Using Inertial Measurement Units and Machine Learning to Classify Body Positions of Adults in a Hospital Bed
In hospitals, timely interventions can prevent avoidable clinical deterioration. Early recognition of deterioration is vital to stopping further decline. Measuring the way patients position themselves in bed and change their positions may signal when further assessment is necessary. While inertial m...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/2/499 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832587499188256768 |
|---|---|
| author | Eliza Becker Siavash Khaksar Harry Booker Kylie Hill Yifei Ren Tele Tan Carol Watson Ethan Wordsworth Meg Harrold |
| author_facet | Eliza Becker Siavash Khaksar Harry Booker Kylie Hill Yifei Ren Tele Tan Carol Watson Ethan Wordsworth Meg Harrold |
| author_sort | Eliza Becker |
| collection | DOAJ |
| description | In hospitals, timely interventions can prevent avoidable clinical deterioration. Early recognition of deterioration is vital to stopping further decline. Measuring the way patients position themselves in bed and change their positions may signal when further assessment is necessary. While inertial measurement units (IMUs) have been used in health research, their use inside hospitals has been limited. This study explores the use of IMUs with machine learning to continuously capture, classify and visualise patient positions in hospital beds. The participants attended a data collection session in a simulated hospital bedspace and were asked to adopt nine positions. Movement data were captured using five IMU Xsens DOTs attached to the forehead, wrists and ankles. Support Vector Machine (SVM) and K-Nearest Neighbours classifiers were trained using five different combinations of sensors (e.g., right wrist only, right and left wrist) to determine body positions. Data from 30 participants were analysed. The highest accuracy (87.7%) was achieved by SVM using forehead and wrist sensors. Adding data from ankle sensors reduced the accuracy. To preserve patient privacy in a hospital setting, a 3D visualisation was developed in Unity, offering a non-identifiable representation of patient positions. This system could help clinicians monitor changes in position which may signal clinical deterioration. |
| format | Article |
| id | doaj-art-677b4fb53dad4e6e899718cb3feefdd0 |
| institution | Kabale University |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-677b4fb53dad4e6e899718cb3feefdd02025-01-24T13:49:08ZengMDPI AGSensors1424-82202025-01-0125249910.3390/s25020499Using Inertial Measurement Units and Machine Learning to Classify Body Positions of Adults in a Hospital BedEliza Becker0Siavash Khaksar1Harry Booker2Kylie Hill3Yifei Ren4Tele Tan5Carol Watson6Ethan Wordsworth7Meg Harrold8Curtin School of Allied Health, Curtin University, Perth 6102, AustraliaSchool of Electrical Engineering, Computing and Mathematical Sciences, Curtin University, Perth 6102, AustraliaSchool of Electrical Engineering, Computing and Mathematical Sciences, Curtin University, Perth 6102, AustraliaCurtin School of Allied Health, Curtin University, Perth 6102, AustraliaSchool of Electrical Engineering, Computing and Mathematical Sciences, Curtin University, Perth 6102, AustraliaSchool of Electrical Engineering, Computing and Mathematical Sciences, Curtin University, Perth 6102, AustraliaPhysiotherapy Department, Royal Perth Hospital, Perth 6000, AustraliaSchool of Electrical Engineering, Computing and Mathematical Sciences, Curtin University, Perth 6102, AustraliaCurtin School of Allied Health, Curtin University, Perth 6102, AustraliaIn hospitals, timely interventions can prevent avoidable clinical deterioration. Early recognition of deterioration is vital to stopping further decline. Measuring the way patients position themselves in bed and change their positions may signal when further assessment is necessary. While inertial measurement units (IMUs) have been used in health research, their use inside hospitals has been limited. This study explores the use of IMUs with machine learning to continuously capture, classify and visualise patient positions in hospital beds. The participants attended a data collection session in a simulated hospital bedspace and were asked to adopt nine positions. Movement data were captured using five IMU Xsens DOTs attached to the forehead, wrists and ankles. Support Vector Machine (SVM) and K-Nearest Neighbours classifiers were trained using five different combinations of sensors (e.g., right wrist only, right and left wrist) to determine body positions. Data from 30 participants were analysed. The highest accuracy (87.7%) was achieved by SVM using forehead and wrist sensors. Adding data from ankle sensors reduced the accuracy. To preserve patient privacy in a hospital setting, a 3D visualisation was developed in Unity, offering a non-identifiable representation of patient positions. This system could help clinicians monitor changes in position which may signal clinical deterioration.https://www.mdpi.com/1424-8220/25/2/499inertial measurement unitshealthcaremonitoringmachine learning |
| spellingShingle | Eliza Becker Siavash Khaksar Harry Booker Kylie Hill Yifei Ren Tele Tan Carol Watson Ethan Wordsworth Meg Harrold Using Inertial Measurement Units and Machine Learning to Classify Body Positions of Adults in a Hospital Bed Sensors inertial measurement units healthcare monitoring machine learning |
| title | Using Inertial Measurement Units and Machine Learning to Classify Body Positions of Adults in a Hospital Bed |
| title_full | Using Inertial Measurement Units and Machine Learning to Classify Body Positions of Adults in a Hospital Bed |
| title_fullStr | Using Inertial Measurement Units and Machine Learning to Classify Body Positions of Adults in a Hospital Bed |
| title_full_unstemmed | Using Inertial Measurement Units and Machine Learning to Classify Body Positions of Adults in a Hospital Bed |
| title_short | Using Inertial Measurement Units and Machine Learning to Classify Body Positions of Adults in a Hospital Bed |
| title_sort | using inertial measurement units and machine learning to classify body positions of adults in a hospital bed |
| topic | inertial measurement units healthcare monitoring machine learning |
| url | https://www.mdpi.com/1424-8220/25/2/499 |
| work_keys_str_mv | AT elizabecker usinginertialmeasurementunitsandmachinelearningtoclassifybodypositionsofadultsinahospitalbed AT siavashkhaksar usinginertialmeasurementunitsandmachinelearningtoclassifybodypositionsofadultsinahospitalbed AT harrybooker usinginertialmeasurementunitsandmachinelearningtoclassifybodypositionsofadultsinahospitalbed AT kyliehill usinginertialmeasurementunitsandmachinelearningtoclassifybodypositionsofadultsinahospitalbed AT yifeiren usinginertialmeasurementunitsandmachinelearningtoclassifybodypositionsofadultsinahospitalbed AT teletan usinginertialmeasurementunitsandmachinelearningtoclassifybodypositionsofadultsinahospitalbed AT carolwatson usinginertialmeasurementunitsandmachinelearningtoclassifybodypositionsofadultsinahospitalbed AT ethanwordsworth usinginertialmeasurementunitsandmachinelearningtoclassifybodypositionsofadultsinahospitalbed AT megharrold usinginertialmeasurementunitsandmachinelearningtoclassifybodypositionsofadultsinahospitalbed |