Dataset Information

A tool for classifying individuals with chronic back pain: using multivariate pattern analysis with functional magnetic resonance imaging data.

ABSTRACT: Chronic pain is one of the most prevalent health problems in the world today, yet neurological markers, critical to diagnosis of chronic pain, are still largely unknown. The ability to objectively identify individuals with chronic pain using functional magnetic resonance imaging (fMRI) data is important for the advancement of diagnosis, treatment, and theoretical knowledge of brain processes associated with chronic pain. The purpose of our research is to investigate specific neurological markers that could be used to diagnose individuals experiencing chronic pain by using multivariate pattern analysis with fMRI data. We hypothesize that individuals with chronic pain have different patterns of brain activity in response to induced pain. This pattern can be used to classify the presence or absence of chronic pain. The fMRI experiment consisted of alternating 14 seconds of painful electric stimulation (applied to the lower back) with 14 seconds of rest. We analyzed contrast fMRI images in stimulation versus rest in pain-related brain regions to distinguish between the groups of participants: 1) chronic pain and 2) normal controls. We employed supervised machine learning techniques, specifically sparse logistic regression, to train a classifier based on these contrast images using a leave-one-out cross-validation procedure. We correctly classified 92.3% of the chronic pain group (N?=?13) and 92.3% of the normal control group (N?=?13) by recognizing multivariate patterns of activity in the somatosensory and inferior parietal cortex. This technique demonstrates that differences in the pattern of brain activity to induced pain can be used as a neurological marker to distinguish between individuals with and without chronic pain. Medical, legal and business professionals have recognized the importance of this research topic and of developing objective measures of chronic pain. This method of data analysis was very successful in correctly classifying each of the two groups.

SUBMITTER: Callan D

PROVIDER: S-EPMC4048172 | biostudies-literature | 2014

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A tool for classifying individuals with chronic back pain: using multivariate pattern analysis with functional magnetic resonance imaging data.

Callan Daniel D Mills Lloyd L Nott Connie C England Robert R England Shaun S

PloS one 20140606 6

Chronic pain is one of the most prevalent health problems in the world today, yet neurological markers, critical to diagnosis of chronic pain, are still largely unknown. The ability to objectively identify individuals with chronic pain using functional magnetic resonance imaging (fMRI) data is important for the advancement of diagnosis, treatment, and theoretical knowledge of brain processes associated with chronic pain. The purpose of our research is to investigate specific neurological markers ...[more]

PMID: 24905072

Similar Datasets

Project description:Study designRetrospective cohort study.ObjectiveTo determine the effect of early (receipt ?30 d postonset) magnetic resonance imaging (MRI) on disability and medical cost outcomes in patients with acute, disabling, work-related low back pain (LBP) with and without radiculopathy.Summary of background dataEvidence-based guidelines suggest that, except for "red flags," MRI is indicated to evaluate patients with persistent radicular pain, after 1 month of conservative management, who are candidates for surgery or epidural steroid injections. Prior research has suggested an independent iatrogenic effect of nonindicated early MRI, but it had limited clinical information and/or patient populations.MethodsA nationally representative sample of workers with acute, disabling, occupational LBP was randomly selected, oversampling those with radiculopathy diagnoses (N = 1000). Clinical information from medical reports was used to exclude cases for which early MRI might have been indicated, or MRI occurred more than 30 days postonset (final cohort = 555). Clinical information was also used to categorize cases into "nonspecific LBP" and "radiculopathy" groups and further divided into "early-MRI" and "no-MRI" subgroups. The Cox proportional hazards model examined the association of early MRI with duration of the first episode of disability. Multivariate linear regression models examined the association with medical costs. All models adjusted for demographic and medical severity measures.ResultsIn our sample, 37% of the nonspecific LBP and 79.9% of the radiculopathy cases received early MRI. The early-MRI groups had similar outcomes regardless of radiculopathy status: much lower rates of going off disability and, on average, $12,948 to $13,816 higher medical costs than the no-MRI groups. Even in a subgroup with relatively minimal disability impact (?30 d of total lost time post-MRI), medical costs were, on average, $7643 to $8584 higher in the early-MRI groups.ConclusionEarly MRI without indication has a strong iatrogenic effect in acute LBP, regardless of radiculopathy status. Providers and patients should be made aware that when early MRI is not indicated, it provides no benefits, and worse outcomes are likely.Level of evidence3.

Project description:PurposeTo conduct a 10-year longitudinal analysis of the relationship between magnetic resonance imaging (MRI) findings and low back pain (LBP).Materials and methodsNinety-one volunteers with a history of LBP, but without current LBP were recruited between 2005 and 2006. Participants' baseline demographics and MRI findings were recorded. All volunteers were invited for a follow-up MRI in 2016; of these, 49 volunteers (53.8%) participated in the follow-up. We enquired whether they had LBP history during the 10 years between the baseline and follow-up examinations. Sagittal T1 and T2-weighted MRI were used to assess the intervertebral space from T12/L1 to L5/S1. We evaluated the presence of disc degeneration by Pfirrmann's grading system, disc bulging, high intensity zone (HIZ), spondylolisthesis, and any type of Modic changes in the follow-up MRIs. We compared the follow-up MRI findings with the baseline findings; the progress of each finding over the 10 years were also compared between the groups with (n = 36) and without (n = 13) LBP.ResultsAverage age of the study participants at follow-up was 44.8 years; 25 were female and 24 were male. Average age, sex, body mass index, and smoking habits of those who did and did not participate in the follow-up study, as well as the demographic characteristics of those who did and did not have LBP history during the 10 years, were not significantly different. Compared with the group without LBP history, the group that had LBP history during the 10 years did not have a significantly increased prevalence of disc degeneration, disc bulging, and HIZ in the follow-up and baseline MRIs. Spondylolisthesis and any type of Modic changes were also not associated with LBP history during the 10 years.ConclusionsFollow-up MRI findings consistent with Pfirrmann grading ≥4, disc bulging, HIZ, spondylolisthesis, and any type of Modic changes were not associated with LBP history during the 10 years between the baseline and follow-up study. The progresses of these findings were also not associated with the LBP history. In addition, baseline MRI findings were not associated with LBP history during the 10 years; therefore, our data suggest that baseline MRI findings cannot predict future LBP.

Dataset Information

A tool for classifying individuals with chronic back pain: using multivariate pattern analysis with functional magnetic resonance imaging data.

Publications

A tool for classifying individuals with chronic back pain: using multivariate pattern analysis with functional magnetic resonance imaging data.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets