{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,3]],"date-time":"2026-11-03T19:20:29Z","timestamp":1793733629698,"version":"4.6.1"},"reference-count":69,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,7,12]],"date-time":"2021-07-12T00:00:00Z","timestamp":1626048000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,7,12]],"date-time":"2021-07-12T00:00:00Z","timestamp":1626048000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100007013","name":"F. Hoffmann-La Roche","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007013","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>The emergence of digital technologies such as smartphones in healthcare applications have demonstrated the possibility of developing rich, continuous, and objective measures of multiple sclerosis (MS) disability that can be administered remotely and out-of-clinic. Deep Convolutional Neural Networks (DCNN) may capture a richer representation of healthy and MS-related ambulatory characteristics from the raw smartphone-based inertial sensor data than standard feature-based methodologies. To overcome the typical limitations associated with remotely generated health data, such as low subject numbers, sparsity, and heterogeneous data, a transfer learning (TL) model from similar large open-source datasets was proposed. Our TL framework leveraged the ambulatory information learned on human activity recognition (HAR) tasks collected from wearable smartphone sensor data. It was demonstrated that fine-tuning TL DCNN HAR models towards MS disease recognition tasks outperformed previous Support Vector Machine (SVM) feature-based methods, as well as DCNN models trained end-to-end, by upwards of 8\u201315%. A lack of transparency of \u201cblack-box\u201d deep networks remains one of the largest stumbling blocks to the wider acceptance of deep learning for clinical applications. Ensuing work therefore aimed to visualise DCNN decisions attributed by relevance heatmaps using Layer-Wise Relevance Propagation (LRP). Through the LRP framework, the patterns captured from smartphone-based inertial sensor data that were reflective of those who are healthy versus people with MS (PwMS) could begin to be established and understood. Interpretations suggested that cadence-based measures, gait speed, and ambulation-related signal perturbations were distinct characteristics that distinguished MS disability from healthy participants. Robust and interpretable outcomes, generated from high-frequency out-of-clinic assessments, could greatly augment the current in-clinic assessment picture for PwMS, to inform better disease management techniques, and enable the development of better therapeutic interventions.<\/jats:p>","DOI":"10.1038\/s41598-021-92776-x","type":"journal-article","created":{"date-parts":[[2021,7,12]],"date-time":"2021-07-12T06:03:06Z","timestamp":1626069786000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":31,"title":["Interpretable deep learning for the remote characterisation of ambulation in multiple sclerosis using smartphones"],"prefix":"10.1038","volume":"11","author":[{"given":"Andrew P.","family":"Creagh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Florian","family":"Lipsmeier","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Lindemann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maarten De","family":"Vos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,7,12]]},"reference":[{"key":"92776_CR1","doi-asserted-by":"publisher","unstructured":"Taylor, K. I., Staunton, H., Lipsmeier, F., Nobbs, D. & Lindemann, M. Outcome measures based on digital health technology sensor data: data- and patient-centric approaches. NPJ Digit. Med. 3, 97. https:\/\/doi.org\/10.1038\/s41746-020-0305-8 (2020).","DOI":"10.1038\/s41746-020-0305-8"},{"key":"92776_CR2","doi-asserted-by":"publisher","unstructured":"Creagh, A. et al. Smartphone-based remote assessment of upper extremity function for multiple sclerosis using the draw a shape test.\u00a0Physiological Measurement 41, 054002, https:\/\/doi.org\/10.1088\/1361-6579\/ab8771 (2020)","DOI":"10.1088\/1361-6579\/ab8771"},{"key":"92776_CR3","doi-asserted-by":"publisher","unstructured":"Creagh, A. P. et al. Smartphone- and Smartwatch-Based Remote Characterisation of Ambulation in Multiple Sclerosis During the Two-Minute Walk Test. IEEE J Biomed Health Inform 25, 838-849, https:\/\/doi.org\/10.1109\/JBHI.2020.2998187 (2021).","DOI":"10.1109\/JBHI.2020.2998187"},{"key":"92776_CR4","doi-asserted-by":"publisher","first-page":"044005","DOI":"10.1088\/1361-6579\/aab512","volume":"39","author":"J Prince","year":"2018","unstructured":"Prince, J., Arora, S. & de Vos, M. Big data in parkinson\u2019s disease: using smartphones to remotely detect longitudinal disease phenotypes. Physiol. Measur. 39, 044005 (2018).","journal-title":"Physiol. Measur."},{"key":"92776_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.patter.2020.100042","volume":"100042","author":"H Zhang","year":"2020","unstructured":"Zhang, H., Deng, K., Li, H., Albin, R. L. & Guan, Y. Deep learning identifies digital biomarkers for self-reported parkinson\u2019s disease. Patterns 100042, 1. https:\/\/doi.org\/10.1016\/j.patter.2020.100042 (2020).","journal-title":"Patterns"},{"key":"92776_CR6","doi-asserted-by":"publisher","first-page":"e177","DOI":"10.2196\/mhealth.9656","volume":"6","author":"M Crouthamel","year":"2018","unstructured":"Crouthamel, M. et al. Using a researchkit smartphone app to collect rheumatoid arthritis symptoms from real-world participants: feasibility study. JMIR mHealth uHealth 6, e177 (2018).","journal-title":"JMIR mHealth uHealth"},{"key":"92776_CR7","first-page":"175","volume":"37","author":"MM Goldenberg","year":"2012","unstructured":"Goldenberg, M. M. Multiple sclerosis review. Pharm. Therap. 37, 175 (2012).","journal-title":"Pharm. Therap."},{"key":"92776_CR8","doi-asserted-by":"publisher","first-page":"e162","DOI":"10.1212\/NXI.0000000000000162","volume":"2","author":"R Bove","year":"2015","unstructured":"Bove, R. et al. Evaluating more naturalistic outcome measures: a 1-year smartphone study in multiple sclerosis. Neurol. Neuroimmunol. Neuroinflamm. 2, e162 (2015).","journal-title":"Neurol. Neuroimmunol. Neuroinflamm."},{"key":"92776_CR9","doi-asserted-by":"publisher","first-page":"1576","DOI":"10.1016\/S0140-6736(00)04725-5","volume":"357","author":"G Comi","year":"2001","unstructured":"Comi, G. et al. Effect of early interferon treatment on conversion to definite multiple sclerosis: a randomised study. The Lancet 357, 1576\u20131582 (2001).","journal-title":"The Lancet"},{"key":"92776_CR10","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1016\/j.gaitpost.2011.11.027","volume":"36","author":"JJ Sosnoff","year":"2012","unstructured":"Sosnoff, J. J., Sandroff, B. M. & Motl, R. W. Quantifying gait abnormalities in persons with multiple sclerosis with minimal disability. Gait Post. 36, 154\u2013156 (2012).","journal-title":"Gait Post."},{"key":"92776_CR11","doi-asserted-by":"publisher","first-page":"620","DOI":"10.1177\/1352458506070658","volume":"12","author":"CL Martin","year":"2006","unstructured":"Martin, C. L. et al. Gait and balance impairment in early multiple sclerosis in the absence of clinical disability. Multiple Scleros. J. 12, 620\u2013628 (2006).","journal-title":"Multiple Scleros. J."},{"key":"92776_CR12","doi-asserted-by":"publisher","first-page":"613","DOI":"10.1177\/1352458505070609","volume":"12","author":"S Crenshaw","year":"2006","unstructured":"Crenshaw, S., Royer, T., Richards, J. & Hudson, D. Gait variability in people with multiple sclerosis. Multiple Scleros. J. 12, 613\u2013619 (2006).","journal-title":"Multiple Scleros. J."},{"key":"92776_CR13","doi-asserted-by":"publisher","first-page":"1670","DOI":"10.1007\/s10439-012-0697-y","volume":"41","author":"JM Huisinga","year":"2013","unstructured":"Huisinga, J. M., Mancini, M., George, R. J. S. & Horak, F. B. Accelerometry reveals differences in gait variability between patients with multiple sclerosis and healthy controls. Ann. Biomed. Eng. 41, 1670\u20131679 (2013).","journal-title":"Ann. Biomed. Eng."},{"key":"92776_CR14","doi-asserted-by":"publisher","first-page":"958","DOI":"10.1016\/j.gaitpost.2013.12.010","volume":"39","author":"RI Spain","year":"2014","unstructured":"Spain, R. I., Mancini, M., Horak, F. B. & Bourdette, D. Body-worn sensors capture variability, but not decline, of gait and balance measures in multiple sclerosis over 18 months. Gait Post. 39, 958\u2013964 (2014).","journal-title":"Gait Post."},{"key":"92776_CR15","doi-asserted-by":"publisher","first-page":"1015","DOI":"10.1177\/1545968312437943","volume":"26","author":"RW Motl","year":"2012","unstructured":"Motl, R. W., Sandroff, B. M., Suh, Y. & Sosnoff, J. J. Energy cost of walking and its association with gait parameters, daily activity, and fatigue in persons with mild multiple sclerosis. Neurorehabil. Neural Repair 26, 1015\u20131021 (2012).","journal-title":"Neurorehabil. Neural Repair"},{"key":"92776_CR16","doi-asserted-by":"publisher","first-page":"1444","DOI":"10.1212\/WNL.33.11.1444","volume":"33","author":"JF Kurtzke","year":"1983","unstructured":"Kurtzke, J. F. Rating neurologic impairment in multiple sclerosis an expanded disability status scale (edss). Neurology 33, 1444\u20131444 (1983).","journal-title":"Neurology"},{"key":"92776_CR17","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1191\/1352458502ms845oa","volume":"8","author":"R Rudick","year":"2002","unstructured":"Rudick, R., Cutter, G. & Reingold, S. The multiple sclerosis functional composite: a new clinical outcome measure for multiple sclerosis trials. Multiple Scleros. J. 8, 359\u2013365 (2002).","journal-title":"Multiple Scleros. J."},{"key":"92776_CR18","doi-asserted-by":"publisher","first-page":"704","DOI":"10.1177\/1352458517690823","volume":"23","author":"RW Motl","year":"2017","unstructured":"Motl, R. W. et al. Validity of the timed 25-foot walk as an ambulatory performance outcome measure for multiple sclerosis. Mult Scler. 23, 704\u2013710. https:\/\/doi.org\/10.1177\/1352458517690823 (2017).","journal-title":"Mult Scler."},{"key":"92776_CR19","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1186\/1471-2377-12-6","volume":"12","author":"RW Motl","year":"2012","unstructured":"Motl, R. W. et al. Evidence for the different physiological significance of the 6-and 2-minute walk tests in multiple sclerosis. BMC Neurol. 12, 6 (2012).","journal-title":"BMC Neurol."},{"key":"92776_CR20","doi-asserted-by":"publisher","first-page":"573","DOI":"10.1016\/j.gaitpost.2011.11.026","volume":"35","author":"R Spain","year":"2012","unstructured":"Spain, R. et al. Body-worn motion sensors detect balance and gait deficits in people with multiple sclerosis who have normal walking speed. Gait Post. 35, 573\u2013578 (2012).","journal-title":"Gait Post."},{"key":"92776_CR21","unstructured":"Goodfellow, I., Bengio, Y. & Courville, A. Deep learning (MIT Press, 2016)."},{"key":"92776_CR22","unstructured":"Cui, Z., Chen, W. & Chen, Y. Multi-scale convolutional neural networks for time series classification. arXiv preprint arXiv.1603.06995 (2016)."},{"key":"92776_CR23","doi-asserted-by":"publisher","unstructured":"Ord\u00f3\u00f1ez, F. J. & Roggen, D. Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition. Sensors (Basel, Switzerland) 16, 115, https:\/\/doi.org\/10.3390\/s16010115 (2016).","DOI":"10.3390\/s16010115"},{"key":"92776_CR24","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.patrec.2018.02.010","volume":"119","author":"J Wang","year":"2019","unstructured":"Wang, J., Chen, Y., Hao, S., Peng, X. & Hu, L. Deep learning for sensor-based activity recognition: a survey. Pattern Recognit. Lett. 119, 3\u201311 (2019).","journal-title":"Pattern Recognit. Lett."},{"key":"92776_CR25","unstructured":"Alsheikh, M.\u00a0A. et\u00a0al. Deep activity recognition models with triaxial accelerometers. arXiv preprint arXiv:1511.04664 (2015)."},{"key":"92776_CR26","doi-asserted-by":"crossref","unstructured":"Cheng, W.-Y. et\u00a0al. Large-scale continuous mobility monitoring of parkinson\u2019s disease patients using smartphones. In Wireless Mobile Communication and Healthcare, pp. 12\u201319 (Springer, 2017).","DOI":"10.1007\/978-3-319-98551-0_2"},{"key":"92776_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/JBHI.2019.2906499","volume":"1","author":"MT Martinez","year":"2019","unstructured":"Martinez, M. T. & Leon, P. D. Falls risk classification of older adults using deep neural networks and transfer learning. IEEE J. Biomed. Health Inf. 1, 1. https:\/\/doi.org\/10.1109\/JBHI.2019.2906499 (2019).","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"92776_CR28","doi-asserted-by":"publisher","unstructured":"Gong, G. & Lach, J. Deepmotion: a deep convolutional neural network on inertial body sensors for gait assessment in multiple sclerosis. In IEEE Wireless Health (WH), pp. 1\u20138, https:\/\/doi.org\/10.1109\/WH.2016.7764572 (IEEE, 2016).","DOI":"10.1109\/WH.2016.7764572"},{"key":"92776_CR29","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1016\/j.patcog.2017.09.005","volume":"74","author":"M Gadaleta","year":"2018","unstructured":"Gadaleta, M. & Rossi, M. Idnet: Smartphone-based gait recognition with convolutional neural networks. Pattern Recognit. 74, 25\u201337. https:\/\/doi.org\/10.1016\/j.patcog.2017.09.005 (2018).","journal-title":"Pattern Recognit."},{"key":"92776_CR30","doi-asserted-by":"crossref","first-page":"3197","DOI":"10.1109\/TIFS.2020.2985628","volume":"15","author":"Q Zou","year":"2020","unstructured":"Zou, Q., Wang, Y., Wang, Q., Zhao, Y. & Li, Q. Deep learning-based gait recognition using smartphones in the wild. IEEE Trans. Inf. Forens. Secur. 15, 3197\u20133212 (2020).","journal-title":"IEEE Trans. Inf. Forens. Secur."},{"key":"92776_CR31","unstructured":"Fawaz, H.\u00a0I., Forestier, G., Weber, J., Idoumghar, L. & Muller, P.-A. Transfer learning for time series classification. In IEEE International Conference on Big Data (Big Data), pp. 1367\u20131376 (IEEE, 2018)."},{"key":"92776_CR32","first-page":"1717","volume":"1","author":"M Oquab","year":"2014","unstructured":"Oquab, M., Bottou, L., Laptev, I. & Sivic, J. Learning and transferring mid-level image representations using convolutional neural networks. Proceedings of the IEEE conference on computer vision and pattern recognition 1, 1717\u20131724 (2014).","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"92776_CR33","doi-asserted-by":"crossref","unstructured":"Andreotti, F. et\u00a0al. Multichannel sleep stage classification and transfer learning using convolutional neural networks. In 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 171\u2013174 (IEEE, 2018).","DOI":"10.1109\/EMBC.2018.8512214"},{"key":"92776_CR34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TBME.2020.3020381","volume":"1","author":"H Phan","year":"2020","unstructured":"Phan, H. et al. Towards more accurate automatic sleep staging via deep transfer learning. IEEE Trans. Biomed. Eng. 1, 1. https:\/\/doi.org\/10.1109\/TBME.2020.3020381 (2020).","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"92776_CR35","doi-asserted-by":"crossref","unstructured":"Morales, F. J. O. & Roggen, D. Deep convolutional feature transfer across mobile activity recognition domains, sensor modalities and locations.\u00a0In\u00a0Proceedings of the 2016 ACM International Symposium on Wearable Computers, pp. 92-99. (2016)","DOI":"10.1145\/2971763.2971764"},{"key":"92776_CR36","doi-asserted-by":"crossref","unstructured":"Kalouris, G., Zacharaki, E. I. & Megalooikonomou, V. Improving cnn-based activity recognition by data augmentation and transfer learning. In\u00a017th International Conference on Industrial Informatics (INDIN) vol. 1, pp 1387\u20131394 (IEEE, 2019).","DOI":"10.1109\/INDIN41052.2019.8972135"},{"key":"92776_CR37","doi-asserted-by":"publisher","first-page":"e14863","DOI":"10.2196\/14863","volume":"21","author":"L Midaglia","year":"2019","unstructured":"Midaglia, L. et al. Adherence and satisfaction of smartphone-and smartwatch-based remote active testing and passive monitoring in people with multiple sclerosis: Nonrandomized interventional feasibility study. J. Med. Internet Res. 21, e14863 (2019).","journal-title":"J. Med. Internet Res."},{"key":"92776_CR38","unstructured":"Anguita, D., Ghio, A., Oneto, L., Parra, X. & Reyes-Ortiz, J.\u00a0L. A public domain dataset for human activity recognition using smartphones. In Esann. 3, 3 (2013)."},{"key":"92776_CR39","doi-asserted-by":"publisher","first-page":"133190","DOI":"10.1109\/ACCESS.2019.2940729","volume":"7","author":"GM Weiss","year":"2019","unstructured":"Weiss, G. M., Yoneda, K. & Hayajneh, T. Smartphone and smartwatch-based biometrics using activities of daily living. IEEE Access 7, 133190\u2013133202. https:\/\/doi.org\/10.1109\/ACCESS.2019.2940729 (2019).","journal-title":"IEEE Access"},{"key":"92776_CR40","doi-asserted-by":"crossref","unstructured":"Samek, Wojciech, Gr\u00e9goire Montavon, Andrea Vedaldi, Lars Kai Hansen, and Klaus-Robert M\u00fcller. Explainable AI: interpreting, explaining and visualizing deep learning. Vol. 11700. Springer Nature, (2019).","DOI":"10.1007\/978-3-030-28954-6"},{"key":"92776_CR41","unstructured":"Simonyan, K., Vedaldi, A. & Zisserman, A. Deep inside convolutional networks: Visualising image classification models and saliency maps. arXiv preprint arXiv.1312.6034 (2013)."},{"key":"92776_CR42","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3236009","volume":"51","author":"R Guidotti","year":"2018","unstructured":"Guidotti, R. et al. A survey of methods for explaining black box models. ACM Comput. Surv. (CSUR) 51, 1\u201342 (2018).","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"92776_CR43","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1038\/s41591-018-0300-7","volume":"25","author":"EJ Topol","year":"2019","unstructured":"Topol, E. J. High-performance medicine: the convergence of human and artificial intelligence. Nat. Med. 25, 44\u201356. https:\/\/doi.org\/10.1038\/s41591-018-0300-7 (2019).","journal-title":"Nat. Med."},{"key":"92776_CR44","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.dsp.2017.10.011","volume":"73","author":"G Montavon","year":"2018","unstructured":"Montavon, G., Samek, W. & M\u00fcller, K.-R. Methods for interpreting and understanding deep neural networks. Digit. Signal Process. 73, 1\u201315. https:\/\/doi.org\/10.1016\/j.dsp.2017.10.011 (2018).","journal-title":"Digit. Signal Process."},{"key":"92776_CR45","doi-asserted-by":"crossref","unstructured":"Zeiler, M.\u00a0D. & Fergus, R. Visualizing and understanding convolutional networks. In European conference on computer vision, pp. 818\u2013833 (Springer, 2014).","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"92776_CR46","doi-asserted-by":"publisher","first-page":"52138","DOI":"10.1109\/ACCESS.2018.2870052","volume":"6","author":"A Adadi","year":"2018","unstructured":"Adadi, A. & Berrada, M. Peeking inside the black-box: a survey on explainable artificial intelligence (xai). IEEE Access 6, 52138\u201352160 (2018).","journal-title":"IEEE Access"},{"key":"92776_CR47","doi-asserted-by":"crossref","unstructured":"Montavon, G., Binder, A., Lapuschkin, S., Samek, W. & M\u00fcller, K.-R. Layer-wise relevance propagation: an overview, 193\u2013209 (Springer, 2019).","DOI":"10.1007\/978-3-030-28954-6_10"},{"key":"92776_CR48","doi-asserted-by":"publisher","first-page":"e0130140","DOI":"10.1371\/journal.pone.0130140","volume":"10","author":"S Bach","year":"2015","unstructured":"Bach, S. et al. On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PloS One 10, e0130140 (2015).","journal-title":"PloS One"},{"key":"92776_CR49","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3389\/fnagi.2019.00194","volume":"11","author":"M B\u00f6hle","year":"2019","unstructured":"B\u00f6hle, M., Eitel, F., Weygandt, M. & Ritter, K. Layer-wise relevance propagation for explaining deep neural network decisions in mri-based alzheimer\u2019s disease classification. Front. Aging Neurosci. 11, 1. https:\/\/doi.org\/10.3389\/fnagi.2019.00194 (2019).","journal-title":"Front. Aging Neurosci."},{"key":"92776_CR50","doi-asserted-by":"publisher","first-page":"102003","DOI":"10.1016\/j.nicl.2019.102003","volume":"24","author":"F Eitel","year":"2019","unstructured":"Eitel, F. et al. Uncovering convolutional neural network decisions for diagnosing multiple sclerosis on conventional mri using layer-wise relevance propagation. NeuroImage Clin. 24, 102003 (2019).","journal-title":"NeuroImage Clin."},{"key":"92776_CR51","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1016\/j.jneumeth.2016.10.008","volume":"274","author":"I Sturm","year":"2016","unstructured":"Sturm, I., Lapuschkin, S., Samek, W. & M\u00fcller, K.-R. Interpretable deep neural networks for single-trial eeg classification. J. Neurosci. Methods 274, 141\u2013145. https:\/\/doi.org\/10.1016\/j.jneumeth.2016.10.008 (2016).","journal-title":"J. Neurosci. Methods"},{"key":"92776_CR52","unstructured":"Slijepcevic, D. et\u00a0al. On the explanation of machine learning predictions in clinical gait analysis. arXiv e-prints arXiv.1912.07737 (2019)."},{"key":"92776_CR53","doi-asserted-by":"publisher","first-page":"2391","DOI":"10.1038\/s41598-019-38748-8","volume":"9","author":"F Horst","year":"2019","unstructured":"Horst, F., Lapuschkin, S., Samek, W., M\u00fcller, K.-R. & Sch\u00f6llhorn, W. I. Explaining the unique nature of individual gait patterns with deep learning. Sci. Rep. 9, 2391. https:\/\/doi.org\/10.1038\/s41598-019-38748-8 (2019).","journal-title":"Sci. Rep."},{"key":"92776_CR54","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1109\/MEMB.2009.934244","volume":"28","author":"PS Addison","year":"2009","unstructured":"Addison, P. S., Walker, J. & Guido, R. C. Time-frequency analysis of biosignals. IEEE Eng. Med. Biol. Mag. 28, 14\u201329. https:\/\/doi.org\/10.1109\/MEMB.2009.934244 (2009).","journal-title":"IEEE Eng. Med. Biol. Mag."},{"key":"92776_CR55","doi-asserted-by":"publisher","first-page":"678","DOI":"10.1016\/j.patcog.2010.09.013","volume":"44","author":"F Petitjean","year":"2011","unstructured":"Petitjean, F., Ketterlin, A. & Gan\u00e7arski, P. A global averaging method for dynamic time warping, with applications to clustering. Pattern Recognit. 44, 678\u2013693 (2011).","journal-title":"Pattern Recognit."},{"key":"92776_CR56","doi-asserted-by":"publisher","first-page":"56855","DOI":"10.1109\/ACCESS.2020.2982225","volume":"8","author":"K Xia","year":"2020","unstructured":"Xia, K., Huang, J. & Wang, H. Lstm-cnn architecture for human activity recognition. IEEE Access 8, 56855\u201356866 (2020).","journal-title":"IEEE Access"},{"key":"92776_CR57","doi-asserted-by":"publisher","first-page":"1662","DOI":"10.1109\/ACCESS.2017.2779939","volume":"6","author":"F Karim","year":"2018","unstructured":"Karim, F., Majumdar, S., Darabi, H. & Chen, S. Lstm fully convolutional networks for time series classification. IEEE Access 6, 1662\u20131669 (2018).","journal-title":"IEEE Access"},{"key":"92776_CR58","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/S0966-6362(02)00190-X","volume":"18","author":"W Zijlstra","year":"2003","unstructured":"Zijlstra, W. & Hof, A. L. Assessment of spatio-temporal gait parameters from trunk accelerations during human walking. Gait Post. 18, 1\u201310. https:\/\/doi.org\/10.1016\/S0966-6362(02)00190-X (2003).","journal-title":"Gait Post."},{"key":"92776_CR59","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1007\/s00421-004-1041-5","volume":"92","author":"W Zijlstra","year":"2004","unstructured":"Zijlstra, W. Assessment of spatio-temporal parameters during unconstrained walking. Eur. J. Appl. Physiol. 92, 39\u201344 (2004).","journal-title":"Eur. J. Appl. Physiol."},{"key":"92776_CR60","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1016\/j.msard.2016.10.007","volume":"10","author":"M Pau","year":"2016","unstructured":"Pau, M. et al. Clinical assessment of gait in individuals with multiple sclerosis using wearable inertial sensors: Comparison with patient-based measure. Multiple Scler. Rel. Disord. 10, 187\u2013191. https:\/\/doi.org\/10.1016\/j.msard.2016.10.007 (2016).","journal-title":"Multiple Scler. Rel. Disord."},{"key":"92776_CR61","unstructured":"van Beek, J. et\u00a0al. Floodlight open\u2013a global, prospective, open-access study to better understand multiple sclerosis using smartphone technology. In Annual Meeting of the Consortium of Multiple Sclerosis Centers (CMSC). (2019)."},{"key":"92776_CR62","doi-asserted-by":"publisher","first-page":"2660","DOI":"10.1109\/TNNLS.2016.2599820","volume":"28","author":"W Samek","year":"2016","unstructured":"Samek, W., Binder, A., Montavon, G., Lapuschkin, S. & M\u00fcller, K.-R. Evaluating the visualization of what a deep neural network has learned. IEEE Trans. Neural Networks Learn. Syst. 28, 2660\u20132673 (2016).","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"key":"92776_CR63","doi-asserted-by":"publisher","first-page":"1263","DOI":"10.1109\/TKDE.2008.239","volume":"21","author":"H He","year":"2009","unstructured":"He, H. & Garcia, E. A. Learning from imbalanced data. IEEE Trans. Knowledge Data Eng. 21, 1263\u20131284 (2009).","journal-title":"IEEE Trans. Knowledge Data Eng."},{"key":"92776_CR64","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1177\/001316446002000104","volume":"20","author":"J Cohen","year":"1960","unstructured":"Cohen, J. A coefficient of agreement for nominal scales. Educ. Psychol. Measur. 20, 37\u201346 (1960).","journal-title":"Educ. Psychol. Measur."},{"key":"92776_CR65","doi-asserted-by":"crossref","unstructured":"Kohlbrenner, M., Bauer, A., Nakajima, S., Binder, A., Samek, W., & Lapuschkin, S. Towards best practice in explaining neural network decisions with LRP. In International Joint Conference on Neural Networks (IJCNN). pp. 1-7. (IEEE, 2020)","DOI":"10.1109\/IJCNN48605.2020.9206975"},{"key":"92776_CR66","first-page":"1","volume":"20","author":"M Alber","year":"2019","unstructured":"Alber, M. et al. Innvestigate neural networks!. J. Mach. Learn. Res. 20, 1\u20138 (2019).","journal-title":"J. Mach. Learn. Res."},{"key":"92776_CR67","doi-asserted-by":"crossref","unstructured":"Alber, M. \"Software and application patterns for explanation methods.\" In Explainable AI: Interpreting, Explaining and Visualizing Deep Learning, pp. 399-433. Springer, Cham, (2019).","DOI":"10.1007\/978-3-030-28954-6_22"},{"key":"92776_CR68","unstructured":"Berndt, D.\u00a0J. & Clifford, J. Using dynamic time warping to find patterns in time series. In KDD workshop, vol. 10, 16, 359\u2013370.(1994)"},{"key":"92776_CR69","doi-asserted-by":"publisher","first-page":"340","DOI":"10.1016\/j.gaitpost.2016.07.184","volume":"49","author":"MM Engelhard","year":"2016","unstructured":"Engelhard, M. M., Dandu, S. R., Patek, S. D., Lach, J. C. & Goldman, M. D. Quantifying six-minute walk induced gait deterioration with inertial sensors in multiple sclerosis subjects. Gait Posture 49, 340\u2013345. https:\/\/doi.org\/10.1016\/j.gaitpost.2016.07.184 (2016).","journal-title":"Gait Posture"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-021-92776-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-021-92776-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-021-92776-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,3]],"date-time":"2022-12-03T05:54:18Z","timestamp":1670046858000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-021-92776-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,12]]},"references-count":69,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2021,12]]}},"alternative-id":["92776"],"URL":"https:\/\/doi.org\/10.1038\/s41598-021-92776-x","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7,12]]},"assertion":[{"value":"27 March 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 June 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 July 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"During the completion of this work, A. P. Creagh was a Ph.D. student at the University of Oxford and acknowledges the support of F. Hoffmann-La Roche Ltd.; F. Lipsmeier is an employee of F. Hoffmann-La Roche Ltd; M. Lindemann is a consultant for F. Hoffmann-La Roche Ltd. via Inovigate; M. De Vos has nothing to disclose.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"14301"}}