Predicting survival of NSCLC patients treated with immune checkpoint inhibitors: Impact and timing of immune-related adverse events and prior tyrosine kinase inhibitor therapy.

Introduction: Immune checkpoint inhibitors (ICIs) produce a broad spectrum of immune-related adverse events (irAEs) affecting various organ systems. While ICIs are established as a therapeutic option in non-small cell lung cancer (NSCLC) treatment, most patients receiving ICI relapse. Additionally, the role of ICIs on survival in patients receiving prior targeted tyrosine kinase inhibitor (TKI) therapy has not been well-defined. Objective: To investigate the impact of irAEs, the relative time of occurrence, and prior TKI therapy to predict clinical outcomes in NSCLC patients treated with ICIs. Methods: A single center retrospective cohort study identified 354 adult patients with NSCLC receiving ICI therapy between 2014 and 2018. Survival analysis utilized overall survival (OS) and real-world progression free survival (rwPFS) outcomes. Model performance matrices for predicting 1-year OS and 6-month rwPFS using linear regression baseline, optimal, and machine learning modeling approaches. Results: Patients experiencing an irAE were found to have a significantly longer OS and rwPFS compared to patients who did not (median OS 25.1 vs. 11.1 months; hazard ratio [HR] 0.51, confidence interval [CI] 0.39- 0.68, P-value <0.001, median rwPFS 5.7 months vs. 2.3; HR 0.52, CI 0.41- 0.66, P-value <0.001, respectively). Patients who received TKI therapy before initiation of ICI experienced significantly shorter OS than patients without prior TKI therapy (median OS 7.6 months vs. 18.5 months; P-value < 0.01). After adjusting for other variables, irAEs and prior TKI therapy significantly impacted OS and rwPFS. Lastly, the performances of models implementing logistic regression and machine learning approaches were comparable in predicting 1-year OS and 6-month rwPFS. Conclusion: The occurrence of irAEs, the timing of the events, and prior TKI therapy were significant predictors of survival in NSCLC patients on ICI therapy. Therefore, our study supports future prospective studies to investigate the impact of irAEs, and sequence of therapy on the survival of NSCLC patients taking ICIs.

Stroke mortality prediction based on ensemble learning and the combination of structured and textual data.

For severe cerebrovascular diseases such as stroke, the prediction of short-term mortality of patients has tremendous medical significance. In this study, we combined machine learning models Random Forest classifier (RF), Adaptive Boosting (AdaBoost), Extremely Randomised Trees (ExtraTree) classifier, XGBoost classifier, TabNet, and DistilBERT to construct a multi-level prediction model that used bioassay data and radiology text reports from haemorrhagic and ischaemic stroke patients to predict six-month mortality. The performances of the prediction models were measured using the area under the receiver operating characteristic curve (AUROC), the area under the precision-recall curve (AUPRC), precision, recall, and F1-score. The prediction models were built with the use of data from 19,616 haemorrhagic stroke patients and 50,178 ischaemic stroke patients. Novel six-month mortality prediction models for these patients were developed, which enhanced the performance of the prediction models by combining laboratory test data, structured data, and textual radiology report data. The achieved performances were as follows: AUROC = 0.89, AUPRC = 0.70, precision = 0.52, recall = 0.78, and F1 score = 0.63 for haemorrhagic patients, and AUROC = 0.88, AUPRC = 0.54, precision = 0.34, recall = 0.80, and F1 score = 0.48 for ischaemic patients. Such models could be used for mortality risk assessment and early identification of high-risk stroke patients. This could contribute to more efficient utilisation of healthcare resources for stroke survivors.

Identifying Predictors of COVID-19 Mortality Using Machine Learning.

(1) Background: Coronavirus disease 2019 (COVID-19) is a dominant, rapidly spreading respiratory disease. However, the factors influencing COVID-19 mortality still have not been confirmed. The pathogenesis of COVID-19 is unknown, and relevant mortality predictors are lacking. This study aimed to investigate COVID-19 mortality in patients with pre-existing health conditions and to examine the association between COVID-19 mortality and other morbidities. (2) Methods: De-identified data from 113,882, including 14,877 COVID-19 patients, were collected from the UK Biobank. Different types of data, such as disease history and lifestyle factors, from the COVID-19 patients, were input into the following three machine learning models: Deep Neural Networks (DNN), Random Forest Classifier (RF), eXtreme Gradient Boosting classifier (XGB) and Support Vector Machine (SVM). The Area under the Curve (AUC) was used to measure the experiment result as a performance metric. (3) Results: Data from 14,876 COVID-19 patients were input into the machine learning model for risk-level mortality prediction, with the predicted risk level ranging from 0 to 1. Of the three models used in the experiment, the RF model achieved the best result, with an AUC value of 0.86 (95% CI 0.84-0.88). (4) Conclusions: A risk-level prediction model for COVID-19 mortality was developed. Age, lifestyle, illness, income, and family disease history were identified as important predictors of COVID-19 mortality. The identified factors were related to COVID-19 mortality.

Effect of chemotherapy on default mode network connectivity in older women with breast cancer.

Chemotherapy may impair cognition and contribute to accelerated aging. The purpose of this study was to assess the effects of chemotherapy on the connectivity of the default mode network (DMN) in older women with breast cancer. This prospective longitudinal study enrolled women aged ≥ 60 years with stage I-III breast cancer (CTx group) and matched healthy controls (HC group). Study assessments, consisting of resting-state functional MRI (rs-fMRI) and the Picture Sequence Memory (psm) test for episodic memory from the NIH Toolbox for Cognition, were obtained at baseline and within one month after the completion of chemotherapy for the CTx group and at matched intervals for the HC group. Two-sample t-test and FDR multiple comparison were used for statistical inference. Our analysis of the CTx group (N = 19; 60-82 years of age, mean = 66.6, SD = 5.24) compared to the HC group (N = 14; 60-78 years of age, mean = 68.1, SD = 5.69) revealed weaker DMN subnetwork connectivity in the anterior brain but stronger connectivity in the posterior brain at baseline. After chemotherapy, this pattern was reversed, with stronger anterior connectivity and weaker posterior connectivity. In addition, the meta-level functional network connectivity (FNC) among the DMN subnetworks after chemotherapy was consistently weaker than the baseline FNC as seen in the couplings between anterior cingulate cortex (ACC) and retrosplenial (rSplenia) region, with ΔFNC('ACC','rSplenia')=-0.14, t value=-2.44, 95 %CI=[-0.27,-0.10], pFDR<0.05). The baseline FNC matrices of DMN subnetworks were correlated with psm scores (corr = 0.58, p < 0.05). Our results support DMN alterations as a potential neuroimaging biomarker for cancer-related cognitive impairment and accelerated aging.

Diagnostic Utility of Radiomics in Thyroid and Head and Neck Cancers.

Radiomics is an emerging field in radiology that utilizes advanced statistical data characterizing algorithms to evaluate medical imaging and objectively quantify characteristics of a given disease. Due to morphologic heterogeneity and genetic variation intrinsic to neoplasms, radiomics have the potential to provide a unique insight into the underlying tumor and tumor microenvironment. Radiomics has been gaining popularity due to potential applications in disease quantification, predictive modeling, treatment planning, and response assessment - paving way for the advancement of personalized medicine. However, producing a reliable radiomic model requires careful evaluation and construction to be translated into clinical practices that have varying software and/or medical equipment. We aim to review the diagnostic utility of radiomics in otorhinolaryngology, including both cancers of the head and neck as well as the thyroid.

Analysis of Gut Microbiome Using Explainable Machine Learning Predicts Risk of Diarrhea Associated With Tyrosine Kinase Inhibitor Neratinib: A Pilot Study.

Neratinib has great efficacy in treating HER2+ breast cancer but is associated with significant gastrointestinal toxicity. The objective of this pilot study was to understand the association of gut microbiome and neratinib-induced diarrhea. Twenty-five patients (age ≥ 60) were enrolled in a phase II trial evaluating safety and tolerability of neratinib in older adults with HER2+ breast cancer (NCT02673398). Fifty stool samples were collected from 11 patients at baseline and during treatment. 16S rRNA analysis was performed and relative abundance data were generated. Shannon's diversity was calculated to examine gut microbiome dysbiosis. An explainable tree-based approach was utilized to classify patients who might experience neratinib-related diarrhea (grade ≥ 1) based on pre-treatment baseline microbial relative abundance data. The hold-out Area Under Receiver Operating Characteristic and Area Under Precision-Recall Curves of the model were 0.88 and 0.95, respectively. Model explanations showed that patients with a larger relative abundance of Ruminiclostridium 9 and Bacteroides sp. HPS0048 may have reduced risk of neratinib-related diarrhea and was confirmed by Kruskal-Wallis test (p ≤ 0.05, uncorrected). Our machine learning model identified microbiota associated with reduced risk of neratinib-induced diarrhea and the result from this pilot study will be further verified in a larger study. CLINICAL TRIAL REGISTRATION: ClinicalTrials.gov, identifier NCT02673398.

Predicting Survival Duration With MRI Radiomics of Brain Metastases From Non-small Cell Lung Cancer.

Background: Brain metastases are associated with poor survival. Molecular genetic testing informs on targeted therapy and survival. The purpose of this study was to perform a MR imaging-based radiomic analysis of brain metastases from non-small cell lung cancer (NSCLC) to identify radiomic features that were important for predicting survival duration. Methods: We retrospectively identified our study cohort via an institutional database search for patients with brain metastases from EGFR, ALK, and/or KRAS mutation-positive NSCLC. We segmented the brain metastatic tumors on the brain MR images, extracted radiomic features, constructed radiomic scores from significant radiomic features based on multivariate Cox regression analysis (p < 0.05), and built predictive models for survival duration. Result: Of the 110 patients in the cohort (mean age 57.51 ± 12.32 years; range: 22-85 years, M:F = 37:73), 75, 26, and 15 had NSCLC with EGFR, ALK, and KRAS mutations, respectively. Predictive modeling of survival duration using both clinical and radiomic features yielded areas under the receiver operative characteristic curve of 0.977, 0.905, and 0.947 for the EGFR, ALK, and KRAS mutation-positive groups, respectively. Radiomic scores enabled the separation of each mutation-positive group into two subgroups with significantly different survival durations, i.e., shorter vs. longer duration when comparing to the median survival duration of the group. Conclusion: Our data supports the use of radiomic scores, based on MR imaging of brain metastases from NSCLC, as non-invasive biomarkers for survival duration. Future research with a larger sample size and external cohorts is needed to validate our results.

Explainable Tree-Based Predictions for Unplanned 30-Day Readmission of Patients With Cancer Using Clinical Embeddings.

PURPOSE: Thirty-day unplanned readmission is one of the key components in measuring quality in patient care. Risk of readmission in oncology patients may be associated with a wide variety of specific factors including laboratory results and diagnoses, and it is hard to include all such features using traditional approaches such as one-hot encoding in predictive models. METHODS: We used clinical embeddings to represent complex medical concepts in lower dimensional spaces. For predictive modeling, we used gradient-boosted trees and adopted the shapley additive explanation framework to offer consistent individualized predictions. We used retrospective inpatient data between 2013 and 2018 with temporal split for training and testing. RESULTS: Our best performing model predicting readmission at discharge using clinical embeddings showed a testing area under receiver operating characteristic curve of 0.78 (95% CI, 0.77 to 0.80). Use of clinical embeddings led to up to 23.1% gain in area under precision-recall curve and 6% in area under receiver operating characteristic curve. Hematology models had more performance gain over surgery and medical oncology. Our study was the first to develop (1) explainable predictive models for the hematology population and (2) dynamic models to keep track of readmission risk throughout the duration of patient visit. CONCLUSION: To our knowledge, our study was the first to develop (1) explainable predictive models for the hematology population and (2) dynamic models to keep track of readmission risk throughout the duration of patient visit.

Radiogenomics of lung cancer.

Machine learning (ML) and artificial intelligence (AI) are aiding in improving sensitivity and specificity of diagnostic imaging. The rapid adoption of these advanced ML algorithms is transforming imaging analysis; taking us from noninvasive detection of pathology to noninvasive precise diagnosis of the pathology by identifying whether detected abnormality is a secondary to infection, inflammation and/or neoplasm. This is led to the emergence of "Radiobiogenomics"; referring to the concept of identifying biologic (genomic, proteomic) alterations in the detected lesion. Radiobiogenomic involves image segmentation, feature extraction, and ML model to predict underlying tumor genotype and clinical outcomes. Lung cancer is the most common cause of cancer related death worldwide. There are several histologic subtypes of lung cancer, e.g., small cell lung cancer (SCLC), non-small cell lung cancer (NSCLC) (adenocarcinoma, squamous cell carcinoma). These variable histologic subtypes not only appear different at microscopic level, but these also differ at genetic and transcription level. This intrinsic heterogeneity reveals itself as different morphologic appearances on diagnostic imaging, such as CT, PET/CT and MRI. Traditional evaluation of imaging findings of lung cancer is limited to morphologic characteristics, such as lesion size, margins, density. Radiomics takes image analysis a step further by looking at imaging phenotype with higher order statistics in efforts to quantify intralesional heterogeneity. This heterogeneity, in turn, can be potentially used to extract intralesional genomic and proteomic data. This review aims to highlight novel concepts in ML and AI and their potential applications in identifying radiobiogenomics of lung cancer.

Differentiating Peripherally-Located Small Cell Lung Cancer From Non-small Cell Lung Cancer Using a CT Radiomic Approach.

Lung cancer can be classified into two main categories: small cell lung cancer (SCLC) and non-small cell lung cancer (NSCLC), which are different in treatment strategy and survival probability. The lung CT images of SCLC and NSCLC are similar such that their subtle differences are hardly visually discernible by the human eye through conventional imaging evaluation. We hypothesize that SCLC/NSCLC differentiation could be achieved via computerized image feature analysis and classification in feature space, as termed a radiomic model. The purpose of this study was to use CT radiomics to differentiate SCLC from NSCLC adenocarcinoma. Patients with primary lung cancer, either SCLC or NSCLC adenocarcinoma, were retrospectively identified. The post-diagnosis pre-treatment lung CT images were used to segment the lung cancers. Radiomic features were extracted from histogram-based statistics, textural analysis of tumor images and their wavelet transforms. A minimal-redundancy-maximal-relevance method was used for feature selection. The predictive model was constructed with a multilayer artificial neural network. The performance of the SCLC/NSCLC adenocarcinoma classifier was evaluated by the area under the receiver operating characteristic curve (AUC). Our study cohort consisted of 69 primary lung cancer patients with SCLC (n = 35; age mean ± SD = 66.91± 9.75 years), and NSCLC adenocarcinoma (n = 34; age mean ± SD = 58.55 ± 11.94 years). The SCLC group had more male patients and smokers than the NSCLC group (P < 0.05). Our SCLC/NSCLC classifier achieved an overall performance of AUC of 0.93 (95% confidence interval = [0.85, 0.97]), sensitivity = 0.85, and specificity = 0.85). Adding clinical data such as smoking history could improve the performance slightly. The top ranking radiomic features were mostly textural features. Our results showed that CT radiomics could quantitatively represent tumor heterogeneity and therefore could be used to differentiate primary lung cancer subtypes with satisfying results. CT image processing with the wavelet transformation technique enhanced the radiomic features for SCLC/NSCLC classification. Our pilot study should motivate further investigation of radiomics as a non-invasive approach for early diagnosis and treatment of lung cancer.

Radiomic prediction of mutation status based on MR imaging of lung cancer brain metastases.

Lung cancer metastases comprise most of all brain metastases in adults and most brain metastases are diagnosed by magnetic resonance (MR) scans. The purpose of this study was to conduct an MR imaging-based radiomic analysis of brain metastatic lesions from patients with primary lung cancer to classify mutational status of the metastatic disease. We retrospectively identified lung cancer patients with brain metastases treated at our institution between 2009 and 2017 who underwent genotype testing of their primary lung cancer. Brain MR Images were used for segmentation of enhancing tumors and peritumoral edema, and for radiomic feature extraction. The most relevant radiomic features were identified and used with clinical data to train random forest classifiers to classify the mutation status. Of 110 patients in the study cohort (mean age 57.51 ± 12.32 years; M: F = 37:73), 75 had an EGFR mutation, 21 had an ALK translocation, and 15 had a KRAS mutation. One patient had both ALK translocation and EGFR mutation. Majority of radiomic features most relevant for mutation classification were textural. Model building using both radiomic features and clinical data yielded more accurate classifications than using either alone. For classification of EGFR, ALK, and KRAS mutation status, the model built with both radiomic features and clinical data resulted in area-under-the-curve (AUC) values based on cross-validation of 0.912, 0.915, and 0.985, respectively. Our study demonstrated that MR imaging-based radiomic analysis of brain metastases in patients with primary lung cancer may be used to classify mutation status. This approach may be useful for devising treatment strategies and informing prognosis.

Effects of chemotherapy on aging white matter microstructure: A longitudinal diffusion tensor imaging study.

OBJECTIVE: We aimed to use diffusion tensor imaging (DTI) to detect alterations in white matter microstructure in older patients with breast cancer receiving chemotherapy. METHODS: We recruited women age ≥60 years with stage I-III breast cancer (chemotherapy [CT] group; n = 19) to undergo two study assessments: at baseline and within one month after chemotherapy. Each assessment consisted of a brain magnetic resonance imaging scan with DTI and neuropsychological (NP) testing using the National Institutes of Health (NIH) Toolbox Cognition Battery. An age- and sex-matched group of healthy controls (HC, n = 14) underwent the same assessments at matched intervals. Four DTI parameters (fractional anisotropy [FA], mean diffusivity [MD], axial diffusivity [AD], and radial diffusivity [RD]) were calculated and correlated with NP testing scores. RESULTS: For CT group but not HCs, we detected statistically significant increases in MD and RD in the genu of the corpus callosum from time point 1 to time point 2 at p < 0.01, effect size:0.3655 and 0.3173, and 95% confidence interval: from 0.1490 to 0.5821, and from 0.1554 to 0.4792, for MD and RD respectively. AD values increased for the CT group and decreased for the HC group over time, resulting in significant between-group differences (p = 0.0056, effect size:1.0215, 95% confidence interval: from 0.2773 to 1.7657). There were no significant correlations between DTI parameters and NP scores (p > 0.05). CONCLUSIONS: We identified alterations in white matter microstructures in older women with breast cancer undergoing chemotherapy. These findings may potentially serve as neuroimaging biomarkers for identifying cognitive impairment in older adults with cancer.

Assessing Cerebral White Matter Microstructure in Children With Congenital Sensorineural Hearing Loss: A Tract-Based Spatial Statistics Study.

OBJECTIVES: To assess the microstructural properties of cerebral white matter in children with congenital sensorineural hearing loss (CSNHL). METHODS: Children (>4 years of age) with profound CSNHL and healthy controls with normal hearing (the control group) were enrolled and underwent brain magnetic resonance imaging (MRI) scans with diffusion tensor imaging (DTI). DTI parameters including fractional anisotropy, mean diffusivity, axial diffusivity, and radial diffusivity were obtained from a whole-brain tract-based spatial statistics analysis and were compared between the two groups. In addition, a region of interest (ROI) approach focusing on auditory cortex, i.e., Heschl's gyrus, using visual cortex, i.e., forceps major as an internal control, was performed. Correlations between mean DTI values and age were obtained with the ROI method. RESULTS: The study cohort consisted of 23 children with CSHNL (11 boys and 12 girls; mean age ± SD: 7.21 ± 2.67 years; range: 4.1-13.5 years) and 18 children in the control group (11 boys and 7 girls; mean age ± SD: 10.86 ± 3.56 years; range: 4.5-15.3 years). We found the axial diffusivity values being significantly greater in the left anterior thalamic radiation, right corticospinal tract, and corpus callosum in the CSHNL group than in the control group (p < 0.05). Significantly higher radial diffusivity values in the white matter tracts were noted in the CSHNL group as compared to the control group (p < 0.05). The fractional anisotropy values in the Heschl's gyrus in the CSNHL group were lower compared to the control group (p = 0.0015). There was significant negative correlation between the mean fractional anisotropy values in Heschl's gyrus and age in the CSNHL group < 7 years of age (r = -0.59, p = 0.004). CONCLUSION: Our study showed higher axial and radial diffusivities in the children affected by CNHNL as compared to the hearing children. We also found lower fractional anisotropy values in the Heschl's gyrus in the CSNHL group. Furthermore, we identified negative correlation between the fractional anisotropy values and age up to 7 years in the children born deaf. Our study findings suggest that myelination and axonal structure may be affected due to acoustic deprivation. This information may help to monitor hearing rehabilitation in the deaf children.

Intrinsic brain activity changes associated with adjuvant chemotherapy in older women with breast cancer: a pilot longitudinal study.

PURPOSE: Older cancer patients are at increased risk of cancer-related cognitive impairment. The purpose of this study was to assess the alterations in intrinsic brain activity associated with adjuvant chemotherapy in older women with breast cancer. METHODS: Chemotherapy treatment (CT) group included sixteen women aged ≥ 60 years (range 60-82 years) with stage I-III breast cancers, who underwent both resting-state functional magnetic resonance imaging (rs-fMRI) and neuropsychological testing with NIH Toolbox for Cognition before adjuvant chemotherapy, at time point 1 (TP1), and again within 1 month after completing chemotherapy, at time point 2 (TP2). Fourteen age- and sex-matched healthy controls (HC) underwent the same assessments at matched intervals. Three voxel-wise rs-fMRI parameters: amplitude of low-frequency fluctuation (ALFF), fractional ALFF (fALFF), and regional homogeneity, were computed at each time point. The changes in rs-fMRI parameters from TP1 to TP2 for each group, the group differences in changes (the CT group vs. the HC group), and the group difference in the baseline rs-fMRI parameters were assessed. In addition, correlative analysis between the rs-fMRI parameters and neuropsychological testing scores was also performed. RESULTS: In the CT group, one brain region, which included parts of the bilateral subcallosal gyri and right anterior cingulate gyrus, displayed increased ALFF from TP1 to TP2 (cluster p-corrected = 0.024); another brain region in the left precuneus displayed decreased fALFF from TP1 to TP2 (cluster level p-corrected = 0.025). No significant changes in the rs-fMRI parameters from TP1 to TP2 were observed in the HC group. Although ALFF and fALFF alterations were observed only in the CT group, none of the between-group differences in rs-fMRI parameter changes reached statistical significance. CONCLUSIONS: Our study results of ALFF and fALFF alterations in the chemotherapy-treated women suggest that adjuvant chemotherapy may affect intrinsic brain activity in older women with breast cancer.

Template-based prediction of vigilance fluctuations in resting-state fMRI.

Changes in vigilance or alertness during a typical resting state fMRI scan are inevitable and have been found to affect measures of functional brain connectivity. Since it is not often feasible to monitor vigilance with EEG during fMRI scans, it would be of great value to have methods for estimating vigilance levels from fMRI data alone. A recent study, conducted in macaque monkeys, proposed a template-based approach for fMRI-based estimation of vigilance fluctuations. Here, we use simultaneously acquired EEG/fMRI data to investigate whether the same template-based approach can be employed to estimate vigilance fluctuations of awake humans across different resting-state conditions. We first demonstrate that the spatial pattern of correlations between EEG-defined vigilance and fMRI in our data is consistent with the previous literature. Notably, however, we observed a significant difference between the eyes-closed (EC) and eyes-open (EO) conditions, finding stronger negative correlations with vigilance in regions forming the default mode network and higher positive correlations in thalamus and insula in the EC condition when compared to the EO condition. Taking these correlation maps as "templates" for vigilance estimation, we found that the template-based approach produced fMRI-based vigilance estimates that were significantly correlated with EEG-based vigilance measures, indicating its generalizability from macaques to humans. We also demonstrate that the performance of this method was related to the overall amount of variability in a subject's vigilance state, and that the template-based approach outperformed the use of the global signal as a vigilance estimator. In addition, we show that the template-based approach can be used to estimate the variability across scans in the amplitude of the vigilance fluctuations. We discuss the benefits and tradeoffs of using the template-based approach in future fMRI studies.

Differences in the resting-state fMRI global signal amplitude between the eyes open and eyes closed states are related to changes in EEG vigilance.

In resting-state functional connectivity magnetic resonance imaging (fcMRI) studies, measures of functional connectivity are often calculated after the removal of a global mean signal component. While the application of the global signal regression approach has been shown to reduce the influence of physiological artifacts and enhance the detection of functional networks, there is considerable controversy regarding its use as the method can lead to significant bias in the resultant connectivity measures. In addition, evidence from recent studies suggests that the global signal is linked to neural activity and may carry clinically relevant information. For instance, in a prior study we found that the amplitude of the global signal was negatively correlated with EEG measures of vigilance across subjects and experimental runs. Furthermore, caffeine-related decreases in global signal amplitude were associated with increases in EEG vigilance. In this study, we extend the prior work by examining measures of global signal amplitude and EEG vigilance under eyes-closed (EC) and eyes-open (EO) resting-state conditions. We show that changes (EO minus EC) in the global signal amplitude are negatively correlated with the associated changes in EEG vigilance. The slope of this EO-EC relation is comparable with the slope of the previously reported relation between caffeine-related changes in the global signal amplitude and EEG vigilance. Our findings provide further support for a basic relationship between global signal amplitude and EEG vigilance.

Resting-state fMRI activity predicts unsupervised learning and memory in an immersive virtual reality environment.

In the real world, learning often proceeds in an unsupervised manner without explicit instructions or feedback. In this study, we employed an experimental paradigm in which subjects explored an immersive virtual reality environment on each of two days. On day 1, subjects implicitly learned the location of 39 objects in an unsupervised fashion. On day 2, the locations of some of the objects were changed, and object location recall performance was assessed and found to vary across subjects. As prior work had shown that functional magnetic resonance imaging (fMRI) measures of resting-state brain activity can predict various measures of brain performance across individuals, we examined whether resting-state fMRI measures could be used to predict object location recall performance. We found a significant correlation between performance and the variability of the resting-state fMRI signal in the basal ganglia, hippocampus, amygdala, thalamus, insula, and regions in the frontal and temporal lobes, regions important for spatial exploration, learning, memory, and decision making. In addition, performance was significantly correlated with resting-state fMRI connectivity between the left caudate and the right fusiform gyrus, lateral occipital complex, and superior temporal gyrus. Given the basal ganglia's role in exploration, these findings suggest that tighter integration of the brain systems responsible for exploration and visuospatial processing may be critical for learning in a complex environment.

The amplitude of the resting-state fMRI global signal is related to EEG vigilance measures.

In resting-state functional magnetic resonance imaging (fMRI), functional connectivity measures can be influenced by the presence of a strong global component. A widely used pre-processing method for reducing the contribution of this component is global signal regression, in which a global mean time series signal is projected out of the fMRI time series data prior to the computation of connectivity measures. However, the use of global signal regression is controversial because the method can bias the correlation values to have an approximately zero mean and may in some instances create artifactual negative correlations. In addition, while many studies treat the global signal as a non-neural confound that needs to be removed, evidence from electrophysiological and fMRI measures in primates suggests that the global signal may contain significant neural correlates. In this study, we used simultaneously acquired fMRI and electroencephalographic (EEG) measures of resting-state activity to assess the relation between the fMRI global signal and EEG measures of vigilance in humans. We found that the amplitude of the global signal (defined as the standard deviation of the global signal) exhibited a significant negative correlation with EEG vigilance across subjects studied in the eyes-closed condition. In addition, increases in EEG vigilance due to the ingestion of caffeine were significantly associated with both a decrease in global signal amplitude and an increase in the average level of anti-correlation between the default mode network and the task-positive network.

Caffeine-Induced Global Reductions in Resting-State BOLD Connectivity Reflect Widespread Decreases in MEG Connectivity.

In resting-state functional magnetic resonance imaging (fMRI), the temporal correlation between spontaneous fluctuations of the blood oxygenation level dependent (BOLD) signal from different brain regions is used to assess functional connectivity. However, because the BOLD signal is an indirect measure of neuronal activity, its complex hemodynamic nature can complicate the interpretation of differences in connectivity that are observed across conditions or subjects. For example, prior studies have shown that caffeine leads to widespread reductions in BOLD connectivity but were not able to determine if neural or vascular factors were primarily responsible for the observed decrease. In this study, we used source-localized magnetoencephalography (MEG) in conjunction with fMRI to further examine the origins of the caffeine-induced changes in BOLD connectivity. We observed widespread and significant (p < 0.01) reductions in both MEG and fMRI connectivity measures, suggesting that decreases in the connectivity of resting-state neuro-electric power fluctuations were primarily responsible for the observed BOLD connectivity changes. The MEG connectivity decreases were most pronounced in the beta band. By demonstrating the similarity in MEG and fMRI based connectivity changes, these results provide evidence for the neural basis of resting-state fMRI networks and further support the potential of MEG as a tool to characterize resting-state connectivity.

Anti-correlated networks, global signal regression, and the effects of caffeine in resting-state functional MRI.

Resting-state functional connectivity magnetic resonance imaging is proving to be an essential tool for the characterization of functional networks in the brain. Two of the major networks that have been identified are the default mode network (DMN) and the task positive network (TPN). Although prior work indicates that these two networks are anti-correlated, the findings are controversial because the anti-correlations are often found only after the application of a pre-processing step, known as global signal regression, that can produce artifactual anti-correlations. In this paper, we show that, for subjects studied in an eyes-closed rest state, caffeine can significantly enhance the detection of anti-correlations between the DMN and TPN without the need for global signal regression. In line with these findings, we find that caffeine also leads to widespread decreases in connectivity and global signal amplitude. Using a recently introduced geometric model of global signal effects, we demonstrate that these decreases are consistent with the removal of an additive global signal confound. In contrast to the effects observed in the eyes-closed rest state, caffeine did not lead to significant changes in global functional connectivity in the eyes-open rest state.