A Machine Learning Framework for Gait Classification Using Inertial Sensors: Application to Elderly, Post-Stroke and Huntington's Disease Patients

Overview

Journal Sensors (Basel)

Publisher MDPI

Specialty Biotechnology

Date 2016 Jan 26

PMID 26805847

Citations 59

Authors

Andrea Mannini

Diana Trojaniello

Andrea Cereatti

Angelo M Sabatini

Affiliations

Soon will be listed here.

Abstract

Machine learning methods have been widely used for gait assessment through the estimation of spatio-temporal parameters. As a further step, the objective of this work is to propose and validate a general probabilistic modeling approach for the classification of different pathological gaits. Specifically, the presented methodology was tested on gait data recorded on two pathological populations (Huntington's disease and post-stroke subjects) and healthy elderly controls using data from inertial measurement units placed at shank and waist. By extracting features from group-specific Hidden Markov Models (HMMs) and signal information in time and frequency domain, a Support Vector Machines classifier (SVM) was designed and validated. The 90.5% of subjects was assigned to the right group after leave-one-subject-out cross validation and majority voting. The long-term goal we point to is the gait assessment in everyday life to early detect gait alterations.

Citing Articles

Quantitative evaluation method of stroke association based on multidimensional gait parameters by using machine learning.

Wang C, Long Z, Wang X, Kong Y, Zhou L, Jia W Front Neuroinform. 2025; 19:1544372.

PMID: 40012766 PMC: 11861528. DOI: 10.3389/fninf.2025.1544372.

Artificial Intelligence in the Diagnosis and Quantitative Phenotyping of Hyperkinetic Movement Disorders: A Systematic Review.

Vizcarra J, Yarlagadda S, Xie K, Ellis C, Spindler M, Hammer L J Clin Med. 2024; 13(23).

PMID: 39685480 PMC: 11642074. DOI: 10.3390/jcm13237009.

CNN-Based Neurodegenerative Disease Classification Using QR-Represented Gait Data.

Erdas C, Sumer E Brain Behav. 2024; 14(10):e70100.

PMID: 39465642 PMC: 11513673. DOI: 10.1002/brb3.70100.

Automatic selection model to identify neurodegenerative diseases.

Sanchez-DelaCruz E, Loeza-Mejia C, Primero-Huerta C, Fuentes-Ramos M Digit Health. 2024; 10:20552076241284376.

PMID: 39372807 PMC: 11456181. DOI: 10.1177/20552076241284376.

Optimizing Rare Disease Gait Classification through Data Balancing and Generative AI: Insights from Hereditary Cerebellar Ataxia.

Trabassi D, Castiglia S, Bini F, Marinozzi F, Ajoudani A, Lorenzini M Sensors (Basel). 2024; 24(11).

PMID: 38894404 PMC: 11175240. DOI: 10.3390/s24113613.

References

Holden M, Gill K, Magliozzi M, Nathan J . Clinical gait assessment in the neurologically impaired. Reliability and meaningfulness. Phys Ther. 1984; 64(1):35-40. DOI: 10.1093/ptj/64.1.35. View

Favre J, Aissaoui R, Jolles B, de Guise J, Aminian K . Functional calibration procedure for 3D knee joint angle description using inertial sensors. J Biomech. 2009; 42(14):2330-5. DOI: 10.1016/j.jbiomech.2009.06.025. View

Mannini A, Sabatini A, Intille S . Accelerometry-based Recognition of the Placement Sites of a Wearable Sensor. Pervasive Mob Comput. 2015; 21:62-74. PMC: 4510470. DOI: 10.1016/j.pmcj.2015.06.003. View

Taborri J, Rossi S, Palermo E, Patane F, Cappa P . A novel HMM distributed classifier for the detection of gait phases by means of a wearable inertial sensor network. Sensors (Basel). 2014; 14(9):16212-34. PMC: 4208171. DOI: 10.3390/s140916212. View

Rao A, Quinn L, Marder K . Reliability of spatiotemporal gait outcome measures in Huntington's disease. Mov Disord. 2005; 20(8):1033-7. DOI: 10.1002/mds.20482. View

Begg R, Palaniswami M, Owen B . Support vector machines for automated gait classification. IEEE Trans Biomed Eng. 2005; 52(5):828-38. DOI: 10.1109/TBME.2005.845241. View

Rueterbories J, Spaich E, Larsen B, Andersen O . Methods for gait event detection and analysis in ambulatory systems. Med Eng Phys. 2010; 32(6):545-52. DOI: 10.1016/j.medengphy.2010.03.007. View

Mannini A, Genovese V, Sabatini A . Online decoding of hidden Markov models for gait event detection using foot-mounted gyroscopes. IEEE J Biomed Health Inform. 2014; 18(4):1122-30. DOI: 10.1109/JBHI.2013.2293887. View

Mannini A, Sabatini A . Walking speed estimation using foot-mounted inertial sensors: comparing machine learning and strap-down integration methods. Med Eng Phys. 2014; 36(10):1312-21. DOI: 10.1016/j.medengphy.2014.07.022. View

10.

Pfau T, Ferrari M, Parsons K, Wilson A . A hidden Markov model-based stride segmentation technique applied to equine inertial sensor trunk movement data. J Biomech. 2007; 41(1):216-20. DOI: 10.1016/j.jbiomech.2007.08.004. View

11.

Mannini A, Trojaniello D, Croce U, Sabatini A . Hidden Markov model-based strategy for gait segmentation using inertial sensors: Application to elderly, hemiparetic patients and Huntington's disease patients. Annu Int Conf IEEE Eng Med Biol Soc. 2016; 2015:5179-82. DOI: 10.1109/EMBC.2015.7319558. View

12.

Trojaniello D, Cereatti A, Pelosin E, Avanzino L, Mirelman A, Hausdorff J . Estimation of step-by-step spatio-temporal parameters of normal and impaired gait using shank-mounted magneto-inertial sensors: application to elderly, hemiparetic, parkinsonian and choreic gait. J Neuroeng Rehabil. 2014; 11:152. PMC: 4242591. DOI: 10.1186/1743-0003-11-152. View

13.

Picerno P, Cereatti A, Cappozzo A . Joint kinematics estimate using wearable inertial and magnetic sensing modules. Gait Posture. 2008; 28(4):588-95. DOI: 10.1016/j.gaitpost.2008.04.003. View

14.

Mannini A, Sabatini A . Machine learning methods for classifying human physical activity from on-body accelerometers. Sensors (Basel). 2011; 10(2):1154-75. PMC: 3244008. DOI: 10.3390/s100201154. View

15.

Chen G, Patten C, Kothari D, Zajac F . Gait differences between individuals with post-stroke hemiparesis and non-disabled controls at matched speeds. Gait Posture. 2005; 22(1):51-6. DOI: 10.1016/j.gaitpost.2004.06.009. View

16.

Picerno P, Cereatti A, Cappozzo A . A spot check for assessing static orientation consistency of inertial and magnetic sensing units. Gait Posture. 2011; 33(3):373-8. DOI: 10.1016/j.gaitpost.2010.12.006. View

17.

Troiano R, Berrigan D, Dodd K, Masse L, Tilert T, McDowell M . Physical activity in the United States measured by accelerometer. Med Sci Sports Exerc. 2007; 40(1):181-8. DOI: 10.1249/mss.0b013e31815a51b3. View

18.

Mannini A, Intille S, Rosenberger M, Sabatini A, Haskell W . Activity recognition using a single accelerometer placed at the wrist or ankle. Med Sci Sports Exerc. 2013; 45(11):2193-203. PMC: 3795931. DOI: 10.1249/MSS.0b013e31829736d6. View

19.

Yang S, Zhang J, Novak A, Brouwer B, Li Q . Estimation of spatio-temporal parameters for post-stroke hemiparetic gait using inertial sensors. Gait Posture. 2012; 37(3):354-8. DOI: 10.1016/j.gaitpost.2012.07.032. View

20.

Mannini A, Sabatini A . Gait phase detection and discrimination between walking-jogging activities using hidden Markov models applied to foot motion data from a gyroscope. Gait Posture. 2012; 36(4):657-61. DOI: 10.1016/j.gaitpost.2012.06.017. View