Help Privacy Policy Disclaimer
  Advanced SearchBrowse


  Mind the gap: Performance metric evaluation in brain‐age prediction

de Lange, A. G., Anatürk, M., Rokicki, J., Han, L. K. M., Franke, K., Alnæs, D., et al. (2022). Mind the gap: Performance metric evaluation in brain‐age prediction. Human Brain Mapping. doi:10.1002/hbm.25837.

Item is


show hide
Genre: Journal Article


show Files
hide Files
deLange_2022.pdf (Publisher version), 4MB
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
Copyright Date:
Copyright Info:




de Lange, Ann‐Marie G.1, 2, 3, Author
Anatürk, Melis3, 4, Author
Rokicki, Jaroslav5, 6, Author
Han, Laura K. M.7, Author
Franke, Katja8, Author
Alnæs, Dag5, Author
Ebmeier, Klaus P.3, Author
Draganski, Bogdan1, 9, Author              
Kaufmann, Tobias5, 10, Author
Westlye, Lars T.2, 5, 11, Author
Hahn, Tim12, Author
Cole, James H.4, 13, Author
1Laboratoire de Recherche en Neuroimagerie (LREN), Centre hospitalier universitaire vaudois, Lausanne, Switzerland, ou_persistent22              
2Department of Psychology, University of Oslo, Norway, ou_persistent22              
3Department of Psychiatry, University of Oxford, United Kingdom, ou_persistent22              
4Centre for Medical Image Computing, University College London, United Kingdom, ou_persistent22              
5NORMENT Norwegian Centre for Mental Disorders Research, Institute of Clinical Medicine, University of Oslo, Norway, ou_persistent22              
6Centre of Research and Education in Forensic Psychiatry, Oslo University Hospital, Norway, ou_persistent22              
7Department of Psychiatry, VU University Medical Center, Amsterdam, the Netherlands, ou_persistent22              
8Structural Brain Mapping Group, Department of Neurology, Jena University Hospital, Germany, ou_persistent22              
9Department Neurology, MPI for Human Cognitive and Brain Sciences, Max Planck Society, ou_634549              
10Department for Psychiatry and Psychotherapy, Eberhard Karls University Tübingen, Germany, ou_persistent22              
11KG Jebsen Centre for Neurodevelopmental Disorders, University of Oslo, Norway, ou_persistent22              
12Institute of Translational Psychiatry, Münster University, Germany, ou_persistent22              
13Dementia Research Centre, UCL Queen Square Institute of Neurology, University College London, United Kingdom, ou_persistent22              


Free keywords: Brain-age prediction; Machine learning; Neuroimaging; Statistics
 Abstract: Estimating age based on neuroimaging-derived data has become a popular approach to developing markers for brain integrity and health. While a variety of machine-learning algorithms can provide accurate predictions of age based on brain characteristics, there is significant variation in model accuracy reported across studies. We predicted age in two population-based datasets, and assessed the effects of age range, sample size and age-bias correction on the model performance metrics Pearson's correlation coefficient (r), the coefficient of determination (R2 ), Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE). The results showed that these metrics vary considerably depending on cohort age range; r and R2 values are lower when measured in samples with a narrower age range. RMSE and MAE are also lower in samples with a narrower age range due to smaller errors/brain age delta values when predictions are closer to the mean age of the group. Across subsets with different age ranges, performance metrics improve with increasing sample size. Performance metrics further vary depending on prediction variance as well as mean age difference between training and test sets, and age-bias corrected metrics indicate high accuracy-also for models showing poor initial performance. In conclusion, performance metrics used for evaluating age prediction models depend on cohort and study-specific data characteristics, and cannot be directly compared across different studies. Since age-bias corrected metrics generally indicate high accuracy, even for poorly performing models, inspection of uncorrected model results provides important information about underlying model attributes such as prediction variance.


Language(s): eng - English
 Dates: 2022-03-21
 Publication Status: Published online
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.1002/hbm.25837
Other: online ahead of print
PMID: 35312210
 Degree: -



Legal Case


Project information

show hide
Project name : Collaboratory on Research Definitions for Reserve and Resilience in Cognitive Aging and Dementia
Grant ID : 5R24AG061421-03
Funding program : -
Funding organization : -
Project name : -
Grant ID : FR 3709/1-2, HA7070/2-2, HA7070/3, HA7070/4
Funding program : -
Funding organization : Deutsche Forschungsgemeinschaft (DFG)
Project name : -
Grant ID : 802998
Funding program : -
Funding organization : European Research Council
Project name : -
Grant ID : 1117747
Funding program : -
Funding organization : HDH Wills 1965 Charitable Trust
Project name : -
Grant ID : 2015073, 2019107
Funding program : -
Funding organization : Helse Sør-Øst RHF
Project name : -
Grant ID : AMSP 07
Funding program : -
Funding organization : Jena University Hospital
Project name : -
Grant ID : MzH 3/020/20
Funding program : -
Funding organization : Medical Faculty of Münster
Project name : -
Grant ID : G1001354, MR/R024790/2
Funding program : -
Funding organization : Medical Research Council
Project name : -
Grant ID : 223273, 249795, 273345, 276082
Funding program : -
Funding organization : Norges Forskningsråd
Project name : -
Grant ID : 32003B_135679, 32003B_159780, 324730_192755, CRSK-3_190185, PZ00P3_193658
Funding program : -
Funding organization : Swiss National Science Foundation

Source 1

Title: Human Brain Mapping
Source Genre: Journal
Publ. Info: New York : Wiley-Liss
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: - Identifier: ISSN: 1065-9471
CoNE: https://pure.mpg.de/cone/journals/resource/954925601686