Early Detection of Exposure to Toxic Chemicals Using Continuously Recorded Multi-Sensor Physiology
Early detection of exposure to a toxic chemical, e.g., in a military context, can be life-saving. We propose to use machine learning techniques and multiple continuously measured physiological signals to detect exposure, and to identify the chemical agent. Such detection and identification could be...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-05-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/11/3616 |
| _version_ | 1797533096929656832 |
|---|---|
| author | Jan Ubbo van Baardewijk Sarthak Agarwal Alex S. Cornelissen Marloes J. A. Joosen Jiska Kentrop Carolina Varon Anne-Marie Brouwer |
| author_facet | Jan Ubbo van Baardewijk Sarthak Agarwal Alex S. Cornelissen Marloes J. A. Joosen Jiska Kentrop Carolina Varon Anne-Marie Brouwer |
| author_sort | Jan Ubbo van Baardewijk |
| collection | DOAJ |
| description | Early detection of exposure to a toxic chemical, e.g., in a military context, can be life-saving. We propose to use machine learning techniques and multiple continuously measured physiological signals to detect exposure, and to identify the chemical agent. Such detection and identification could be used to alert individuals to take appropriate medical counter measures in time. As a first step, we evaluated whether exposure to an opioid (fentanyl) or a nerve agent (VX) could be detected in freely moving guinea pigs using features from respiration, electrocardiography (ECG) and electroencephalography (EEG), where machine learning models were trained and tested on different sets (across subject classification). Results showed this to be possible with close to perfect accuracy, where respiratory features were most relevant. Exposure detection accuracy rose steeply to over 95% correct during the first five minutes after exposure. Additional models were trained to correctly classify an exposed state as being induced either by fentanyl or VX. This was possible with an accuracy of almost 95%, where EEG features proved to be most relevant. Exposure detection models that were trained on subsets of animals generalized to subsets of animals that were exposed to other dosages of different chemicals. While future work is required to validate the principle in other species and to assess the robustness of the approach under different, realistic circumstances, our results indicate that utilizing different continuously measured physiological signals for early detection and identification of toxic agents is promising. |
| first_indexed | 2024-03-10T11:09:43Z |
| format | Article |
| id | doaj.art-c9cc9345261c4eebb4851f62754d5d18 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T11:09:43Z |
| publishDate | 2021-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-c9cc9345261c4eebb4851f62754d5d182023-11-21T20:56:19ZengMDPI AGSensors1424-82202021-05-012111361610.3390/s21113616Early Detection of Exposure to Toxic Chemicals Using Continuously Recorded Multi-Sensor PhysiologyJan Ubbo van Baardewijk0Sarthak Agarwal1Alex S. Cornelissen2Marloes J. A. Joosen3Jiska Kentrop4Carolina Varon5Anne-Marie Brouwer6Department Human Performance, The Netherlands Organisation for Applied Scientific Research (TNO), 3769 DE Soesterberg, The NetherlandsDepartment Human Performance, The Netherlands Organisation for Applied Scientific Research (TNO), 3769 DE Soesterberg, The NetherlandsDepartment CBRN Protection, The Netherlands Organisation for Applied Scientific Research (TNO), 2288 GJ Rijswijk, The NetherlandsDepartment CBRN Protection, The Netherlands Organisation for Applied Scientific Research (TNO), 2288 GJ Rijswijk, The NetherlandsDepartment CBRN Protection, The Netherlands Organisation for Applied Scientific Research (TNO), 2288 GJ Rijswijk, The NetherlandsCircuits and Systems (CAS) Group, Delft University of Technology, 2628 CD Delft, The NetherlandsDepartment Human Performance, The Netherlands Organisation for Applied Scientific Research (TNO), 3769 DE Soesterberg, The NetherlandsEarly detection of exposure to a toxic chemical, e.g., in a military context, can be life-saving. We propose to use machine learning techniques and multiple continuously measured physiological signals to detect exposure, and to identify the chemical agent. Such detection and identification could be used to alert individuals to take appropriate medical counter measures in time. As a first step, we evaluated whether exposure to an opioid (fentanyl) or a nerve agent (VX) could be detected in freely moving guinea pigs using features from respiration, electrocardiography (ECG) and electroencephalography (EEG), where machine learning models were trained and tested on different sets (across subject classification). Results showed this to be possible with close to perfect accuracy, where respiratory features were most relevant. Exposure detection accuracy rose steeply to over 95% correct during the first five minutes after exposure. Additional models were trained to correctly classify an exposed state as being induced either by fentanyl or VX. This was possible with an accuracy of almost 95%, where EEG features proved to be most relevant. Exposure detection models that were trained on subsets of animals generalized to subsets of animals that were exposed to other dosages of different chemicals. While future work is required to validate the principle in other species and to assess the robustness of the approach under different, realistic circumstances, our results indicate that utilizing different continuously measured physiological signals for early detection and identification of toxic agents is promising.https://www.mdpi.com/1424-8220/21/11/3616electrocardiographyelectroencephalographyrespirationmachine learningchemical exposuretoxidrome detection |
| spellingShingle | Jan Ubbo van Baardewijk Sarthak Agarwal Alex S. Cornelissen Marloes J. A. Joosen Jiska Kentrop Carolina Varon Anne-Marie Brouwer Early Detection of Exposure to Toxic Chemicals Using Continuously Recorded Multi-Sensor Physiology Sensors electrocardiography electroencephalography respiration machine learning chemical exposure toxidrome detection |
| title | Early Detection of Exposure to Toxic Chemicals Using Continuously Recorded Multi-Sensor Physiology |
| title_full | Early Detection of Exposure to Toxic Chemicals Using Continuously Recorded Multi-Sensor Physiology |
| title_fullStr | Early Detection of Exposure to Toxic Chemicals Using Continuously Recorded Multi-Sensor Physiology |
| title_full_unstemmed | Early Detection of Exposure to Toxic Chemicals Using Continuously Recorded Multi-Sensor Physiology |
| title_short | Early Detection of Exposure to Toxic Chemicals Using Continuously Recorded Multi-Sensor Physiology |
| title_sort | early detection of exposure to toxic chemicals using continuously recorded multi sensor physiology |
| topic | electrocardiography electroencephalography respiration machine learning chemical exposure toxidrome detection |
| url | https://www.mdpi.com/1424-8220/21/11/3616 |
| work_keys_str_mv | AT janubbovanbaardewijk earlydetectionofexposuretotoxicchemicalsusingcontinuouslyrecordedmultisensorphysiology AT sarthakagarwal earlydetectionofexposuretotoxicchemicalsusingcontinuouslyrecordedmultisensorphysiology AT alexscornelissen earlydetectionofexposuretotoxicchemicalsusingcontinuouslyrecordedmultisensorphysiology AT marloesjajoosen earlydetectionofexposuretotoxicchemicalsusingcontinuouslyrecordedmultisensorphysiology AT jiskakentrop earlydetectionofexposuretotoxicchemicalsusingcontinuouslyrecordedmultisensorphysiology AT carolinavaron earlydetectionofexposuretotoxicchemicalsusingcontinuouslyrecordedmultisensorphysiology AT annemariebrouwer earlydetectionofexposuretotoxicchemicalsusingcontinuouslyrecordedmultisensorphysiology |