]]},"reference":[{"key":"ref_1","first-page":"275","article-title":"Reducing fall risk in the elderly: Risk factors and fall prevention, a systematic review","volume":"105","author":"Pfortmueller","year":"2014","journal-title":"Minerva Med."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1016\/j.apnr.2015.05.007","article-title":"Falls prevention: Identification of predictive fall risk factors","volume":"29","author":"Natalie","year":"2016","journal-title":"Appl. Nurs. Res."},{"key":"ref_3","unstructured":"Centre for Clinical Practice at NICE (UK) (2023, June 05). Falls: Assessment and Prevention of Falls in Older People. Available online: https:\/\/www.nice.org.uk\/guidance\/cg161."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1111\/j.1741-6612.2009.00375.x","article-title":"Four-item fall risk screening tool for subacute and residential aged care: The first step in fall prevention","volume":"28","author":"Stapleton","year":"2009","journal-title":"Australas. J. Ageing"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1177\/2150131916659282","article-title":"Timed Up and Go (TUG) Test: Normative Reference Values for Ages 20 to 59 Years and Relationships with Physical and Mental Health Risk Factors","volume":"8","author":"Kear","year":"2017","journal-title":"J. Prim. Care Commu. Health"},{"key":"ref_6","unstructured":"Miranda-Cantellops, N., and Tiu, T.K. (2023, June 05). Berg Balance Testing. Updated 17 February 2023, StatPearls [Internet], Available online: https:\/\/www.ncbi.nlm.nih.gov\/books\/NBK574518\/."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1046\/j.1440-172X.2003.00430.x","article-title":"Hospital fall risk assessment tools: A critique of the literature","volume":"9","author":"Helen","year":"2003","journal-title":"Int. J. Nurs. Pract."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1111\/j.1365-2834.2010.01218.x","article-title":"Testing the sensitivity, specificity and feasibility of four falls risk assessment tools in a clinical setting","volume":"19","author":"Chapman","year":"2011","journal-title":"J. Nurs. Manag."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"921506","DOI":"10.3389\/fdgth.2022.921506","article-title":"Wearable Sensor Systems for Fall Risk Assessment: A Review","volume":"4","author":"Subramaniam","year":"2022","journal-title":"Front. Digit. Health"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Ferreira, R.N., Ribeiro, N.F., and Santos, C.P. (2022). Fall Risk Assessment Using Wearable Sensors: A Narrative Review. Sensors, 22.","DOI":"10.3390\/s22030984"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Chen, B., Chen, C., Hu, J., Sayeed, Z., Qi, J., Darwiche, H.F., Little, B.E., Lou, S., Darwish, M., and Foote, C. (2022). Computer Vision and Machine Learning-Based Gait Pattern Recognition for Flat Fall Prediction. Sensors, 22.","DOI":"10.3390\/s22207960"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Amann, J., Blasimme, A., Vayena, E., Frey, D., Madai, V.I., and on behalf of the Precise4Q consortium (2020). Explainability for artificial intelligence in healthcare: A multidisciplinary perspective. BMC Med. Inf. Decis Mak., 20.","DOI":"10.1186\/s12911-020-01332-6"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Tang, Y.T., and Romero-Ortuno, R. (2022). Using Explainable AI (XAI) for the Prediction of Falls in the Older Population. Algorithms, 15.","DOI":"10.3390\/a15100353"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"5974","DOI":"10.1109\/JBHI.2022.3205058","article-title":"Identification of Neurodegenerative Diseases from Gait Rhythm through Time Domain and Time-Dependent Spectral Descriptors","volume":"26","author":"Mengarelli","year":"2022","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"493.E1","DOI":"10.1016\/j.amjmed.2006.07.022","article-title":"Falls in older adults: Risk assessment, management and prevention","volume":"120","author":"Moylan","year":"2007","journal-title":"Am. J. Med."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1016\/j.arr.2010.03.004","article-title":"Resistance exercise for muscular strength in older adults: A meta-analysis","volume":"9","author":"Peterson","year":"2010","journal-title":"Ageing Res. Rev."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1019094","DOI":"10.3389\/fmed.2022.1019094","article-title":"Risk factors for falls among community-dwelling older adults: A systematic review and meta-analysis","volume":"9","author":"Li","year":"2023","journal-title":"Front. Med."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"372.e1","DOI":"10.1016\/j.jamda.2017.12.099","article-title":"Fall-Risk-Increasing Drugs: A Systematic Review and Meta-analysis: III. Others","volume":"19","author":"Seppala","year":"2018","journal-title":"J. Am. Med Dir. Assoc."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"2273","DOI":"10.1007\/s00520-014-2598-0","article-title":"Geriatric assessment as an aide to understanding falls in older adults with cancer","volume":"23","author":"Williams","year":"2015","journal-title":"Sup. Care Cancer"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"569","DOI":"10.1016\/j.cger.2010.06.002","article-title":"Vision and falls in older people: Risk factors and intervention strategies","volume":"26","author":"Lord","year":"2010","journal-title":"Clin. Geriatr. Med."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1016\/j.jamda.2016.10.008","article-title":"Falls, Cognitive Impairment, and Gait Performance: Results from the GOOD Initiative","volume":"18","author":"Allali","year":"2017","journal-title":"J. Am. Med. Dir. Assoc."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"100124","DOI":"10.1016\/j.iot.2019.100124","article-title":"Practical fall detection based on IoT technologies: A survey","volume":"8","author":"Mozaffari","year":"2019","journal-title":"Internet Things"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Razum, D., Seketa, G., Vugrin, J., and Lackovic, I. (2018, January 21\u201325). Optimal threshold selection for threshold-based fall detection algorithms with multiple features. Proceedings of the 2018 41st International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO), Opatija, Croatia.","DOI":"10.23919\/MIPRO.2018.8400272"},{"key":"ref_24","first-page":"576364","article-title":"Development of a wearable-sensor-based fall detection system","volume":"2015","author":"Wu","year":"2015","journal-title":"Int. J. Telemed. Appl."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Mao, A., Ma, X., He, Y., and Luo, J. (2017). Highly Portable, Sensor-Based System for Human Fall Monitoring. Sensors, 17.","DOI":"10.3390\/s17092096"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Chaitep, T., and Chawachat, J. (2017, January 27\u201330). A 3-phase threshold algorithm for smartphone-based fall detection. Proceedings of the 2017 14th International Conference on Electrical Engineering\/Electronics, Computer, Telecommunications and Information Technology, Phuket, Thailand.","DOI":"10.1109\/ECTICon.2017.8096203"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"18398","DOI":"10.1109\/JSEN.2021.3090454","article-title":"Performance, challenges, and limitations in multimodal fall detection systems: A review","volume":"21","author":"Xefteris","year":"2021","journal-title":"IEEE Sens. J."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"167830","DOI":"10.1109\/ACCESS.2020.3022818","article-title":"Latest Research Trends in Gait Analysis Using Wearable Sensors and Machine Learning: A Systematic Review","volume":"8","author":"Saboor","year":"2020","journal-title":"IEEE Access"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1007\/s11517-020-02295-6","article-title":"A comparison of machine learning classifiers for smartphone-based gait analysis","volume":"59","author":"Altilio","year":"2021","journal-title":"Med. Biol. Eng. Comput."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Makino, K., Lee, S., Bae, S., Chiba, I., Harada, K., Katayama, O., Tomida, K., Morikawa, M., and Shimada, H. (2021). Simplified Decision-Tree Algorithm to Predict Falls for Community-Dwelling Older Adults. J. Clin. Med., 10.","DOI":"10.3390\/jcm10215184"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Alizadeh, J., Bogdan, M., Classen, J., and Fricke, C. (2021). Support Vector Machine Classifiers Show High Generalizability in Automatic Fall Detection in Older Adults. Sensors, 21.","DOI":"10.3390\/s21217166"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1849","DOI":"10.1109\/JSEN.2013.2245231","article-title":"HMM-Based Human Fall Detection and Prediction Method Using Tri-Axial Accelerometer","volume":"13","author":"Tong","year":"2013","journal-title":"Sensor. J. IEEE"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Guti\u00e9rrez, J., Rodr\u00edguez, V., and Martin, S. (2021). Comprehensive Review of Vision-Based Fall Detection Systems. Sensors, 21.","DOI":"10.3390\/s21030947"},{"key":"ref_34","first-page":"8697805","article-title":"Comparing Machine Learning Methods to Improve Fall Risk Detection in Elderly with Osteoporosis from Balance Data","volume":"2021","author":"Morales","year":"2021","journal-title":"J. Heal. Eng."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"114226","DOI":"10.1016\/j.eswa.2020.114226","article-title":"A multimodal approach using deep learning for fall detection","volume":"168","author":"Ferreira","year":"2021","journal-title":"Expert Syst. Appl."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Nait Aicha, A., Englebienne, G., Van Schooten, K.S., Pijnappels, M., and Kr\u00f6se, B. (2018). Deep Learning to Predict Falls in Older Adults Based on Daily-Life Trunk Accelerometry. Sensors, 18.","DOI":"10.3390\/s18051654"},{"key":"ref_37","unstructured":"Shickel, B., and Rashidi, P. (2020). Sequential interpretability: Methods, applications, and future direction for understanding deep learning models in the context of sequential data. arXiv."},{"key":"ref_38","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., and Polosukhin, I. (2017). Attention is all you need. arXiv."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"103946","DOI":"10.1016\/j.ijmedinf.2019.08.006","article-title":"Fall detection and fall risk assessment in older person using wearable sensors: A systematic review","volume":"130","author":"Bet","year":"2019","journal-title":"Int. J. Med Inform."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1186\/s12984-017-0255-9","article-title":"Feature selection for elderly faller classification based on wearable sensors","volume":"14","author":"Howcroft","year":"2017","journal-title":"J. Neuroeng. Rehabil."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1007\/s00391-009-0035-7","article-title":"Predicting in-patient falls in a geriatric clinic: A clinical study combining assessment data and simple sensory gait measurements","volume":"42","author":"Marschollek","year":"2009","journal-title":"Z. Gerontol. Geriatr."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"1824","DOI":"10.1109\/JBHI.2020.3025049","article-title":"Wearables and Deep Learning Classify Fall Risk from Gait in Multiple Sclerosis","volume":"25","author":"Meyer","year":"2021","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Wu, S., Ou, J., Shu, L., Hu, G., Song, Z., Xu, X., and Chen, Z. (2022). MhNet: Multi-scale spatio-temporal hierarchical network for real-time wearable fall risk assessment of the elderly. Comput. Biol. Med., 144.","DOI":"10.1016\/j.compbiomed.2022.105355"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Carrara, F., Pasco, L., Gennaro, C., and Falchi, F. (2022, January 14\u201316). Learning to Detect Fallen People in Virtual Worlds. Proceedings of the 19th International Conference on Content-Based Multimedia Indexing (CBMI\u201922), Graz, Austria.","DOI":"10.1145\/3549555.3549573"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"1738","DOI":"10.1109\/JSEN.2021.3131037","article-title":"Wearable Pre-Impact Fall Detection System Based on 3D Accelerometer and Subject\u2019s Height","volume":"22","author":"Escriba","year":"2022","journal-title":"IEEE Sens. J."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"2477","DOI":"10.11591\/eei.v10i5.3152","article-title":"A FPGA threshold-based fall detection algorithm for elderly fall monitoring with verilog","volume":"10","author":"Lo","year":"2021","journal-title":"Bull. Electr. Eng. Inform."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Thella, A.K., Suryadevara, V.K., Rizkalla, M., and Hossain, G. (2016, January 25\u201329). Smart unit care for pre fall detection and prevention. Proceedings of the 2016 IEEE National Aerospace and Electronics Conference (NAECON) and Ohio Innovation Summit (OIS), Dayton, OH, USA.","DOI":"10.1109\/NAECON.2016.7856802"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"340","DOI":"10.1016\/j.irbm.2008.08.002","article-title":"A proposal for the classification and evaluation of fall detectors","volume":"29","author":"Noury","year":"2008","journal-title":"Irbm"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/22\/9194\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:23:22Z","timestamp":1760131402000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/22\/9194"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,15]]},"references-count":48,"journal-issue":{"issue":"22","published-online":{"date-parts":[[2023,11]]}},"alternative-id":["s23229194"],"URL":"https:\/\/doi.org\/10.3390\/s23229194","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2023,11,15]]}}}