Development and Assessment of a Movement Disorder Simulator Based on Inertial Data
Abstract
:1. Introduction
2. State of the Art: Remote Monitoring in Neurodegenerative Diseases
3. Methods: The Proposed Simulator
3.1. The Proposed Architecture
- the vertical resolution of the analog-to-digital converter (), which influences the digitization process of the acquired data;
- the axis misalignment value for the three-axis IMU considered ();
- the constant bias value (), which influences all measurements by altering their average values and which is generally attributable to hardware defects.
- white noise;
- random walk, i.e., the amount of Brownian noise;
- bias instability, which concerns the level of pink or flicker noise in the measurement.
- bias temperature (), defined as the difference from the predefined operating temperature;
- temperature scaling factor (), which considers the error due to variations in the operating temperature.
3.2. Experimental Validation
3.2.1. The Simulator Validation
3.2.2. Results Validation
3.3. Pathological Movement Generation
Adopted Tremor Typologies
- Test for the identification of postural tremor of the hands: the subject’s arms are stretched out in front of the body with the palms down, the wrist should be straight and the fingers should not touch. (Section 3.15);
- Test for the identification of kinetic tremor of the hands: this test uses the finger-to-nose technique. Specifically, the subject starts with the arm outstretched and must then perform at least three finger-nose movements with each hand extending as far as possible until it touches the examiner’s finger. (Section 3.16);
- Test for identification of resting tremor: the subject sits quietly in a chair with hands resting on the arms of the chair and feet resting on the floor. This position should be held for 10 s without any other directions. (Section 3.17).
- Before generating the pathological tests, baseline tests for each task were carried out. The operator placed the SBG sensor on the top of the hand and performed the tests as described in the guide. This first collection of data was considered free of any pathology.
- Subsequently, tremors to these traces were added: they were modeled analytically as multisine signals whose frequency and amplitude range [17] were derived from [32] and added to the baseline perturbed traces (the MMR-like signals are always generated using the simulator). On each baseline inertial trace, several 2 s pathological tremors at disjoint intervals were superimposed for each axis. For each test, 1000 trials of 60 s duration were generated, each containing five 2 s tremor time segments. Tremor was generated for each interval randomly in terms of frequency and amplitudes, although within the recommended values, in order to generate a widely general dataset.
4. Results: Tremor Classification
4.1. The Machine Learning Tool
- Mean [39];
- Averange [39];
- Square sum of data under 25th percentile;
- Squared sum of data under 75th percentile;
- Low pass energy (below 2 Hz signal energy, to identify voluntary movement) [40];
- High pass energy (over 2.5 Hz signal energy, to identify involuntary movement) [40];
- Lag of first autocorrelation peak (to find the dominant frequency of the involuntary movement) [32];
- Height of first peak in autocorrelation (to discriminate periodic movements from aperiodic ones) [32];
- Maximum frequency in the spectrum;
- Sum of amplitude values of frequency components below 5 Hz;
- Number of peaks in the same frequency spectrum interval;
4.2. Classification Metrics and Performance
5. Discussion: Classification Performance Stability under Data Quality Variation
- a.
- Training and testing with data coming from the same high-performance sensor (best/best);
- b.
- Training with high-performance sensor data and testing with lower-level sensor data (best/worst);
- c.
- Training with lower-level sensor data and testing with high-performance sensor data (worst/best).
- d.
- Training and testing with data coming from the same lower level sensor data (worst/worst);
6. Conclusions and Future Directions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- World Health Organization. Ageing and Health. 2022. Available online: https://www.who.int/en/news-room/fact-sheets/detail/ageing-and-health (accessed on 2 February 2022).
- Haleem, A.; Javaid, M.; Singh, R.P.; Suman, R. Telemedicine for healthcare: Capabilities, features, barriers, and applications. Sens. Int. 2021, 2, 100117. [Google Scholar] [CrossRef] [PubMed]
- Weinstein, R.S.; Lopez, A.M.; Joseph, B.A.; Erps, K.A.; Holcomb, M.; Barker, G.P.; Krupinski, E.A. Telemedicine, telehealth, and mobile health applications that work: Opportunities and barriers. Am. J. Med. 2014, 127, 183–187. [Google Scholar] [CrossRef] [PubMed]
- Tornese, G.; Schiaffini, R.; Mozzillo, E.; Franceschi, R.; Frongia, A.P.; Scaramuzza, A.; on behalf of HCL Expert Pathway Pediatric Group; the Diabetes Study Group of the Italian Society for Pediatric Endocrinology. Telemedicine in the Time of the COVID-19 Pandemic: Results from the First Survey among Italian Pediatric Diabetes Centers. Healthcare 2021, 9, 815. [Google Scholar] [CrossRef]
- Giansanti, D.; Morone, G.; Loreti, A.; Germanotta, M.; Aprile, I. A Narrative Review of the Launch and the Deployment of Telemedicine in Italy during the COVID-19 Pandemic. Healthcare 2022, 10, 415. [Google Scholar] [CrossRef] [PubMed]
- Cortis, C.; Giancotti, G.; Rodio, A.; Bianco, A.; Fusco, A. Home is the new gym: Exergame as a potential tool to maintain adequate fitness levels also during quarantine. Hum. Mov. 2020, 21, 79–87. [Google Scholar] [CrossRef]
- World Health Organization. Telemedicine: Opportunities and Developments in Member States; Report on the Second Global Survey on eHealth; World Health Organization: Geneva, Switzerland, 2010. [Google Scholar]
- Milano, F.; Cerro, G.; Santoni, F.; De Angelis, A.; Miele, G.; Rodio, A.; Moschitta, A.; Ferrigno, L.; Carbone, P. Parkinson’s Disease Patient Monitoring: A Real-Time Tracking and Tremor Detection System Based on Magnetic Measurements. Sensors 2021, 21, 4196. [Google Scholar] [CrossRef]
- Ferrigno, L.; Miele, G.; Milano, F.; Rodio, A.; Santoni, F.; De Angelis, A.; Moschitta, A.; Carbone, P.; Cerro, G. A real-time tracking system for tremor and trajectory estimation in Parkinson’s disease affected patients. In Proceedings of the 2020 IEEE International Symposium on Medical Measurements and Applications (MeMeA), Bari, Italy, 1 June–1 July 2020; pp. 1–6. [Google Scholar] [CrossRef]
- Erkkinen, M.G.; Kim, M.O.; Geschwind, M.D. Clinical neurology and epidemiology of the major neurodegenerative diseases. Cold Spring Harb. Perspect. Biol. 2018, 10, a033118. [Google Scholar] [CrossRef]
- De Marchi, F.; Contaldi, E.; Magistrelli, L.; Cantello, R.; Comi, C.; Mazzini, L. Telehealth in neurodegenerative diseases: Opportunities and challenges for patients and physicians. Brain Sci. 2021, 11, 237. [Google Scholar] [CrossRef]
- Yahya, M.; Shah, J.A.; Kadir, K.A.; Yusof, Z.M.; Khan, S.; Warsi, A. Motion capture sensing techniques used in human upper limb motion: A review. Sens. Rev. 2019, 39, 504–511. [Google Scholar] [CrossRef]
- Butt, A.H.; Rovini, E.; Dolciotti, C.; Bongioanni, P.; De Petris, G.; Cavallo, F. Leap motion evaluation for assessment of upper limb motor skills in Parkinson’s disease. In Proceedings of the 2017 International Conference on Rehabilitation Robotics (ICORR), London, UK, 17–20 July 2017; IEEE: Piscataway, NJ, USA, 2017; pp. 116–121. [Google Scholar]
- Patel, S.; Lorincz, K.; Hughes, R.; Huggins, N.; Growdon, J.; Standaert, D.; Akay, M.; Dy, J.; Welsh, M.; Bonato, P. Monitoring motor fluctuations in patients with Parkinson’s disease using wearable sensors. IEEE Trans. Inf. Technol. Biomed. 2009, 13, 864–873. [Google Scholar] [CrossRef]
- Moon, S.; Song, H.J.; Sharma, V.D.; Lyons, K.E.; Pahwa, R.; Akinwuntan, A.E.; Devos, H. Classification of Parkinson’s disease and essential tremor based on balance and gait characteristics from wearable motion sensors via machine learning techniques: A data-driven approach. J. Neuroeng. Rehabil. 2020, 17, 1–8. [Google Scholar] [CrossRef] [PubMed]
- Papadopoulos, A.; Kyritsis, K.; Klingelhoefer, L.; Bostanjopoulou, S.; Chaudhuri, K.R.; Delopoulos, A. Detecting parkinsonian tremor from IMU data collected in-the-wild using deep multiple-instance learning. IEEE J. Biomed. Health Inform. 2019, 24, 2559–2569. [Google Scholar] [CrossRef] [PubMed]
- Goetz, C.G.; Fahn, S.; Martinez-Martin, P.; Poewe, W.; Sampaio, C.; Stebbins, G.T.; Stern, M.B.; Tilley, B.C.; Dodel, R.; Dubois, B.; et al. Movement Disorder Society-sponsored revision of the Unified Parkinson’s Disease Rating Scale (MDS-UPDRS): Process, format, and clinimetric testing plan. Mov. Disord. 2007, 22, 41–47. [Google Scholar] [CrossRef] [PubMed]
- Daneault, J.F.; Vergara-Diaz, G.; Parisi, F.; Admati, C.; Alfonso, C.; Bertoli, M.; Bonizzoni, E.; Carvalho, G.F.; Costante, G.; Fabara, E.E.; et al. Accelerometer data collected with a minimum set of wearable sensors from subjects with Parkinson’s disease. Sci. Data 2021, 8, 1–13. [Google Scholar] [CrossRef] [PubMed]
- Bo, F.; Yerebakan, M.; Dai, Y.; Wang, W.; Li, J.; Gao, S.; Boyi, H. IMU-Based Monitoring for Assistive Disease Diagnosis and Management of IoHT: A Review. Healthcare 2022, 10, 1210. [Google Scholar] [CrossRef]
- Roetenberg, D.; Holler, C.; Mattmüller, K.; Degen, M.; Allum, J.H. Comparison of a low-cost miniature inertial sensor module and a fiber-optic gyroscope for clinical balance and gait assessments. J. Healthc. Eng. 2019, 2019, 9816961. [Google Scholar] [CrossRef]
- Sethi, K.D. Clinical aspects of Parkinson disease. Curr. Opin. Neurol. 2002, 15, 457–460. [Google Scholar] [CrossRef]
- Cancela, J.; Pastorino, M.; Arredondo, M.T.; Hurtado, O. A telehealth system for Parkinson’s disease remote monitoring. The PERFORM approach. In Proceedings of the 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Osaka, Japan, 3–7 July 2013; IEEE: Piscataway, NJ, USA, 2013; pp. 7492–7495. [Google Scholar]
- Hssayeni, M.D.; Jimenez-Shahed, J.; Burack, M.A.; Ghoraani, B. Wearable sensors for estimation of parkinsonian tremor severity during free body movements. Sensors 2019, 19, 4215. [Google Scholar] [CrossRef]
- Rigas, G.; Tzallas, A.T.; Tsipouras, M.G.; Bougia, P.; Tripoliti, E.E.; Baga, D.; Fotiadis, D.I.; Tsouli, S.G.; Konitsiotis, S. Assessment of tremor activity in the Parkinson’s disease using a set of wearable sensors. IEEE Trans. Inf. Technol. Biomed. 2012, 16, 478–487. [Google Scholar] [CrossRef]
- Deuschl, G.; Bain, P.; Brin, M.; Committee, A.H.S. Consensus statement of the movement disorder society on tremor. Mov. Disord. 1998, 13, 2–23. [Google Scholar] [CrossRef]
- Dai, H.; Zhang, P.; Lueth, T.C. Quantitative assessment of parkinsonian tremor based on an inertial measurement unit. Sensors 2015, 15, 25055–25071. [Google Scholar] [CrossRef] [PubMed]
- Pasquini, J.; Ceravolo, R.; Qamhawi, Z.; Lee, J.Y.; Deuschl, G.; Brooks, D.J.; Bonuccelli, U.; Pavese, N. Progression of tremor in early stages of Parkinson’s disease: A clinical and neuroimaging study. Brain 2018, 141, 811–821. [Google Scholar] [CrossRef] [PubMed]
- Budzianowska, A.; Honczarenko, K. Assessment of rest tremor in Parkinson’s disease. Neurol. Neurochir. Pol. 2008, 42, 12–21. [Google Scholar]
- Powell, H.C.; Hanson, M.A.; Lach, J. A wearable inertial sensing technology for clinical assessment of tremor. In Proceedings of the 2007 IEEE Biomedical Circuits and Systems Conference, Montreal, QC, Canada, 27 November 2007; IEEE: Piscataway, NJ, USA, 2007; pp. 9–12. [Google Scholar]
- Mathworks. imuSensor. 2022. Available online: https://it.mathworks.com/help/nav/ref/imusensor-system-object.html, (accessed on 8 March 2022).
- Elble, R.J. Tremor: Clinical features, pathophysiology, and treatment. Neurol. Clin. 2009, 27, 679–695. [Google Scholar] [CrossRef]
- Cole, B.T.; Roy, S.H.; De Luca, C.J.; Nawab, S.H. Dynamical learning and tracking of tremor and dyskinesia from wearable sensors. IEEE Trans. Neural Syst. Rehabil. Eng. 2014, 22, 982–991. [Google Scholar] [CrossRef] [PubMed]
- SBG. Elipse-E. 2022. Available online: https://www.sbg-systems.com/products/ellipse-series/ (accessed on 8 March 2022).
- MbientLab. METAMOTIONRL. 2022. Available online: https://mbientlab.com/metamotionrl/ (accessed on 8 March 2022).
- Henderi, H.; Wahyuningsih, T.; Rahwanto, E. Comparison of Min-Max normalization and Z-Score Normalization in the K-nearest neighbor (kNN) Algorithm to Test the Accuracy of Types of Breast Cancer. Int. J. Inform. Inf. Syst. 2021, 4, 13–20. [Google Scholar] [CrossRef]
- Crawford, P.F., III; Zimmerman, E.E. Differentiation and diagnosis of tremor. Am. Fam. Physician 2011, 83, 697–702. [Google Scholar]
- Delrobaei, M.; Memar, S.; Pieterman, M.; Stratton, T.W.; McIsaac, K.; Jog, M. Towards remote monitoring of Parkinson’s disease tremor using wearable motion capture systems. J. Neurol. Sci. 2018, 384, 38–45. [Google Scholar] [CrossRef]
- Habib-ur-Rehman, M.R.C.P. Diagnosis and management of tremor. Arch. Intern Med. 2000, 160, 2438–2444. [Google Scholar] [CrossRef]
- Zhang, M.; Sawchuk, A.A. A feature selection-based framework for human activity recognition using wearable multimodal sensors. In Proceedings of the BodyNets, Beijing, China, 7–10 November 2011; pp. 92–98. [Google Scholar]
- Roy, S.H.; Cole, B.T.; Gilmore, L.D.; De Luca, C.J.; Nawab, S.H. Resolving signal complexities for ambulatory monitoring of motor function in Parkinson’s disease. In Proceedings of the 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Boston, MA, USA, 30 August–3 September 2011; IEEE: Piscataway, NJ, USA, 2011; pp. 4836–4839. [Google Scholar]
- Thorp, J.E.; Adamczyk, P.G.; Ploeg, H.L.; Pickett, K.A. Monitoring motor symptoms during activities of daily living in individuals with Parkinson’s disease. Front. Neurol. 2018, 9, 1036. [Google Scholar] [CrossRef]
- Matlab. Elipse-E. 2022. Available online: https://it.mathworks.com/help/matlab/ref/double.normalize/ (accessed on 17 March 2022).
SBG Ellipse-E | MetaMotionR | |
---|---|---|
Sample Rate | 1000 Hz | 100 Hz |
Resolution | 16 bit | 16 bit |
Accelerometer Range | ±16 g | ±16 g |
Gyroscope Range | °/s | °/s |
Accelerometer Noise Density | 57 | 180 g/ |
Gyroscope Noise Density | °/s/ | °/s/ |
Pearson’s Correlation [%] | RMSE [%] | |
---|---|---|
x | 95.70 | 3.51 |
y | 94.30 | 4.98 |
z | 99.35 | 2.77 |
abs | 98.38 | 4.40 |
Pearson’s Correlation [%] | RMSE [%] | |
---|---|---|
x | 99.88 | 0.99 |
y | 97.21 | 5.66 |
z | 97.94 | 4.59 |
abs | 93.64 | 4.43 |
Types of Tremor | Clinical Features |
---|---|
Rest Tremor | RT occurs when there are not voluntary movements and the limbs are at rest and supported against gravity. |
Postural Tremor | PT is define as an action tremor, it is occurs when a position is maintained against gravity. |
Kinetic Tremor | KT is an action tremor, which appears during voluntary movement |
Class\Metrics | p | r | |
---|---|---|---|
No Tremor (1) | 96.81% | 93.27% | 95.01% |
Postural Tremor (2) | 98.75% | 99.70% | 99.22% |
Rest Tremor (3) | 98.81% | 99.47% | 99.14% |
Kinetic Tremor (4) | 95.45% | 97.42% | 96.43% |
Test Accuracy | 97.46% |
Class\Metrics | p | r | |
---|---|---|---|
No Tremor (1) | 97.98% | 95.81% | 96.88% |
Postural Tremor (2) | 99.31% | 99.63% | 99.47% |
Rest Tremor (3) | 99.21% | 99.70% | 99.45% |
Kinetic Tremor (4) | 97.31% | 98.67% | 97.99% |
Test Accuracy | 98.45% |
accelerometer x-axis only | accelerometer xz-axes | |||||
---|---|---|---|---|---|---|
Class\Metrics | p | r | p | r | ||
No Tremor (1) | 96.24% | 91.15% | 93.62% | 97.19% | 91.19% | 94.09% |
Postural Tremor (2) | 97.91% | 98.17% | 98.04% | 98.52% | 99.70% | 99.11% |
Rest Tremor (3) | 97.49% | 99.27% | 98.37% | 98.75% | 99.44% | 99.09% |
Kinetic Tremor (4) | 94.21% | 97.25% | 95.71% | 93.77% | 97.81% | 95.75% |
Test Accuracy | 96.71% | 97.03% | ||||
accelerometer and gyroscope: x-axis | accelerometer and gyroscope: xz-axes | |||||
Class\Metrics | p | r | p | r | ||
No Tremor (1) | 97.57% | 92.77% | 95.11% | 96.54% | 94.78% | 95.65% |
Postural Tremor (2) | 97.92% | 98.41% | 98.16% | 98.58% | 99.20% | 98.89% |
Rest Tremor (3) | 97.32% | 98.61% | 97.96% | 98.55% | 99.40% | 98.98% |
Kinetic Tremor (4) | 95.95% | 98.94% | 97.42% | 97.19% | 97.51% | 97.35% |
Test Accuracy | 97.19% | 97.72% |
Class\Metrics | p | r | |
---|---|---|---|
No Tremor (1) | 89.85% | 78.28% | 83.67% |
Postural Tremor (2) | 82.17% | 98.81% | 89.72% |
Rest Tremor (3) | 96.81% | 79.66% | 87.40% |
Kinetic Tremor (4) | 83.10% | 91.73% | 87.20% |
Test Accuracy | 87.11% |
Class\Metrics | p | r | |
---|---|---|---|
No Tremor (1) | 97.40% | 92.77% | 95.03% |
Postural Tremor (2) | 99.17% | 99.83% | 99.45% |
Rest Tremor (3) | 98.62% | 99.60% | 99.11% |
Kinetic Tremor (4) | 95.04% | 97.91% | 96.46% |
Test Accuracy | 97.52% |
Class\Metrics | p | r | |
---|---|---|---|
No Tremor (1) | 33.78% | 91.71% | 49.38% |
Postural Tremor (2) | 16.67% | 0.03% | 0.07% |
Rest Tremor (3) | 36.36% | 1.73% | 3.30% |
Kinetic Tremor (4) | 78.03% | 95.62% | 85.94% |
Test Accuracy | 47.36% |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Carissimo, C.; Cerro, G.; Ferrigno, L.; Golluccio, G.; Marino, A. Development and Assessment of a Movement Disorder Simulator Based on Inertial Data. Sensors 2022, 22, 6341. https://doi.org/10.3390/s22176341
Carissimo C, Cerro G, Ferrigno L, Golluccio G, Marino A. Development and Assessment of a Movement Disorder Simulator Based on Inertial Data. Sensors. 2022; 22(17):6341. https://doi.org/10.3390/s22176341
Chicago/Turabian StyleCarissimo, Chiara, Gianni Cerro, Luigi Ferrigno, Giacomo Golluccio, and Alessandro Marino. 2022. "Development and Assessment of a Movement Disorder Simulator Based on Inertial Data" Sensors 22, no. 17: 6341. https://doi.org/10.3390/s22176341
APA StyleCarissimo, C., Cerro, G., Ferrigno, L., Golluccio, G., & Marino, A. (2022). Development and Assessment of a Movement Disorder Simulator Based on Inertial Data. Sensors, 22(17), 6341. https://doi.org/10.3390/s22176341