Rxivist logo

Many studies have highlighted the difficulty inherent to the clinical application of fundamental neuroscience knowledge based on machine learning techniques. It is difficult to generalize machine learning brain markers to the data acquired from independent imaging sites, mainly due to large site differences in functional magnetic resonance imaging. We address the difficulty of finding a generalizable major depressive disorder (MDD) brain network markers which would distinguish patients from healthy controls (a classifier) or would predict symptom severity (a prediction model) based on resting state functional connectivity patterns. For the discovery dataset with 713 participants from 4 imaging sites, we removed site differences using our recently developed harmonization method and developed a machine learning MDD brain network markers. The classifier achieved 70% generalization accuracy, and the prediction model moderately well predicted symptom severity for an independent validation dataset with 449 participants from 4 different imaging sites. Finally, we found common 2 functional connections between those related to MDD diagnosis and those related to depression symptoms. The successful generalization to the perfectly independent dataset acquired from multiple imaging sites is novel and ensures scientific reproducibility and clinical applicability. ### Competing Interest Statement Competing financial interests: M.K., N.Y., R.H., H.I., N.K. and K.K are inventors of a patent owned by Advanced Telecommunications Research (ATR) Institute International related to the present work [PCT/JP2014/061543 (WO2014178322)]. M.K., N.Y., R.H., N.K. and K.K. are inventors of a patent owned by ATR Institute International related to the present work [PCT/JP2014/061544 (WO2014178323)]. M.K. and N.Y. are inventors of a patent application submitted by ATR Institute International related to the present work [JP2015-228970]. A.Y. and M.K. are inventors of a patent application submitted by ATR Institute International related to the present work [JP2018-192842].

Download data

  • Downloaded 382 times
  • Download rankings, all-time:
    • Site-wide: 87,640
    • In neuroscience: 13,049
  • Year to date:
    • Site-wide: 70,201
  • Since beginning of last month:
    • Site-wide: 112,646

Altmetric data


Downloads over time

Distribution of downloads per paper, site-wide


PanLingua

News