1
|
Jamshed M, Shahzad A, Riaz F, Kim K. Exploring inertial sensor-based balance biomarkers for early detection of mild cognitive impairment. Sci Rep 2024; 14:9829. [PMID: 38684687 PMCID: PMC11059265 DOI: 10.1038/s41598-024-59928-1] [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: 01/22/2024] [Accepted: 04/16/2024] [Indexed: 05/02/2024] Open
Abstract
Dementia is characterized by a progressive loss of cognitive abilities, and diagnosing its early stages Mild Cognitive Impairment (MCI), is difficult since it is a transitory state that is different from total cognitive collapse. Recent clinical research studies have identified that balance impairments can be a significant indicator for predicting dementia in older adults. Accordingly, the current research focuses on finding innovative postural balance-based digital biomarkers by using wearable inertial sensors and pre-screening of MCI in home settings using machine learning techniques. For this research, sixty subjects (30 cognitively normal and 30 MCI) with waist-mounted inertial sensor performed balance tasks in four different standing postures: eyes-open, eyes-closed, right-leg-lift, and left-leg-lift. The significant balance biomarkers for MCI identification are discovered by our research, demonstrating specific characteristics in each of these four states. A robust feature selection approach is ensured by the multi-step methodology that combines the strengths of Filter techniques, Wrapper methods, and SHAP (Shapley Additive exPlanations) technique. The proposed balance biomarkers have the potential to detect MCI (with 75.8% accuracy), as evidenced by the results of machine learning algorithms for classification. This work adds to the growing body of literature targeted at enhancing understanding and proactive management of cognitive loss in older populations and lays the groundwork for future research efforts aimed at refining digital biomarkers, validating findings, and exploring longitudinal perspectives.
Collapse
Affiliation(s)
- Mobeena Jamshed
- Department of Computer and Software Engineering, National University of Sciences and Technology, Islamabad, 44000, Pakistan
| | - Ahsan Shahzad
- Department of Computer and Software Engineering, National University of Sciences and Technology, Islamabad, 44000, Pakistan.
| | - Farhan Riaz
- School of Computer Science, University of Lincoln, Lincoln, LN67TS, UK
| | - Kiseon Kim
- School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, Gwangju, 61005, South Korea
| |
Collapse
|
2
|
Jaworski J, Lech G, Witkowski K, Kubacki R, Piepiora P. Evaluation of measurement reliability for selected indices of postural stability based on data from the GYKO Inertial Sensor System. Biol Sport 2024; 41:155-161. [PMID: 38524829 PMCID: PMC10955751 DOI: 10.5114/biolsport.2024.132986] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/07/2023] [Revised: 09/27/2023] [Accepted: 10/20/2023] [Indexed: 03/26/2024] Open
Abstract
The main aim of this study is to use comprehensive statistical analyses to evaluate measurement reliability of selected variables that characterize postural stability. The study examined twenty-nine healthy non-athlete students. The examinations were performed twice, with a one-week interval. The Microgate GYKO inertial sensor system was used to evaluate the reliability of variables that characterize postural stability. The relative reliability of the repeated test was evaluated using the intraclass correlation coefficient (ICC) with 95% confidence interval (95% CI). Next, the standard error of measurement (SEM) and minimal detectable change (MDC) were computed. Relative reliability of the repeated test for all analysed variables of ICC ranged from 0.31 to 0.75. For four variables, ICC values were ca. 0.7, i.e., they can be considered as good. For four other variables, ICC ranged from 0.41 to 0.54, with these values considered fair. Satisfactory reproducibility of postural stability measurements using the GYKO inertial sensor system demonstrates that it can offer an inexpensive and efficient alternative to measurements that use force balance platforms.
Collapse
Affiliation(s)
- Janusz Jaworski
- Faculty of Physical Education and Sport, University of Physical Education in Kraków, Poland
| | - Grzegorz Lech
- Faculty of Physical Education and Sport, University of Physical Education in Kraków, Poland
| | - Kazimierz Witkowski
- Faculty of Physical Education and Sports, Wroclaw University of Health and Sport Sciences, 51-612 Wrocław, Poland
| | - Rafał Kubacki
- Faculty of Physical Education and Sports, Wroclaw University of Health and Sport Sciences, 51-612 Wrocław, Poland
| | - Paweł Piepiora
- Faculty of Physical Education and Sports, Wroclaw University of Health and Sport Sciences, 51-612 Wrocław, Poland
| |
Collapse
|
3
|
Kang JH, Hsieh EH, Lee CY, Sun YM, Lee TY, Hsu JBK, Chang TH. Assessing Non-Specific Neck Pain through Pose Estimation from Images Based on Ensemble Learning. Life (Basel) 2023; 13:2292. [PMID: 38137893 PMCID: PMC10744896 DOI: 10.3390/life13122292] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/20/2023] [Revised: 11/27/2023] [Accepted: 11/28/2023] [Indexed: 12/24/2023] Open
Abstract
BACKGROUND Mobile phones, laptops, and computers have become an indispensable part of our lives in recent years. Workers may have an incorrect posture when using a computer for a prolonged period of time. Using these products with an incorrect posture can lead to neck pain. However, there are limited data on postures in real-life situations. METHODS In this study, we used a common camera to record images of subjects carrying out three different tasks (a typing task, a gaming task, and a video-watching task) on a computer. Different artificial intelligence (AI)-based pose estimation approaches were applied to analyze the head's yaw, pitch, and roll and coordinate information of the eyes, nose, neck, and shoulders in the images. We used machine learning models such as random forest, XGBoost, logistic regression, and ensemble learning to build a model to predict whether a subject had neck pain by analyzing their posture when using the computer. RESULTS After feature selection and adjustment of the predictive models, nested cross-validation was applied to evaluate the models and fine-tune the hyperparameters. Finally, the ensemble learning approach was utilized to construct a model via bagging, which achieved a performance with 87% accuracy, 92% precision, 80.3% recall, 95.5% specificity, and an AUROC of 0.878. CONCLUSIONS We developed a predictive model for the identification of non-specific neck pain using 2D video images without the need for costly devices, advanced environment settings, or extra sensors. This method could provide an effective way for clinically evaluating poor posture during real-world computer usage scenarios.
Collapse
Affiliation(s)
- Jiunn-Horng Kang
- Department of Physical Medicine and Rehabilitation, Taipei Medical University Hospital, Taipei 110, Taiwan;
- Graduate Institute of Nanomedicine and Medical Engineering, Taipei Medical University, Taipei 110, Taiwan
| | - En-Han Hsieh
- Graduate Institute of Biomedical Informatics, Taipei Medical University, Taipei 110, Taiwan
| | - Cheng-Yang Lee
- Graduate Institute of Biomedical Informatics, Taipei Medical University, Taipei 110, Taiwan
| | | | - Tzong-Yi Lee
- Institute of Bioinformatics and Systems Biology, National Yang Ming Chiao Tung University, Hsinchu 300, Taiwan
| | - Justin Bo-Kai Hsu
- Department of Computer Science and Engineering, Yuan Ze University, Taoyuan 320, Taiwan
| | - Tzu-Hao Chang
- Graduate Institute of Biomedical Informatics, Taipei Medical University, Taipei 110, Taiwan
- Clinical Big Data Research Center, Taipei Medical University Hospital, Taipei 110, Taiwan
| |
Collapse
|
4
|
Jaworski J, Lech G, Żak M, Witkowski K, Piepiora P. Relationships between selected indices of postural stability and sports performance in elite badminton players: Pilot study. Front Psychol 2023; 14:1110164. [PMID: 37034914 PMCID: PMC10074591 DOI: 10.3389/fpsyg.2023.1110164] [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: 11/28/2022] [Accepted: 02/23/2023] [Indexed: 04/11/2023] Open
Abstract
The main aim of this study was to determine the relationships between postural stability and the place in the ranking of badminton players. The study examined 10 elite players from Polish national badminton team. The scope of the study included basic somatic characteristics, such as body height, body weight, BMI, and training experience. A Microgate GYKO inertial sensor system was used to assess the postural stability of athletes. Using Spearman's rank correlation, cause-and-effect relationships between the place in the sports ranking and the analyzed variables characterizing postural stability were recognized. Depending on the distribution and homogeneity of variance, the significance of differences in variables that characterize postural stability between players of different sports skill levels (two groups) was calculated. The Student's t-test or Mann-Whitney's U-test was used for this purpose. In general, the athletes with higher positions on the ranking list presented a higher level of postural stability in both tests, which is also confirmed by the normalized values. However, for all variables of postural stability, no statistically significant correlations with sports ranking were observed. Higher values of Spearman's rank correlation coefficients were found for the test performed in the one-foot standing test compared to the two-foot test. The results obtained indicate that particular attention in badminton training should be paid to the development of the level of postural stability in order to improve sports performance.
Collapse
Affiliation(s)
- Janusz Jaworski
- Faculty of Physical Education and Sport, University of Physical Education in Kraków, Krakow, Poland
| | - Grzegorz Lech
- Faculty of Physical Education and Sport, University of Physical Education in Kraków, Krakow, Poland
| | - Michał Żak
- Faculty of Physical Education and Sport, University of Physical Education in Kraków, Krakow, Poland
| | - Kazimierz Witkowski
- Faculty of Physical Education and Sports, Wroclaw University of Health and Sport Sciences, Wrocław, Poland
| | - Paweł Piepiora
- Faculty of Physical Education and Sports, Wroclaw University of Health and Sport Sciences, Wrocław, Poland
- *Correspondence: Paweł Piepiora,
| |
Collapse
|
5
|
Koontz AM, Neti A, Chung CS, Ayiluri N, Slavens BA, Davis CG, Wei L. Reliability of 3D Depth Motion Sensors for Capturing Upper Body Motions and Assessing the Quality of Wheelchair Transfers. SENSORS 2022; 22:s22134977. [PMID: 35808471 PMCID: PMC9269685 DOI: 10.3390/s22134977] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 04/30/2022] [Revised: 06/14/2022] [Accepted: 06/28/2022] [Indexed: 02/01/2023]
Abstract
Wheelchair users must use proper technique when performing sitting-pivot-transfers (SPTs) to prevent upper extremity pain and discomfort. Current methods to analyze the quality of SPTs include the TransKinect, a combination of machine learning (ML) models, and the Transfer Assessment Instrument (TAI), to automatically score the quality of a transfer using Microsoft Kinect V2. With the discontinuation of the V2, there is a necessity to determine the compatibility of other commercial sensors. The Intel RealSense D435 and the Microsoft Kinect Azure were compared against the V2 for inter- and intra-sensor reliability. A secondary analysis with the Azure was also performed to analyze its performance with the existing ML models used to predict transfer quality. The intra- and inter-sensor reliability was higher for the Azure and V2 (n = 7; ICC = 0.63 to 0.92) than the RealSense and V2 (n = 30; ICC = 0.13 to 0.7) for four key features. Additionally, the V2 and the Azure both showed high agreement with each other on the ML outcomes but not against a ground truth. Therefore, the ML models may need to be retrained ideally with the Azure, as it was found to be a more reliable and robust sensor for tracking wheelchair transfers in comparison to the V2.
Collapse
Affiliation(s)
- Alicia Marie Koontz
- Human Engineering Research Laboratories, VA Pittsburgh Healthcare System, Pittsburgh, PA 15206, USA
- Department of Bioengineering, Swanson School of Engineering, University of Pittsburgh, Pittsburgh, PA 15213, USA
- Department of Rehabilitation Science and Technology, School of Health and Rehabilitation Sciences, University of Pittsburgh, Pittsburgh, PA 15213, USA
| | - Ahlad Neti
- Human Engineering Research Laboratories, VA Pittsburgh Healthcare System, Pittsburgh, PA 15206, USA
- Department of Bioengineering, Swanson School of Engineering, University of Pittsburgh, Pittsburgh, PA 15213, USA
| | - Cheng-Shiu Chung
- Human Engineering Research Laboratories, VA Pittsburgh Healthcare System, Pittsburgh, PA 15206, USA
- Department of Rehabilitation Science and Technology, School of Health and Rehabilitation Sciences, University of Pittsburgh, Pittsburgh, PA 15213, USA
| | - Nithin Ayiluri
- Human Engineering Research Laboratories, VA Pittsburgh Healthcare System, Pittsburgh, PA 15206, USA
- Department of Rehabilitation Science and Technology, School of Health and Rehabilitation Sciences, University of Pittsburgh, Pittsburgh, PA 15213, USA
| | - Brooke A Slavens
- Collage of Health Sciences, University of Wisconsin-Milwaukee, Milwaukee, WI 53211, USA
| | - Celia Genevieve Davis
- Human Engineering Research Laboratories, VA Pittsburgh Healthcare System, Pittsburgh, PA 15206, USA
- Department of Bioengineering, Swanson School of Engineering, University of Pittsburgh, Pittsburgh, PA 15213, USA
| | - Lin Wei
- Human Engineering Research Laboratories, VA Pittsburgh Healthcare System, Pittsburgh, PA 15206, USA
- Texas Health Resources, Allen, TX 75013, USA
| |
Collapse
|