↓ Skip to main content

Promises, Pitfalls, and Basic Guidelines for Applying Machine Learning Classifiers to Psychiatric Imaging Data, with Autism as an Example

Overview of attention for article published in Frontiers in Psychiatry, December 2016
Altmetric Badge

About this Attention Score

  • In the top 25% of all research outputs scored by Altmetric
  • High Attention Score compared to outputs of the same age (85th percentile)
  • Good Attention Score compared to outputs of the same age and source (76th percentile)

Mentioned by

twitter
17 X users

Citations

dimensions_citation
94 Dimensions

Readers on

mendeley
206 Mendeley
You are seeing a free-to-access but limited selection of the activity Altmetric has collected about this research output. Click here to find out more.
Title
Promises, Pitfalls, and Basic Guidelines for Applying Machine Learning Classifiers to Psychiatric Imaging Data, with Autism as an Example
Published in
Frontiers in Psychiatry, December 2016
DOI 10.3389/fpsyt.2016.00177
Pubmed ID
Authors

Pegah Kassraian-Fard, Caroline Matthis, Joshua H. Balsters, Marloes H. Maathuis, Nicole Wenderoth

Abstract

Most psychiatric disorders are associated with subtle alterations in brain function and are subject to large interindividual differences. Typically, the diagnosis of these disorders requires time-consuming behavioral assessments administered by a multidisciplinary team with extensive experience. While the application of Machine Learning classification methods (ML classifiers) to neuroimaging data has the potential to speed and simplify diagnosis of psychiatric disorders, the methods, assumptions, and analytical steps are currently opaque and not accessible to researchers and clinicians outside the field. In this paper, we describe potential classification pipelines for autism spectrum disorder, as an example of a psychiatric disorder. The analyses are based on resting-state fMRI data derived from a multisite data repository (ABIDE). We compare several popular ML classifiers such as support vector machines, neural networks, and regression approaches, among others. In a tutorial style, written to be equally accessible for researchers and clinicians, we explain the rationale of each classification approach, clarify the underlying assumptions, and discuss possible pitfalls and challenges. We also provide the data as well as the MATLAB code we used to achieve our results. We show that out-of-the-box ML classifiers can yield classification accuracies of about 60-70%. Finally, we discuss how classification accuracy can be further improved, and we mention methodological developments that are needed to pave the way for the use of ML classifiers in clinical practice.

X Demographics

X Demographics

The data shown below were collected from the profiles of 17 X users who shared this research output. Click here to find out more about how the information was compiled.
Mendeley readers

Mendeley readers

The data shown below were compiled from readership statistics for 206 Mendeley readers of this research output. Click here to see the associated Mendeley record.

Geographical breakdown

Country Count As %
Germany 1 <1%
Austria 1 <1%
Unknown 204 99%

Demographic breakdown

Readers by professional status Count As %
Student > Ph. D. Student 41 20%
Researcher 27 13%
Student > Master 23 11%
Student > Bachelor 14 7%
Student > Doctoral Student 13 6%
Other 42 20%
Unknown 46 22%
Readers by discipline Count As %
Psychology 34 17%
Neuroscience 32 16%
Computer Science 25 12%
Engineering 18 9%
Medicine and Dentistry 17 8%
Other 25 12%
Unknown 55 27%
Attention Score in Context

Attention Score in Context

This research output has an Altmetric Attention Score of 11. This is our high-level measure of the quality and quantity of online attention that it has received. This Attention Score, as well as the ranking and number of research outputs shown below, was calculated when the research output was last mentioned on 21 February 2017.
All research outputs
#2,868,400
of 22,896,955 outputs
Outputs from Frontiers in Psychiatry
#1,508
of 10,049 outputs
Outputs of similar age
#58,701
of 416,446 outputs
Outputs of similar age from Frontiers in Psychiatry
#10
of 42 outputs
Altmetric has tracked 22,896,955 research outputs across all sources so far. Compared to these this one has done well and is in the 87th percentile: it's in the top 25% of all research outputs ever tracked by Altmetric.
So far Altmetric has tracked 10,049 research outputs from this source. They typically receive a lot more attention than average, with a mean Attention Score of 10.4. This one has done well, scoring higher than 84% of its peers.
Older research outputs will score higher simply because they've had more time to accumulate mentions. To account for age we can compare this Altmetric Attention Score to the 416,446 tracked outputs that were published within six weeks on either side of this one in any source. This one has done well, scoring higher than 85% of its contemporaries.
We're also able to compare this research output to 42 others from the same source and published within six weeks on either side of this one. This one has done well, scoring higher than 76% of its contemporaries.