Dataset Information

Prediction of Differential Pharmacologic Response in Chronic Pain Using Functional Neuroimaging Biomarkers and a Support Vector Machine Algorithm: An Exploratory Study.

ABSTRACT:

Objective

There is increasing demand for prediction of chronic pain treatment outcomes using machine-learning models, in order to improve suboptimal pain management. In this exploratory study, we used baseline brain functional connectivity patterns from chronic pain patients with fibromyalgia (FM) to predict whether a patient would respond differentially to either milnacipran or pregabalin, 2 drugs approved by the US Food and Drug Administration for the treatment of FM.

Methods

FM patients participated in 2 separate double-blind, placebo-controlled crossover studies, one evaluating milnacipran (n = 15) and one evaluating pregabalin (n = 13). Functional magnetic resonance imaging during rest was performed before treatment to measure intrinsic functional brain connectivity in several brain regions involved in pain processing. A support vector machine algorithm was used to classify FM patients as responders, defined as those with a ≥20% improvement in clinical pain, to either milnacipran or pregabalin.

Results

Connectivity patterns involving the posterior cingulate cortex (PCC) and dorsolateral prefrontal cortex (DLPFC) individually classified pregabalin responders versus milnacipran responders with 77% accuracy. Performance of this classification improved when both PCC and DLPFC connectivity patterns were combined, resulting in a 92% classification accuracy. These results were not related to confounding factors, including head motion, scanner sequence, or hardware status. Connectivity patterns failed to differentiate drug nonresponders across the 2 studies.

Conclusion

Our findings indicate that brain functional connectivity patterns used in a machine-learning framework differentially predict clinical response to pregabalin and milnacipran in patients with chronic pain. These findings highlight the promise of machine learning in pain prognosis and treatment prediction.

SUBMITTER: Ichesco E

PROVIDER: S-EPMC8597096 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:In the pursuit of clinical utility, neuroimaging researchers of psychiatric and neurological illness are increasingly using analyses, such as support vector machine, that allow inference at the single-subject level. Recent studies employing single-modality data, however, suggest that classification accuracies must be improved for such utility to be realized. One possible solution is to integrate different data types to provide a single combined output classification; either by generating a single decision function based on an integrated kernel matrix, or, by creating an ensemble of multiple single modality classifiers and integrating their predictions. Here, we describe four integrative approaches: (1) an un-weighted sum of kernels, (2) multi-kernel learning, (3) prediction averaging, and (4) majority voting, and compare their ability to enhance classification accuracy relative to the best single-modality classification accuracy. We achieve this by integrating structural, functional, and diffusion tensor magnetic resonance imaging data, in order to compare ultra-high risk (n = 19), first episode psychosis (n = 19) and healthy control subjects (n = 23). Our results show that (i) whilst integration can enhance classification accuracy by up to 13%, the frequency of such instances may be limited, (ii) where classification can be enhanced, simple methods may yield greater increases relative to more computationally complex alternatives, and, (iii) the potential for classification enhancement is highly influenced by the specific diagnostic comparison under consideration. In conclusion, our findings suggest that for moderately sized clinical neuroimaging datasets, combining different imaging modalities in a data-driven manner is no "magic bullet" for increasing classification accuracy. However, it remains possible that this conclusion is dependent on the use of neuroimaging modalities that had little, or no, complementary information to offer one another, and that the integration of more diverse types of data would have produced greater classification enhancement. We suggest that future studies ideally examine a greater variety of data types (e.g., genetic, cognitive, and neuroimaging) in order to identify the data types and combinations optimally suited to the classification of early stage psychosis.

Project description:BackgroundThe prevalence of Alzheimer's disease (AD) varies based on gender. Due to the lack of early stage biomarkers, most of them are diagnosed at the terminal stage. This study aimed to explore sex-specific signaling pathways and identify diagnostic biomarkers of AD.MethodsMicroarray dataset for blood was obtained from the Gene Expression Omnibus (GEO) database of GSE63060 to conduct differentially expressed genes (DEGs) analysis by R software limma. Gene Ontology (GO) analysis, Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analysis and Gene set enrichment analysis (GSEA) were conducted. Immune checkpoint gene expression was compared between females and males. Using CytoHubba, we identified hub genes in a protein-protein interaction network (PPI). Then, we evaluated their distinct effectiveness using unsupervised hierarchical clustering. Support vector machine (SVM) and ten-fold cross-validation were used to further verify these biomarkers. Lastly, we confirmed our findings by using another independent dataset.ResultsA total of 37 female-specific DEGs and 27 male-specific DEGs were identified from GSE63060 datasets. Analyses of enrichment showed that female-specific DEGs primarily focused on energy metabolism, while male-specific DEGs mostly involved in immune regulation. Three immune-checkpoint-relevant genes dysregulated in males. In females, however, these eight genes were not differentially expressed. SNRPG, RPS27A, COX7A2, ATP5PO, LSM3, COX7C, PFDN5, HINT1, PSMA6, RPS3A and RPL31 were regarded as hub genes for females, while SNRPG, RPL31, COX7C, RPS27A, RPL35A, RPS3A, RPS20 and PFDN5 were regarded as hub genes for males. Thirteen hub genes mentioned above was significantly lower in both AD and mild cognitive impairment (MCI). The diagnostic model of 15-marker panel (13 hub genes with sex and age) was developed. Both the training dataset and the independent validation dataset have area under the curve (AUC) with a high value (0.919, 95%CI 0.901-0.929 and 0.803, 95%CI 0.789-0.826). Based on GSEA for hub genes, they were associated with some aspects of AD pathogenesis.ConclusionDEGs in males and females contribute differently to AD pathogenesis. Algorithms combining blood-based biomarkers may improve AD diagnostic accuracy, but large validation studies are needed.