M. Rosenblatt
26 Papers
1 Citations
M. Rosenblatt is an academic researcher. The author has contributed to research in topics: Computer science & Medicine. The author has an hindex of 2, co-authored 15 publications.
Chat about Author
Papers
Data leakage inflates prediction performance in connectome-based machine learning models
M. Rosenblatt,Link Tejavibulya,Rongtao Jiang,Stephanie Noble,Dustin Scheinost +4 more
TL;DR: Data leakage, a pervasive issue in machine learning, inflates prediction performance in connectome-based models, particularly through feature selection and repeated subjects, but has minor effects via other forms, highlighting the need for leakage avoidance.
35
Elevated C-reactive protein mediates the liver-brain axis: a preliminary study
Rongtao Jiang,Jing Wu,M. Rosenblatt,Wei-chuan Dai,Raimundo X. Rodriguez,Jing Sui,Shile Qi,Qinghao Liang,Bin Xu,Qinghua Meng,Vince D. Calhoun,Dustin Scheinost +11 more
TL;DR: In this article , the authors examined the cross-sectional association of liver fibrosis with cognitive functioning and regional grey matter volumes (GMVs) while adjusting for numerous covariates and multiple comparisons.
17
Connectome-based machine learning models are vulnerable to subtle data manipulations
M. Rosenblatt,Raimundo X. Rodriguez,Margaret L. Westwater,Wei Dai,Corey Horien,Abigail S. Greene,R. Todd Constable,Stephanie Noble,Dustin Scheinost +8 more
TL;DR: Mejia et al. as mentioned in this paper used functional connectomes to explore how minor data manipulations could affect machine learning predictions, and showed that only minor manipulations of the data could lead to drastically different performance.
17
Machine Learning and Prediction in Fetal, Infant, and Toddler Neuroimaging: A Review and Primer
Dustin Scheinost,Angeliki Pollatou,Alexander J. Dufford,Rongtao Jiang,Michael C. Farruggia,M. Rosenblatt,H Peterson,Raimundo X. Rodriguez,Javid Dadashkarimi,Qinghao Liang,Wei-chuan Dai,Maya L. Foster,Christopher C. Camp,Link Tejavibulya,Brendan Adkinson,Huili Sun,Jean Ye,Qi Cheng,Marisa N. Spann,Max Rolison,Stephanie Noble,Margaret L. Westwater +21 more
TL;DR: Predictive models in neuroimaging are increasingly designed with the intent to improve risk stratification and support interventional efforts in psychiatry as discussed by the authors , however, despite growing evidence that altered brain maturation during the fetal, infant, and toddler period modulates risk for poor mental health outcomes in childhood, these models are rarely implemented in FIT samples.
15
The brain structure, inflammatory, and genetic mechanisms mediate the association between physical frailty and depression
Rongtao Jiang,Stephanie Noble,M. Rosenblatt,Wei-chuan Dai,Jean Ye,Shu Liu,Shile Qi,Vince D. Calhoun,Jing Sui,Dustin Scheinost +9 more
TL;DR: This study of 352,277 UK Biobank participants over 12.25 years finds a strong association between physical frailty and depression, with frail individuals at increased risk, particularly in males and those under 65, and identifies potential mediating factors including inflammatory markers and brain volumes.
13