{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T15:45:38Z","timestamp":1766159138460,"version":"3.41.2"},"reference-count":61,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2023,3,27]],"date-time":"2023-03-27T00:00:00Z","timestamp":1679875200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["P50NS108676"],"award-info":[{"award-number":["P50NS108676"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. ACM Interact. Mob. Wearable Ubiquitous Technol."],"published-print":{"date-parts":[[2023,3,27]]},"abstract":"<jats:p>Many patients with neurological disorders, such as Ataxia, do not have easy access to neurologists, -especially those living in remote localities and developing\/underdeveloped countries. Ataxia is a degenerative disease of the nervous system that surfaces as difficulty with motor control, such as walking imbalance. Previous studies have attempted automatic diagnosis of Ataxia with the help of wearable biomarkers, Kinect, and other sensors. These sensors, while accurate, do not scale efficiently well to naturalistic deployment settings. In this study, we propose a method for identifying ataxic symptoms by analyzing videos of participants walking down a hallway, captured with a standard monocular camera. In a collaboration with 11 medical sites located in 8 different states across the United States, we collected a dataset of 155 videos along with their severity rating from 89 participants (24 controls and 65 diagnosed with or are pre-manifest spinocerebellar ataxias). The participants performed the gait task of the Scale for the Assessment and Rating of Ataxia (SARA). We develop a computer vision pipeline to detect, track, and separate the participants from their surroundings and construct several features from their body pose coordinates to capture gait characteristics such as step width, step length, swing, stability, speed, etc. Our system is able to identify and track a patient in complex scenarios. For example, if there are multiple people present in the video or an interruption from a passerby. Our Ataxia risk-prediction model achieves 83.06% accuracy and an 80.23% F1 score. Similarly, our Ataxia severity-assessment model achieves a mean absolute error (MAE) score of 0.6225 and a Pearson's correlation coefficient score of 0.7268. Our model competitively performed when evaluated on data from medical sites not used during training. Through feature importance analysis, we found that our models associate wider steps, decreased walking speed, and increased instability with greater Ataxia severity, which is consistent with previously established clinical knowledge. Furthermore, we are releasing the models and the body-pose coordinate dataset to the research community - the largest dataset on ataxic gait (to our knowledge). Our models could contribute to improving health access by enabling remote Ataxia assessment in non-clinical settings without requiring any sensors or special cameras. Our dataset will help the computer science community to analyze different characteristics of Ataxia and to develop better algorithms for diagnosing other movement disorders.<\/jats:p>","DOI":"10.1145\/3580845","type":"journal-article","created":{"date-parts":[[2023,3,28]],"date-time":"2023-03-28T14:57:51Z","timestamp":1680015471000},"page":"1-19","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Auto-Gait"],"prefix":"10.1145","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9736-442X","authenticated-orcid":false,"given":"Wasifur","family":"Rahman","sequence":"first","affiliation":[{"name":"University of Rochester, Rochester, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8682-522X","authenticated-orcid":false,"given":"Masum","family":"Hasan","sequence":"additional","affiliation":[{"name":"University of Rochester, Rochester, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3725-3493","authenticated-orcid":false,"given":"Md Saiful","family":"Islam","sequence":"additional","affiliation":[{"name":"University of Rochester, Rochester, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7331-8499","authenticated-orcid":false,"given":"Titilayo","family":"Olubajo","sequence":"additional","affiliation":[{"name":"Houston Methodist, Houston, Texas, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3656-8223","authenticated-orcid":false,"given":"Jeet","family":"Thaker","sequence":"additional","affiliation":[{"name":"University of Rochester, Rochester, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4536-1390","authenticated-orcid":false,"given":"Abdel-Rahman","family":"Abdelkader","sequence":"additional","affiliation":[{"name":"University of Rochester, Rochester, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4222-5895","authenticated-orcid":false,"given":"Phillip","family":"Yang","sequence":"additional","affiliation":[{"name":"Center for Health + Technology, University of Rochester Medical Center, Rochester, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0382-7535","authenticated-orcid":false,"given":"Henry","family":"Paulson","sequence":"additional","affiliation":[{"name":"University of Michigan, Ann Arbor, Michigan, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5769-183X","authenticated-orcid":false,"given":"Gulin","family":"Oz","sequence":"additional","affiliation":[{"name":"University of Minnesota, Minneapolis, Minnesota, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8921-7104","authenticated-orcid":false,"given":"Alexandra","family":"Durr","sequence":"additional","affiliation":[{"name":"H\u00f4pital de la Piti\u00e9-Salp\u00eatri\u00e8re, Paris, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6174-5442","authenticated-orcid":false,"given":"Thomas","family":"Klockgether","sequence":"additional","affiliation":[{"name":"University Hospital Bonn, Bonn, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7180-2869","authenticated-orcid":false,"given":"Tetsuo","family":"Ashizawa","sequence":"additional","affiliation":[{"name":"Houston Methodist, Houston, Texas, USA"}]},{"given":"Readisca","family":"Investigators","sequence":"additional","affiliation":[{"name":"Houston Methodist, Houston, Texas, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4781-4733","authenticated-orcid":false,"given":"Ehsan","family":"Hoque","sequence":"additional","affiliation":[{"name":"University of Rochester, Rochester, NY, USA"}]}],"member":"320","published-online":{"date-parts":[[2023,3,28]]},"reference":[{"key":"e_1_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2632048.2632071"},{"key":"e_1_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3351231"},{"key":"e_1_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"e_1_2_2_4_1","volume-title":"Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934","author":"Bochkovskiy Alexey","year":"2020","unstructured":"Alexey Bochkovskiy, Chien-Yao Wang, and Hong-Yuan Mark Liao. 2020. Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)."},{"key":"e_1_2_2_5_1","unstructured":"Body and Mind staff. 2021. Ataxia sufferer faces a neurological disorder that's often misdiagnosed. https:\/\/www.pennlive.com\/bodyandmind\/2011\/11\/positive_attitude_is_best_medi.html."},{"key":"e_1_2_2_6_1","volume-title":"Michael Kellen, Arno Klein, Christopher Bare, Megan Doerr, Abhishek Pratap, John Wilbanks, E Dorsey, et al.","author":"Bot Brian M","year":"2016","unstructured":"Brian M Bot, Christine Suver, Elias Chaibub Neto, Michael Kellen, Arno Klein, Christopher Bare, Megan Doerr, Abhishek Pratap, John Wilbanks, E Dorsey, et al. 2016. The mPower study, Parkinson disease mobile data collected using ResearchKit. Scientific data 3, 1 (2016), 1--9."},{"key":"e_1_2_2_7_1","volume-title":"Dobb's journal of software tools 3","author":"Bradski Gary","year":"2000","unstructured":"Gary Bradski and Adrian Kaehler. 2000. OpenCV. Dr. Dobb's journal of software tools 3 (2000), 2."},{"key":"e_1_2_2_8_1","volume-title":"A systematic review of the gait characteristics associated with Cerebellar Ataxia. Gait & posture 60","author":"Buckley Ellen","year":"2018","unstructured":"Ellen Buckley, Claudia Mazz\u00e0, and Alisdair McNeill. 2018. A systematic review of the gait characteristics associated with Cerebellar Ataxia. Gait & posture 60 (2018), 154--163."},{"key":"e_1_2_2_9_1","doi-asserted-by":"crossref","unstructured":"Katrin B\u00fcrk Ulrike M\u00e4lzig Stefanie Wolf Suzette Heck Konstantinos Dimitriadis Tanja Schmitz-H\u00fcbsch Sascha Hering Tobias M Lindig Verena Haug Dagmar Timmann et al. 2009. Comparison of three clinical rating scales in Friedreich ataxia (FRDA). Movement disorders 24 12 (2009) 1779--1784.","DOI":"10.1002\/mds.22660"},{"key":"e_1_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132272.3134111"},{"key":"e_1_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3399715.3399744"},{"key":"e_1_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijhcs.2021.102607"},{"key":"e_1_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2022.102285"},{"key":"e_1_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1002\/mds.28296"},{"key":"e_1_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-020-05103-2"},{"key":"e_1_2_2_16_1","doi-asserted-by":"crossref","unstructured":"Christopher G Goetz Barbara C Tilley Stephanie R Shaftman Glenn T Stebbins Stanley Fahn Pablo Martinez-Martin Werner Poewe Cristina Sampaio Matthew B Stern Richard Dodel et al. 2008. Movement Disorder Society-sponsored revision of the Unified Parkinson's Disease Rating Scale (MDS-UPDRS): scale presentation and clinimetric testing results. Movement disorders: official journal of the Movement Disorder Society 23 15 (2008) 2129--2170.","DOI":"10.1002\/mds.22340"},{"key":"e_1_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1002\/mds.28478"},{"key":"e_1_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2493988.2494328"},{"key":"e_1_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00381-015-2650-5"},{"key":"e_1_2_2_20_1","doi-asserted-by":"crossref","unstructured":"Takeru Honda Hiroshi Mitoma Hirotaka Yoshida Kyota Bando Hiroo Terashi Takeshi Taguchi Yohane Miyata Satoko Kumada Takashi Hanakawa Hitoshi Aizawa et al. 2020. Assessment and rating of motor cerebellar ataxias with the Kinect v2 depth sensor: extending our appraisal. Frontiers in neurology 11 (2020) 179.","DOI":"10.3389\/fneur.2020.00179"},{"key":"e_1_2_2_21_1","volume-title":"Quantification of EEG irregularity by use of the entropy of the power spectrum. Electroencephalography and clinical neurophysiology 79, 3","author":"Inouye Tsuyoshi","year":"1991","unstructured":"Tsuyoshi Inouye, Kazuhiro Shinosaki, H Sakamoto, Seigo Toi, Satoshi Ukai, Akinori Iyama, Y Katsuda, and M Hirano. 1991. Quantification of EEG irregularity by use of the entropy of the power spectrum. Electroencephalography and clinical neurophysiology 79, 3 (1991), 204--210."},{"key":"e_1_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12311-011-0292-z"},{"key":"e_1_2_2_23_1","volume-title":"Machine Learning for Healthcare Conference. PMLR, 204--216","author":"Jaroensri Ronnachai","year":"2017","unstructured":"Ronnachai Jaroensri, Amy Zhao, Guha Balakrishnan, Derek Lo, Jeremy D Schmahmann, Fr\u00e9do Durand, and John Guttag. 2017. A video-based method for automatically rating ataxia. In Machine Learning for Healthcare Conference. PMLR, 204--216."},{"key":"e_1_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460421.3478810"},{"key":"e_1_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2370216.2370354"},{"key":"e_1_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2021.106525"},{"key":"e_1_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2949744"},{"key":"e_1_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12984-019-0490-3"},{"key":"e_1_2_2_29_1","volume-title":"Associations between gait speed and well-known fall risk factors among community-dwelling older adults. Physiotherapy research international 24, 1","author":"Kyrdalen Ingebj\u00f8rg Lavrantsdatter","year":"2019","unstructured":"Ingebj\u00f8rg Lavrantsdatter Kyrdalen, Pernille Thingstad, Leiv Sandvik, and Heidi Ormstad. 2019. Associations between gait speed and well-known fall risk factors among community-dwelling older adults. Physiotherapy research international 24, 1 (2019), e1743."},{"key":"e_1_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3328925"},{"key":"e_1_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/BSN.2016.7516249"},{"key":"e_1_2_2_32_1","doi-asserted-by":"publisher","unstructured":"Jiarong Li Zihan Wang Zihao Zhao Yuchao Jin Jihong Yin Shao-Lun Huang and Jiyu Wang. 2021. TriboGait: A Deep Learning Enabled Triboelectric Gait Sensor System for Human Activity Recognition and Individual Identification. In Adjunct Proceedings of the 2021 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2021 ACM International Symposium on Wearable Computers (Virtual USA) (UbiComp '21). Association for Computing Machinery New York NY USA 643--648. https:\/\/doi.org\/10.1145\/3460418.3480410","DOI":"10.1145\/3460418.3480410"},{"key":"e_1_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-018-0304-0"},{"key":"e_1_2_2_34_1","volume-title":"Frank Van Overwalle, et al","author":"Manto Mario","year":"2020","unstructured":"Mario Manto, Nicolas Dupre, Marios Hadjivassiliou, Elan D Louis, Hiroshi Mitoma, Marco Molinari, Aasef G Shaikh, Bing-Wen Soong, Michael Strupp, Frank Van Overwalle, et al. 2020. Medical and paramedical care of patients with cerebellar Ataxia during the COVID-19 outbreak: seven practical recommendations of the COVID 19 cerebellum task force. Frontiers in neurology 11 (2020), 516."},{"key":"e_1_2_2_35_1","unstructured":"Mayo-Clinic-Stuff. 2021. Ataxia. https:\/\/www.mayoclinic.org\/diseases-conditions\/ataxia\/symptoms-causes\/syc-20355652."},{"key":"e_1_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3267305.3274187"},{"key":"e_1_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2020.101916"},{"key":"e_1_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/2968219.2971408"},{"key":"e_1_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11517-018-1795-2"},{"key":"e_1_2_2_40_1","volume-title":"Mar\u00eda Trinidad Herrero-Ezquerro, and Ram\u00f3n A Mollineda","author":"Ortells Javier","year":"2018","unstructured":"Javier Ortells, Mar\u00eda Trinidad Herrero-Ezquerro, and Ram\u00f3n A Mollineda. 2018. Vision-based gait impairment analysis for aided diagnosis. Medical & biological engineering & computing 56, 9 (2018), 1553--1564."},{"key":"e_1_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1002\/mds.28313"},{"key":"e_1_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2019.2943879"},{"key":"e_1_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2021.3051093"},{"key":"e_1_2_2_44_1","volume-title":"Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems 28","author":"Ren Shaoqing","year":"2015","unstructured":"Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems 28 (2015), 91--99."},{"key":"e_1_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1212\/01.wnl.0000219042.60538.92"},{"key":"e_1_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejpn.2022.07.001"},{"key":"e_1_2_2_47_1","volume-title":"Ataxia: Definition, types, causes, diagnosis, treatment. https:\/\/www.healthline.com\/health\/ataxia#types-of-ataxia","author":"Seladi-Schulman Jill","year":"2020","unstructured":"Jill Seladi-Schulman. 2020. Ataxia: Definition, types, causes, diagnosis, treatment. https:\/\/www.healthline.com\/health\/ataxia#types-of-ataxia"},{"volume-title":"Handbook of Human Motion","author":"Serrao Mariano","key":"e_1_2_2_48_1","unstructured":"Mariano Serrao and Carmela Conte. 2018. Detecting and measuring ataxia in gait. In Handbook of Human Motion. Springer International Publishing, 937--954."},{"key":"e_1_2_2_49_1","doi-asserted-by":"crossref","unstructured":"Cosmin Stamate George D Magoulas Stefan K\u00fcppers Effrosyni Nomikou Ioannis Daskalopoulos Ashwani Jha JS Pons J Rothwell Marco U Luchini Theano Moussouri et al. 2018. The cloudUPDRS app: A medical device for the clinical assessment of Parkinson's Disease. Pervasive and mobile computing 43 (2018) 146--166.","DOI":"10.1016\/j.pmcj.2017.12.005"},{"key":"e_1_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/PERCOM.2017.7917848"},{"key":"e_1_2_2_51_1","volume-title":"SARA-a new clinical scale for the assessment and rating of ataxia. Nature clinical practice Neurology 3, 3","author":"Subramony Sub H","year":"2007","unstructured":"Sub H Subramony. 2007. SARA-a new clinical scale for the assessment and rating of ataxia. Nature clinical practice Neurology 3, 3 (2007), 136--137."},{"key":"e_1_2_2_52_1","volume-title":"Alberto Romano, Martina Favetta, Enza Maria Valente, Enrico Bertini, Enrico Castelli, Maurizio Petrarca, Giovanni Pioggia, et al.","author":"Summa Susanna","year":"2020","unstructured":"Susanna Summa, Tommaso Schirinzi, Giuseppe Massimo Bernava, Alberto Romano, Martina Favetta, Enza Maria Valente, Enrico Bertini, Enrico Castelli, Maurizio Petrarca, Giovanni Pioggia, et al. 2020. Development of SaraHome: a novel, well-accepted, technology-based assessment tool for patients with ataxia. Computer methods and programs in biomedicine 188 (2020), 105257."},{"key":"e_1_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2020.106307"},{"key":"e_1_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11556-013-0134-8"},{"key":"e_1_2_2_55_1","volume-title":"Laura Power, and David J Szmulewicz","author":"Tran Ha","year":"2019","unstructured":"Ha Tran, Pubudu N Pathirana, Malcolm Horne, Laura Power, and David J Szmulewicz. 2019. Automated Evaluation of Upper Limb Motor Impairment of Patient with Cerebellar Ataxia. In 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE, 6846--6849."},{"key":"e_1_2_2_56_1","unstructured":"Rafayel Vallat. 2022. entropy.spectral_entropy. https:\/\/raphaelvallat.com\/entropy\/build\/html\/generated\/entropy.spectral_entropy.html."},{"key":"e_1_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.3390\/s21165576"},{"key":"e_1_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/2971648.2971670"},{"key":"e_1_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3351273"},{"key":"e_1_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3161415"},{"key":"e_1_2_2_61_1","doi-asserted-by":"publisher","unstructured":"Peicheng Yang Lei Xie Chuyu Wang and Sanglu Lu. 2019. IMU-Kinect: A Motion Sensor-Based Gait Monitoring System for Intelligent Healthcare. In Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2019 ACM International Symposium on Wearable Computers (London United Kingdom) (UbiComp\/ISWC '19 Adjunct). Association for Computing Machinery New York NY USA 350--353. https:\/\/doi.org\/10.1145\/3341162.3343766","DOI":"10.1145\/3341162.3343766"}],"container-title":["Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3580845","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3580845","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T04:45:13Z","timestamp":1752468313000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3580845"}},"subtitle":["Automatic Ataxia Risk Assessment with Computer Vision from Gait Task Videos"],"short-title":[],"issued":{"date-parts":[[2023,3,27]]},"references-count":61,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,3,27]]}},"alternative-id":["10.1145\/3580845"],"URL":"https:\/\/doi.org\/10.1145\/3580845","relation":{},"ISSN":["2474-9567"],"issn-type":[{"type":"electronic","value":"2474-9567"}],"subject":[],"published":{"date-parts":[[2023,3,27]]},"assertion":[{"value":"2023-03-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}