Dataset Information

Functional Connectivities Are More Informative Than Anatomical Variables in Diagnostic Classification of Autism.

ABSTRACT: Machine learning techniques have been implemented to reveal brain features that distinguish people with autism spectrum disorders (ASDs) from typically developing (TD) peers. However, it remains unknown whether different neuroimaging modalities are equally informative for diagnostic classification. We combined anatomical magnetic resonance imaging (aMRI), diffusion weighted imaging (DWI), and functional connectivity MRI (fcMRI) using conditional random forest (CRF) for supervised learning to compare how informative each modality was in diagnostic classification. In-house data (N?=?93) included 47 TD and 46 ASD participants, matched on age, motion, and nonverbal IQ. Four main analyses consistently indicated that fcMRI variables were significantly more informative than anatomical variables from aMRI and DWI. This was found (1) when the top 100 variables from CRF (run separately in each modality) were combined for multimodal CRF; (2) when only 19 top variables reaching >67% accuracy in each modality were combined in multimodal CRF; and (3) when the large number of initial variables (before dimension reduction) potentially biasing comparisons in favor of fcMRI was reduced using a less granular region of interest scheme. Consistent superiority of fcMRI was even found (4) when 100 variables per modality were randomly selected, removing any such potential bias. Greater informative value of functional than anatomical modalities may relate to the nature of fcMRI data, reflecting more closely behavioral condition, which is also the basis of diagnosis, whereas brain anatomy may be more reflective of neurodevelopmental history.

SUBMITTER: Eill A

PROVIDER: S-EPMC6798803 | biostudies-literature | 2019 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Functional Connectivities Are More Informative Than Anatomical Variables in Diagnostic Classification of Autism.

Eill Aina A Jahedi Afrooz A Gao Yangfeifei Y Kohli Jiwandeep S JS Fong Christopher H CH Solders Seraphina S Carper Ruth A RA Valafar Faramarz F Bailey Barbara A BA Müller Ralph-Axel RA

Brain connectivity 20190823 8

Machine learning techniques have been implemented to reveal brain features that distinguish people with autism spectrum disorders (ASDs) from typically developing (TD) peers. However, it remains unknown whether different neuroimaging modalities are equally informative for diagnostic classification. We combined anatomical magnetic resonance imaging (aMRI), diffusion weighted imaging (DWI), and functional connectivity MRI (fcMRI) using conditional random forest (CRF) for supervised learning to com ...[more]

PMID: 31328535

Similar Datasets

Project description:Group differences in resting state functional magnetic resonance imaging connectivity between individuals with autism and typically developing controls have been widely replicated for a small number of discrete brain regions, yet the whole-brain distribution of connectivity abnormalities in autism is not well characterized. It is also unclear whether functional connectivity is sufficiently robust to be used as a diagnostic or prognostic metric in individual patients with autism. We obtained pairwise functional connectivity measurements from a lattice of 7266 regions of interest covering the entire grey matter (26.4 million connections) in a well-characterized set of 40 male adolescents and young adults with autism and 40 age-, sex- and IQ-matched typically developing subjects. A single resting state blood oxygen level-dependent scan of 8 min was used for the classification in each subject. A leave-one-out classifier successfully distinguished autism from control subjects with 83% sensitivity and 75% specificity for a total accuracy of 79% (P = 1.1 × 10(-7)). In subjects <20 years of age, the classifier performed at 89% accuracy (P = 5.4 × 10(-7)). In a replication dataset consisting of 21 individuals from six families with both affected and unaffected siblings, the classifier performed at 71% accuracy (91% accuracy for subjects <20 years of age). Classification scores in subjects with autism were significantly correlated with the Social Responsiveness Scale (P = 0.05), verbal IQ (P = 0.02) and the Autism Diagnostic Observation Schedule-Generic's combined social and communication subscores (P = 0.05). An analysis of informative connections demonstrated that region of interest pairs with strongest correlation values were most abnormal in autism. Negatively correlated region of interest pairs showed higher correlation in autism (less anticorrelation), possibly representing weaker inhibitory connections, particularly for long connections (Euclidean distance >10 cm). Brain regions showing greatest differences included regions of the default mode network, superior parietal lobule, fusiform gyrus and anterior insula. Overall, classification accuracy was better for younger subjects, with differences between autism and control subjects diminishing after 19 years of age. Classification scores of unaffected siblings of individuals with autism were more similar to those of the control subjects than to those of the subjects with autism. These findings indicate feasibility of a functional connectivity magnetic resonance imaging diagnostic assay for autism.

Project description:Failure of arteriovenous fistulas (AVF) to mature and thrombosis in matured fistulas have been the major causes of morbidity and mortality in hemodialysis patients. Stenosis, which occurs due to adverse remodeling in AVFs, is one of the major underlying factors under both scenarios. Early diagnosis of a stenosis in an AVF can provide an opportunity to intervene in a timely manner for either assisting the maturation process or avoiding the thrombosis. The goal of surveillance strategies was to supplement the clinical evaluation (i.e., physical examination) of the AVF for better and earlier diagnosis of a developing stenosis. Surveillance strategies were mainly based on measurement of functional hemodynamic endpoints, including blood flow (Qa) to the vascular access and venous access pressure (VAP). As the changes in arterial pressure (MAP) affects the level of VAP, the ratio of VAP to MAP (VAPR = VAP/MAP) was used for diagnosis. A Qa < 400-500 mL/min or a VAPR > 0.55 is considered sign of significant stenosis, which requires immediate intervention. However, due to the complex nature of AVFs, the surveillance strategies have failed to consistently detect stenosis under different scenarios. VAPR has been primarily developed to detect outflow stenosis in arteriovenous grafts, and it hasn't been successful in accurate diagnosis of outflow lesions in AVFs. Similarly, AVFs can maintain relatively high blood flow despite the presence of a significant outflow stenosis and thus, Qa has been found to be a better predictor of only inflow lesions. Similar shortcomings have been reported in the detection of functional severity of coronary stenosis using diagnostic endpoints that were based on either flow or pressure. This limitation has been associated with the fact that both pressure and flow change in the presence of a stenosis and thus, hemodynamic diagnostic endpoints that employ only one of these parameters are inherently prone to inaccuracies. Recent attempts have resulted in development of new diagnostic endpoints that can combine the effects of pressure and flow. These new hemodynamic diagnostic endpoints have shown to be better predictors of functional severity of lesions as compared to either flow or pressure based counterparts. In this review article, we discussed the advantages and limitations of current functional and anatomical diagnostic endpoints in AVFs.

Project description:PROMISE (PROspective Multicenter Imaging Study for Evaluation of Chest Pain) found that initial use of at least 64-slice multidetector computed tomography angiography (CTA) versus functional diagnostic testing strategies did not improve clinical outcomes in stable symptomatic patients with suspected coronary artery disease (CAD) requiring noninvasive testing.To conduct an economic analysis for PROMISE (a major secondary aim of the study).Prospective economic study from the U.S. perspective. Comparisons were made according to the intention-to-treat principle, and CIs were calculated using bootstrap methods. (ClinicalTrials.gov: NCT01174550).190 U.S. centers.9649 U.S. patients enrolled in PROMISE between July 2010 and September 2013. Median follow-up was 25 months.Technical costs of the initial (outpatient) testing strategy were estimated from Premier Research Database data. Hospital-based costs were estimated using hospital bills and Medicare cost-charge ratios. Physician fees were taken from the Medicare Physician Fee Schedule. Costs were expressed in 2014 U.S. dollars, discounted at 3% annually, and estimated out to 3 years using inverse probability weighting methods.The mean initial testing costs were $174 for exercise electrocardiography; $404 for CTA; $501 to $514 for pharmacologic and exercise stress echocardiography, respectively; and $946 to $1132 for exercise and pharmacologic stress nuclear testing, respectively. Mean costs at 90 days were $2494 for the CTA strategy versus $2240 for the functional strategy (mean difference, $254 [95% CI, -$634 to $906]). The difference was associated with more revascularizations and catheterizations (4.25 per 100 patients) with CTA use. After 90 days, the mean cost difference between the groups out to 3 years remained small.Cost weights for test strategies were obtained from sources outside PROMISE.Computed tomography angiography and functional diagnostic testing strategies in patients with suspected CAD have similar costs through 3 years of follow-up.National Heart, Lung, and Blood Institute.

Project description:The accurate prediction of general neuropsychiatric disorders, on an individual basis, using resting-state functional magnetic resonance imaging (fMRI) is a challenging task of great clinical significance. Despite the progress to chart the differences between the healthy controls and patients at the group level, the pattern classification of functional brain networks across individuals is still less developed. In this paper we identify two novel neuroimaging measures that prove to be strongly predictive neuroimaging markers in pattern classification between healthy controls and general epileptic patients. These measures characterize two important aspects of the functional brain network in a quantitative manner: (i) coordinated operation among spatially distributed brain regions, and (ii) the asymmetry of bilaterally homologous brain regions, in terms of their global patterns of functional connectivity. This second measure offers a unique understanding of brain asymmetry at the network level, and, to the best of our knowledge, has not been previously used in pattern classification of functional brain networks. Using modern pattern-recognition approaches like sparse regression and support vector machine, we have achieved a cross-validated classification accuracy of 83.9% (specificity: 82.5%; sensitivity: 85%) across individuals from a large dataset consisting of 180 healthy controls and epileptic patients. We identified significantly changed functional pathways and subnetworks in epileptic patients that underlie the pathophysiological mechanism of the impaired cognitive functions. Specifically, we find that the asymmetry of brain operation for epileptic patients is markedly enhanced in temporal lobe and limbic system, in comparison with healthy individuals. The present study indicates that with specifically designed informative neuroimaging markers, resting-state fMRI can serve as a most promising tool for clinical diagnosis, and also shed light onto the physiology behind complex neuropsychiatric disorders. The systematic approaches we present here are expected to have wider applications in general neuropsychiatric disorders.

Dataset Information

Functional Connectivities Are More Informative Than Anatomical Variables in Diagnostic Classification of Autism.

Publications

Functional Connectivities Are More Informative Than Anatomical Variables in Diagnostic Classification of Autism.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets