Increasing Robustness in the Detection of Freezing of Gait in Parkinson’s Disease
Open accessThe DOI matches its Crossref record; 29 of the 29 references it cites were found in a registry or an index.
Abstract
This paper focuses on detecting freezing of gait in Parkinson’s patients using body-worn accelerometers. In this study, we analyzed the robustness of four feature sets, two of which are new features adapted from speech processing: mel frequency cepstral coefficients and quality assessment metrics. For classification based on these features, we compared random forest, multilayer perceptron, hidden Markov models, and deep neural networks. These algorithms were evaluated using a leave-one-subject-out (LOSO) cross validation to match the situation where a system is being constructed for patients for whom there is no training data. This evaluation was performed using the Daphnet dataset, which includes recordings from ten patients using three accelerometers situated on the ankle, knee, and lower back. We obtained a reduction from 17.3% to 12.5% of the equal error rate compared to the previous best results using this dataset and LOSO testing. For high levels of sensitivity (such as 0.95), the specificity increased from 0.63 to 0.75. The biggest improvement across all of the feature sets and algorithms tested in this study was obtained by integrating information from longer periods of time in a deep neural network with convolutional layers.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures




![Figure 5 Results for Mazilu et al.'s features [22] (curves) for each subject compared to [13] when using optimized thresholds and R10Fold evaluation.](https://figures.cochat.ai/paper-figures/00bf87add4f244f0a19826d748212833/increasing-robustness-in-the-detection-of-freezing-of-gait-in-parkinsons-disease-figure-5.png)
![Figure 6 Specificity vs. sensitivity curves, AUC, and EER for the four sets of features using random forest with 4-s windows and 75% overlap, a leave-one-subject-out (LOSO) evaluation, and excluding subjects 4 and 10. The isolated point shows the results reported in Mazilu et al. [22] without subjects 4 and 10 (sensitivity = 0.55 and specificity = 0.95).](https://figures.cochat.ai/paper-figures/b9d574231b7d4ddda75e6a689dc2c684/increasing-robustness-in-the-detection-of-freezing-of-gait-in-parkinsons-disease-figure-6.png)





Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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?
The cited source says what the claim attributes to it.
In the citing paper
“Therefore, for making a usable FOG detection system it is necessary that event detection must be fast without adding delays to the detection process [67,74].”
From Deep Learning Approaches for Detecting Freezing of Gait in Parkinson’s Disease Patients through On-Body Acceleration Sensors (2020) · cites this paper as [67]
In the citing paper
“In the literature, the use of longer temporal windows has shown an improvement performance in FOG detection, while increasing the latency time.”
From Deep Learning Approaches for Detecting Freezing of Gait in Parkinson’s Disease Patients through On-Body Acceleration Sensors (2020) · cites this paper as [67]
In the citing paper
“To address the reduced amount of FOG events in the data and to achieve a windowing strategy similar to that reported in the literature [65,67] a window was labeled as a FOG only if more than 50% of its samples were labeled as FOG.”
From Deep Learning Approaches for Detecting Freezing of Gait in Parkinson’s Disease Patients through On-Body Acceleration Sensors (2020) · cites this paper as [67]
In the citing paper
“The addition of data from previous windows has shown an improvement in FOG detection, without the need of increasing the window size and avoiding increasing latency [65,67].”
From Deep Learning Approaches for Detecting Freezing of Gait in Parkinson’s Disease Patients through On-Body Acceleration Sensors (2020) · cites this paper as [67]
In the citing paper
“Despite being a widely used methodology, the R10Fold evaluation could show overly optimistic performance when using overlapped windows, because there is a high probability that the training and test subsets share some of the same data, because of the random splitting process [67].”
From Deep Learning Approaches for Detecting Freezing of Gait in Parkinson’s Disease Patients through On-Body Acceleration Sensors (2020) · cites this paper as [67]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
The meaning and use of the area under a receiver operating characteristic (ROC) curve.
Hanley, J. A., & McNeil, B. J. (1982) · Radiology · doi:10.1148/radiology.143.1.7063747 · Cited by 21,856 · cited 1×
“0005, according to Hanley’s method [29].”
Goetz, C. G., Tilley, B. C., Shaftman, S. R., Stebbins, G. T., Fahn, S., Martinez‐Martin, P., Poewe, W., Sampaio, C., Stern, M. B., Dodel, R., et al. (2008) · Movement Disorders · doi:10.1002/mds.22340 · Cited by 7,536
Freezing of gait: moving forward on a mysterious clinical phenomenon
Nutt, J. G., Bloem, B. R., Giladi, N., Hallett, M., Horak, F. B., & Nieuwboer, A. (2011) · The Lancet Neurology · doi:10.1016/s1474-4422(11)70143-0 · Cited by 1,304
Schaafsma, J. D., Balash, Y., Gurevich, T., Bartels, A. L., Hausdorff, J. M., & Giladi, N. (2003) · European Journal of Neurology · doi:10.1046/j.1468-1331.2003.00611.x · Cited by 725
Wearable Assistant for Parkinson’s Disease Patients With the Freezing of Gait Symptom
Bachlin, M., Plotnik, M., Roggen, D., Maidan, I., Hausdorff, J. M., Giladi, N., & Troster, G. (2010) · IEEE Transactions on Information Technology in Biomedicine · doi:10.1109/titb.2009.2036165 · Cited by 693 · cited 7×
“FOG episodes were detected using an FI threshold, and this feature was used in later experiments [13,18].”
BackgroundMethodInfluentialAmbulatory monitoring of freezing of gait in Parkinson’s disease
Moore, S. T., MacDougall, H. G., & Ondo, W. G. (2008) · Journal of Neuroscience Methods · doi:10.1016/j.jneumeth.2007.08.023 · Cited by 526 · cited 4×
“[20] found that frequency components of leg movements in the 3–8 Hz band during FOG episodes are characteristic of this symptom and do not appear during normal walking.”
BackgroundInfluentialMoore, O., Peretz, C., & Giladi, N. (2007) · Movement Disorders · doi:10.1002/mds.21659 · Cited by 337
Ravi, D., Wong, C., Lo, B., & Yang, G.-Z. (2016) · 2016 IEEE 13th International Conference on Wearable and Implantable Body Sensor Networks (BSN) · doi:10.1109/bsn.2016.7516235 · Cited by 269 · cited 1×
“[23] used a convolutional neural network (CNN) with one convolutional layer for feature extraction and one fully connected layer for classification.”
MethodOnline Detection of Freezing of Gait with Smartphones and Machine Learning Techniques
Mazilu, S., Hardegger, M., Zhu, Z., Roggen, D., Troester, G., Plotnik, M., & Hausdorff, J. (2012) · Proceedings of the 6th International Conference on Pervasive Computing Technologies for Healthcare · doi:10.4108/icst.pervasivehealth.2012.248680 · Cited by 231 · cited 10×
“[22] without subjects 4 and 10 (sensitivity = 0.”
BackgroundMethodResultInfluentialDeep Activity Recognition Models with Triaxial Accelerometers
Alsheikh, M. A., Selim, A., Niyato, D. T., Doyle, L., Lin, S., & Tan, H.-P. (2015) · DR-NTU (Nanyang Technological University) · Cited by 204
Speech Quality of VoIP: Assessment and Prediction
Raake, A. (2006) · Cited by 165
Arias, P., & Cudeiro, J. (2010) · PLoS ONE · doi:10.1371/journal.pone.0009675 · Cited by 161
Speech Quality of VoIP: Assessment and Prediction
Raake, A. (2006) · Wiley eBooks · doi:10.1002/9780470033005 · Cited by 153
Hammerla, N. Y., Kirkham, R., Andras, P., & Ploetz, T. (2013) · Proceedings of the 2013 International Symposium on Wearable Computers · doi:10.1145/2493988.2494353 · Cited by 138 · cited 3×
“[17] proposed the empirical cumulative distribution function as feature representation.”
BackgroundMethodDeep Activity Recognition Models with Triaxial Accelerometers
Alsheikh, M. A., Selim, A., Niyato, D., Doyle, L., Lin, S., & Tan, H.-P. (2015) · arXiv · doi:10.48550/arxiv.1511.04664 · Cited by 126
Plotnik, M., Giladi, N., & Hausdorff, J. M. (2012) · Parkinson's Disease · doi:10.1155/2012/459321 · Cited by 107
Development of intelligent multisensor surveillance systems with agents
Pavón, J., Gómez-Sanz, J. J., Fernández‐Caballero, A., & Valencia-Jiménez, J. J. (2007) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2007.07.009 · Cited by 107
Feature Learning for Detection and Prediction of Freezing of Gait in Parkinson’s Disease
Mazilu, S., Calatroni, A., Gazit, E., Roggen, D., Hausdorff, J. M., & Tröster, G. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-39712-7_11 · Cited by 106
Feature extraction from smartphone inertial signals for human activity segmentation
San-Segundo, R., Montero, J. M., Barra-Chicote, R., Fernández-Martínez, F., & Pardo, J. M. (2015) · Signal Processing · doi:10.1016/j.sigpro.2015.09.029 · Cited by 106
Self-citationRobust Human Activity Recognition using smartwatches and smartphones
San-Segundo, R., Blunck, H., Moreno-Pimentel, J., Stisen, A., & Gil-Martín, M. (2018) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2018.04.002 · Cited by 105
Self-citationXia, Y., Gao, Q., & Ye, Q. (2015) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2015.02.002 · Cited by 87
Dyskinesia and motor state detection in Parkinson's Disease patients with a single movement sensor
Sama, A., Perez-Lopez, C., Romagosa, J., Rodriguez-Martin, D., Catala, A., Cabestany, J., Perez-Martinez, D. A., & Rodriguez-Molinero, A. (2012) · 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society · doi:10.1109/embc.2012.6346150 · Cited by 82
Young, W. R., Shreve, L., Quinn, E. J., Craig, C., & Bronte-Stewart, H. (2016) · Neuropsychologia · doi:10.1016/j.neuropsychologia.2016.04.034 · Cited by 75
Wu, Y., Chen, P., Luo, X., Wu, M., Liao, L., Yang, S., & Rangayyan, R. M. (2016) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2016.08.022 · Cited by 73
Segmenting human activities based on HMMs using smartphone inertial sensors
San-Segundo, R., Lorenzo-Trueba, J., Martínez-González, B., & Pardo, J. M. (2016) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2016.01.004 · Cited by 53
Self-citationCharacterizing gait asymmetry via frequency sub-band components of the ground reaction force
Su, B.-L., Song, R., Guo, L.-Y., & Yen, C. (2014) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2014.11.008 · Cited by 50
Assam, R., & Seidl, T. (2014) · ACM SIGSPATIAL International Workshop on the Use of GIS in Public Health (HealthGIS) · doi:10.1145/2676629.2676630 · Cited by 14
Ambulatory Treatment and Telemonitoring of Patients with Parkinson’s Disease
Herrlich, S., Spieth, S., Nouna, R., Zengerle, R., Giannola, L. I., Pardo-Ayala, D. E., Federico, E., & Garino, P. (2011) · Springer eBooks · doi:10.1007/978-3-642-18167-2_20 · Cited by 13
Richard, I. H., Frank, S., LaDonna, K. A., Wang, H., McDermott, M., & Kurlan, R. (2005) · Neuropsychiatric Disease and Treatment · doi:10.2147/ndt.a791 · Cited by 7
Cited by
Classification of epileptic EEG recordings using signal transforms and convolutional neural networks
San-Segundo, R., Gil-Martín, M., D'Haro-Enríquez, L. F., & Pardo, J. M. (2019) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2019.04.031 · Cited by 172
Self-citationParkinson’s Disease Detection from Drawing Movements Using Convolutional Neural Networks
Gil-Martín, M., Montero, J., & San-Segundo, R. (2019) · Electronics · doi:10.3390/electronics8080907 · Cited by 130
Self-citationSigcha, L., Borzì, L., Amato, F., Rechichi, I., Ramos-Romero, C. A., Cardenas, A. J. A., Gascó, L., & Olmo, G. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.120541 · Cited by 172
Sigcha, L., Costa, N., Pavón, I., Costa, S., Arezes, P., López, J. M., & De Arcas, G. (2020) · Sensors · doi:10.3390/s20071895 · Cited by 126
Detection and assessment of Parkinson's disease based on gait analysis: A survey
Guo, Y., Yang, J., Liu, Y., Chen, X., & Yang, G. (2022) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2022.916971 · Cited by 128
Metadata
- Authors
- San-Segundo, R., Navarro-Hellín, H., Torres-Sánchez, R., Hodgins, J., & De la Torre, F.
- Affiliations
- Information Processing and Telecommunications Center (ES)
- Carnegie Mellon University (US)
- Universidad Politécnica de Cartagena (ES)
- Robotics Institute, Carnegie Mellon University, Pittsburgh, PA 15213, USA
- Corresponding author
- San-Segundo, Rubén
- Venue
- Electronics
- Publisher
- MDPI AG
- Published
- 2019-01-22
- Volume
- 8
- Issue
- 2
- Pages
- 119
- ISSN
- 2079-9292 (ISSN-L)
- OpenAlex
- W2913141042
- Cited by
- 86
- References
- 29
- Citations by year
- 2026: 3 · 2025: 12 · 2024: 17 · 2023: 11 · 2022: 14 · 2021: 12 · 2020: 14 · 2019: 3
- FWCI
- 24.76
- Type
- journal article
- Language
- en
- Open access
- gold
- dx.doi.org
- Licence
- Locations
- Electronics (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- National Science Foundation (1602337)
- Ministerio de Educación, Cultura y Deporte and the Fulbright Commission in Spain (PRX16/00103)
- Topics
- Health Sciences › Health Professions › Physical Therapy, Sports Therapy and Rehabilitation › Balance, Gait, and Falls Prevention
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Physical Sciences › Engineering › Biomedical Engineering › Gait Recognition and Analysis
- Keywords
- freezing of gait, Parkinson's disease, wearable accelerometers, gait analysis, feature robustness, Mel-frequency cepstral coefficients, leave-one-subject-out cross-validation, deep neural network, convolutional neural networks, hidden Markov models, random forest, multilayer perceptron
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.
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
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.