4.6 Article

Preliminary Clinical Application of Textile Insole Sensor for Hemiparetic Gait Pattern Analysis

Journal

SENSORS
Volume 19, Issue 18, Pages -

Publisher

MDPI
DOI: 10.3390/s19183950

Keywords

conductive textile; gait; stroke; hemiparetic; real-time monitoring

Funding

  1. MSIT (Ministry of Science and ICT), Korea, under the ITRC (Information Technology Research Center) support program [IITP-2019-2014-1-00720]
  2. Soonchunhyang University Research Fund

Ask authors/readers for more resources

Post-stroke gait dysfunction occurs at a very high prevalence. A practical method to quantitatively analyze the characteristics of hemiparetic gait is needed in both clinical and community settings. This study developed a 10-channeled textile capacitive pressure sensing insole (TCPSI) with a real-time monitoring system and tested its performance through hemiparetic gait pattern analysis. Thirty-five subjects (18 hemiparetic, 17 healthy) walked down a 40-m long corridor at a comfortable speed while wearing TCPSI inside the shoe. For gait analysis, the percentage of the plantar pressure difference (PPD), the step count, the stride time, the coefficient of variation, and the phase coordination index (PCI) were used. The results of the stroke patients showed a threefold higher PPD, a higher step count (41.61 +/- 10.7), a longer average stride time on the affected side, a lower mean plantar pressure on the affected side, higher plantar pressure in the toe area and the lateral side of the foot, and a threefold higher PCI (hemi: 19.50 +/- 13.86%, healthy: 5.62 +/- 5.05%) compared to healthy subjects. This study confirmed that TCPSI is a promising tool for distinguishing hemiparetic gait patterns and thus may be used as a wearable gait function evaluation tool, the external feedback gait training device, and a simple gait pattern analyzer for both hemiparetic patients and healthy individuals.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.6
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

Article Health Care Sciences & Services

Novel Analgesic Index for Postoperative Pain Assessment Based on a Photoplethysmographic Spectrogram and Convolutional Neural Network: Observational Study

Byung-Moon Choi, Ji Yeon Yim, Hangsik Shin, Gyujeong Noh

Summary: This study developed a new analgesic index using PPG spectrograms and a CNN to objectively assess postoperative pain in conscious patients. The index showed high sensitivity and specificity in detecting pain, confirming its efficiency in detecting postoperative pain in conscious patients. Further research is needed to assess the feasibility of the index in different populations and to prevent overfitting.

JOURNAL OF MEDICAL INTERNET RESEARCH (2021)

Article Physiology

Performance of the Surgical Pleth Index and Analgesia Nociception Index in Healthy Volunteers and Parturients

Byung-Moon Choi, Hangsik Shin, Joo-Hyun Lee, Ji-Yeon Bang, Eun-Kyung Lee, Gyu-Jeong Noh

Summary: The clinical performance of the SPI and ANI in conscious healthy volunteers and parturients was evaluated in this study, with results indicating that both indices were effective for detecting pain in these populations.

FRONTIERS IN PHYSIOLOGY (2021)

Article Chemistry, Analytical

Recurrence Plot and Machine Learning for Signal Quality Assessment of Photoplethysmogram in Mobile Environment

Donggeun Roh, Hangsik Shin

Summary: This study successfully developed a machine learning model that accurately evaluates the quality of a photoplethysmogram. Through data expansion, it achieved high accuracy in signal quality assessment without requiring complicated pre-processing or feature detection.

SENSORS (2021)

Article Computer Science, Information Systems

XGBoost Regression of the Most Significant Photoplethysmogram Features for Assessing Vascular Aging

Hangsik Shin

Summary: This study explores a vascular aging assessment model based on photoplethysmogram (PPG) features and confirms the importance of specific PPG features using explainable artificial intelligence. The developed XGBoost regression model shows comparable performance to existing PPG-based models in estimating age.

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS (2022)

Article Biology

Deep convolutional neural network-based signal quality assessment for photoplethysmogram

Hangsik Shin

Summary: A deep neural network-based signal quality assessment model for photoplethysmogram (PPG) was developed and optimized to achieve high accuracy in distinguishing waveform quality, with potential application in wearable healthcare.

COMPUTERS IN BIOLOGY AND MEDICINE (2022)

Article Chemistry, Analytical

Deep Convolutional Neural Network-Based Hemiplegic Gait Detection Using an Inertial Sensor Located Freely in a Pocket

Hangsik Shin

Summary: The study successfully distinguished between hemiplegic and normal gaits using a convolutional neural network with signal measured by a sensor freely located in the pocket, avoiding additional preprocessing steps. The model demonstrated high accuracy, precision, and recall in a clinical trial.

SENSORS (2022)

Article Geriatrics & Gerontology

Inhibitory Control of Saccadic Eye Movements and Cognitive Impairment in Mild Cognitive Impairment

Julius Opwonya, Changwon Wang, Kyoung-Mi Jang, Kunho Lee, Joong Il Kim, Jaeuk U. Kim

Summary: This study investigated executive control deficits and saccade behavioral changes in patients with MCI using comprehensive neuropsychological assessment and interleaved saccade paradigms. The results demonstrate that patients with MCI have impairments in inhibitory control and error monitoring, and the saccade paradigms have clinical potential as a screening tool for MCI.

FRONTIERS IN AGING NEUROSCIENCE (2022)

Review Physiology

Photoplethysmogram Analysis and Applications: An Integrative Review

Junyung Park, Hyeon Seok Seok, Sang-Su Kim, Hangsik Shin

Summary: This review examines the use of photoplethysmogram (PPG) in clinical and daily life settings, focusing on its generation mechanisms, measurement principles, clinical applications, noise definition, pre-processing techniques, feature detection techniques, and post-processing techniques. The study finds that the application field of PPG is expanding from clinical to mobile environments, and machine learning-based methods hold promise for future solutions.

FRONTIERS IN PHYSIOLOGY (2022)

Article Medical Informatics

Vascular Aging Estimation Based on Artificial Neural Network Using Photoplethysmogram Waveform Decomposition: Retrospective Cohort Study

Junyung Park, Hangsik Shin

Summary: This study discovered highly correlated features from the incident and reflected waves decomposed from a photoplethysmogram waveform and developed an artificial neural network-based regression model for the assessment of vascular aging. The results showed that the features defined from the reflected wave and skewness of the photoplethysmogram were useful for assessing vascular aging, and the regression model using these features had a strong correlation with the participant's real age.

JMIR MEDICAL INFORMATICS (2022)

Article Medicine, General & Internal

Deep Learning in Multi-Class Lung Diseases' Classification on Chest X-ray Images

Sungyeup Kim, Beanbonyka Rim, Seongjun Choi, Ahyoung Lee, Sedong Min, Min Hong

Summary: This paper proposes a deep learning method with transfer learning to classify lung diseases on chest X-ray images, aiming to improve the efficiency and accuracy of computer-aided diagnostic systems. The experiments on different datasets have achieved promising results in terms of the accuracy and specificity of disease classification.

DIAGNOSTICS (2022)

Article Multidisciplinary Sciences

Photoplethysmogram based vascular aging assessment using the deep convolutional neural network

Hangsik Shin, Gyujeong Noh, Byung-Moon Choi

Summary: In this study, a deep learning-based model was developed for non-invasive assessment of vascular age using photoplethysmogram (PPG). The model showed good performance, and the contribution of PPG waveform to vascular age estimation was analyzed using Grad-Cam.

SCIENTIFIC REPORTS (2022)

Article Psychology, Biological

A novel method for non-invasive blood pressure estimation based on continuous pulse transit time: An observational study

Hangsik Shin

Summary: This study evaluated the feasibility of continuous pulse transit time (CPTT) as a non-invasive method for continuous blood pressure estimation. The results showed that CPTT-based blood pressure estimation had good correlations and small root-mean-squared-error, indicating its potential as a non-invasive continuous blood pressure monitoring method.

PSYCHOPHYSIOLOGY (2023)

Article Chemistry, Analytical

Customized Textile Capacitive Insole Sensor for Center of Pressure Analysis

Jong-Gab Ho, Young Kim, Se-Dong Min

Summary: In this study, a lightweight insole-type textile capacitive sensor was developed to analyze plantar pressure distribution and center of pressure trajectory. The results showed that the sensor was capable of accurately identifying pressure segments at different gait speeds, and it exhibited similar accuracy and consistency compared to the traditional F-scan sensor. These findings provide a basis for future research in rehabilitation engineering and the development of smart devices.

SENSORS (2022)

Article Health Care Sciences & Services

Digital therapeutics from bench to bedside

Changwon Wang, Chungkeun Lee, Hangsik Shin

Summary: As a new therapeutic technique based on digital technology, the commercialization and clinical application of digital therapeutics (DTx) are increasing. However, the lack of consensus on a definition, insufficiencies in research and development, clinical trials, standardization of regulatory frameworks, and technological maturity have made the use of DTx as a general medical component ambiguous. This study investigates definitions, clinical trials, commercial products, and regulatory status related to DTx and suggests the necessity and considerations for international agreements on the definition and characteristics of DTx, focusing on commercialization characteristics.

NPJ DIGITAL MEDICINE (2023)

Article Computer Science, Information Systems

Three-Dimensional Atrial Wall Thickness Measurement Algorithm From a Segmented Atrial Wall Using a Partial Differential Equation

Oh-Seok Kwon, Jisu Lee, Je-Wook Park, So-Hyun Yang, Inseok Hwang, Hee Tae Yu, Hangsik Shin, Hui-Nam Pak

Summary: This study proposes a novel algorithm for automated three-dimensional cardiac wall thickness measurement, including automated boundary detection and solving geometric problems. The results of the verification experiments demonstrate the potential of the algorithm in terms of measurement accuracy and efficiency.

IEEE ACCESS (2022)

No Data Available