Pain phenotypes classified by machine learning using electroencephalography features

Levitt, Joshua; Edhi, Muhammad Muzzammil; Thorpe, Ryan; Leung, Jason; Michishita, Mai; Koyama, Suguru; Yoshikawa, Shinya; Scarfo, Keith; Carayannopoulos, Alexios G.; Gu, Wendy; Srivastava, Kyle H.; Clark, Bryan A.; Esteller, Rosana; Borton, David A.; Jones, Stephanie R.; Saab, Carl Y.

doi:10.1016/j.neuroimage.2020.117256

Cited by 40 publications

(31 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In their case controlled study, Santana et al used functional magnetic resonance imaging (fMRI) data in 60 patients with chronic pain (36 subjects with fibromyalgia and 24 subjects with low back pain) and 98 pain-free controls in order to compare the performance of different ML models in pain classification and found that CNN, which assessed data using the MSDL probabilistic atlas, was the most efficient with balanced accuracy ranging from 69% to 86% [ 16 ]. In two studies, EEG data have been used for pain classification in patients with osteoarthritis [ 21 ] and in patients with pain due to spinal cord injury [ 26 ]. Overall, the results of these studies suggested that supervised ML algorithms can accurately classify the intensity of pain regardless of its type.…”

Section: Resultsmentioning

confidence: 99%

“…Table 2 presents the characteristics of the studies, including the ML method that was applied and the respective results. ML techniques for classifying the intensity of pain were found to be effective in patients with low back pain (LBP) [9,12,13,16], osteoarthritis [21], ankylosing spondylitis [30], spinal cord injury [26], thoracic pain [29], sickle cell disease (SCD) [32], evoked heat pain [25,27], and other types of pain [15]. In their case-controlled study, Abdollahi et al classified pain based on quantitative kinematic data.…”

Section: Effectiveness Of ML In Pain Classification Diagnosis Manifestation and Managementmentioning

confidence: 99%

“…Most of these algorithms were supervised classification or regression techniques to address issues related to pain. The selected studies used mostly classical ML algorithms, such as SVM [9,12,15,21,22,[25][26][27], and random forest (RF) [14,15,28,29,31,32] followed by Bayes [17,19,20,22] techniques to classify tasks by assigning a predefined class label to an observation.…”

Section: Techniquesmentioning

confidence: 99%

See 2 more Smart Citations

Machine Learning in Pain Medicine: An Up-To-Date Systematic Review

et al. 2021

View full text Add to dashboard Cite

Introduction: Pain is the unpleasant sensation and emotional experience that leads to poor quality of life for millions of people worldwide. Considering the complexity in understanding the principles of pain and its significant impact on individuals and society, research focuses to deliver innovative pain relief methods and techniques. This review explores the clinical uses of machine learning (ML) for the diagnosis, classification, and management of pain. Methods: A systematic review of the current literature was conducted using the PubMed database library.Results: Twenty-six papers related to pain and ML research were included. Most of the studies used ML for effectively classifying the patients' level of pain, followed by use of ML for the prediction of manifestation of pain and for pain management. A less common reason for performing ML analysis was for the diagnosis of pain. The different approaches are thoroughly discussed. Conclusion: ML is increasingly used in pain medicine and appears to be more effective compared to traditional statistical approaches in the diagnosis, classification, and management of pain.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Effectiveness Of ML In Pain Classification Diagnosis Manifestation and Managementmentioning

confidence: 99%

Section: Techniquesmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning in Pain Medicine: An Up-To-Date Systematic Review

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The magnitude of gamma-band ERS correlates with perceived noxious stimulus intensity (Peng et al, 2018), is independent of saliency (Zhang et al, 2012), and predicts nociceptive-specific perception both within and across subjects (Heid et al, 2020;Hu and Iannetti, 2019). Further evidence suggests that spontaneous bursts of EEG gamma-band activity emerging from EEG electrodes over SI can differentiate human participants who are experiencing chronic pain from those who are not (Levitt et al, 2020).…”

Section: Model Predicts That Extrinsically-driven Bursts Of Gamma Oscillations Combined With Network Resonance Indicate Nociceptive Procementioning

confidence: 96%

Distinct neocortical mechanisms underlie human SI responses to median nerve and laser evoked peripheral activation

Thorpe

Black

Borton

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Magneto- and/or electro-encephalography (M/EEG) are non-invasive clinically-relevant tools that have long been used to measure electromagnetic fields in somatosensory cortex evoked by non-painful and painful somatosensory stimuli. Two commonly applied stimulation paradigms that produce distinct responses in primary somatosensory cortex (SI) linked to non-painful and painful sensations are electrical median nerve (MN) stimulation and cutaneous laser-evoked (LE) stimulation to the dorsum of the hand, respectively. Despite their prevalence, the physiological mechanisms that produce stereotypic macroscale MN and LE responses have yet to be fully articulated, limiting their utility in understanding brain dynamics associated with non-painful or painful somatosensation. We examined the neocortical circuit mechanisms contributing to MN and LE responses in SI using the Human Neocortical Neurosolver (HNN) neural modeling software tool. HNN was specifically designed for biophysically principled interpretation of the cell and circuit origin of M/EEG signals (Neymotin et al., 2020). Detailed analysis of the timing and orientation of peaks in source localized SI current dipole responses from MN and laser-evoked (LE) stimulation showed that these features were robust and conserved across prior studies. The first peak in the MN response at ~20 ms corresponds to outward-directed deep-to-superficial electrical current flow through the cortical laminae, while the initial LE response occurs later at ~170 ms and is oriented in the opposite direction. Historically, these peaks have both been labeled N20 and N1, despite their opposite current orientations. Simulating the cellular and circuit-level mechanisms accounting for these and later peaks with HNN's detailed laminar neocortical column model revealed that the MN response can be simulated with a sequence of layer-specific exogenous excitatory feedforward and feedback synaptic drive. This sequence was similar to that previously reported for tactile evoked responses (Jones et al., 2007; Neymotin et al., 2020), with the novel discovery of an early excitatory feedback input to superficial layers at ~30 ms post-stimulus that facilitated generation of the MN response's first prominent inward-oriented deflection, known historically as the P30. Simulations of the LE response revealed that the initial ~170 ms inward-deflection required a burst of repetitive gamma-frequency (~40 Hz) excitatory supragranular feedback drives, consistent with prior reports of LE gamma-frequency activity. These results make novel and detailed multiscale predictions about the dynamic laminar circuit mechanisms underlying temporal and spectral features of MN and LE responses in SI, and can guide further investigations in follow-up studies. Ultimately, these findings may help with the development of targeted therapeutics for pathological somatosensation, such as chronic and neuropathic pain.

show abstract

“…The clinical variations in SZ and MDD are very heterogeneous (4)(5)(6). Beyond clinical diagnosis based on phenomenological distinctions between SZ and MDD, the definition of EEG endophenotypes using machine learning could provide insights facilitating therapeutic breakthroughs for a variety of pathologic phenotypes (7)(8)(9)(10). Especially, classification performance in psychiatric disorders was assured by applying linear discriminant analysis (LDA) and support vector machine (SVM) (11).…”

Section: Introductionmentioning

confidence: 99%

Machine Learning-Based Electroencephalographic Phenotypes of Schizophrenia and Major Depressive Disorder

Jang

Kim

et al. 2021

Front. Psychiatry

View full text Add to dashboard Cite

Background: Psychiatric diagnosis is formulated by symptomatic classification; disease-specific neurophysiological phenotyping could help with its fundamental treatment. Here, we investigated brain phenotyping in patients with schizophrenia (SZ) and major depressive disorder (MDD) by using electroencephalography (EEG) and conducted machine-learning-based classification of the two diseases by using EEG components.Materials and Methods: We enrolled healthy controls (HCs) (n = 30) and patients with SZ (n = 34) and MDD (n = 33). An auditory P300 (AP300) task was performed, and the N1 and P3 components were extracted. Two-group classification was conducted using linear discriminant analysis (LDA) and support vector machine (SVM) classifiers. Positive and negative symptoms and depression and/or anxiety symptoms were evaluated.Results: Considering both the results of statistical comparisons and machine learning-based classifications, patients and HCs showed significant differences in AP300, with SZ and MDD showing lower N1 and P3 than HCs. In the sum of amplitudes and cortical sources, the findings for LDA with classification accuracy (SZ vs. HCs: 71.31%, MDD vs. HCs: 74.55%), sensitivity (SZ vs. HCs: 77.67%, MDD vs. HCs: 79.00%), and specificity (SZ vs. HCs: 64.00%, MDD vs. HCs: 69.67%) supported these results. The SVM classifier showed reasonable scores between SZ and HCs and/or MDD and HCs. The comparison between SZ and MDD showed low classification accuracy (59.71%), sensitivity (65.08%), and specificity (54.83%).Conclusions: Patients with SZ and MDD showed deficiencies in N1 and P3 components in the sum of amplitudes and cortical sources, indicating attentional dysfunction in both early and late sensory/cognitive gating input. The LDA and SVM classifiers in the AP300 are useful to distinguish patients with SZ and HCs and/or MDD and HCs.

show abstract

Pain phenotypes classified by machine learning using electroencephalography features

Cited by 40 publications

References 55 publications

Machine Learning in Pain Medicine: An Up-To-Date Systematic Review

Machine Learning in Pain Medicine: An Up-To-Date Systematic Review

Distinct neocortical mechanisms underlie human SI responses to median nerve and laser evoked peripheral activation

Machine Learning-Based Electroencephalographic Phenotypes of Schizophrenia and Major Depressive Disorder

Contact Info

Product

Resources

About