1
|
Voisard C, de l'Escalopier N, Ricard D, Oudre L. Automatic gait events detection with inertial measurement units: healthy subjects and moderate to severe impaired patients. J Neuroeng Rehabil 2024; 21:104. [PMID: 38890696 PMCID: PMC11184826 DOI: 10.1186/s12984-024-01405-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/08/2023] [Accepted: 06/11/2024] [Indexed: 06/20/2024] Open
Abstract
BACKGROUND Recently, the use of inertial measurement units (IMUs) in quantitative gait analysis has been widely developed in clinical practice. Numerous methods have been developed for the automatic detection of gait events (GEs). While many of them have achieved high levels of efficiency in healthy subjects, detecting GEs in highly degraded gait from moderate to severely impaired patients remains a challenge. In this paper, we aim to present a method for improving GE detection from IMU recordings in such cases. METHODS We recorded 10-meter gait IMU signals from 13 healthy subjects, 29 patients with multiple sclerosis, and 21 patients with post-stroke equino varus foot. An instrumented mat was used as the gold standard. Our method detects GEs from filtered acceleration free from gravity and gyration signals. Firstly, we use autocorrelation and pattern detection techniques to identify a reference stride pattern. Next, we apply multiparametric Dynamic Time Warping to annotate this pattern from a model stride, in order to detect all GEs in the signal. RESULTS We analyzed 16,819 GEs recorded from healthy subjects and achieved an F1-score of 100%, with a median absolute error of 8 ms (IQR [3-13] ms). In multiple sclerosis and equino varus foot cohorts, we analyzed 6067 and 8951 GEs, respectively, with F1-scores of 99.4% and 96.3%, and median absolute errors of 18 ms (IQR [8-39] ms) and 26 ms (IQR [12-50] ms). CONCLUSIONS Our results are consistent with the state of the art for healthy subjects and demonstrate a good accuracy in GEs detection for pathological patients. Therefore, our proposed method provides an efficient way to detect GEs from IMU signals, even in degraded gaits. However, it should be evaluated in each cohort before being used to ensure its reliability.
Collapse
Affiliation(s)
- Cyril Voisard
- Université Paris Saclay, Université Paris Cité, ENS Paris Saclay, CNRS, SSA, INSERM, Centre Borelli, Gif-sur-Yvette, France.
- Service de Neurologie, Service de Santé des Armées, HIA Percy, Clamart, France.
| | - Nicolas de l'Escalopier
- Université Paris Cité, Université Paris Saclay, ENS Paris Saclay, CNRS, SSA, INSERM, Centre Borelli, Paris, France
- Service de Chirurgie Orthopédique, Traumatologique et Réparatrice des Membres, Service de Santé des Armées, HIA Percy, Clamart, France
| | - Damien Ricard
- Université Paris Cité, Université Paris Saclay, ENS Paris Saclay, CNRS, SSA, INSERM, Centre Borelli, Paris, France
- Service de Neurologie, Service de Santé des Armées, HIA Percy, Clamart, France
- Ecole du Val-de-Grâce, Service de Santé des Armées, Paris, France
| | - Laurent Oudre
- Université Paris Saclay, Université Paris Cité, ENS Paris Saclay, CNRS, SSA, INSERM, Centre Borelli, Gif-sur-Yvette, France
| |
Collapse
|
2
|
Dammeyer C, Nüesch C, Visscher RMS, Kim YK, Ismailidis P, Wittauer M, Stoffel K, Acklin Y, Egloff C, Netzer C, Mündermann A. Classification of inertial sensor-based gait patterns of orthopaedic conditions using machine learning: A pilot study. J Orthop Res 2024. [PMID: 38341759 DOI: 10.1002/jor.25797] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/10/2023] [Revised: 12/21/2023] [Accepted: 01/19/2024] [Indexed: 02/13/2024]
Abstract
Elderly patients often have more than one disease that affects walking behavior. An objective tool to identify which disease is the main cause of functional limitations may aid clinical decision making. Therefore, we investigated whether gait patterns could be used to identify degenerative diseases using machine learning. Data were extracted from a clinical database that included sagittal joint angles and spatiotemporal parameters measured using seven inertial sensors, and anthropometric data of patients with unilateral knee or hip osteoarthritis, lumbar or cervical spinal stenosis, and healthy controls. Various classification models were explored using the MATLAB Classification Learner app, and the optimizable Support Vector Machine was chosen as the best performing model. The accuracy of discrimination between healthy and pathologic gait was 82.3%, indicating that it is possible to distinguish pathological from healthy gait. The accuracy of discrimination between the different degenerative diseases was 51.4%, indicating the similarities in gait patterns between diseases need to be further explored. Overall, the differences between pathologic and healthy gait are distinct enough to classify using a classical machine learning model; however, routinely recorded gait characteristics and anthropometric data are not sufficient for successful discrimination of the degenerative diseases.
Collapse
Affiliation(s)
- Constanze Dammeyer
- Department of Orthopaedics and Traumatology, University Hospital Basel, Basel, Switzerland
- Department of Psychology and Sport Science, University of Bielefeld, Bielefeld, Germany
| | - Corina Nüesch
- Department of Orthopaedics and Traumatology, University Hospital Basel, Basel, Switzerland
- Department of Biomedical Engineering, University of Basel, Basel, Switzerland
- Department of Clinical Research, University of Basel, Basel, Switzerland
- Department of Spine Surgery, University Hospital Basel, Basel, Switzerland
| | - Rosa M S Visscher
- Department of Biomedical Engineering, University of Basel, Basel, Switzerland
- Institute for Biomechanics, ETH Zürich, Zürich, Switzerland
| | - Yong K Kim
- Institute for Biomechanics, ETH Zürich, Zürich, Switzerland
| | - Petros Ismailidis
- Department of Orthopaedics and Traumatology, University Hospital Basel, Basel, Switzerland
| | - Matthias Wittauer
- Department of Orthopaedics and Traumatology, University Hospital Basel, Basel, Switzerland
| | - Karl Stoffel
- Department of Orthopaedics and Traumatology, University Hospital Basel, Basel, Switzerland
| | - Yves Acklin
- Department of Orthopaedics and Traumatology, University Hospital Basel, Basel, Switzerland
| | - Christian Egloff
- Department of Orthopaedics and Traumatology, University Hospital Basel, Basel, Switzerland
| | - Cordula Netzer
- Department of Biomedical Engineering, University of Basel, Basel, Switzerland
- Department of Clinical Research, University of Basel, Basel, Switzerland
- Department of Spine Surgery, University Hospital Basel, Basel, Switzerland
| | - Annegret Mündermann
- Department of Orthopaedics and Traumatology, University Hospital Basel, Basel, Switzerland
- Department of Biomedical Engineering, University of Basel, Basel, Switzerland
- Department of Clinical Research, University of Basel, Basel, Switzerland
| |
Collapse
|
3
|
Marimon X, Mengual I, López-de-Celis C, Portela A, Rodríguez-Sanz J, Herráez IA, Pérez-Bellmunt A. Kinematic Analysis of Human Gait in Healthy Young Adults Using IMU Sensors: Exploring Relevant Machine Learning Features for Clinical Applications. Bioengineering (Basel) 2024; 11:105. [PMID: 38391591 PMCID: PMC10886386 DOI: 10.3390/bioengineering11020105] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/27/2023] [Revised: 10/12/2023] [Accepted: 01/22/2024] [Indexed: 02/24/2024] Open
Abstract
BACKGROUND Gait is the manner or style of walking, involving motor control and coordination to adapt to the surrounding environment. Knowing the kinesthetic markers of normal gait is essential for the diagnosis of certain pathologies or the generation of intelligent ortho-prostheses for the treatment or prevention of gait disorders. The aim of the present study was to identify the key features of normal human gait using inertial unit (IMU) recordings in a walking test. METHODS Gait analysis was conducted on 32 healthy participants (age range 19-29 years) at speeds of 2 km/h and 4 km/h using a treadmill. Dynamic data were obtained using a microcontroller (Arduino Nano 33 BLE Sense Rev2) with IMU sensors (BMI270). The collected data were processed and analyzed using a custom script (MATLAB 2022b), including the labeling of the four relevant gait phases and events (Stance, Toe-Off, Swing, and Heel Strike), computation of statistical features (64 features), and application of machine learning techniques for classification (8 classifiers). RESULTS Spider plot analysis revealed significant differences in the four events created by the most relevant statistical features. Among the different classifiers tested, the Support Vector Machine (SVM) model using a Cubic kernel achieved an accuracy rate of 92.4% when differentiating between gait events using the computed statistical features. CONCLUSIONS This study identifies the optimal features of acceleration and gyroscope data during normal gait. The findings suggest potential applications for injury prevention and performance optimization in individuals engaged in activities involving normal gait. The creation of spider plots is proposed to obtain a personalised fingerprint of each patient's gait fingerprint that could be used as a diagnostic tool. A deviation from a normal gait pattern can be used to identify human gait disorders. Moving forward, this information has potential for use in clinical applications in the diagnosis of gait-related disorders and developing novel orthoses and prosthetics to prevent falls and ankle sprains.
Collapse
Affiliation(s)
- Xavier Marimon
- Bioengineering Institute of Technology, Universitat Internacional de Catalunya (UIC), 08195 Barcelona, Spain
- Automatic Control Department, Universitat Politècnica de Catalunya (UPC-BarcelonaTECH), 08034 Barcelona, Spain
- Institut de Recerca Sant Joan de Déu (IRSJD), 08950 Barcelona, Spain
| | - Itziar Mengual
- Bioengineering Institute of Technology, Universitat Internacional de Catalunya (UIC), 08195 Barcelona, Spain
| | - Carlos López-de-Celis
- ACTIUM Research Group, Universitat Internacional de Catalunya (UIC), 08195 Barcelona, Spain
- Institut Universitari d'Investigació en Atenció Primària (IDIAP Jordi Gol), 08007 Barcelona, Spain
| | - Alejandro Portela
- Bioengineering Institute of Technology, Universitat Internacional de Catalunya (UIC), 08195 Barcelona, Spain
| | - Jacobo Rodríguez-Sanz
- ACTIUM Research Group, Universitat Internacional de Catalunya (UIC), 08195 Barcelona, Spain
| | - Iria Andrea Herráez
- Bioengineering Institute of Technology, Universitat Internacional de Catalunya (UIC), 08195 Barcelona, Spain
| | - Albert Pérez-Bellmunt
- ACTIUM Research Group, Universitat Internacional de Catalunya (UIC), 08195 Barcelona, Spain
| |
Collapse
|
4
|
Bibbo D, De Marchis C, Schmid M, Ranaldi S. Machine learning to detect, stage and classify diseases and their symptoms based on inertial sensor data: a mapping review. Physiol Meas 2023; 44:12TR01. [PMID: 38061062 DOI: 10.1088/1361-6579/ad133b] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/19/2023] [Accepted: 12/07/2023] [Indexed: 12/27/2023]
Abstract
This article presents a systematic review aimed at mapping the literature published in the last decade on the use of machine learning (ML) for clinical decision-making through wearable inertial sensors. The review aims to analyze the trends, perspectives, strengths, and limitations of current literature in integrating ML and inertial measurements for clinical applications. The review process involved defining four research questions and applying four relevance assessment indicators to filter the search results, providing insights into the pathologies studied, technologies and setups used, data processing schemes, ML techniques applied, and their clinical impact. When combined with ML techniques, inertial measurement units (IMUs) have primarily been utilized to detect and classify diseases and their associated motor symptoms. They have also been used to monitor changes in movement patterns associated with the presence, severity, and progression of pathology across a diverse range of clinical conditions. ML models trained with IMU data have shown potential in improving patient care by objectively classifying and predicting motor symptoms, often with a minimally encumbering setup. The findings contribute to understanding the current state of ML integration with wearable inertial sensors in clinical practice and identify future research directions. Despite the widespread adoption of these technologies and techniques in clinical applications, there is still a need to translate them into routine clinical practice. This underscores the importance of fostering a closer collaboration between technological experts and professionals in the medical field.
Collapse
Affiliation(s)
- Daniele Bibbo
- Department of Industrial, Electronic and Mechanical Engineering, Roma Tre University, Rome, Italy
| | | | - Maurizio Schmid
- Department of Industrial, Electronic and Mechanical Engineering, Roma Tre University, Rome, Italy
| | - Simone Ranaldi
- Department of Industrial, Electronic and Mechanical Engineering, Roma Tre University, Rome, Italy
| |
Collapse
|
5
|
Katmah R, Shehhi AA, Jelinek HF, Hulleck AA, Khalaf K. A Systematic Review of Gait Analysis in the Context of Multimodal Sensing Fusion and AI. IEEE Trans Neural Syst Rehabil Eng 2023; 31:4189-4202. [PMID: 37847624 DOI: 10.1109/tnsre.2023.3325215] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/19/2023]
Abstract
BACKGROUND Neurological diseases are a leading cause of disability and mortality. Gait, or human walking, is a significant predictor of quality of life, morbidity, and mortality. Gait patterns and other kinematic, kinetic, and balance gait features are accurate and powerful diagnostic and prognostic tools. OBJECTIVE This review article focuses on the applicability of gait analysis using fusion techniques and artificial intelligence (AI) models. The aim is to examine the significance of mixing several types of wearable and non-wearable sensor data and the impact of this combination on the performance of AI models. METHOD In this systematic review, 66 studies using more than two modalities to record and analyze gait were identified. 40 studies incorporated multiple gait analysis modalities without the use of artificial intelligence to extract gait features such as kinematic, kinetic, margin of stability, temporal, and spatial gait parameters, as well as cerebral activity. Similarly, 26 studies analyzed gait data using multimodal fusion sensors and AI algorithms. RESULTS The research summarized here demonstrates that the quality of gait analysis and the effectiveness of AI models can both benefit from the integration of data from many sensors. Meanwhile, the utilization of EMG signals in fusion data is especially advantageous. CONCLUSION The findings of this review suggest that a smart, portable, wearable-based gait and balance assessment system can be developed using multimodal sensing of the most cutting-edge, clinically relevant tools and technology available. The information presented in this article may serve as a vital springboard for such development.
Collapse
|
6
|
Bi CL, Kurland DB, Ber R, Kondziolka D, Lau D, Pacione D, Frempong-Boadu A, Laufer I, Oermann EK. Digital Biomarkers and the Evolution of Spine Care Outcomes Measures: Smartphones and Wearables. Neurosurgery 2023; 93:745-754. [PMID: 37246874 DOI: 10.1227/neu.0000000000002519] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/19/2022] [Accepted: 03/19/2023] [Indexed: 05/30/2023] Open
Abstract
Over the past generation, outcome measures in spine care have evolved from a reliance on clinician-reported assessment toward recognizing the importance of the patient's perspective and the wide incorporation of patient-reported outcomes (PROs). While patient-reported outcomes are now considered an integral component of outcomes assessments, they cannot wholly capture the state of a patient's functionality. There is a clear need for quantitative and objective patient-centered outcome measures. The pervasiveness of smartphones and wearable devices in modern society, which passively collect data related to health, has ushered in a new era of spine care outcome measurement. The patterns emerging from these data, so-called "digital biomarkers," can accurately describe characteristics of a patient's health, disease, or recovery state. Broadly, the spine care community has thus far concentrated on digital biomarkers related to mobility, although the researcher's toolkit is anticipated to expand in concert with advancements in technology. In this review of the nascent literature, we describe the evolution of spine care outcome measurements, outline how digital biomarkers can supplement current clinician-driven and patient-driven measures, appraise the present and future of the field in the modern era, as well as discuss present limitations and areas for further study, with a focus on smartphones (see Supplemental Digital Content , http://links.lww.com/NEU/D809 , for a similar appraisal of wearable devices).
Collapse
Affiliation(s)
- Christina L Bi
- Department of Neurological Surgery, New York University, New York , New York , USA
| | | | | | | | | | | | | | | | | |
Collapse
|
7
|
Zhao H, Cao J, Xie J, Liao WH, Lei Y, Cao H, Qu Q, Bowen C. Wearable sensors and features for diagnosis of neurodegenerative diseases: A systematic review. Digit Health 2023; 9:20552076231173569. [PMID: 37214662 PMCID: PMC10192816 DOI: 10.1177/20552076231173569] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/10/2023] [Accepted: 04/17/2023] [Indexed: 05/24/2023] Open
Abstract
Objective Neurodegenerative diseases affect millions of families around the world, while various wearable sensors and corresponding data analysis can be of great support for clinical diagnosis and health assessment. This systematic review aims to provide a comprehensive overview of the existing research that uses wearable sensors and features for the diagnosis of neurodegenerative diseases. Methods A systematic review was conducted of studies published between 2015 and 2022 in major scientific databases such as Web of Science, Google Scholar, PubMed, and Scopes. The obtained studies were analyzed and organized into the process of diagnosis: wearable sensors, feature extraction, and feature selection. Results The search led to 171 eligible studies included in this overview. Wearable sensors such as force sensors, inertial sensors, electromyography, electroencephalography, acoustic sensors, optical fiber sensors, and global positioning systems were employed to monitor and diagnose neurodegenerative diseases. Various features including physical features, statistical features, nonlinear features, and features from the network can be extracted from these wearable sensors, and the alteration of features toward neurodegenerative diseases was illustrated. Moreover, different kinds of feature selection methods such as filter, wrapper, and embedded methods help to find the distinctive indicator of the diseases and benefit to a better diagnosis performance. Conclusions This systematic review enables a comprehensive understanding of wearable sensors and features for the diagnosis of neurodegenerative diseases.
Collapse
Affiliation(s)
- Huan Zhao
- School of Mechanical Engineering, Xi’an Jiaotong University, Xi'an, P.R. China
| | - Junyi Cao
- School of Mechanical Engineering, Xi’an Jiaotong University, Xi'an, P.R. China
| | - Junxiao Xie
- School of Mechanical Engineering, Xi’an Jiaotong University, Xi'an, P.R. China
| | - Wei-Hsin Liao
- Department of Mechanical and Automation
Engineering, The Chinese University of Hong
Kong, Shatin, N.T., Hong Kong, China
| | - Yaguo Lei
- School of Mechanical Engineering, Xi’an Jiaotong University, Xi'an, P.R. China
| | - Hongmei Cao
- Department of Neurology, The First
Affiliated Hospital of Xi’an Jiaotong University, Xi’an, P.R. China
| | - Qiumin Qu
- Department of Neurology, The First
Affiliated Hospital of Xi’an Jiaotong University, Xi’an, P.R. China
| | - Chris Bowen
- Department of Mechanical Engineering, University of Bath, Bath, UK
| |
Collapse
|
8
|
Sandic Spaho R, Uhrenfeldt L, Fotis T, Kymre IG. Wearable devices in palliative care for people 65 years and older: A scoping review. Digit Health 2023; 9:20552076231181212. [PMID: 37426582 PMCID: PMC10328013 DOI: 10.1177/20552076231181212] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/28/2022] [Accepted: 05/24/2023] [Indexed: 07/11/2023] Open
Abstract
Objective The objective of this scoping review is to map existing evidence on the use of wearable devices in palliative care for older people. Methods The databases searched included MEDLINE (via Ovid), Cumulative Index to Nursing and Allied Health Literature (CINAHL) and Google Scholar, which was included to capture grey literature. Databases were searched in the English language, without date restrictions. Reviewed results included studies and reviews involving patients aged 65 years or older who were active users of non-invasive wearable devices in the context of palliative care, with no limitations on gender or medical condition. The review followed the Joanna Briggs Institute's comprehensive and systematic guidelines for conducting scoping reviews. Results Of the 1,520 reports identified through searching the databases, reference lists, and citations, six reports met our inclusion criteria. The types of wearable devices discussed in these reports were accelerometers and actigraph units. Wearable devices were found to be useful in various health conditions, as the patient monitoring data enabled treatment adjustments. The results are mapped in tables as well as a Preferred Reporting Items for Systematic reviews and Meta-Analyses extension for Scoping Reviews (PRISMA-ScR) chart. Conclusions The findings indicate limited and sparse evidence for the population group of patients aged 65 years and older in the palliative context. Hence, more research on this particular age group is needed. The available evidence shows the benefits of wearable device use in enabling patient-centred palliative care, treatment adjustments and symptom management, and reducing the need for patients to travel to clinics while maintaining communication with healthcare professionals.
Collapse
Affiliation(s)
- Rada Sandic Spaho
- Faculty of Nursing and Health Sciences, Nord University, Bodo, Norway
| | - Lisbeth Uhrenfeldt
- Faculty of Nursing and Health Sciences, Nord University, Bodo, Norway
- Danish Centre of Systematic Reviews: An
Affiliate Center of The Joanna Briggs Institute, The Center of Clinical Guidelines –
Clearing House, Aalborg University Denmark, Aalborg, Denmark
- Institute of Regional Health Research,
Lillebaelt University Hospital, Southern Danish University, Kolding, Denmark
| | - Theofanis Fotis
- School of Sport & Health Sciences,
Centre for Secure, Intelligent and Usable Systems, University of Brighton, Brighton, UK
| | | |
Collapse
|
9
|
Rana A, Dumka A, Singh R, Panda MK, Priyadarshi N. A Computerized Analysis with Machine Learning Techniques for the Diagnosis of Parkinson's Disease: Past Studies and Future Perspectives. Diagnostics (Basel) 2022; 12:2708. [PMID: 36359550 PMCID: PMC9689408 DOI: 10.3390/diagnostics12112708] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/12/2022] [Revised: 10/30/2022] [Accepted: 11/02/2022] [Indexed: 08/03/2023] Open
Abstract
According to the World Health Organization (WHO), Parkinson's disease (PD) is a neurodegenerative disease of the brain that causes motor symptoms including slower movement, rigidity, tremor, and imbalance in addition to other problems like Alzheimer's disease (AD), psychiatric problems, insomnia, anxiety, and sensory abnormalities. Techniques including artificial intelligence (AI), machine learning (ML), and deep learning (DL) have been established for the classification of PD and normal controls (NC) with similar therapeutic appearances in order to address these problems and improve the diagnostic procedure for PD. In this article, we examine a literature survey of research articles published up to September 2022 in order to present an in-depth analysis of the use of datasets, various modalities, experimental setups, and architectures that have been applied in the diagnosis of subjective disease. This analysis includes a total of 217 research publications with a list of the various datasets, methodologies, and features. These findings suggest that ML/DL methods and novel biomarkers hold promising results for application in medical decision-making, leading to a more methodical and thorough detection of PD. Finally, we highlight the challenges and provide appropriate recommendations on selecting approaches that might be used for subgrouping and connection analysis with structural magnetic resonance imaging (sMRI), DaTSCAN, and single-photon emission computerized tomography (SPECT) data for future Parkinson's research.
Collapse
Affiliation(s)
- Arti Rana
- Computer Science & Engineering, Veer Madho Singh Bhandari Uttarakhand Technical University, Dehradun 248007, Uttarakhand, India
| | - Ankur Dumka
- Department of Computer Science and Engineering, Women Institute of Technology, Dehradun 248007, Uttarakhand, India
- Department of Computer Science & Engineering, Graphic Era Deemed to be University, Dehradun 248001, Uttarakhand, India
| | - Rajesh Singh
- Division of Research and Innovation, Uttaranchal Institute of Technology, Uttaranchal University, Dehradun 248007, Uttarakhand, India
- Department of Project Management, Universidad Internacional Iberoamericana, Campeche 24560, Mexico
| | - Manoj Kumar Panda
- Department of Electrical Engineering, G.B. Pant Institute of Engineering and Technology, Pauri 246194, Uttarakhand, India
| | - Neeraj Priyadarshi
- Department of Electrical Engineering, JIS College of Engineering, Kolkata 741235, West Bengal, India
| |
Collapse
|
10
|
Machine Learning Approach to Support the Detection of Parkinson's Disease in IMU-Based Gait Analysis. SENSORS 2022; 22:s22103700. [PMID: 35632109 PMCID: PMC9148133 DOI: 10.3390/s22103700] [Citation(s) in RCA: 20] [Impact Index Per Article: 10.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 04/05/2022] [Revised: 05/03/2022] [Accepted: 05/10/2022] [Indexed: 02/01/2023]
Abstract
The aim of this study was to determine which supervised machine learning (ML) algorithm can most accurately classify people with Parkinson’s disease (pwPD) from speed-matched healthy subjects (HS) based on a selected minimum set of IMU-derived gait features. Twenty-two gait features were extrapolated from the trunk acceleration patterns of 81 pwPD and 80 HS, including spatiotemporal, pelvic kinematics, and acceleration-derived gait stability indexes. After a three-level feature selection procedure, seven gait features were considered for implementing five ML algorithms: support vector machine (SVM), artificial neural network, decision trees (DT), random forest (RF), and K-nearest neighbors. Accuracy, precision, recall, and F1 score were calculated. SVM, DT, and RF showed the best classification performances, with prediction accuracy higher than 80% on the test set. The conceptual model of approaching ML that we proposed could reduce the risk of overrepresenting multicollinear gait features in the model, reducing the risk of overfitting in the test performances while fostering the explainability of the results.
Collapse
|