Integrating functional connectivity and MVPA through a multiple constraint network analysis

McNorgan, Chris; Smith, Gregory J.; Edwards, Erica S.

doi:10.1016/j.neuroimage.2019.116412

Cited by 7 publications

(14 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Both full and reduced feature set models demonstrated very high classification performance on clinical diagnosis and IGT performance classifications, explicitly linking IGT performance with ADHD through a shared connectomic fingerprint. Because model weights are shared between output categories, classifier training for both categories constrains the solution space to the set of functional connections that are optimally diagnostic for both types of classification (McNorgan et al, 2020). Both classifications were at well over chance accuracy (M Clinical = 0.91, SD = 0.07, t(29) = 32.78, p < 0.00001; M IGT = 0.91, SD = 0.06, t(29) = 34.10, p < 0.00001).…”

Section: Resultsmentioning

confidence: 99%

“…We applied here the data processing pipeline used in a recent application of a multilayer machine learning classifier to functional connectivity and coarse-scale cortical pattern analysis (McNorgan et al, 2020). Functional images were co-registered with the 3D anatomical surface generated by FreeSurfer (Version 6.0) for each participant and mapped onto a common structural template for group analysis using isomorphic 2 mm voxels.…”

Section: Functional Data Processingmentioning

confidence: 99%

“…The algorithm subdivides the vertices within each ROI perpendicular to its longest axis so that all subdivisions have roughly equal number of vertices and cover up to a designated surface area (400 mm 2 in our study). This approach has been used in previous studies of functional connectivity in surface space (Hagmann et al, 2008;Honey et al, 2009;Hagmann et al, 2010;McNorgan and Joanisse, 2014;McNorgan et al, 2020; Figure 1A).…”

Section: General Linear Model Analysis and Functional Region Of Intermentioning

confidence: 99%

“…These activations fed forward to a two-unit classifier layer which simultaneously classified patterns with respect to both Clinical Diagnosis and IGT performance. This model architecture was informed by previously published applications of multilayer feedforward classifiers to neuroimaging data (Liu et al, 2018;McNorgan et al, 2020). The training set was balanced with respect to both classifications and the categories were orthogonal (i.e., knowing one classification was uninformative for the other).…”

Section: Classifier Trainingmentioning

confidence: 99%

See 3 more Smart Citations

Linking ADHD and Behavioral Assessment Through Identification of Shared Diagnostic Task-Based Functional Connections

et al. 2020

Self Cite

View full text Add to dashboard Cite

A mixed literature implicates atypical connectivity involving attentional, reward and task inhibition networks in ADHD. The neural mechanisms underlying the utility of behavioral tasks in ADHD diagnosis are likewise underexplored. We hypothesized that a machine-learning classifier may use task-based functional connectivity to compute a joint probability function that identifies connectivity signatures that accurately predict ADHD diagnosis and performance on a clinically-relevant behavioral task, providing an explicit neural mechanism linking behavioral phenotype to diagnosis. We analyzed archival MRI and behavioral data of 80 participants (64 male) who had completed the go/no-go task from the longitudinal follow-up of the Multimodal Treatment Study of ADHD (MTA 168) (mean age = 24 years). Cross-mutual information within a functionally-defined mask measured functional connectivity for each task run. Multilayer feedforward classifier models identified the subset of functional connections that predicted clinical diagnosis (ADHD vs. Control) and split-half performance on the Iowa Gambling Task (IGT). A sample of random models trained on functional connectivity profiles predicted validation set clinical diagnosis and IGT performance with 0.91 accuracy and d′ > 2.9, indicating very high sensitivity and specificity. We identified the most diagnostic functional connections between visual and ventral attentional networks and the anterior default mode network. Our results show that task-based functional connectivity is a biomarker of ADHD. Our analytic framework provides a template approach that explicitly ties behavioral assessment measures to both clinical diagnosis, and functional connectivity. This may differentiate otherwise similar diagnoses, and promote more efficacious intervention strategies.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Functional Data Processingmentioning

confidence: 99%

Section: General Linear Model Analysis and Functional Region Of Intermentioning

confidence: 99%

Section: Classifier Trainingmentioning

confidence: 99%

See 2 more Smart Citations

Linking ADHD and Behavioral Assessment Through Identification of Shared Diagnostic Task-Based Functional Connections

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…In contrast to previous work, our preliminary results did not show improvement between hyperaligned and anatomically aligned acrosssubject decodability (data not shown). Still, it is possible that variants of hyperalignment may be useful in brain activity-based across-subject decodability (e.g., 43 ).…”

Section: Discussionmentioning

confidence: 99%

The Hard Limits of Decoding Mental States: The Decodability of fMRI

Jabakhanji

Vigotsky

Bielefeld

et al. 2020

Preprint

View full text Add to dashboard Cite

SUMMARYHigh-profile studies claim to assess mental states across individuals using multi-voxel decoders of brain activity. The fixed, fine-grained, multi-voxel patterns in these “optimized” decoders are purportedly necessary for discriminating between, and accurately identifying, mental states. Here, we present compelling evidence that the efficacy of these decoders is overstated. Across a variety of tasks, decoder patterns were not necessary. Not only were “optimized decoders” spatially imprecise and 90% redundant, but they also performed similarly to simpler decoders, built from average brain activity. We distinguish decoder performance when used for discriminating between, in contrast to identifying, mental states, and show even when discrimination performance is strong, identification can be poor. Using similarity rules, we derived novel and intuitive discriminability metrics that capture 95% and 68% of discrimination performance within- and across-subjects, respectively. These findings demonstrate that current across-subject decoders remain inadequate for real-life decision making.

show abstract

Neuroimaging analysis methods.

Xiong¹,

Newman²

2023

APA Handbook of Research Methods in Psychology: Foundations, Planning, Measures, and Psychometrics (Vol. 1) (2nd Ed.).

View full text Add to dashboard Cite

Integrating functional connectivity and MVPA through a multiple constraint network analysis

Cited by 7 publications

References 58 publications

Linking ADHD and Behavioral Assessment Through Identification of Shared Diagnostic Task-Based Functional Connections

Linking ADHD and Behavioral Assessment Through Identification of Shared Diagnostic Task-Based Functional Connections

The Hard Limits of Decoding Mental States: The Decodability of fMRI

Neuroimaging analysis methods.

Contact Info

Product

Resources

About