Limits...
Making Large-Scale Networks from fMRI Data.

Schmittmann VD, Jahfari S, Borsboom D, Savi AO, Waldorp LJ - PLoS ONE (2015)

Bottom Line: However, this approach generally results in a poor representation of the true underlying network.As a result, pairwise correlation networks can lead to fallacious conclusions; for example, one may conclude that a network is a small-world when it is not.We conclude that using partial correlations, informed by a sparseness penalty, results in more accurate networks and corresponding metrics than pairwise correlation networks.

View Article: PubMed Central - PubMed

Affiliation: Department of Methodology and Statistics/Social and Behavioral Sciences, Tilburg University, Tilburg, the Netherlands.

ABSTRACT
Pairwise correlations are currently a popular way to estimate a large-scale network (> 1000 nodes) from functional magnetic resonance imaging data. However, this approach generally results in a poor representation of the true underlying network. The reason is that pairwise correlations cannot distinguish between direct and indirect connectivity. As a result, pairwise correlation networks can lead to fallacious conclusions; for example, one may conclude that a network is a small-world when it is not. In a simulation study and an application to resting-state fMRI data, we compare the performance of pairwise correlations in large-scale networks (2000 nodes) against three other methods that are designed to filter out indirect connections. Recovery methods are evaluated in four simulated network topologies (small world or not, scale-free or not) in scenarios where the number of observations is very small compared to the number of nodes. Simulations clearly show that pairwise correlation networks are fragmented into separate unconnected components with excessive connectedness within components. This often leads to erroneous estimates of network metrics, like small-world structures or low betweenness centrality, and produces too many low-degree nodes. We conclude that using partial correlations, informed by a sparseness penalty, results in more accurate networks and corresponding metrics than pairwise correlation networks. However, even with these methods, the presence of hubs in the generating network can be problematic if the number of observations is too small. Additionally, we show for resting-state fMRI that partial correlations are more robust than correlations to different parcellation sets and to different lengths of time-series.

No MeSH data available.


Related in: MedlinePlus

The false positive rate for the four networks and estimation methods.The dotted line ⋯ shows the level of the false positive rate above which the absolute number of false positive edges even exceeds the absolute number of edges in the true network.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4556712&req=5

pone.0129074.g010: The false positive rate for the four networks and estimation methods.The dotted line ⋯ shows the level of the false positive rate above which the absolute number of false positive edges even exceeds the absolute number of edges in the true network.

Mentions: To consider to what extent connections were correctly identified, we examine the false positive rate (FPR), that is, the probability of deciding that there is a connection given that there is no true connection, and the true positive rate (TPR), that is, the probability of deciding that there is a connection given that there actually is one. The FPRs of the methods, shown in Fig 10, may seem small considering their absolute values. However, as the networks were sparse, the number of erroneously inferred edges is divided by a very large number of non-existent connections. In order to set FPRs into perspective, the proportion of edges in the true network is indicated as well (dotted line). The FPR of the pairwise correlation networks is nearly always higher than that of the lasso and shrinkage based partial correlation networks (Fig 10). Ridge regression partial correlation networks have an unacceptably large FPR if the number of observations is smaller than the number of nodes, as expected. In most cases, the FPR is lower than the proportion of edges in the true network (dotted line). However, this result does not occur in the presence of hubs.


Making Large-Scale Networks from fMRI Data.

Schmittmann VD, Jahfari S, Borsboom D, Savi AO, Waldorp LJ - PLoS ONE (2015)

The false positive rate for the four networks and estimation methods.The dotted line ⋯ shows the level of the false positive rate above which the absolute number of false positive edges even exceeds the absolute number of edges in the true network.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4556712&req=5

pone.0129074.g010: The false positive rate for the four networks and estimation methods.The dotted line ⋯ shows the level of the false positive rate above which the absolute number of false positive edges even exceeds the absolute number of edges in the true network.
Mentions: To consider to what extent connections were correctly identified, we examine the false positive rate (FPR), that is, the probability of deciding that there is a connection given that there is no true connection, and the true positive rate (TPR), that is, the probability of deciding that there is a connection given that there actually is one. The FPRs of the methods, shown in Fig 10, may seem small considering their absolute values. However, as the networks were sparse, the number of erroneously inferred edges is divided by a very large number of non-existent connections. In order to set FPRs into perspective, the proportion of edges in the true network is indicated as well (dotted line). The FPR of the pairwise correlation networks is nearly always higher than that of the lasso and shrinkage based partial correlation networks (Fig 10). Ridge regression partial correlation networks have an unacceptably large FPR if the number of observations is smaller than the number of nodes, as expected. In most cases, the FPR is lower than the proportion of edges in the true network (dotted line). However, this result does not occur in the presence of hubs.

Bottom Line: However, this approach generally results in a poor representation of the true underlying network.As a result, pairwise correlation networks can lead to fallacious conclusions; for example, one may conclude that a network is a small-world when it is not.We conclude that using partial correlations, informed by a sparseness penalty, results in more accurate networks and corresponding metrics than pairwise correlation networks.

View Article: PubMed Central - PubMed

Affiliation: Department of Methodology and Statistics/Social and Behavioral Sciences, Tilburg University, Tilburg, the Netherlands.

ABSTRACT
Pairwise correlations are currently a popular way to estimate a large-scale network (> 1000 nodes) from functional magnetic resonance imaging data. However, this approach generally results in a poor representation of the true underlying network. The reason is that pairwise correlations cannot distinguish between direct and indirect connectivity. As a result, pairwise correlation networks can lead to fallacious conclusions; for example, one may conclude that a network is a small-world when it is not. In a simulation study and an application to resting-state fMRI data, we compare the performance of pairwise correlations in large-scale networks (2000 nodes) against three other methods that are designed to filter out indirect connections. Recovery methods are evaluated in four simulated network topologies (small world or not, scale-free or not) in scenarios where the number of observations is very small compared to the number of nodes. Simulations clearly show that pairwise correlation networks are fragmented into separate unconnected components with excessive connectedness within components. This often leads to erroneous estimates of network metrics, like small-world structures or low betweenness centrality, and produces too many low-degree nodes. We conclude that using partial correlations, informed by a sparseness penalty, results in more accurate networks and corresponding metrics than pairwise correlation networks. However, even with these methods, the presence of hubs in the generating network can be problematic if the number of observations is too small. Additionally, we show for resting-state fMRI that partial correlations are more robust than correlations to different parcellation sets and to different lengths of time-series.

No MeSH data available.


Related in: MedlinePlus