Building better biomarkers: brain models in translational neuroimaging

By Choong-Wan Woo, Luke J. Chang, Martin A. Lindquist, Tor D. Wager. Nature Neuroscience, 2017

972 citations recorded by the source corpus.

Despite its great promise, neuroimaging has yet to substantially impact clinical practice and public health. However, a developing synergy between emerging analysis techniques and data-sharing initiatives has the potential to transform the role of neuroimaging in clinical applications. We review the state of translational neuroimaging and outline an approach to developing brain signatures that can be shared, tested in multiple contexts and applied in clinical settings. The approach rests on three pillars: (i) the use of multivariate pattern-recognition techniques to develop brain signatures for clinical outcomes and relevant mental processes; (ii) assessment and optimization of their diagnostic value; and (iii) a program of broad exploration followed by increasingly rigorous assessment of generalizability across samples, research contexts and populations. Increasingly sophisticated models based on these principles will help to overcome some of the obstacles on the road from basic neuroscience to better health and will ultimately serve both basic and applied goals.

Subfields: Biophysics, Cognitive Neuroscience, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/f1369e823081a94bf62d523c181ba153d5bd588c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biophysics

In Cognitive Neuroscience

In Statistics and Probability

Citations in the corpus

Establishment of Best Practices for Evidence for Prediction A Review (2019, methodology): “CONCLUSIONS AND RELEVANCE—To ensure accurate estimates of predictive validity, the recommended best practices for predictive modeling include the following: (1) in-sample model fit indices should not be reported as evidence for predictive accuracy, (2) the cross-validation procedure should encompass”
Cross‐validation failure: Small sample sizes lead to large error bars (2017, background): “However, biomarkers that are too specific to a certain site or a certain cohort have reduced clinical value (Woo et al., 2017).”
Ten simple rules for predictive modeling of individual differences in neuroimaging (2019, background): “More importantly, validating models in different datasets helps to ensure that the model is not fitting features that are dataset specific by making the testing data more heterogeneous and more representative of the general population (Woo et al., 2017).”
Machine Learning for Precision Psychiatry: Opportunities and Challenges. (2017, methodology): “In a second step, the ensuing trained predictive models can be shared collaboratively as a research product (6) and be applied with little effort in a possibly large number of individual patients in various mental health contexts.”
Benchmarking functional connectome‐based predictive models for resting‐state fMRI (2019, positive): “Predictive models on rest-fMRI bring the promise of robust and reliable biomarkers: given new brain imaging data, they should give accurate predictions of clinics or behavior (Woo et al., 2017).”
The relation between statistical power and inference in fMRI (2017, background): “These later machine learning analyses aim to infer for instance mental states or psychiatric disorder diagnosis (e.g. references [78,79]) from observed patterns of brain activity.”
The promise of machine learning in predicting treatment outcomes in psychiatry (2021, background): “Restingstate fMRI is a popular alternative, because it measures behaviourallyrelevant, synchronized brain network activity at rest, and the imaging pro tocols can be more easily harmonized across scanners 165 .”
Individualized prediction of heroin cue-induced craving using task-based EEG functional connectivity (2026, unknown): “This speci ﬁ city ensures the bio-marker ’ sutilityasaprecisemetricforcoreaddictionpathologyratherthan a generalized re ﬂ ection of generic psychiatric distress 47 .”