L Test Subtask Segmentation for Lower-Limb Amputees Using a Random Forest Algorithm
Abstract
:1. Introduction
2. Materials and Methods
2.1. Participants
2.2. Data Collection
2.3. Ground Truth
2.4. Data Processing
2.5. Datasets
2.6. Feature Extraction
2.7. Classification Technique
2.8. Data Analysis
3. Results
4. Discussion
Limitations
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Deathe, A.B.; Miller, W.C. The L Test of Functional Mobility: Measurement Properties of a Modified Version of the Timed “Up & Go” Test Designed for People With Lower-Limb Amputations. Phys. Ther. 2005, 85, 626–635. [Google Scholar] [CrossRef] [PubMed]
- Ortega-Bastidas, P.; Gómez, B.; Aqueveque, P.; Luarte-Martínez, S.; Cano-de-la-Cuerda, R. Instrumented Timed Up and Go Test (iTUG)—More Than Assessing Time to Predict Falls: A Systematic Review. Sensors 2023, 23, 3426. [Google Scholar] [CrossRef] [PubMed]
- Burger, H.; Kuželički, J.; Marinček, Č. Transition from Sitting to Standing after Trans-Femoral Amputation. Prosthet. Orthot. Int. 2005, 29, 139–151. [Google Scholar] [CrossRef]
- Kuželički, J.; Žefran, M.; Burger, H.; Bayd, T. Synthesis of Standing-up Trajectories Using Dynamic Optimization. Gait Posture 2005, 21, 1–11. [Google Scholar] [CrossRef] [PubMed]
- Slajpah, S.; Kamnik, R.; Burger, H.; Bajd, T.; Munih, M. Asymmetry in Sit-to-Stand Movement in Patients Following Transtibial Amputation and Healthy Individuals. Int. J. Rehabil. Res. 2013, 36, 275–283. [Google Scholar] [CrossRef] [PubMed]
- Burger, H.; Marinček, Č. Functional Testing of Elderly Subjects after Lower Limb Amputation. Prosthet. Orthot. Int. 2001, 25, 102–107. [Google Scholar] [CrossRef] [PubMed]
- Caronni, A.; Sterpi, I.; Antoniotti, P.; Aristidou, E.; Nicolaci, F.; Picardi, M.; Pintavalle, G.; Redaelli, V.; Achille, G.; Sciumè, L.; et al. Criterion Validity of the Instrumented Timed Up and Go Test: A Partial Least Square Regression Study. Gait Posture 2018, 61, 287–293. [Google Scholar] [CrossRef] [PubMed]
- Williams, J.M.; Nyman, S.R. Age Moderates Differences in Performance on the Instrumented Timed Up and Go Test Between People With Dementia and Their Informal Caregivers. J. Geriatr. Phys. Ther. 2021, 44, E150. [Google Scholar] [CrossRef]
- Gailey, R.S.; Roach, K.E.; Applegate, E.B.; Cho, B.; Cunniffe, B.; Licht, S.; Maguire, M.; Nash, M.S. The Amputee Mobility Predictor: An Instrument to Assess Determinants of the Lower-Limb Amputee’s Ability to Ambulate. Arch. Phys. Med. Rehabil. 2002, 83, 613–627. [Google Scholar] [CrossRef]
- McCreath Frangakis, A.L.; Lemaire, E.D.; Baddour, N. Subtask Segmentation Methods of the Timed Up and Go Test and L Test Using Inertial Measurement Units—A Scoping Review. Information 2023, 14, 127. [Google Scholar] [CrossRef]
- Jallon, P.; Dupre, B.; Antonakios, M. A Graph Based Method for Timed up & Go Test Qualification Using Inertial Sensors. In Proceedings of the 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Prague, Czech Republic, 22–27 May 2011; pp. 689–692. [Google Scholar]
- Yahalom, G.; Yekutieli, Z.; Israeli-Korn, S.; Elincx-Benizri, S.; Livneh, V.; Fay-Karmon, T.; Rubel, Y.; Tchelet, K.; Zauberman, J.; Hassin-Baer, S. AppTUG-A Smartphone Application of Instrumented ‘Timed Up and Go’ for Neurological Disorders. EC Neurol. 2018, 10, 689–695. [Google Scholar]
- Nguyen, H.; Lebel, K.; Boissy, P.; Bogard, S.; Goubault, E.; Duval, C. Auto Detection and Segmentation of Daily Living Activities during a Timed Up and Go Task in People with Parkinson’s Disease Using Multiple Inertial Sensors. J. Neuroeng. Rehabil. 2017, 14, 26. [Google Scholar] [CrossRef]
- Nguyen, H.P.; Ayachi, F.; Lavigne-Pelletier, C.; Blamoutier, M.; Rahimi, F.; Boissy, P.; Jog, M.; Duval, C. Auto Detection and Segmentation of Physical Activities during a Timed-Up-and-Go (TUG) Task in Healthy Older Adults Using Multiple Inertial Sensors. J. Neuroeng. Rehabil. 2015, 12, 36. [Google Scholar] [CrossRef]
- Hsieh, C.-Y.; Huang, H.-Y.; Liu, K.-C.; Chen, K.-H.; Hsu, S.J.; Chan, C.-T. Automatic Subtask Segmentation Approach of the Timed Up and Go Test for Mobility Assessment System Using Wearable Sensors. In Proceedings of the 2019 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI), Chicago, IL, USA, 19–22 May 2019; IEEE: New York, NY, USA, 2019. [Google Scholar]
- Beyea, J.B.A. Automating the Timed up and Go Test (Tug Test) with Wearable Sensors. Master’s Thesis, University of New Brunswick, Fredericton, NB, Canada, 2017. [Google Scholar]
- Beyea, J.; McGibbon, C.A.; Sexton, A.; Noble, J.; O’Connell, C. Convergent Validity of a Wearable Sensor System for Measuring Sub-Task Performance during the Timed Up-and-Go Test. Sensors 2017, 17, 934. [Google Scholar] [CrossRef] [PubMed]
- Matey-Sanz, M.; González-Pérez, A.; Casteleyn, S.; Granell, C. Instrumented Timed Up and Go Test Using Inertial Sensors from Consumer Wearable Devices. In Artificial Intelligence in Medicine; Michalowski, M., Abidi, S.S.R., Abidi, S., Eds.; Springer International Publishing: Berlin/Heidelberg, Germany, 2022; pp. 144–154. [Google Scholar]
- Abdollah, V.; Dief, T.N.; Ralston, J.; Ho, C.; Rouhani, H. Investigating the Validity of a Single Tri-Axial Accelerometer Mounted on the Head for Monitoring the Activities of Daily Living and the Timed-up and Go Test. Gait Posture 2021, 90, 137–140. [Google Scholar] [CrossRef]
- Higashi, Y.; Yamakoshi, K.; Fujimoto, T.; Sekine, M.; Tamura, T. Quantitative Evaluation of Movement Using the Timed Up-and-Go Test. IEEE Eng. Med. Biol. Mag. 2008, 27, 38–46. [Google Scholar] [CrossRef]
- Hellmers, S.; Izadpanah, B.; Dasenbrock, L.; Diekmann, R.; Bauer, J.M.; Hein, A.; Fudickar, S. Towards an Automated Unsupervised Mobility Assessment for Older People Based on Inertial TUG Measurements. Sensors 2018, 18, 3310. [Google Scholar] [CrossRef] [PubMed]
- De Luca, V.; Muaremi, A.; Giggins, O.M.; Walsh, L.; Clay, I. Towards Fully Instrumented and Automated Assessment of Motor Function Tests. In Proceedings of the 2018 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI), Las Vegas, NV, USA, 4–7 March 2018; pp. 83–87. [Google Scholar]
- Adame, M.R.; Al-Jawad, A.; Romanovas, M.; Hobert, M.A.; Maetzler, W.; Möller, K.; Manoli, Y. TUG Test Instrumentation for Parkinson’s Disease Patients Using Inertial Sensors and Dynamic Time Warping. Biomed. Eng./Biomed. Tech. 2012, 57, 1071–1074. [Google Scholar] [CrossRef]
- Ortega-Bastidas, P.; Aqueveque, P.; Gómez, B.; Saavedra, F.; Cano-de-la-Cuerda, R. Use of a Single Wireless IMU for the Segmentation and Automatic Analysis of Activities Performed in the 3-m Timed Up & Go Test. Sensors 2019, 19, 1647. [Google Scholar] [CrossRef] [PubMed]
- Negrini, S.; Serpelloni, M.; Amici, C.; Gobbo, M.; Silvestro, C.; Buraschi, R.; Borboni, A.; Crovato, D.; Lopomo, N.F. Use of Wearable Inertial Sensor in the Assessment of Timed-Up-and-Go Test: Influence of Device Placement on Temporal Variable Estimation. In Wireless Mobile Communication and Healthcare: 6th International Conference, MobiHealth 2016; Perego, P., Andreoni, G., Rizzo, G., Eds.; Springer International Publishing: Berlin/Heidelberg, Germany, 2017; pp. 310–317. [Google Scholar]
- Weiss, A.; Herman, T.; Plotnik, M.; Brozgol, M.; Maidan, I.; Giladi, N.; Gurevich, T.; Hausdorff, J.M. Can an Accelerometer Enhance the Utility of the Timed Up & Go Test When Evaluating Patients with Parkinson’s Disease? Med. Eng. Phys. 2010, 32, 119–125. [Google Scholar] [CrossRef]
- Silva, J.; Sousa, I. Instrumented Timed up and Go: Fall Risk Assessment Based on Inertial Wearable Sensors. In Proceedings of the 2016 IEEE International Symposium on Medical Measurements and Applications (MeMeA), Benevento, Italy, 15–18 May 2016; pp. 1–6. [Google Scholar]
- Salarian, A.; Horak, F.B.; Zampieri, C.; Carlson-Kuhta, P.; Nutt, J.G.; Aminian, K. iTUG, a Sensitive and Reliable Measure of Mobility. IEEE Trans. Neural Syst. Rehabil. Eng. 2010, 18, 303–310. [Google Scholar] [CrossRef] [PubMed]
- Vervoort, D.; Vuillerme, N.; Kosse, N.; Hortobágyi, T.; Lamoth, C.J.C. Multivariate Analyses and Classification of Inertial Sensor Data to Identify Aging Effects on the Timed-Up-and-Go Test. PLoS ONE 2016, 11, e0155984. [Google Scholar] [CrossRef] [PubMed]
- Miller Koop, M.; Ozinga, S.J.; Rosenfeldt, A.B.; Alberts, J.L. Quantifying Turning Behavior and Gait in Parkinson’s Disease Using Mobile Technology. IBRO Rep. 2018, 5, 10–16. [Google Scholar] [CrossRef] [PubMed]
- Milosevic, M.; Jovanov, E.; Milenković, A. Quantifying Timed-Up-and-Go Test: A Smartphone Implementation. In Proceedings of the 2013 IEEE International Conference on Body Sensor Networks, Cambridge, MA, USA, 6–9 May 2013. [Google Scholar]
- Zakaria, N.A.; Kuwae, Y.; Tamura, T.; Minato, K.; Kanaya, S. Quantitative Analysis of Fall Risk Using TUG Test. Comput. Methods Biomech. Biomed. Eng. 2013, 18, 426–437. [Google Scholar] [CrossRef] [PubMed]
- Greene, B.R.; O’Donovan, A.; Romero-Ortuno, R.; Cogan, L.; Scanaill, C.N.; Kenny, R.A. Quantitative Falls Risk Assessment Using the Timed Up and Go Test. IEEE Trans. Biomed. Eng. 2010, 57, 2918–2926. [Google Scholar] [CrossRef] [PubMed]
- Witchel, H.J.; Oberndorfer, C.; Needham, R.; Healy, A.; Westling, C.E.I.; Guppy, J.H.; Bush, J.; Barth, J.; Herberz, C.; Roggen, D.; et al. Thigh-Derived Inertial Sensor Metrics to Assess the Sit-to-Stand and Stand-to-Sit Transitions in the Timed Up and Go (TUG) Task for Quantifying Mobility Impairment in Multiple Sclerosis. EC Neurol. 2018, 9, 689–695. [Google Scholar] [CrossRef] [PubMed]
- Capela, N.A.; Lemaire, E.D.; Baddour, N. Novel Algorithm for a Smartphone-Based 6-Minute Walk Test Application: Algorithm, Application Development, and Evaluation. J. Neuroeng. Rehabil. 2015, 12, 19. [Google Scholar] [CrossRef] [PubMed]
- Use of Mobile Device Accelerometry to Enhance Evaluation of Postural Instability in Parkinson Disease—ScienceDirect. Available online: https://www.sciencedirect.com/science/article/pii/S0003999316309856 (accessed on 6 December 2023).
- McCreath Frangakis, A.L.; Lemaire, E.D.; Baddour, N. Subtask Segmentation of the L Test Using Smartphone Inertial Measurement Units. In Proceedings of the 2023 5th International Conference on Bio-engineering for Smart Technologies (BioSMART), Paris, France, 7–9 June 2023; pp. 1–4. [Google Scholar]
- McCreath Frangakis, A.L.; Lemaire, E.D.; Baddour, N. A Smartphone-Based Algorithm for L Test Subtask Segmentation. BioMedInformatics 2024, 4, 1262–1274. [Google Scholar] [CrossRef]
- McCreath Frangakis, A.L.; Baddour, N.; Burger, H.; Lemaire, E.D. A Smartphone-Based Algorithm for L Test Subtask Segmentation Applied to a Lower Limb Amputee Population. In Proceedings of the 24th Congress of the European Society for Physical and Rehabilitation Medicine, Ljubljana, Slovenia, 23–27 April 2024. [Google Scholar]
- Juneau, P.; Lemaire, E.D.; Bavec, A.; Burger, H.; Baddour, N. Automated Step Detection with 6-Minute Walk Test Smartphone Sensors Signals for Fall Risk Classification in Lower Limb Amputees. PLoS Digit. Health 2022, 1, e0000088. [Google Scholar] [CrossRef]
- Pew, C.; Klute, G.K. Turn Intent Detection For Control of a Lower Limb Prosthesis. IEEE Trans. Biomed. Eng. 2018, 65, 789–796. [Google Scholar] [CrossRef]
- Shi, L.-F.; Qiu, C.-X.; Xin, D.-J.; Liu, G.-X. Gait Recognition via Random Forests Based on Wearable Inertial Measurement Unit. J. Ambient. Intell. Hum. Comput. 2020, 11, 5329–5340. [Google Scholar] [CrossRef]
- Khaksar, S.; Pan, H.; Borazjani, B.; Murray, I.; Agrawal, H.; Liu, W.; Elliott, C.; Imms, C.; Campbell, A.; Walmsley, C. Application of Inertial Measurement Units and Machine Learning Classification in Cerebral Palsy: Randomized Controlled Trial. JMIR Rehabil. Assist. Technol. 2021, 8, e29769. [Google Scholar] [CrossRef] [PubMed]
- Hua, A.; Chaudhari, P.; Johnson, N.; Quinton, J.; Schatz, B.; Buchner, D.; Hernandez, M.E. Evaluation of Machine Learning Models for Classifying Upper Extremity Exercises Using Inertial Measurement Unit-Based Kinematic Data. IEEE J. Biomed. Health Inform. 2020, 24, 2452–2460. [Google Scholar] [CrossRef] [PubMed]
- VSDC Free Video Software: Complete Toolset for Video Editing. 2023. Available online: https://www.videosoftdev.com/ (accessed on 6 December 2023).
- Hsieh, C.-Y.; Huang, H.-Y.; Liu, K.-C.; Chen, K.-H.; Hsu, S.J.-P.; Chan, C.-T. Subtask Segmentation of Timed Up and Go Test for Mobility Assessment of Perioperative Total Knee Arthroplasty. Sensors 2020, 20, 6302. [Google Scholar] [CrossRef] [PubMed]
- Sklearn.Ensemble.RandomForestClassifier. Available online: https://scikit-learn/stable/modules/generated/sklearn.ensemble.RandomForestClassifier.html (accessed on 25 March 2024).
- Sklearn.Model_selection.GridSearchCV. Available online: https://scikit-learn/stable/modules/generated/sklearn.model_selection.GridSearchCV.html (accessed on 5 April 2024).
Age | Sex | Able-Bodied | Amputee |
---|---|---|---|
18–29 | Male | 3 | 0 |
Female | 9 | 1 | |
30–39 | Male | 0 | 0 |
Female | 1 | 1 | |
40–49 | Male | 0 | 0 |
Female | 0 | 4 | |
50–59 | Male | 2 | 3 |
Female | 4 | 3 | |
60–69 | Male | 1 | 8 |
Female | 1 | 1 | |
70–79 | Male | 0 | 1 |
Female | 0 | 0 | |
80–89 | Male | 0 | 3 |
Female | 0 | 0 |
Characteristic | Number of Participants |
---|---|
Congenital | 1 (4%) |
Injury | 5 (20%) |
Peripheral Vascular Disease | 5 (20%) |
Diabetes Mellitus | 9 (36%) |
Other | 4 (16%) |
Unilateral | 23 (88%) |
Bilateral | 2 (8%) |
Ankle Exarticulation | 2 1 (8%) |
Transtibial | 22 1,2 (81%) |
Knee Exarticulation | 2 (8%) |
Transfemoral | 1 (4%) |
No Aids | 20 (80%) |
Single Crutch | 5 (20%) |
Subtask | Earliest Instance (%) | Latest Instance (%) |
---|---|---|
Stand-Up | 0 | 31 |
First 90° Turn | 10 | 42 |
First 180° Turn | 36 | 63 |
Second 90° Turn | 61 | 84 |
Second 180° Turn | 72 | 97 |
Sit-Down | 76 | 100 |
Subtask | AccuracyAD (%) | Trees | Number of Features | Direction of Analysis |
---|---|---|---|---|
Start of Stand-Up | 96 | 250 | 5 | Forward |
End of Stand-Up | 96 | 250 | 50 | Forward |
Start of First 90° Turn | 92 | 1000 | 10 | Forward |
End of First 90° Turn | 76 | 1000 | 10 | Forward |
Start of First 180° Turn | 80 | 500 | 25 | Forward |
End of First 180° Turn | 92 | 500 | 75 | Forward |
Start of Second 90° Turn | 92 | 500 | 5 | Reversed |
End of Second 90° Turn | 72 | 500 | 5 | Reversed |
Start of Second 180° Turn | 76 | 250 | 5 | Reversed |
End of Second 180° Turn | 84 | 250 | 5 | Reversed |
Start of Sit-Down | 92 | 1000 | 75 | Reversed |
End of Sit-Down | 92 | 1000 | 75 | Reversed |
Stand-Up | First 90-Degree Turn | First 180-Degree Turn | Second 90-Degree Turn | Second 180-Degree Turn | Sit-Down |
---|---|---|---|---|---|
Linear Acceleration X Minimum | Azimuth Range | Azimuth Range | Azimuth Range | Azimuth Range | Pitch Maximum |
Pitch Maximum | Azimuth Standard Deviation | Azimuth Standard Deviation | Azimuth Standard Deviation | Azimuth Standard Deviation | Pitch Mean |
Linear Acceleration X | Gyroscope Y Range | Azimuth Variation | Azimuth Variation | Azimuth Variation | Pitch |
Pitch Standard Deviation | Gyroscope Y Standard Deviation | Gyroscope Y Maximum | Gyroscope Y Minimum | Gyroscope Y Range | Pitch Range |
Pitch Range | Azimuth Variation | Gyroscope Y Range | Azimuth Kurtosis | Gyroscope Y Standard Deviation | Pitch Standard Deviation |
Gyroscope X Range | Linear Acceleration Y Standard Deviation | Linear Acceleration Y Standard Deviation | Gyroscope Y | Gyroscope Y Variation | Gyroscope X Range |
Gyroscope X Standard Deviation | Linear Acceleration Y Range | Linear Acceleration Y Range | Gyroscope Y Mean | Gyroscope X | Pitch Minimum |
Linear Acceleration X Mean | System Time | Gyroscope Y | Gyroscope Y Maximum | Linear Acceleration X Minimum | Gyroscope X Standard Deviation |
Linear Acceleration X Range | Gyroscope Y | Gyroscope Y Standard Deviation | Roll | Linear Acceleration X | Pitch Variation |
Pitch Mean | Gyroscope Y Maximum | Gyroscope Y Mean | Roll Minimum | Linear Acceleration X Mean | Gyroscope X Variation |
Subtask | Accuracy (%) | Sensitivity (%) | Specificity (%) |
---|---|---|---|
Stand-Up | 95 | 92 | 100 |
First 90° Turn | 97 | 77 | 100 |
First 180° Turn | 98 | 87 | 98 |
Second 90° Turn | 85 | 75 | 95 |
Second 180° Turn | 88 | 85 | 99 |
Sit-Down | 98 | 77 | 100 |
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. |
© 2024 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
McCreath Frangakis, A.L.; Lemaire, E.D.; Burger, H.; Baddour, N. L Test Subtask Segmentation for Lower-Limb Amputees Using a Random Forest Algorithm. Sensors 2024, 24, 4953. https://doi.org/10.3390/s24154953
McCreath Frangakis AL, Lemaire ED, Burger H, Baddour N. L Test Subtask Segmentation for Lower-Limb Amputees Using a Random Forest Algorithm. Sensors. 2024; 24(15):4953. https://doi.org/10.3390/s24154953
Chicago/Turabian StyleMcCreath Frangakis, Alexis L., Edward D. Lemaire, Helena Burger, and Natalie Baddour. 2024. "L Test Subtask Segmentation for Lower-Limb Amputees Using a Random Forest Algorithm" Sensors 24, no. 15: 4953. https://doi.org/10.3390/s24154953