Papers › Systematic Misestimation of Machine Learning Performance in Neuroimaging Studies of Depression
Systematic Misestimation of Machine Learning Performance in Neuroimaging Studies of Depression
Claas Flint, Micah Cearns, Nils Opel, Ronny Redlich, David M. A. Mehler, Daniel Emden, Nils R. Winter, Ramona Leenings, Simon B. Eickhoff, Tilo Kircher, Axel Krug, Igor Nenadic, Volker Arolt, Scott Clark, Bernhard T. Baune, Xiaoyi Jiang, Udo Dannlowski, Tim Hahn
We currently observe a disconcerting phenomenon in machine learning studies in psychiatry: While we would expect larger samples to yield better results due to the availability of more data, larger machine learning studies consistently show much weaker performance than the numerous small-scale studies. Here, we systematically investigated this effect focusing on one of the most heavily studied questions in the field, namely the classification of patients suffering from major depressive disorder (MDD) and healthy control (HC) based on neuroimaging data. Drawing upon structural magnetic resonance imaging (MRI) data from a balanced sample of N = 1,868 MDD patients and HC from our recent international Predictive Analytics Competition (PAC), we first trained and tested a classification model on the full dataset which yielded an accuracy of 61 %. Next, we mimicked the process by which researchers would draw samples of various sizes (N = 4 to N = 150) from the population and showed a strong risk of misestimation. Specifically, for small sample sizes (N = 20), we observe accuracies of up to 95 %. For medium sample sizes (N = 100) accuracies up to 75 % were found. Importantly, further investigation showed that sufficiently large test sets effectively protect against performance misestimation whereas larger datasets per se do not. While these results question the validity of a substantial part of the current literature, we outline the relatively low-cost remedy of larger test sets, which is readily available in most cases.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections