Dyskinesia estimation during activities of daily living using wearable motion sensors and deep recurrent networks.
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
12 04 2021
12 04 2021
Historique:
received:
07
08
2020
accepted:
09
03
2021
entrez:
13
4
2021
pubmed:
14
4
2021
medline:
9
11
2021
Statut:
epublish
Résumé
Levodopa-induced dyskinesias are abnormal involuntary movements experienced by the majority of persons with Parkinson's disease (PwP) at some point over the course of the disease. Choreiform as the most common phenomenology of levodopa-induced dyskinesias can be managed by adjusting the dose/frequency of PD medication(s) based on a PwP's motor fluctuations over a typical day. We developed a sensor-based assessment system to provide such information. We used movement data collected from the upper and lower extremities of 15 PwPs along with a deep recurrent model to estimate dyskinesia severity as they perform different activities of daily living (ADL). Subjects performed a variety of ADLs during a 4-h period while their dyskinesia severity was rated by the movement disorder experts. The estimated dyskinesia severity scores from our model correlated highly with the expert-rated scores (r = 0.87 (p < 0.001)), which was higher than the performance of linear regression that is commonly used for dyskinesia estimation (r = 0.81 (p < 0.001)). Our model provided consistent performance at different ADLs with minimum r = 0.70 (during walking) to maximum r = 0.84 (drinking) in comparison to linear regression with r = 0.00 (walking) to r = 0.76 (cutting food). These findings suggest that when our model is applied to at-home sensor data, it can provide an accurate picture of changes of dyskinesia severity facilitating effective medication adjustments.
Identifiants
pubmed: 33846387
doi: 10.1038/s41598-021-86705-1
pii: 10.1038/s41598-021-86705-1
pmc: PMC8041801
doi:
Substances chimiques
Antiparkinson Agents
0
Levodopa
46627O600J
Types de publication
Journal Article
Research Support, N.I.H., Extramural
Research Support, U.S. Gov't, Non-P.H.S.
Langues
eng
Sous-ensembles de citation
IM
Pagination
7865Subventions
Organisme : NINDS NIH HHS
ID : R43 NS071882
Pays : United States
Références
Dorsey, E., Sherer, T., Okun, M. S. & Bloem, B. R. The emerging evidence of the Parkinson pandemic. J. Parkinson’s Dis. 8, S3–S8 (2018).
doi: 10.3233/JPD-181474
Jankovic, J. Parkinson’s disease: Clinical features and diagnosis. J. Neurol. Neurosurg. Psychiatry 79, 368–376 (2008).
pubmed: 18344392
doi: 10.1136/jnnp.2007.131045
Perez-Lloret, S. et al. L-dopa-induced dyskinesias, motor fluctuations and health-related quality of life: The copark survey. Eur. J. Neurol. 24, 1532–1538 (2017).
pubmed: 28940893
doi: 10.1111/ene.13466
Pahwa, R. et al. Impact of dyskinesia on activities of daily living in Parkinson’s disease: Results from pooled phase 3 ads-5102 clinical trials. Parkinson. Relat. Disord. 60, 118–125 (2019).
doi: 10.1016/j.parkreldis.2018.09.005
Parkinson Study Group. Levodopa and the progression of Parkinson’s disease. N. Engl. J. Med. 351, 2498–2508 (2004).
doi: 10.1056/NEJMoa033447
Fabbrini, G., Brotchie, J. M., Grandas, F., Nomoto, M. & Goetz, C. G. Levodopa-induced dyskinesias. Mov. Disord. 22, 1379–1389 (2007).
pubmed: 17427940
doi: 10.1002/mds.21475
Thanvi, B., Lo, N. & Robinson, T. Levodopa-induced dyskinesia in Parkinson’s disease: Clinical features, pathogenesis, prevention and treatment. Postgrad. Med. J. 83, 384–388 (2007).
pubmed: 17551069
pmcid: 2600052
doi: 10.1136/pgmj.2006.054759
Goetz, C. G., Nutt, J. G. & Stebbins, G. T. The unified dyskinesia rating scale: Presentation and clinimetric profile. Mov. Disord. 23, 2398–2403 (2008).
pubmed: 19025759
doi: 10.1002/mds.22341
Guy, W. Abnormal involuntary movement scale (AIMS). ECDEU Assessment Manual for Psychopharmacology (1976).
Pandey, S. & Srivanitchapoom, P. Levodopa-induced dyskinesia: Clinical features, pathophysiology, and medical management. Ann. Indian Acad. Neurol. 20, 190 (2017).
pubmed: 28904447
pmcid: 5586110
Dorsey, E. R., Venuto, C., Venkataraman, V., Harris, D. A. & Kieburtz, K. Novel methods and techs for 21st-century clinical trials: A review. JAMA Neurol. 72, 582–588 (2015).
pubmed: 25730665
pmcid: 4708881
doi: 10.1001/jamaneurol.2014.4524
Li, M. H., Mestre, T. A., Fox, S. H. & Taati, B. Vision-based assessment of Parkinsonism and levodopa-induced dyskinesia with pose estimation. J. Neuroeng. Rehabil. 15, 97 (2018).
pubmed: 30400914
pmcid: 6219082
doi: 10.1186/s12984-018-0446-z
Rao, A. S. et al. Validating an objective video-based dyskinesia severity score in Parkinson’s disease patients. Parkins. Relat. Disord. 19, 232–237 (2013).
doi: 10.1016/j.parkreldis.2012.10.015
Botros, A. et al. Long-term home-monitoring sensor technology in patients with Parkinson’s disease-acceptance and adherence. Sensors 19, 5169 (2019).
doi: 10.3390/s19235169
Monje, M. H., Foffani, G., Obeso, J. & Sánchez-Ferro, Á. New sensor and wearable technologies to aid in the diagnosis and treatment monitoring of Parkinson’s disease. Annu. Rev. Biomed. Eng. 21, 111–143 (2019).
pubmed: 31167102
doi: 10.1146/annurev-bioeng-062117-121036
Keijsers, N. L., Horstink, M. W. & Gielen, S. C. Automatic assessment of levodopa-induced dyskinesias in daily life by neural networks. Mov. Disord. 18, 70–80 (2003).
pubmed: 12518302
doi: 10.1002/mds.10310
Samà, A. et al. Dyskinesia and motor state detection in Parkinson’s disease patients with a single movement sensor. In 2012 IEEE EMBC, 1194–1197 (IEEE, 2012).
Tsipouras, M. G. et al. An automated methodology for levodopa-induced dyskinesia: Assessment based on gyroscope and accelerometer signals. Artif. Intell. Med. 55, 127–135 (2012).
pubmed: 22484102
doi: 10.1016/j.artmed.2012.03.003
Tzallas, A. T. et al. Perform: A system for monitoring, assessment and management of patients with Parkinson’s disease. Sensors 14, 21329–21357 (2014).
pubmed: 25393786
doi: 10.3390/s141121329
Hammerla, N. Y. et al. Pd disease state assessment in naturalistic environments using deep learning. In Twenty-Ninth AAAI Conference on Artificial Intelligence (2015).
Lopane, G. et al. Dyskinesia detection and monitoring by a single sensor in patients with Parkinson’s disease. Mov. Disord. 30, 1267–1271 (2015).
pubmed: 26179817
doi: 10.1002/mds.26313
Fisher, J. M. et al. Unsupervised home monitoring of Parkinson’s disease motor symptoms using body-worn accelerometers. Parkins. Relat. Disord. 33, 44–50 (2016).
doi: 10.1016/j.parkreldis.2016.09.009
Pérez-López, C. et al. Dopaminergic-induced dyskinesia assessment based on a single belt-worn accelerometer. Artif. Intell. Med. 67, 47–56 (2016).
pubmed: 26831150
doi: 10.1016/j.artmed.2016.01.001
Pulliam, C. L. et al. Continuous assessment of levodopa response in Parkinson’s disease using wearable motion sensors. IEEE Trans. Biomed. Eng. 65, 159–164 (2017).
pubmed: 28459677
pmcid: 5755593
doi: 10.1109/TBME.2017.2697764
Lang, M. F. Human Motor Behavior Prediction through Gaussian Process Modeling on Manifolds. Ph.D. thesis, Technische Universität München (2019).
Powers, R. et al. Smartwatch inertial sensors continuously monitor real-world motor fluctuations in Parkinson’s disease. Sci. Transl. Med. 13, 20 (2021).
doi: 10.1126/scitranslmed.abd7865
Montel, S., Bonnet, A.-M. & Bungener, C. Quality of life in relation to mood, coping strategies, and dyskinesia in Parkinson’s disease. J. Geriatr. Psychiatry Neurol. 22, 95–102 (2009).
pubmed: 19150974
doi: 10.1177/0891988708328219
Griffiths, R. I. et al. Automated assessment of bradykinesia and dyskinesia in Parkinson’s disease. J. Parkinson’s Dis. 2, 47–55 (2012).
doi: 10.3233/JPD-2012-11071
Mera, T. O., Burack, M. A. & Giuffrida, J. P. Objective motion sensor assessment highly correlated with scores of global Levodopa-induced dyskinesia in Parkinson’s disease. J. Parkinson’s Dis. 3, 399 (2013).
doi: 10.3233/JPD-120166
Pulliam, C. L., Burack, M. A., Heldman, D. A., Giuffrida, J. P. & Mera, T. O. Motion sensor dyskinesia assessment during activities of daily living. J. Parkinson’s Dis. 4, 609–615 (2014).
doi: 10.3233/JPD-140348
Ramsperger, R. et al. Continuous leg dyskinesia assessment in Parkinson’s disease-clinical validity and ecological effect. Parkins. Relat. Disord. 26, 41–46 (2016).
doi: 10.1016/j.parkreldis.2016.02.007
Thomas, I. et al. A treatment-response index from wearable sensors for quantifying Parkinson’s disease motor states. IEEE J. Biomed. Health Inform. 22, 1341–1349 (2017).
pubmed: 29989996
doi: 10.1109/JBHI.2017.2777926
Rodríguez-Molinero, A. et al. Estimating dyskinesia severity in Parkinson’s disease by using a waist-worn sensor: concurrent validity study. Sci. Rep. 9, 1–7 (2019).
doi: 10.1038/s41598-019-49798-3
Pfister, F. M. et al. High-resolution motor state detection in Parkinson’s disease using convolutional neural networks. Sci. Rep. 10, 1–11 (2020).
doi: 10.1038/s41598-020-61789-3
Hoff, J., v/d Plas, A., Wagemans, E. & Van Hilten, J. Accelerometric assessment of levodopa-induced dyskinesias in Parkinson’s disease.. Mov. Disord. 16, 58–61 (2001).
pubmed: 11215593
doi: 10.1002/1531-8257(200101)16:1<58::AID-MDS1018>3.0.CO;2-9
FitzGerald, J. J., Lu, Z., Jareonsettasin, P. & Antoniades, C. A. Quantifying motor impairment in movement disorders. Front. Neurosci. 12, 202 (2018).
pubmed: 29695949
pmcid: 5904266
doi: 10.3389/fnins.2018.00202
Gers, F. A., Schmidhuber, J. & Cummins, F. Learning to forget: continual prediction with LSTM. IET Conf. Proc. 5, 850–855 (1999).
Yu, Y., Si, X., Hu, C. & Zhang, J. A review of recurrent neural networks: LSTM cells and network architectures. Neural Comput. 31, 1235–1270 (2019).
pubmed: 31113301
doi: 10.1162/neco_a_01199
Guan, Y. & Plötz, T. Ensembles of deep LSTM learners for activity recognition using wearables. Proc. ACM Interact. Mobile Wearable Ubiquitous Technol. 1, 1–28 (2017).
doi: 10.1145/3090076
Schuster, M. & Paliwal, K. K. Bidirectional recurrent neural networks. IEEE Trans. Signal Process. 45, 2673–2681 (1997).
doi: 10.1109/78.650093
Ghoraani, B., Galvin, J. E. & Jimenez-Shahed, J. Point of view: Wearable systems for at-home monitoring of motor complications in Parkinson’s disease should deliver clinically actionable information. Parkins. Relat. Disord. 20, 20 (2021).
Davis, J. & Goadrich, M. The relationship between precision-recall and roc curves. In Proceedings of the 23rd International Conference on Machine Learning, 233–240 (2006).
Turcano, P. et al. Levodopa-induced dyskinesia in Parkinson disease: A population-based cohort study. Neurology 91, e2238–e2243 (2018).
pubmed: 30404780
pmcid: 6329327
doi: 10.1212/WNL.0000000000006643
Ahlskog, J. E. & Muenter, M. D. Frequency of levodopa-related dyskinesias and motor fluctuations as estimated from the cumulative literature. Mov. Disord. 16, 448–458 (2001).
pubmed: 11391738
doi: 10.1002/mds.1090
Ji, T. Frequency and velocity of people walking. Struct. Eng. 20, 20 (2005).
Ferreira, J. J. et al. Quantitative home-based assessment of Parkinson’s symptoms: The sense-park feasibility and usability study. BMC Neurol. 15, 1–7 (2015).
doi: 10.1186/s12883-015-0343-z
Patel, S. et al. Monitoring motor fluctuations in patients with Parkinson’s disease using wearable sensors. IEEE Trans. Inf Technol. Biomed. 13, 864–873 (2009).
pubmed: 19846382
pmcid: 5432434
doi: 10.1109/TITB.2009.2033471
Zaremba, W., Sutskever, I. & Vinyals, O. Recurrent neural network regularization. arXiv:1409.2329 (arXiv Preprint) (2014).
Hssayeni, M. D., Jimenez-Shahed, J., Burack, M. A. & Ghoraani, B. Symptom-based, dual-channel LSTM network for the estimation of unified Parkinson’s disease rating scale III. In 2019 IEEE BHI, 1–4 (IEEE, 2019).
Abadi, M. et al. TensorFlow: Large-scale machine learning on heterogeneous systems (2015). Software available from tensorflow.org.
Kingma, D. & Ba, J. Adam: A method for stochastic optimization. arXiv:1412.6980 (arXiv Preprint) (2014).