Multilevel Pain Assessment with Functional Near-Infrared Spectroscopy: Evaluating Δ<i>HBO</i><sub>2</sub> and Δ<i>HHB</i> Measures for Comprehensive Analysis
Assessing pain in non-verbal patients is challenging, often depending on clinical judgment which can be unreliable due to fluctuations in vital signs caused by underlying medical conditions. To date, there is a notable absence of objective diagnostic tests to aid healthcare practitioners in pain ass...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/2/458 |
| _version_ | 1797339440957358080 |
|---|---|
| author | Muhammad Umar Khan Maryam Sousani Niraj Hirachan Calvin Joseph Maryam Ghahramani Girija Chetty Roland Goecke Raul Fernandez-Rojas |
| author_facet | Muhammad Umar Khan Maryam Sousani Niraj Hirachan Calvin Joseph Maryam Ghahramani Girija Chetty Roland Goecke Raul Fernandez-Rojas |
| author_sort | Muhammad Umar Khan |
| collection | DOAJ |
| description | Assessing pain in non-verbal patients is challenging, often depending on clinical judgment which can be unreliable due to fluctuations in vital signs caused by underlying medical conditions. To date, there is a notable absence of objective diagnostic tests to aid healthcare practitioners in pain assessment, especially affecting critically-ill or advanced dementia patients. Neurophysiological information, i.e., functional near-infrared spectroscopy (fNIRS) or electroencephalogram (EEG), unveils the brain’s active regions and patterns, revealing the neural mechanisms behind the experience and processing of pain. This study focuses on assessing pain via the analysis of fNIRS signals combined with machine learning, utilising multiple fNIRS measures including oxygenated haemoglobin (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>Δ</mo><mi>H</mi><mi>B</mi><msub><mi>O</mi><mn>2</mn></msub></mrow></semantics></math></inline-formula>) and deoxygenated haemoglobin (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>Δ</mo><mi>H</mi><mi>H</mi><mi>B</mi></mrow></semantics></math></inline-formula>). Initially, a channel selection process filters out highly contaminated channels with high-frequency and high-amplitude artifacts from the 24-channel fNIRS data. The remaining channels are then preprocessed by applying a low-pass filter and common average referencing to remove cardio-respiratory artifacts and common gain noise, respectively. Subsequently, the preprocessed channels are averaged to create a single time series vector for both <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>Δ</mo><mi>H</mi><mi>B</mi><msub><mi>O</mi><mn>2</mn></msub></mrow></semantics></math></inline-formula> and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>Δ</mo><mi>H</mi><mi>H</mi><mi>B</mi></mrow></semantics></math></inline-formula> measures. From each measure, ten statistical features are extracted and fusion occurs at the feature level, resulting in a fused feature vector. The most relevant features, selected using the Minimum Redundancy Maximum Relevance method, are passed to a Support Vector Machines classifier. Using leave-one-subject-out cross validation, the system achieved an accuracy of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>68.51</mn><mo>%</mo><mo>±</mo><mn>9.02</mn><mo>%</mo></mrow></semantics></math></inline-formula> in a multi-class task (No Pain, Low Pain, and High Pain) using a fusion of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>Δ</mo><mi>H</mi><mi>B</mi><msub><mi>O</mi><mn>2</mn></msub></mrow></semantics></math></inline-formula> and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>Δ</mo><mi>H</mi><mi>H</mi><mi>B</mi></mrow></semantics></math></inline-formula>. These two measures collectively demonstrated superior performance compared to when they were used independently. This study contributes to the pursuit of an objective pain assessment and proposes a potential biomarker for human pain using fNIRS. |
| first_indexed | 2024-03-08T09:47:26Z |
| format | Article |
| id | doaj.art-d270d0f5e076449e8eb42766abe14439 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-08T09:47:26Z |
| publishDate | 2024-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-d270d0f5e076449e8eb42766abe144392024-01-29T14:14:56ZengMDPI AGSensors1424-82202024-01-0124245810.3390/s24020458Multilevel Pain Assessment with Functional Near-Infrared Spectroscopy: Evaluating Δ<i>HBO</i><sub>2</sub> and Δ<i>HHB</i> Measures for Comprehensive AnalysisMuhammad Umar Khan0Maryam Sousani1Niraj Hirachan2Calvin Joseph3Maryam Ghahramani4Girija Chetty5Roland Goecke6Raul Fernandez-Rojas7Human-Centred Technology Research Centre, Faculty of Science and Technology, University of Canberra, Canberra, ACT 2617, AustraliaHuman-Centred Technology Research Centre, Faculty of Science and Technology, University of Canberra, Canberra, ACT 2617, AustraliaHuman-Centred Technology Research Centre, Faculty of Science and Technology, University of Canberra, Canberra, ACT 2617, AustraliaHuman-Centred Technology Research Centre, Faculty of Science and Technology, University of Canberra, Canberra, ACT 2617, AustraliaHuman-Centred Technology Research Centre, Faculty of Science and Technology, University of Canberra, Canberra, ACT 2617, AustraliaHuman-Centred Technology Research Centre, Faculty of Science and Technology, University of Canberra, Canberra, ACT 2617, AustraliaHuman-Centred Technology Research Centre, Faculty of Science and Technology, University of Canberra, Canberra, ACT 2617, AustraliaHuman-Centred Technology Research Centre, Faculty of Science and Technology, University of Canberra, Canberra, ACT 2617, AustraliaAssessing pain in non-verbal patients is challenging, often depending on clinical judgment which can be unreliable due to fluctuations in vital signs caused by underlying medical conditions. To date, there is a notable absence of objective diagnostic tests to aid healthcare practitioners in pain assessment, especially affecting critically-ill or advanced dementia patients. Neurophysiological information, i.e., functional near-infrared spectroscopy (fNIRS) or electroencephalogram (EEG), unveils the brain’s active regions and patterns, revealing the neural mechanisms behind the experience and processing of pain. This study focuses on assessing pain via the analysis of fNIRS signals combined with machine learning, utilising multiple fNIRS measures including oxygenated haemoglobin (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>Δ</mo><mi>H</mi><mi>B</mi><msub><mi>O</mi><mn>2</mn></msub></mrow></semantics></math></inline-formula>) and deoxygenated haemoglobin (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>Δ</mo><mi>H</mi><mi>H</mi><mi>B</mi></mrow></semantics></math></inline-formula>). Initially, a channel selection process filters out highly contaminated channels with high-frequency and high-amplitude artifacts from the 24-channel fNIRS data. The remaining channels are then preprocessed by applying a low-pass filter and common average referencing to remove cardio-respiratory artifacts and common gain noise, respectively. Subsequently, the preprocessed channels are averaged to create a single time series vector for both <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>Δ</mo><mi>H</mi><mi>B</mi><msub><mi>O</mi><mn>2</mn></msub></mrow></semantics></math></inline-formula> and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>Δ</mo><mi>H</mi><mi>H</mi><mi>B</mi></mrow></semantics></math></inline-formula> measures. From each measure, ten statistical features are extracted and fusion occurs at the feature level, resulting in a fused feature vector. The most relevant features, selected using the Minimum Redundancy Maximum Relevance method, are passed to a Support Vector Machines classifier. Using leave-one-subject-out cross validation, the system achieved an accuracy of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>68.51</mn><mo>%</mo><mo>±</mo><mn>9.02</mn><mo>%</mo></mrow></semantics></math></inline-formula> in a multi-class task (No Pain, Low Pain, and High Pain) using a fusion of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>Δ</mo><mi>H</mi><mi>B</mi><msub><mi>O</mi><mn>2</mn></msub></mrow></semantics></math></inline-formula> and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>Δ</mo><mi>H</mi><mi>H</mi><mi>B</mi></mrow></semantics></math></inline-formula>. These two measures collectively demonstrated superior performance compared to when they were used independently. This study contributes to the pursuit of an objective pain assessment and proposes a potential biomarker for human pain using fNIRS.https://www.mdpi.com/1424-8220/24/2/458pain assessmentfNIRSstatistical featuresSVMmachine learning |
| spellingShingle | Muhammad Umar Khan Maryam Sousani Niraj Hirachan Calvin Joseph Maryam Ghahramani Girija Chetty Roland Goecke Raul Fernandez-Rojas Multilevel Pain Assessment with Functional Near-Infrared Spectroscopy: Evaluating Δ<i>HBO</i><sub>2</sub> and Δ<i>HHB</i> Measures for Comprehensive Analysis Sensors pain assessment fNIRS statistical features SVM machine learning |
| title | Multilevel Pain Assessment with Functional Near-Infrared Spectroscopy: Evaluating Δ<i>HBO</i><sub>2</sub> and Δ<i>HHB</i> Measures for Comprehensive Analysis |
| title_full | Multilevel Pain Assessment with Functional Near-Infrared Spectroscopy: Evaluating Δ<i>HBO</i><sub>2</sub> and Δ<i>HHB</i> Measures for Comprehensive Analysis |
| title_fullStr | Multilevel Pain Assessment with Functional Near-Infrared Spectroscopy: Evaluating Δ<i>HBO</i><sub>2</sub> and Δ<i>HHB</i> Measures for Comprehensive Analysis |
| title_full_unstemmed | Multilevel Pain Assessment with Functional Near-Infrared Spectroscopy: Evaluating Δ<i>HBO</i><sub>2</sub> and Δ<i>HHB</i> Measures for Comprehensive Analysis |
| title_short | Multilevel Pain Assessment with Functional Near-Infrared Spectroscopy: Evaluating Δ<i>HBO</i><sub>2</sub> and Δ<i>HHB</i> Measures for Comprehensive Analysis |
| title_sort | multilevel pain assessment with functional near infrared spectroscopy evaluating δ i hbo i sub 2 sub and δ i hhb i measures for comprehensive analysis |
| topic | pain assessment fNIRS statistical features SVM machine learning |
| url | https://www.mdpi.com/1424-8220/24/2/458 |
| work_keys_str_mv | AT muhammadumarkhan multilevelpainassessmentwithfunctionalnearinfraredspectroscopyevaluatingdihboisub2subanddihhbimeasuresforcomprehensiveanalysis AT maryamsousani multilevelpainassessmentwithfunctionalnearinfraredspectroscopyevaluatingdihboisub2subanddihhbimeasuresforcomprehensiveanalysis AT nirajhirachan multilevelpainassessmentwithfunctionalnearinfraredspectroscopyevaluatingdihboisub2subanddihhbimeasuresforcomprehensiveanalysis AT calvinjoseph multilevelpainassessmentwithfunctionalnearinfraredspectroscopyevaluatingdihboisub2subanddihhbimeasuresforcomprehensiveanalysis AT maryamghahramani multilevelpainassessmentwithfunctionalnearinfraredspectroscopyevaluatingdihboisub2subanddihhbimeasuresforcomprehensiveanalysis AT girijachetty multilevelpainassessmentwithfunctionalnearinfraredspectroscopyevaluatingdihboisub2subanddihhbimeasuresforcomprehensiveanalysis AT rolandgoecke multilevelpainassessmentwithfunctionalnearinfraredspectroscopyevaluatingdihboisub2subanddihhbimeasuresforcomprehensiveanalysis AT raulfernandezrojas multilevelpainassessmentwithfunctionalnearinfraredspectroscopyevaluatingdihboisub2subanddihhbimeasuresforcomprehensiveanalysis |