Enhanced Detection and Segmentation of Sit Phases in Patients with Parkinson’s Disease Using a Single SmartWatch and Random Forest Algorithms
Abstract
1. Introduction
2. Materials and Methods
2.1. Participants
2.2. Experimental Procedures
2.3. Manual Segmentation
2.4. Data Processing and Feature Calculations
2.5. Random Forest Algorithms
2.6. Statistical Analyses
3. Results
3.1. Sit Phase Detection
3.2. Activity Segmentation
4. Discussion
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
Abbreviations
ADLs | Activities of daily living |
PD | Parkinson’s disease |
References
- Jung, S.; Michaud, M.; Oudre, L.; Dorveaux, E.; Gorintin, L.; Vayatis, N.; Ricard, D. The Use of Inertial Measurement Units for the Study of Free Living Environment Activity Assessment: A Literature Review. Sensors 2020, 20, 5625. [Google Scholar] [CrossRef] [PubMed]
- Adams, J.L.; Kangarloo, T.; Tracey, B.; O’Donnell, P.; Volfson, D.; Latzman, R.D.; Zach, N.; Alexander, R.; Bergethon, P.; Cosman, J.; et al. Using a Smartwatch and Smartphone to Assess Early Parkinson’s Disease in the WATCH-PD Study. NPJ Park. Dis. 2023, 9, 64. [Google Scholar] [CrossRef] [PubMed]
- Jung, S.; de l’Escalopier, N.; Oudre, L.; Truong, C.; Dorveaux, E.; Gorintin, L.; Ricard, D. A Machine Learning Pipeline for Gait Analysis in a Semi Free-Living Environment. Sensors 2023, 23, 4000. [Google Scholar] [CrossRef] [PubMed]
- Sun, X.; Qiu, L.; Wu, Y.; Cao, G. ActDetector: Detecting Daily Activities Using Smartwatches. In Proceedings of the 2017 IEEE 14th International Conference on Mobile Ad Hoc and Sensor Systems (MASS), Orlando, FL, USA, 22–25 October 2017; pp. 1–9. [Google Scholar]
- Navarro-López, V.; Fernández-Vázquez, D.; Molina-Rueda, F.; Cuesta-Gómez, A.; García-Prados, P.; del-Valle-Gratacós, M.; Carratalá-Tejada, M. Arm-Swing Kinematics in Parkinson’s Disease: A Systematic Review and Meta-Analysis. Gait Posture 2022, 98, 85–95. [Google Scholar] [CrossRef] [PubMed]
- Goubault, E.; Nguyen, H.P.; Bogard, S.; Blanchet, P.J.; Bézard, E.; Vincent, C.; Langlois, M.; Duval, C. Cardinal Motor Features of Parkinson’s Disease Coexist with Peak-Dose Choreic-Type Drug-Induced Dyskinesia: Parkinson’s Symptoms Coexist with Dyskinesia. J. Park. Dis. 2018, 8, 323–331. [Google Scholar] [CrossRef]
- Goubault, E.; Nguyen, H.P.; Bogard, S.; Blanchet, P.J.; Bézard, E.; Vincent, C.; Sarna, J.; Monchi, O.; Duval, C. Remnants of Cardinal Symptoms of Parkinson’s Disease, Not Dyskinesia, Are Problematic for Dyskinetic Patients Performing Activities of Daily Living. Front. Neurol. 2019, 10, 256. [Google Scholar] [CrossRef] [PubMed]
- Goubault, E.; Duval, C.; Martin, C.; Lebel, K. Innovative Detection and Segmentation of Mobility Activities in Patients Living with Parkinson’s Disease Using a Single Ankle-Positioned Smartwatch. Sensors 2024, 24, 5486. [Google Scholar] [CrossRef] [PubMed]
- Breiman, L. Random Forests. Mach. Learn. 2001, 45, 5–32. [Google Scholar] [CrossRef]
- Cutler, A.; Cutler, D.R.; Stevens, J.R. Random Forests. In Ensemble Machine Learning: Methods and Applications; Zhang, C., Ma, Y., Eds.; Springer: New York, NY, USA, 2012; pp. 157–175. ISBN 978-1-4419-9326-7. [Google Scholar]
- Lakshmi, G.S.; Poulose, A. From Wrist to Ankle: Understanding IMU Sensor Placement in Human Activity Recognition. In Proceedings of the 2025 Emerging Technologies for Intelligent Systems (ETIS), Thiruvananthapuram, India, 7–9 February 2025; pp. 1–6. [Google Scholar]
- Hughes, A.J.; Daniel, S.E.; Kilford, L.; Lees, A.J. Accuracy of Clinical Diagnosis of Idiopathic Parkinson’s Disease: A Clinico-Pathological Study of 100 Cases. J. Neurol. Neurosurg. Psychiatr. 1992, 55, 181–184. [Google Scholar] [CrossRef] [PubMed]
- Oshiro, T.M.; Perez, P.S.; Baranauskas, J.A. How Many Trees in a Random Forest? In Machine Learning and Data Mining in Pattern Recognition; Perner, P., Ed.; Springer: Berlin/Heidelberg, Germany, 2012; pp. 154–168. [Google Scholar]
- Tang, Q.; John, D.; Thapa-Chhetry, B.; Arguello, D.J.; Intille, S. Posture and Physical Activity Detection: Impact of Number of Sensors and Feature Type. Med. Sci. Sports Exerc. 2020, 52, 1834–1845. [Google Scholar] [CrossRef] [PubMed]
- Davoudi, A.; Mardini, M.T.; Nelson, D.; Albinali, F.; Ranka, S.; Rashidi, P.; Manini, T.M. The Effect of Sensor Placement and Number on Physical Activity Recognition and Energy Expenditure Estimation in Older Adults: Validation Study. JMIR MHealth UHealth 2021, 9, e23681. [Google Scholar] [CrossRef] [PubMed]
- Mekruksavanich, S.; Hnoohom, N.; Jitpattanakul, A. Smartwatch-Based Sitting Detection with Human Activity Recognition for Office Workers Syndrome. In Proceedings of the 2018 International ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunications Engineering (ECTI-NCON), Chiang Rai, Thailand, 25–28 February 2018; pp. 160–164. [Google Scholar]
- Marin, F.; Warmerdam, E.; Marin, Z.; Ben Mansour, K.; Maetzler, W.; Hansen, C. Scoring the Sit-to-Stand Performance of Parkinson’s Patients with a Single Wearable Sensor. Sensors 2022, 22, 8340. [Google Scholar] [CrossRef] [PubMed]
- Pham, M.H.; Warmerdam, E.; Elshehabi, M.; Schlenstedt, C.; Bergeest, L.-M.; Heller, M.; Haertner, L.; Ferreira, J.J.; Berg, D.; Schmidt, G.; et al. Validation of a Lower Back “Wearable”-Based Sit-to-Stand and Stand-to-Sit Algorithm for Patients With Parkinson’s Disease and Older Adults in a Home-Like Environment. Front. Neurol. 2018, 9, 652. [Google Scholar] [CrossRef] [PubMed]
- Chatzaki, C.; Skaramagkas, V.; Tachos, N.; Christodoulakis, G.; Maniadi, E.; Kefalopoulou, Z.; Fotiadis, D.I.; Tsiknakis, M. The Smart-Insole Dataset: Gait Analysis Using Wearable Sensors with a Focus on Elderly and Parkinson’s Patients. Sensors 2021, 21, 2821. [Google Scholar] [CrossRef] [PubMed]
- Morgan, C.; Masullo, A.; Mirmehdi, M.; Isotalus, H.K.; Jovan, F.; McConville, R.; Tonkin, E.L.; Whone, A.; Craddock, I. Automated Real-World Video Analysis of Sit-to-Stand Transitions Predicts Parkinson’s Disease Severity. Digit. Biomark. 2023, 7, 92–103. [Google Scholar] [CrossRef] [PubMed]
- Mughal, H.; Javed, A.R.; Rizwan, M.; Almadhor, A.S.; Kryvinska, N. Parkinson’s Disease Management via Wearable Sensors: A Systematic Review. IEEE Access 2022, 10, 35219–35237. [Google Scholar] [CrossRef]
- Okuma, Y.; Yanagisawa, N. The Clinical Spectrum of Freezing of Gait in Parkinson’s Disease. Mov. Disord. 2008, 23, S426–S430. [Google Scholar] [CrossRef] [PubMed]
Characteristics | Mean ± SD | Range |
---|---|---|
Patients (n = 20, 10 Females) | ||
Age (year) | 66.6 ± 9.0 | 47–78 |
Weight (kg) | 74.3 ± 13.4 | 50–97 |
Height (cm) | 166.9 ± 8.9 | 152–180 |
Years since diagnosis * | 7.0 ± 5.5 | 1–21 |
Comorbidity index (/18) | 5.1 ± 2.4 | 1–9 |
Moca (/30) | 27.3 ± 2.8 | 19–30 |
Notthingham ADL scale (/22) | 19.7 ± 1.7 | 16–22 |
MDS-UPDRS Part III(On state) ** | ||
Speech (3.1) | 0.4 ± 0.6 | 0–2 |
Facial expression (3.2) | 0.6 ± 1.0 | 0–4 |
Neck rigidity (3.3) | 0.7 ± 0.8 | 0–2 |
Arm rigidity (3.3) | 0.9 ± 0.8 | 0–2 |
Leg rigidity (3.3) | 0.7 ± 0.7 | 0–2 |
Finger tapping (3.4) | 0.6 ± 0.7 | 0–2 |
Hand movements (3.5) | 0.8 ± 0.6 | 0–2 |
Pro-sup movements of hands (3.6) | 0.7 ± 0.7 | 0–2 |
Toe tapping (3.7) | 0.3 ± 0.4 | 0–1 |
Leg agility (3.8) | 0.3 ± 0.6 | 0–2 |
Arising from chair (3.9) | 0.1 ± 0.3 | 0–1 |
Gait (3.10) | 0.4 ± 0.8 | 0–2 |
Freezing of gait (3.11) | 0.1 ± 0.2 | 0–1 |
Postural stability (3.12) | 0.7 ± 0.8 | 0–2 |
Posture (3.13) | 0.4 ± 0.5 | 0–1 |
Body bradykinesia (3.14) | 0.3 ± 0.5 | 0–1 |
Postural tremor (3.15) | 0.4 ± 0.6 | 0–2 |
Kinetic tremor (3.16) | 0.7 ± 0.6 | 0–2 |
Rest tremor amplitude upper limbs (3.17) | 0.6 ± 0.8 | 0–3 |
Constancy of rest tremor (3.18) | 1.4 ± 1.3 | 0–4 |
Hoehn and Yahr score On | 1.4 ± 0.5 | 1–2 |
Variable | N Variables Acceleration | N Variables Ang. Velocity |
---|---|---|
Mean | 8 | 8 |
Standard deviation | 8 | 8 |
Ankle | 16 | 16 |
Trial | Sensitivity (%) | Specificity (%) | F-Score |
---|---|---|---|
3 min | 78.3 | 93.8 | 84.7 |
4 min | 78.8 | 85.5 | 80.6 |
5 min | 71.6 | 84.8 | 75.6 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 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
Goubault, E.; Martin, C.; Duval, C.; Daneault, J.-F.; Boissy, P.; Lebel, K. Enhanced Detection and Segmentation of Sit Phases in Patients with Parkinson’s Disease Using a Single SmartWatch and Random Forest Algorithms. Sensors 2025, 25, 6104. https://doi.org/10.3390/s25196104
Goubault E, Martin C, Duval C, Daneault J-F, Boissy P, Lebel K. Enhanced Detection and Segmentation of Sit Phases in Patients with Parkinson’s Disease Using a Single SmartWatch and Random Forest Algorithms. Sensors. 2025; 25(19):6104. https://doi.org/10.3390/s25196104
Chicago/Turabian StyleGoubault, Etienne, Camille Martin, Christian Duval, Jean-François Daneault, Patrick Boissy, and Karina Lebel. 2025. "Enhanced Detection and Segmentation of Sit Phases in Patients with Parkinson’s Disease Using a Single SmartWatch and Random Forest Algorithms" Sensors 25, no. 19: 6104. https://doi.org/10.3390/s25196104
APA StyleGoubault, E., Martin, C., Duval, C., Daneault, J.-F., Boissy, P., & Lebel, K. (2025). Enhanced Detection and Segmentation of Sit Phases in Patients with Parkinson’s Disease Using a Single SmartWatch and Random Forest Algorithms. Sensors, 25(19), 6104. https://doi.org/10.3390/s25196104