Quantifying performance of machine learning methods for neuroimaging data
Open accessThe DOI matches its Crossref record; 28 of the 28 references it cites were found in a registry or an index.
Abstract
Machine learning is increasingly being applied to neuroimaging data. However, most machine learning algorithms have not been designed to accommodate neuroimaging data, which typically has many more data points than subjects, in addition to multicollinearity and low signal-to-noise. Consequently, the relative efficacy of different machine learning regression algorithms for different types of neuroimaging data are not known. Here, we sought to quantify the performance of a variety of machine learning algorithms for use with neuroimaging data with various sample sizes, feature set sizes, and predictor effect sizes. The contribution of additional machine learning techniques – embedded feature selection and bootstrap aggregation (bagging) – to model performance was also quantified. Five machine learning regression methods – Gaussian Process Regression, Multiple Kernel Learning, Kernel Ridge Regression, the Elastic Net and Random Forest, were examined with both real and simulated MRI data, and in comparison to standard multiple regression. The different machine learning regression algorithms produced varying results, which depended on sample size, feature set size, and predictor effect size. When the effect size was large, the Elastic Net, Kernel Ridge Regression and Gaussian Process Regression performed well at most sample sizes and feature set sizes. However, when the effect size was small, only the Elastic Net made accurate predictions, but this was limited to analyses with sample sizes greater than 400. Random Forest also produced a moderate performance for small effect sizes, but could do so across all sample sizes. Machine learning techniques also improved prediction accuracy for multiple regression. These data provide empirical evidence for the differential performance of various machines on neuroimaging data, which are dependent on number of sample size, features and effect size.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Regularization and Variable Selection Via the Elastic Net
Zou, H., & Hastie, T. (2005) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.1467-9868.2005.00503.x · Cited by 20,957
Tzourio-Mazoyer, N., Landeau, B., Papathanassiou, D., Crivello, F., Etard, O., Delcroix, N., Mazoyer, B., & Joliot, M. (2002) · NeuroImage · doi:10.1006/nimg.2001.0978 · Cited by 16,319
Power failure: why small sample size undermines the reliability of neuroscience
Button, K. S., Ioannidis, J. P. A., Mokrysz, C., Nosek, B. A., Flint, J., Robinson, E. S. J., & Munafò, M. R. (2013) · Nature Reviews Neuroscience · doi:10.1038/nrn3475 · Cited by 7,641 · cited 1×
“Another important consideration in neuroimaging is that flexible or ‘exploratory’ analysis introduces a high risk of false positive results or overestimated effect sizes (Button et al., 2013).”
BackgroundPower, J. D., Barnes, K. A., Snyder, A. Z., Schlaggar, B. L., & Petersen, S. E. (2012) · NeuroImage · doi:10.1016/j.neuroimage.2011.10.018 · Cited by 7,429
Simmons, J. P., Nelson, L. D., & Simonsohn, U. (2011) · Psychological Science · doi:10.1177/0956797611417632 · Cited by 6,567
A survey on feature selection methods
Chandrashekar, G., & Sahin, F. (2014) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2013.11.024 · Cited by 5,189
The Alzheimer’s disease neuroimaging initiative (ADNI): MRI methods
Jack, C. R., Bernstein, M. A., Fox, N. C., Thompson, P., Alexander, G., Harvey, D., Borowski, B., Britson, P. J., L. Whitwell, J., Ward, C., et al. (2008) · Journal of Magnetic Resonance Imaging · doi:10.1002/jmri.21049 · Cited by 4,347
Toward discovery science of human brain function
Biswal, B. B., Mennes, M., Zuo, X.-N., Gohel, S., Kelly, C., Smith, S. M., Beckmann, C. F., Adelstein, J. S., Buckner, R. L., Colcombe, S., et al. (2010) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.0911855107 · Cited by 2,970
Prediction of individual brain maturity using fMRI
Dosenbach, N. U. F., Nardos, B., Cohen, A. L., Fair, D. A., Power, J. D., Church, J. A., Nelson, S. M., Wig, G. S., Vogel, A. C., Lessov-Schlaggar, C. N., et al. (2010) · Science · doi:10.1126/science.1194144 · Cited by 2,183 · cited 1×
“There have also been successful efforts to predict continuous outcome variables, mostly using Relevance or Support vector regression, such as age (Dosenbach et al., 2010; Franke et al., 2010; Mwangi et al., 2013), cognitive ability (Stonnington et al.,2010), language ability (Formisano et al.,…”
BackgroundStatistics versus machine learning
Bzdok, D., Altman, N., & Krzywinski, M. (2018) · Nature Methods · doi:10.1038/nmeth.4642 · Cited by 1,508 · cited 1×
“Here we have selected a number of machine learning algorithms (see Bzdok, Altman,& Krzywinski, 2018 for a treatment of the overlap between statistics and machine learning) as the target of a structured quantitative examination of their performance on the same neuroimaging datasets.”
MethodBuilding better biomarkers: brain models in translational neuroimaging
Woo, C.-W., Chang, L. J., Lindquist, M. A., & Wager, T. D. (2017) · Nature Neuroscience · doi:10.1038/nn.4478 · Cited by 1,056
The neuroscience of human intelligence differences
Deary, I. J., Penke, L., & Johnson, W. (2010) · Nature Reviews Neuroscience · doi:10.1038/nrn2793 · Cited by 1,038
Machine Learning Approaches for Clinical Psychology and Psychiatry
Dwyer, D. B., Falkai, P., & Koutsouleris, N. (2018) · Annual Review of Clinical Psychology · doi:10.1146/annurev-clinpsy-032816-045037 · Cited by 966 · cited 2×
“In large datasets comprised of data from multiple sites, generalizability can be further quantified by using leave-site-out CV, where data from one site is withheld as a test set and the model is developed using data from the remaining sites (Dwyer, Falkai, & Koutsouleris, 2018).”
MethodSingle subject prediction of brain disorders in neuroimaging: Promises and pitfalls
Arbabshirani, M. R., Plis, S., Sui, J., & Calhoun, V. D. (2017) · NeuroImage · doi:10.1016/j.neuroimage.2016.02.079 · Cited by 912
Cole, J. H., Poudel, R. P. K., Tsagkrasoulis, D., Caan, M. W. A., Steves, C., Spector, T. D., & Montana, G. (2017) · NeuroImage · doi:10.1016/j.neuroimage.2017.07.059 · Cited by 872 · cited 1×
“The linear outcome variable used was participants’ age, which has been shown to have a moderate-large effect size (Cole et al., 2017).”
MethodInferring mental states from neuroimaging data: from reverse inference to large-scale decoding
Poldrack, R. A. (2011) · Neuron · doi:10.1016/j.neuron.2011.11.001 · Cited by 821 · cited 1×
“Several authors have emphasized the importance of moving away from explanatory and univariate analysis procedures and towards multivariate outcome prediction in psychology and neuroscience (Gabrieli et al., 2015; Jollans & Whelan, 2016; Poldrack, 2011; Westfall & Yarkoni, 2016).”
BackgroundCross-trial prediction of treatment outcome in depression: a machine learning approach
Chekroud, A. M., Zotti, R. J., Shehzad, Z., Gueorguieva, R., Johnson, M. K., Trivedi, M. H., Cannon, T. D., Krystal, J. H., & Corlett, P. R. (2016) · The Lancet Psychiatry · doi:10.1016/s2215-0366(15)00471-x · Cited by 676 · cited 1×
“The Elastic Net has gained popularity among neuroimaging researchers in recent years, and has been successfully used in several studies with large samples (e.g. Chekroud et al., 2016; Whelan et al., 2014).”
MethodMeasurement error and the replication crisis
Loken, E., & Gelman, A. (2017) · Science · doi:10.1126/science.aal3618 · Cited by 628 · cited 1×
“…iterations of analyses without reporting the findings (e.g., with and without covariates), or to tweak parameters for group inclusion to better represent the problem has been termed ‘researcher degrees of freedom’ (Simmons, Nelson, & Simonsohn, 2011; Loken & Gelman, 2017; Westfall & Yarkoni, 2016).”
BackgroundA Review of Feature Reduction Techniques in Neuroimaging
Mwangi, B., Tian, T. S., & Soares, J. C. (2014) · Neuroinformatics · doi:10.1007/s12021-013-9204-3 · Cited by 559
Statistically controlling for confounding constructs is harder than you think
Westfall, J., & Yarkoni, T. (2016) · PLOS ONE · doi:10.1371/journal.pone.0152719 · Cited by 547 · cited 2×
“…iterations of analyses without reporting the findings (e.g., with and without covariates), or to tweak parameters for group inclusion to better represent the problem has been termed ‘researcher degrees of freedom’ (Simmons, Nelson, & Simonsohn, 2011; Loken & Gelman, 2017; Westfall & Yarkoni, 2016).”
BackgroundOgutu, J. O., Schulz-Streeck, T., & Piepho, H.-P. (2012) · BMC Proceedings · doi:10.1186/1753-6561-6-s2-s10 · Cited by 440
Koutsouleris, N., Kambeitz-Ilankovic, L., Ruhrmann, S., Rosen, M., Ruef, A., Dwyer, D. B., Paolini, M., Chisholm, K., Kambeitz, J., Haidl, T., et al. (2018) · JAMA Psychiatry · doi:10.1001/jamapsychiatry.2018.2165 · Cited by 341
Neuroanatomical Assessment of Biological Maturity
Brown, T. T., Kuperman, J. M., Chung, Y., Erhart, M., McCabe, C., Hagler, D. J., Venkatraman, V. K., Akshoomoff, N., Amaral, D. G., Bloss, C. S., et al. (2012) · Current Biology · doi:10.1016/j.cub.2012.07.002 · Cited by 332 · cited 1×
“While some neuroimaging studies use test sets comprised of only one observation (leave-one-out CV; e.g. Brown et al., 2012; Clark et al., 2014; Duff et al., 2012; Niehaus et al., 2014), larger test sets (leave-k-out, where k typically equals 5 or 10; e.g. Wang et al., 2013; Whelan et al., 2014) are…”
MethodChu, C., Hsu, A.-L., Chou, K.-H., Bandettini, P., & Lin, C. (2012) · NeuroImage · doi:10.1016/j.neuroimage.2011.11.066 · Cited by 319
Prognostic and diagnostic potential of the structural neuroanatomy of depression
Costafreda, S. G., Chu, C., Ashburner, J., & Fu, C. H. Y. (2009) · PLoS ONE · doi:10.1371/journal.pone.0006353 · Cited by 232 · cited 1×
“…algorithms to classify individuals based on structural or functional imaging data using, among other algorithms, Support Vector Machines (e.g. Costafreda et al., 2009; Davatzikos et al., 2011; Koutsouleris et al., 2012), Random Forest (e.g. Ball et al. 2014, Ramirez et al., 2010), and Naïve…”
MethodNeuromarkers for Mental Disorders: Harnessing Population Neuroscience
Jollans, L., & Whelan, R. (2018) · Frontiers in Psychiatry · doi:10.3389/fpsyt.2018.00242 · Cited by 56 · cited 1×
“…researchers to verify the neurophysiological plausibility of the model, while also enabling future research to consider which variables are strong or poor predictors of an outcome in the development of further experiments, studies, and prediction models (Woo et al., 2017; Jollans & Whelan, 2018).”
BackgroundSelf-citationBiomarkers With a Mechanistic Focus
Pine, D. S., & Leibenluft, E. (2015) · JAMA Psychiatry · doi:10.1001/jamapsychiatry.2015.0498 · Cited by 40
Wang, J., Redmond, S. J., Bertoux, M., Hodges, J. R., & Hornberger, M. (2016) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2016.00119 · Cited by 35 · cited 1×
“…Support Vector Machines (e.g. Costafreda et al., 2009; Davatzikos et al., 2011; Koutsouleris et al., 2012), Random Forest (e.g. Ball et al. 2014, Ramirez et al., 2010), and Naïve Bayes classifiers (e.g. Adar et al., 2016; Wang, Redmond, Bertoux, Hodges & Hornberger, 2016; Zhou et al., 2015).”
Background
Cited by
Accurate brain age prediction with lightweight deep neural networks
Peng, H., Gong, W., Beckmann, C. F., Vedaldi, A., & Smith, S. M. (2021) · Medical Image Analysis · doi:10.1016/j.media.2020.101871 · Cited by 505
Dhamala, E., Yeo, B. T. T., & Holmes, A. J. (2023) · Biological Psychiatry · doi:10.1016/j.biopsych.2022.09.024 · Cited by 91
“Limited sample sizes result in decreased reliability of predictions regardless of algorithm, feature type, and phenotype(84, 118-120), and produce overly optimistic estimates of prediction accuracy(117, 121).”
Chen, Z., Liu, X., Yang, Q., Wang, Y.-J., Miao, K., Gong, Z., Yu, Y., Leonov, A., Liu, C., Feng, Z., et al. (2023) · JAMA Network Open · doi:10.1001/jamanetworkopen.2023.1671 · Cited by 43
Metadata
- Authors
- Jollans, L., Boyle, R., Artiges, E., Banaschewski, T., Desrivières, S., Grigis, A., Martinot, J.-L., Paus, T., Smolka, M. N., Walter, H., Schumann, G., Garavan, H., & Whelan, R.
- Venue
- NeuroImage
- Publisher
- Elsevier BV
- Published
- 2019-10
- Volume
- 199
- Pages
- 351-365
- ISSN
- 1053-8119 (ISSN-L)
- OpenAlex
- W2948537574
- Cited by
- 173
- References
- 28
- FWCI
- 11.36
- Type
- journal article
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.