A Raspberry Pi-Based Traumatic Brain Injury Detection System for Single-Channel Electroencephalogram
Traumatic Brain Injury (TBI) is a common cause of death and disability. However, existing tools for TBI diagnosis are either subjective or require extensive clinical setup and expertise. The increasing affordability and reduction in the size of relatively high-performance computing systems combined...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-04-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/8/2779 |
| _version_ | 1797537688111284224 |
|---|---|
| author | Navjodh Singh Dhillon Agustinus Sutandi Manoj Vishwanath Miranda M. Lim Hung Cao Dong Si |
| author_facet | Navjodh Singh Dhillon Agustinus Sutandi Manoj Vishwanath Miranda M. Lim Hung Cao Dong Si |
| author_sort | Navjodh Singh Dhillon |
| collection | DOAJ |
| description | Traumatic Brain Injury (TBI) is a common cause of death and disability. However, existing tools for TBI diagnosis are either subjective or require extensive clinical setup and expertise. The increasing affordability and reduction in the size of relatively high-performance computing systems combined with promising results from TBI related machine learning research make it possible to create compact and portable systems for early detection of TBI. This work describes a Raspberry Pi based portable, real-time data acquisition, and automated processing system that uses machine learning to efficiently identify TBI and automatically score sleep stages from a single-channel Electroencephalogram (EEG) signal. We discuss the design, implementation, and verification of the system that can digitize the EEG signal using an Analog to Digital Converter (ADC) and perform real-time signal classification to detect the presence of mild TBI (mTBI). We utilize Convolutional Neural Networks (CNN) and XGBoost based predictive models to evaluate the performance and demonstrate the versatility of the system to operate with multiple types of predictive models. We achieve a peak classification accuracy of more than 90% with a classification time of less than 1 s across 16–64 s epochs for TBI vs. control conditions. This work can enable the development of systems suitable for field use without requiring specialized medical equipment for early TBI detection applications and TBI research. Further, this work opens avenues to implement connected, real-time TBI related health and wellness monitoring systems. |
| first_indexed | 2024-03-10T12:19:07Z |
| format | Article |
| id | doaj.art-e66e9b56f7664b2aac0eb16b16222dd9 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T12:19:07Z |
| publishDate | 2021-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-e66e9b56f7664b2aac0eb16b16222dd92023-11-21T15:38:39ZengMDPI AGSensors1424-82202021-04-01218277910.3390/s21082779A Raspberry Pi-Based Traumatic Brain Injury Detection System for Single-Channel ElectroencephalogramNavjodh Singh Dhillon0Agustinus Sutandi1Manoj Vishwanath2Miranda M. Lim3Hung Cao4Dong Si5Computing and Software Systems, University of Washington, Bothell, WA 98011, USAComputing and Software Systems, University of Washington, Bothell, WA 98011, USADepartment of Electrical Engineering and Computer Science, University of California, Irvine, CA 92697, USAVA Portland Health Care System, Portland, OR 97239, USADepartment of Electrical Engineering and Computer Science, University of California, Irvine, CA 92697, USAComputing and Software Systems, University of Washington, Bothell, WA 98011, USATraumatic Brain Injury (TBI) is a common cause of death and disability. However, existing tools for TBI diagnosis are either subjective or require extensive clinical setup and expertise. The increasing affordability and reduction in the size of relatively high-performance computing systems combined with promising results from TBI related machine learning research make it possible to create compact and portable systems for early detection of TBI. This work describes a Raspberry Pi based portable, real-time data acquisition, and automated processing system that uses machine learning to efficiently identify TBI and automatically score sleep stages from a single-channel Electroencephalogram (EEG) signal. We discuss the design, implementation, and verification of the system that can digitize the EEG signal using an Analog to Digital Converter (ADC) and perform real-time signal classification to detect the presence of mild TBI (mTBI). We utilize Convolutional Neural Networks (CNN) and XGBoost based predictive models to evaluate the performance and demonstrate the versatility of the system to operate with multiple types of predictive models. We achieve a peak classification accuracy of more than 90% with a classification time of less than 1 s across 16–64 s epochs for TBI vs. control conditions. This work can enable the development of systems suitable for field use without requiring specialized medical equipment for early TBI detection applications and TBI research. Further, this work opens avenues to implement connected, real-time TBI related health and wellness monitoring systems.https://www.mdpi.com/1424-8220/21/8/2779traumatic brain injury (TBI)machine learning (ML)electroencephalogram (EEG)raspberry pi (RPI) |
| spellingShingle | Navjodh Singh Dhillon Agustinus Sutandi Manoj Vishwanath Miranda M. Lim Hung Cao Dong Si A Raspberry Pi-Based Traumatic Brain Injury Detection System for Single-Channel Electroencephalogram Sensors traumatic brain injury (TBI) machine learning (ML) electroencephalogram (EEG) raspberry pi (RPI) |
| title | A Raspberry Pi-Based Traumatic Brain Injury Detection System for Single-Channel Electroencephalogram |
| title_full | A Raspberry Pi-Based Traumatic Brain Injury Detection System for Single-Channel Electroencephalogram |
| title_fullStr | A Raspberry Pi-Based Traumatic Brain Injury Detection System for Single-Channel Electroencephalogram |
| title_full_unstemmed | A Raspberry Pi-Based Traumatic Brain Injury Detection System for Single-Channel Electroencephalogram |
| title_short | A Raspberry Pi-Based Traumatic Brain Injury Detection System for Single-Channel Electroencephalogram |
| title_sort | raspberry pi based traumatic brain injury detection system for single channel electroencephalogram |
| topic | traumatic brain injury (TBI) machine learning (ML) electroencephalogram (EEG) raspberry pi (RPI) |
| url | https://www.mdpi.com/1424-8220/21/8/2779 |
| work_keys_str_mv | AT navjodhsinghdhillon araspberrypibasedtraumaticbraininjurydetectionsystemforsinglechannelelectroencephalogram AT agustinussutandi araspberrypibasedtraumaticbraininjurydetectionsystemforsinglechannelelectroencephalogram AT manojvishwanath araspberrypibasedtraumaticbraininjurydetectionsystemforsinglechannelelectroencephalogram AT mirandamlim araspberrypibasedtraumaticbraininjurydetectionsystemforsinglechannelelectroencephalogram AT hungcao araspberrypibasedtraumaticbraininjurydetectionsystemforsinglechannelelectroencephalogram AT dongsi araspberrypibasedtraumaticbraininjurydetectionsystemforsinglechannelelectroencephalogram AT navjodhsinghdhillon raspberrypibasedtraumaticbraininjurydetectionsystemforsinglechannelelectroencephalogram AT agustinussutandi raspberrypibasedtraumaticbraininjurydetectionsystemforsinglechannelelectroencephalogram AT manojvishwanath raspberrypibasedtraumaticbraininjurydetectionsystemforsinglechannelelectroencephalogram AT mirandamlim raspberrypibasedtraumaticbraininjurydetectionsystemforsinglechannelelectroencephalogram AT hungcao raspberrypibasedtraumaticbraininjurydetectionsystemforsinglechannelelectroencephalogram AT dongsi raspberrypibasedtraumaticbraininjurydetectionsystemforsinglechannelelectroencephalogram |