A wearable system for gait training in subjects with Parkinson's disease
Open accessThe DOI matches its Crossref record; 44 of the 45 references it cites were found in a registry or an index; none of the 28 sources its claims cite is checked for support yet.
Abstract
In this paper, a system for gait training and rehabilitation for Parkinson's disease (PD) patients in a daily life setting is presented. It is based on a wearable architecture aimed at the provision of real-time auditory feedback. Recent studies have, in fact, shown that PD patients can receive benefit from a motor therapy based on auditory cueing and feedback, as happens in traditional rehabilitation contexts with verbal instructions given by clinical operators. To this extent, a system based on a wireless body sensor network and a smartphone has been developed. The system enables real-time extraction of gait spatio-temporal features and their comparison with a patient's reference walking parameters captured in the lab under clinical operator supervision. Feedback is returned to the user in form of vocal messages, encouraging the user to keep her/his walking behavior or to correct it. This paper describes the overall concept, the proposed usage scenario and the parameters estimated for the gait analysis. It also presents, in detail, the hardware-software architecture of the system and the evaluation of system reliability by testing it on a few subjects.
Overview
CoChat Summary
## TL;DR
The paper presents a fully portable, wearable closed-loop gait training system for people with Parkinson’s disease that uses IMUs plus a smartphone to compute gait features in real time and return vocal feedback. It reports preliminary validation on multiple PD patients and reliability checks showing real-time operation, with step-length estimation agreeing closely with instrumented walkway measurements.
## Key findings
- The system was designed around three sensors and one smartphone: two sensors on the shoes and one on the trunk, with vocal feedback delivered via headphones.
- In step-length validation, five male PD patients performed nine trials each on an 8.80-meter instrumented GAITRite walkway; the paper reports a bias close to zero and standard deviation within 3% for stride duration and 2% for stride length.
- The sensing and orientation components were compared against commercial or MATLAB reference implementations: the node’s static-noise comparison with an Xsens platform showed very similar performance, and orientation estimation error versus MATLAB was reported as RMSE lower than 0.004 degrees for roll, pitch, and yaw; a second comparison reported RMSE of 1.818, 0.594, and 2.941 degrees for the three estimated angles.
- The Android application was tested on different dual-core smartphones and achieved real-time performance; on an LG Nexus 5, the main operations took 0.11 ms per new sample and 0.23 ms per new detected step.
## Methods
- The paper describes a patient-specific closed-loop gait training system built on a wireless body sensor network with IMUs and an Android smartphone for real-time processing and feedback.
- For clinical validation of step-length estimation, five male PD patients walked at comfortable, increased, and decreased speeds over an 8.80-meter GAITRite walkway, while two foot-mounted IMUs streamed data at 200 Hz.
- The analysis included real-time gait-event detection (initial contact and foot-off), ZUPT-aided inertial navigation for step-length estimation, and Bland–Altman plots to compare IMU-derived stride duration and length with GAITRite measurements.
## Limitations
- The paper explicitly notes that the system was evaluated only on a few subjects, and that it is now being used for pilot trials with PD patients rather than already established for extensive clinical use.
- The authors state that further analysis is desirable to validate the spatio-temporal feature estimation.
- Evident from the text: the validation sample for step-length accuracy was small (five male PD patients), and the paper also reports one case where a subject produced accelerations above the IMU full scale (±6 g), indicating a hardware range limitation.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures







Verification
Claims the paper makes
0 Valid · 0 Not valid · 17 Not checked · 17 Own results and interpretations
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The results are in Table 2, and they show a very similar performance for the two platforms, reporting the standard deviations of each axis for the three sensors.”
§ A Wearable System for Gait Training in Subjects with Parkinson's Disease > System Architecture > Sensing Nodes Calibration and On-Board Orientation Estimate
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
In the paper
“It is used only when advantageous, since we found that for high transmission rates, the Sniff mode uses more energy than the normal operating mode [24].”
§ A Wearable System for Gait Training in Subjects with Parkinson's Disease > System Architecture > Power Management
What the sources say
- Not checked yetcites [24] Casamassima, F., Farella, E., and Benini, L. (2013, January 9–11). Power saving policies for multipurpose WBAN. Karlsruhe, Germany. source
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Feedback is returned to the user in form of vocal messages, encouraging the user to keep her/his walking behavior or to correct it.”
§ A Wearable System for Gait Training in Subjects with Parkinson's Disease > Abstract
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The difference between the orientation computed on the two platforms is negligible, having an RMSE lower than 0.004 degrees for roll, pitch and yaw angles.”
§ A Wearable System for Gait Training in Subjects with Parkinson's Disease > System Architecture > Sensing Nodes Calibration and On-Board Orientation Estimate
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This new algorithm is able to determine IC and FO by processing the angular velocity signal arising along the medio-lateral axis of the foot.”
§ A Wearable System for Gait Training in Subjects with Parkinson's Disease > Algorithms and Real-Time Feedback for Gait Rehabilitation > Soft Real-Time Gait Events Detection
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
11 more claims
Create a free account to see all 34 claims and to verify the 28 references still open.
- It may state two separate claims as one. 13
- Probably not a substantial claim. 6
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Technical features and algorithms were first validated for the detection of gait abnormalities against standard gait registration systems [26]”
Citations
Cites
A New Approach to Linear Filtering and Prediction Problems
Kalman, R. E. (1960) · Journal of Basic Engineering · doi:10.1115/1.3662552 · Cited by 31,751 · cited 1×
“State-of-the-art algorithms for the estimation of orientation from IMU sensor data were optimized for the EXLs1 sensor node, including the Kalman filter [30], its extended variation [31] and recently developed complementary filters [32,33].”
MethodGait Analysis: Normal and Pathological Function
(1992) · JAMA: The Journal of the American Medical Association · doi:10.1001/jama.1992.03490220101046 · Cited by 3,875
Estimation of IMU and MARG orientation using a gradient descent algorithm
Madgwick, S. O. H., Harrison, A. J. L., & Vaidyanathan, R. (2011) · 2011 IEEE International Conference on Rehabilitation Robotics · doi:10.1109/icorr.2011.5975346 · Cited by 2,068 · cited 1×
“State-of-the-art algorithms for the estimation of orientation from IMU sensor data were optimized for the EXLs1 sensor node, including the Kalman filter [30], its extended variation [31] and recently developed complementary filters [32,33].”
MethodNonlinear Complementary Filters on the Special Orthogonal Group
Mahony, R., Hamel, T., & Pflimlin, J.-M. (2008) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2008.923738 · Cited by 1,751 · cited 1×
“State-of-the-art algorithms for the estimation of orientation from IMU sensor data were optimized for the EXLs1 sensor node, including the Kalman filter [30], its extended variation [31] and recently developed complementary filters [32,33].”
MethodPedestrian Tracking with Shoe-Mounted Inertial Sensors
Foxlin, E. (2005) · IEEE Computer Graphics and Applications · doi:10.1109/mcg.2005.140 · Cited by 1,399 · cited 1×
“…is an unfeasible operation, since the orientation-dependent gravitational component is not straightforwardly separable from the inertial acceleration, and even minor drift internal to the gyroscope or the accelerometer (being single-/double-integrated) causes errors that increase cubically [39].”
BackgroundA survey of design techniques for system-level dynamic power management
Benini, L., Bogliolo, A., & De Micheli, G. (2000) · IEEE Transactions on Very Large Scale Integration (VLSI) Systems · doi:10.1109/92.845896 · Cited by 1,241 · cited 1×
“The scheduling protocol is defined taking into account the application’s sampling rate requirements and the cost of the transitions between the different power states [23].”
BackgroundAided Navigation: GPS with High Rate Sensors
Farrell, J. A. (2008) · Cited by 776
The pathogenesis of gait hypokinesia in Parkinson's disease
Morris, M. E., Iansek, R., Matyas, T. A., & Summers, J. J. (1994) · Brain · doi:10.1093/brain/117.5.1169 · Cited by 709 · cited 1×
“In addition, patients show problems in maintaining rhythmicity and the amplitude of the gait [11,12].”
BackgroundFisher, B. E., Wu, A. D., Salem, G. J., Song, J., Lin, C.-H. (., Yip, J., Cen, S., Gordon, J., Jakowec, M., & Petzinger, G. (2008) · Archives of Physical Medicine and Rehabilitation · doi:10.1016/j.apmr.2008.01.013 · Cited by 474 · cited 2×
“Although the rates of motor learning may be slower in PD, recent evidence highlights that PD patients can acquire motor skills and improve their motor performance with sustained personalized training [5,6,9].”
BackgroundImpaired regulation of stride variability in Parkinson's disease subjects with freezing of gait
Hausdorff, J. M., Schaafsma, J. D., Balash, Y., Bartels, A. L., Gurevich, T., & Giladi, N. (2003) · Experimental Brain Research · doi:10.1007/s00221-002-1354-8 · Cited by 442 · cited 1×
“PD gait is characterized by a difficulty with the internal regulation of stride length and step clearance and increased gait variability [1,10].”
Background
Cited by
Zhu, M., Shi, Q., He, T., Yi, Z., Ma, Y., Yang, B., Chen, T., & Lee, C. (2019) · ACS Nano · doi:10.1021/acsnano.8b08329 · Cited by 411
Wearable sensor-based real-time gait detection: A systematic review
Prasanth, H., Caban, M., Keller, U., Courtine, G., Ijspeert, A., Vallery, H., & von Zitzewitz, J. (2021) · Sensors · doi:10.3390/s21082727 · Cited by 348
“[48] compared these two methods based on accuracy, computational cost, and energy efficiency and concluded that the Kalman filter-based method was their preferred choice.”
MethodPasluosta, C. F., Gassner, H., Winkler, J., Klucken, J., & Eskofier, B. M. (2015) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2015.2461555 · Cited by 323
“Motion sensors attached to the patient’s body are used to quantify the effectiveness of new medication and rehabilitation therapies [32], [62], [102].”
BackgroundGinis, P., Nieuwboer, A., Dorfman, M., Ferrari, A., Gazit, E., Canning, C. G., Rocchi, L., Chiari, L., Hausdorff, J. M., & Mirelman, A. (2016) · Parkinsonism & Related Disorders · doi:10.1016/j.parkreldis.2015.11.004 · Cited by 225
“2A in Supplementary Materials); 2) A menu of four training targets: cadence, stride length, symmetry and gait speed; 3) A ‘therapeutic window’ allowing calibration of feedback according to the individual's optimal gait performance [26], and set per gait parameter as a percentage above and below the median of every 5 s…”
BackgroundMethodSelf-citationAssessing Gait in Parkinson’s Disease Using Wearable Motion Sensors: A Systematic Review
Brognara, L., Palumbo, P., Grimm, B., & Palmerini, L. (2019) · Diseases · doi:10.3390/diseases7010018 · Cited by 189
Metadata
- Authors
- Casamassima, F., Ferrari, A., Milosevic, B., Ginis, P., Farella, E., & Rocchi, L.
- Affiliations
- University of Bologna (IT)
- KU Leuven (BE)
- Fondazione Bruno Kessler (IT)
- Corresponding author
- Farella, Elisabetta
- Venue
- Sensors
- Publisher
- MDPI AG
- Published
- 2014-03-28
- Volume
- 14
- Issue
- 4
- Pages
- 6229-6246
- ISSN
- 1424-8220 (ISSN-L)
- PMC
- PMC4029669
- OpenAlex
- W2033453630
- Cited by
- 131
- References
- 45
- Citations by year
- 2026: 2 · 2025: 10 · 2024: 12 · 2023: 6 · 2022: 14 · 2021: 9 · 2020: 13 · 2019: 9 · 2018: 10 · 2017: 16 · 2016: 15 · 2015: 14 · 2014: 1
- FWCI
- 39.74
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Sensors (publishedVersion, cc-by)
- Europe PMC (PubMed Central) (publishedVersion, other-oa)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- IRIS UNIMORE (University of Modena and Reggio Emilia) (submittedVersion, cc-by)
- Lirias (submittedVersion, other-oa)
- Archivio istituzionale della ricerca (Alma Mater Studiorum Università di Bologna) (submittedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- European Commission (2007–2013, FP7 2007-2013, 288516, FP7/2007)
- Topics
- Health Sciences › Health Professions › Physical Therapy, Sports Therapy and Rehabilitation › Balance, Gait, and Falls Prevention
- Physical Sciences › Engineering › Biomedical Engineering › Gait Recognition and Analysis
- Health Sciences › Medicine › Rehabilitation › Stroke Rehabilitation and Recovery
- Keywords
- Parkinson's disease, gait training, wearable sensors, auditory feedback, auditory cueing, gait rehabilitation, wireless body sensor networks, real-time gait analysis, home-based rehabilitation
- MeSH terms
- Algorithms, Calibration, Computer Systems, Feedback, Gait, Humans, Male, Parkinson Disease, Telemetry, Thermodynamics
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-10-11, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-11 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: A wearable system for gait training in subjects with Parkinson's disease. https://app.cochat.ai/papers/10.3390/s140406229
- The paper
- Casamassima, F., Ferrari, A., Milosevic, B., Ginis, P., Farella, E., & Rocchi, L. (2014). A wearable system for gait training in subjects with Parkinson's disease. Sensors. https://doi.org/10.3390/s140406229
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.