Explainable Artificial Intelligence and Wearable Sensor-Based Gait Analysis to Identify Patients with Osteopenia and Sarcopenia in Daily Life
Osteopenia and sarcopenia can cause various senile diseases and are key factors related to the quality of life in old age. There is need for portable tools and methods that can analyze osteopenia and sarcopenia risks during daily life, rather than requiring a specialized hospital setting. Gait is a...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-03-01
|
| Series: | Biosensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-6374/12/3/167 |
| _version_ | 1797472586780639232 |
|---|---|
| author | Jeong-Kyun Kim Myung-Nam Bae Kangbok Lee Jae-Chul Kim Sang Gi Hong |
| author_facet | Jeong-Kyun Kim Myung-Nam Bae Kangbok Lee Jae-Chul Kim Sang Gi Hong |
| author_sort | Jeong-Kyun Kim |
| collection | DOAJ |
| description | Osteopenia and sarcopenia can cause various senile diseases and are key factors related to the quality of life in old age. There is need for portable tools and methods that can analyze osteopenia and sarcopenia risks during daily life, rather than requiring a specialized hospital setting. Gait is a suitable indicator of musculoskeletal diseases; therefore, we analyzed the gait signal obtained from an inertial-sensor-based wearable gait device as a tool to manage bone loss and muscle loss in daily life. To analyze the inertial-sensor-based gait, the inertial signal was classified into seven gait phases, and descriptive statistical parameters were obtained for each gait phase. Subsequently, explainable artificial intelligence was utilized to analyze the contribution and importance of descriptive statistical parameters on osteopenia and sarcopenia. It was found that XGBoost yielded a high accuracy of 88.69% for osteopenia, whereas the random forest approach showed a high accuracy of 93.75% for sarcopenia. Transfer learning with a ResNet backbone exhibited appropriate performance but showed lower accuracy than the descriptive statistical parameter-based identification result. The proposed gait analysis method confirmed high classification accuracy and the statistical significance of gait factors that can be used for osteopenia and sarcopenia management. |
| first_indexed | 2024-03-09T20:03:33Z |
| format | Article |
| id | doaj.art-1f9ea0a6ddd94570a8512a8df471d30d |
| institution | Directory Open Access Journal |
| issn | 2079-6374 |
| language | English |
| last_indexed | 2024-03-09T20:03:33Z |
| publishDate | 2022-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Biosensors |
| spelling | doaj.art-1f9ea0a6ddd94570a8512a8df471d30d2023-11-24T00:36:33ZengMDPI AGBiosensors2079-63742022-03-0112316710.3390/bios12030167Explainable Artificial Intelligence and Wearable Sensor-Based Gait Analysis to Identify Patients with Osteopenia and Sarcopenia in Daily LifeJeong-Kyun Kim0Myung-Nam Bae1Kangbok Lee2Jae-Chul Kim3Sang Gi Hong4Department of Computer Software, University of Science and Technology, Daejeon 34113, KoreaIntelligent Convergence Research Laboratory, Electronics and Telecommunications Research Institute, Daejeon 34129, KoreaIntelligent Convergence Research Laboratory, Electronics and Telecommunications Research Institute, Daejeon 34129, KoreaIntelligent Convergence Research Laboratory, Electronics and Telecommunications Research Institute, Daejeon 34129, KoreaDepartment of Computer Software, University of Science and Technology, Daejeon 34113, KoreaOsteopenia and sarcopenia can cause various senile diseases and are key factors related to the quality of life in old age. There is need for portable tools and methods that can analyze osteopenia and sarcopenia risks during daily life, rather than requiring a specialized hospital setting. Gait is a suitable indicator of musculoskeletal diseases; therefore, we analyzed the gait signal obtained from an inertial-sensor-based wearable gait device as a tool to manage bone loss and muscle loss in daily life. To analyze the inertial-sensor-based gait, the inertial signal was classified into seven gait phases, and descriptive statistical parameters were obtained for each gait phase. Subsequently, explainable artificial intelligence was utilized to analyze the contribution and importance of descriptive statistical parameters on osteopenia and sarcopenia. It was found that XGBoost yielded a high accuracy of 88.69% for osteopenia, whereas the random forest approach showed a high accuracy of 93.75% for sarcopenia. Transfer learning with a ResNet backbone exhibited appropriate performance but showed lower accuracy than the descriptive statistical parameter-based identification result. The proposed gait analysis method confirmed high classification accuracy and the statistical significance of gait factors that can be used for osteopenia and sarcopenia management.https://www.mdpi.com/2079-6374/12/3/167osteopeniasarcopeniaXAISHAPIMUgait analysis |
| spellingShingle | Jeong-Kyun Kim Myung-Nam Bae Kangbok Lee Jae-Chul Kim Sang Gi Hong Explainable Artificial Intelligence and Wearable Sensor-Based Gait Analysis to Identify Patients with Osteopenia and Sarcopenia in Daily Life Biosensors osteopenia sarcopenia XAI SHAP IMU gait analysis |
| title | Explainable Artificial Intelligence and Wearable Sensor-Based Gait Analysis to Identify Patients with Osteopenia and Sarcopenia in Daily Life |
| title_full | Explainable Artificial Intelligence and Wearable Sensor-Based Gait Analysis to Identify Patients with Osteopenia and Sarcopenia in Daily Life |
| title_fullStr | Explainable Artificial Intelligence and Wearable Sensor-Based Gait Analysis to Identify Patients with Osteopenia and Sarcopenia in Daily Life |
| title_full_unstemmed | Explainable Artificial Intelligence and Wearable Sensor-Based Gait Analysis to Identify Patients with Osteopenia and Sarcopenia in Daily Life |
| title_short | Explainable Artificial Intelligence and Wearable Sensor-Based Gait Analysis to Identify Patients with Osteopenia and Sarcopenia in Daily Life |
| title_sort | explainable artificial intelligence and wearable sensor based gait analysis to identify patients with osteopenia and sarcopenia in daily life |
| topic | osteopenia sarcopenia XAI SHAP IMU gait analysis |
| url | https://www.mdpi.com/2079-6374/12/3/167 |
| work_keys_str_mv | AT jeongkyunkim explainableartificialintelligenceandwearablesensorbasedgaitanalysistoidentifypatientswithosteopeniaandsarcopeniaindailylife AT myungnambae explainableartificialintelligenceandwearablesensorbasedgaitanalysistoidentifypatientswithosteopeniaandsarcopeniaindailylife AT kangboklee explainableartificialintelligenceandwearablesensorbasedgaitanalysistoidentifypatientswithosteopeniaandsarcopeniaindailylife AT jaechulkim explainableartificialintelligenceandwearablesensorbasedgaitanalysistoidentifypatientswithosteopeniaandsarcopeniaindailylife AT sanggihong explainableartificialintelligenceandwearablesensorbasedgaitanalysistoidentifypatientswithosteopeniaandsarcopeniaindailylife |