Identifying resting state differences salient for resilience to chronic pain based on machine learning multivariate pattern analysis

Resting-state brain activity as a biomarker of chronic pain impairment and a mediator of its association with pain resilience

Past cross-sectional chronic pain studies have revealed aberrant resting-state brain activity in regions involved in pain processing and affect regulation. However, there is a paucity of longitudinal research examining links of resting-state activity and pain resilience with changes in chronic pain outcomes over time. In this prospective study, we assessed the status of baseline (T1) resting-state brain activity as a biomarker of later impairment from chronic pain and a mediator of the relation between pain resilience and impairment at follow-up. One hundred forty-two adults with chronic musculoskeletal pain completed a T1 assessment comprising a resting-state functional magnetic resonance imaging scan based on regional homogeneity (ReHo) and self-report measures of demographics, pain characteristics, psychological status, pain resilience, pain severity, and pain impairment. Subsequently, pain impairment was reassessed at a 6-month follow-up (T2). Hierarchical multiple regression and mediation analyses assessed relations of T1 ReHo and pain resilience scores with changes in pain impairment. Higher T1 ReHo values in the right caudate nucleus were associated with increased pain impairment at T2, after controlling for all other statistically significant self-report measures. ReHo also partially mediated associations of T1 pain resilience dimensions with T2 pain impairment. T1 right caudate nucleus ReHo emerged as a possible biomarker of later impairment from chronic musculoskeletal pain and a neural mechanism that may help to explain why pain resilience is related to lower levels of later chronic pain impairment. Findings provide empirical foundations for prospective extensions that assess the status of ReHo activity and self-reported pain resilience as markers for later impairment from chronic pain and targets for interventions to reduce impairment. PRACTITIONER POINTS: Resting-state markers of impairment: Higher baseline (T1) regional homogeneity (ReHo) values, localized in the right caudate nucleus, were associated with exacerbations in impairment from chronic musculoskeletal pain at a 6-month follow-up, independent of T1 demographics, pain experiences, and psychological factors. Mediating role of ReHo values: ReHo values in the right caudate nucleus also mediated the relationship between baseline pain resilience levels and later pain impairment among participants. Therapeutic implications: Findings provide empirical foundations for research extensions that evaluate (1) the use of resting-state activity in assessment to identify people at risk for later impairment from pain and (2) changes in resting-state activity as biomarkers for the efficacy of treatments designed to improve resilience and reduce impairment among those in need.

Cracking the Chronic Pain code: A scoping review of Artificial Intelligence in Chronic Pain research

OBJECTIVE

The aim of this review is to identify gaps and provide a direction for future research in the utilization of Artificial Intelligence (AI) in chronic pain (CP) management.

METHODS

A comprehensive literature search was conducted using various databases, including Ovid MEDLINE, Web of Science Core Collection, IEEE Xplore, and ACM Digital Library. The search was limited to studies on AI in CP research, focusing on diagnosis, prognosis, clinical decision support, self-management, and rehabilitation. The studies were evaluated based on predefined inclusion criteria, including the reporting quality of AI algorithms used.

RESULTS

After the screening process, 60 studies were reviewed, highlighting AI's effectiveness in diagnosing and classifying CP while revealing gaps in the attention given to treatment and rehabilitation. It was found that the most commonly used algorithms in CP research were support vector machines, logistic regression and random forest classifiers. The review also pointed out that attention to CP mechanisms is negligible despite being the most effective way to treat CP.

CONCLUSION

The review concludes that to achieve more effective outcomes in CP management, future research should prioritize identifying CP mechanisms, CP management, and rehabilitation while leveraging a wider range of algorithms and architectures.

SIGNIFICANCE

This review highlights the potential of AI in improving the management of CP, which is a significant personal and economic burden affecting more than 30% of the world's population. The identified gaps and future research directions provide valuable insights to researchers and practitioners in the field, with the potential to improve healthcare utilization.

Diagnosis of Chronic Musculoskeletal Pain by Using Functional Near-Infrared Spectroscopy and Machine Learning

Chronic pain (CP) has been found to cause significant alternations of the brain's structure and function due to changes in pain processing and disrupted cognitive functions, including with respect to the prefrontal cortex (PFC). However, until now, no studies have used a wearable, low-cost neuroimaging tool capable of performing functional near-infrared spectroscopy (fNIRS) to explore the functional alternations of the PFC and thus automatically achieve a clinical diagnosis of CP. In this case-control study, the pain characteristics of 19 chronic pain patients and 32 healthy controls were measured using fNIRS. Functional connectivity (FC), FC in the PFC, and spontaneous brain activity of the PFC were examined in the CP patients and compared to those of healthy controls (HCs). Then, leave-one-out cross-validation and machine learning algorithms were used to automatically achieve a diagnosis corresponding to a CP patient or an HC. The current study found significantly weaker FC, notably higher small-worldness properties of FC, and increased spontaneous brain activity during resting state within the PFC. Additionally, the resting-state fNIRS measurements exhibited excellent performance in identifying the chronic pain patients via supervised machine learning, achieving F1 score of 0.8229 using only seven features. It is expected that potential FC features can be identified, which can thus serve as a neural marker for the detection of CP using machine learning algorithms. Therefore, the present study will open a new avenue for the diagnosis of chronic musculoskeletal pain by using fNIRS and machine learning techniques.

Intrinsic Brain Functional Activity Abnormalities in Episodic Tension-Type Headache

Objective

The neurobiological basis of episodic tension-type headache (ETTH) remains largely unclear. The aim of the present study was to explore intrinsic brain functional activity alterations in ETTH.

Methods

Resting-state functional magnetic resonance imaging (rs-fMRI) data were collected from 32 patients with ETTH and 32 age- and gender-matched healthy controls (HCs). Differences in intrinsic brain functional activity between patients with ETTH and HCs were analyzed utilizing the fractional amplitude of low-frequency fluctuation (fALFF) approach. Correlation analyses were performed to examine the relationship between fALFF alterations and clinical characteristics.

Results

Compared to HCs, patients with ETTH exhibited increased fALFF in the right posterior insula and anterior insula and decreased fALFF in the posterior cingulate cortex. Moreover, the fALFF in the right anterior insula was negatively correlated with attack frequency in ETTH.

Conclusions

This study highlights alterations in the intrinsic brain functional activity in the insula and posterior cingulate cortex in ETTH that can help us understand its neurobiological underpinnings.

Neuroimaging mechanisms of acupuncture on functional reorganization for post-stroke motor improvement: a machine learning-based functional magnetic resonance imaging study

Objective

Motor recovery is crucial in stroke rehabilitation, and acupuncture can influence recovery. Neuroimaging and machine learning approaches provide new research directions to explore the brain functional reorganization and acupuncture mechanisms after stroke. We applied machine learning to predict the classification of the minimal clinically important differences (MCID) for motor improvement and identify the neuroimaging features, in order to explore brain functional reorganization and acupuncture mechanisms for motor recovery after stroke.

Methods

In this study, 49 patients with unilateral motor pathway injury (basal ganglia and/or corona radiata) after ischemic stroke were included and evaluated the motor function by Fugl-Meyer Assessment scores (FMA) at baseline and at 2-week follow-up sessions. Patients were divided by the difference between the twice FMA scores into one group showing minimal clinically important difference (MCID group, n = 28) and the other group with no minimal clinically important difference (N-MCID, n = 21). Machine learning was performed by PRoNTo software to predict the classification of the patients and identify the feature brain regions of interest (ROIs). In addition, a matched group of healthy controls (HC, n = 26) was enrolled. Patients and HC underwent magnetic resonance imaging examination in the resting state and in the acupuncture state (acupuncture at the Yanglingquan point on one side) to compare the differences in brain functional connectivity (FC) and acupuncture effects.

Results

Through machine learning, we obtained a balance accuracy rate of 75.51% and eight feature ROIs. Compared to HC, we found that the stroke patients with lower FC between these feature ROIs with other brain regions, while patients in the MCID group exhibited a wider range of lower FC. When acupuncture was applied to Yanglingquan (GB 34), the abnormal FC of patients was decreased, with different targets of effects in different groups.

Conclusion

Feature ROIs identified by machine learning can predict the classification of stroke patients with different motor improvements, and the FC between these ROIs with other brain regions is decreased. Acupuncture can modulate the bilateral cerebral hemispheres to restore abnormal FC via different targets, thereby promoting motor recovery after stroke.

Clinical trial registration

https://www.chictr.org.cn/showproj.html?proj=37359, ChiCTR1900022220.

Brain system segregation and pain catastrophizing in chronic pain progression

Pain processing involves emotional and cognitive factors that can modify pain perception. Increasing evidence suggests that pain catastrophizing (PC) is implicated, through pain-related self-thoughts, in the maladaptive plastic changes related to the maintenance of chronic pain (CP). Functional magnetic resonance imaging (fMRI) studies have shown an association between CP and two main networks: default mode (DMN) and dorsoattentional (DAN). Brain system segregation degree (SyS), an fMRI framework used to quantify the extent to which functional networks are segregated from each other, is associated with cognitive abilities in both healthy individuals and neurological patients. We hypothesized that individuals suffering from CP would show worst health-related status compared to healthy individuals and that, within CP individuals, longitudinal changes in pain experience (pain intensity and affective interference), could be predicted by SyS and PC subdomains (rumination, magnification, and helplessness). To assess the longitudinal progression of CP, two pain surveys were taken before and after an in-person assessment (physical evaluation and fMRI). We first compared the sociodemographic, health-related, and SyS data in the whole sample (no pain and pain groups). Secondly, we ran linear regression and a moderation model only in the pain group, to see the predictive and moderator values of PC and SyS in pain progression. From our sample of 347 individuals (mean age = 53.84, 55.2% women), 133 responded to having CP, and 214 denied having CP. When comparing groups, results showed significant differences in health-related questionnaires, but no differences in SyS. Within the pain group, helplessness (β = 0.325; p = 0.003), higher DMN (β = 0.193; p = 0.037), and lower DAN segregation (β = 0.215; p = 0.014) were strongly associated with a worsening in pain experience over time. Moreover, helplessness moderated the association between DMN segregation and pain experience progression (p = 0.003). Our findings indicate that the efficient functioning of these networks and catastrophizing could be used as predictors of pain progression, bringing new light to the influence of the interplay between psychological aspects and brain networks. Consequently, approaches focusing on these factors could minimize the impact on daily life activities.

Characterization of white matter microstructural abnormalities associated with cognitive dysfunction in cerebral small vessel disease with cerebral microbleeds

BACKGROUND

Diffusion tensor imaging (DTI) is recommended as a sensitive method to explore white matter (WM) microstructural alterations. Cerebral small vessel disease (CSVD) may be accompanied by extensive WM microstructural deterioration, while cerebral microbleeds (CMBs) are an important factor affecting CSVD.

METHODS

Fractional anisotropy (FA), mean diffusivity (MD), axial diffusivity (AD) and radial diffusivity (RD) images from 49 CSVD patients with CMBs (CSVD-c), 114 CSVD patients without CMBs (CSVD-n), and 83 controls were analyzed using DTI-derived tract-based spatial statistics to detect WM diffusion changes among groups.

RESULTS

Compared with the CSVD-n and control groups, the CSVD-c group showed a significant FA decrease and AD, RD and MD increases mainly in the cognitive and sensorimotor-related WM tracts. There was no significant difference in any diffusion metric between the CSVD-n and control groups. Furthermore, the widespread regional diffusion alterations among groups were significantly correlated with cognitive parameters in both the CSVD-c and CSVD-n groups. Notably, we applied the multiple kernel learning technique in multivariate pattern analysis to combine multiregion and multiparameter diffusion features, yielding an average accuracy >77 % for three binary classifications, which showed a considerable improvement over the single modality approach.

LIMITATIONS

We only grouped the study according to the presence or absence of CMBs.

CONCLUSIONS

CSVD patients with CMBs have extensive WM microstructural deterioration. Combining DTI-derived diffusivity and anisotropy metrics can provide complementary information for assessing WM alterations associated with cognitive dysfunction and serve as a potential discriminative pattern to detect CSVD at the individual level.

Altered brain functional activity and connectivity in bone metastasis pain of lung cancer patients: A preliminary resting-state fMRI study

Bone metastasis pain (BMP) is one of the most prevalent symptoms among cancer survivors. The present study aims to explore the brain functional activity and connectivity patterns in BMP of lung cancer patients preliminarily. Thirty BMP patients and 33 healthy controls (HCs) matched for age and sex were recruited from inpatients and communities, respectively. All participants underwent fMRI data acquisition and pain assessment. Low-frequency fluctuations (ALFF) and regional homogeneity (ReHo) were applied to evaluate brain functional activity. Then, functional connectivity (FC) was calculated for the ALFF- and ReHo-identified seed brain regions. A two-sample t-test or Manny–Whitney U-test was applied to compare demographic and neuropsychological data as well as the neuroimaging indices according to the data distribution. A correlation analysis was conducted to explore the potential relationships between neuroimaging indices and pain intensity. Receiver operating characteristic curve analysis was applied to assess the classification performance of neuroimaging indices in discriminating individual subjects between the BMP patients and HCs. No significant intergroup differences in demographic and neuropsychological data were noted. BMP patients showed reduced ALFF and ReHo largely in the prefrontal cortex and increased ReHo in the bilateral thalamus and left fusiform gyrus. The lower FC was found within the prefrontal cortex. No significant correlation between the neuroimaging indices and pain intensity was observed. The neuroimaging indices showed satisfactory classification performance between the BMP patients and HCs, and the combined ALFF and ReHo showed a better accuracy rate (93.7%) than individual indices. In conclusion, altered brain functional activity and connectivity in the prefrontal cortex, fusiform gyrus, and thalamus may be associated with the neuropathology of BMP and may represent a potential biomarker for classifying BMP patients and healthy controls.