Prediction of human errors by maladaptive changes in event-related brain networks

doi:10.1073/pnas.0708965105

Prediction of human errors by maladaptive changes in event-related brain networks

*Department of Biological and Medical Psychology, University of Bergen, 5009 Bergen, Norway;
^‡Medical Research Council Institute of Hearing Research, Southampton SO14 OYG, United Kingdom;
^§MIND Institute, Albuquerque, NM 87131;
^¶Department of Electrical and Computer Engineering, University of New Mexico, Albuquerque, NM 87131;
^‖Department of Psychiatry, Yale University School of Medicine, New Haven, CT 06520;
**Haukeland University Hospital, 5021 Bergen, Norway;
^††Department of Neurophysiology and Pathophysiology, University Medical Center Hamburg–Eppendorf, 20246 Hamburg, Germany;
^‡‡Max Planck Institute for Human Cognitive and Brain Sciences, 04103 Leipzig, Germany; and
^§§Max Planck Institute for Neurological Research, 50931 Cologne, Germany

Edited by Marcus E. Raichle, Washington University School of Medicine, St. Louis, MO, and approved March 4, 2008 (received for review September 21, 2007)

Abstract

Humans engaged in monotonous tasks are susceptible to occasional errors that may lead to serious consequences, but little is known about brain activity patterns preceding errors. Using functional MRI and applying independent component analysis followed by deconvolution of hemodynamic responses, we studied error preceding brain activity on a trial-by-trial basis. We found a set of brain regions in which the temporal evolution of activation predicted performance errors. These maladaptive brain activity changes started to evolve ≈30 sec before the error. In particular, a coincident decrease of deactivation in default mode regions of the brain, together with a decline of activation in regions associated with maintaining task effort, raised the probability of future errors. Our findings provide insights into the brain network dynamics preceding human performance errors and suggest that monitoring of the identified precursor states may help in avoiding human errors in critical real-world situations.

Footnotes

^†To whom correspondence should be addressed. E-mail: tom.eichele{at}psybp.uib.no
Author contributions: S.D., A.K.E., D.Y.v.C., and M.U. designed research; S.D. and M.U. performed research; T.E. and V.D.C. contributed new reagents/analytic tools; T.E., S.D., V.D.C., K.S., and M.U. analyzed data; and T.E., S.D., V.D.C., K.S., A.K.E., K.H., D.Y.v.C., and M.U. wrote the paper.
The authors declare no conflict of interest.
This article is a PNAS Direct Submission.
Data deposition: The fMRI dataset has been deposited in the Mind Research database, http://portal.mind.unm.edu/dcon/.
This article contains supporting information online at www.pnas.org/cgi/content/full/0708965105/DCSupplemental.
Freely available online through the PNAS open access option.