Category Ranking
98%
Total Visits
921
Avg Visit Duration
2 minutes
Citations
20
Article Abstract
Establishing reliable, robust, and unique brain signatures from neuroimaging data is a prerequisite for precision psychiatry, and therefore a highly sought-after goal in contemporary neuroscience. Recently, the procedure of connectome fingerprinting, using brain functional connectivity profiles as such signatures, was shown to be able to accurately identify individuals from a group of 126 subjects from the Human Connectome Project (HCP). However, the specificity and generalizability of this procedure were not tested. In this replication study, we show both for the original and an extended HCP data set (n = 900 subjects), as well as for an additional data set of more commonly acquired imaging quality (n = 84) that (i) although the high accuracy can be replicated for the larger HCP 900 data set, accuracy is (ii) lower for standard neuroimaging data, and, that (iii) connectome fingerprinting may not be specific enough to distinguish between individuals. In addition, both accuracy and specificity are projected to drop considerably as the size of a data set increases. Although the moderate-to-high accuracies do suggest there is a portion of unique variance, our results suggest that connectomes may actually be quite similar across individuals. This outcome may be relevant to how precision psychiatry could benefit from inferences based on functional connectomes.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.neuroimage.2017.07.016 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Designing Buchwald-Hartwig Reaction Graph for Yield Prediction.
J Org Chem
September 2025
State Key Laboratory of Fine Chemicals, School of Chemical Engineering, Ocean and Life Sciences, Dalian University of Technology, Panjin 124221, P. R. China.
The Buchwald-Hartwig (B-H) reaction graph, a novel graph for deep learning models, is designed to simulate the interactions among multiple chemical components in the B-H reaction by representing each reactant as an individual node within a custom-designed reaction graph, thereby capturing both single-molecule and intermolecular relationship features. Trained on a high-throughput B-H reaction data set, B-H Reaction Graph Neural Network (BH-RGNN) achieves near-state-of-the-art performance with an score of 0.971 while maintaining low computational costs.
View Article and Find Full Text PDFPredicting HOMO-LUMO Gaps Using Hartree-Fock Calculated Data and Machine Learning Models.
J Chem Inf Model
September 2025
Department of Chemistry, Delaware State University, Dover, Delaware 19901, United States.
The calculation of the highest occupied molecular orbital-lowest unoccupied molecular orbital (HOMO-LUMO) gap for chemical molecules is computationally intensive using quantum mechanics (QM) methods, while experimental determination is often costly and time-consuming. Machine Learning (ML) offers a cost-effective and rapid alternative, enabling efficient predictions of HOMO-LUMO gap values across large data sets without the need for extensive QM computations or experiments. ML models facilitate the screening of diverse molecules, providing valuable insights into complex chemical spaces and integrating seamlessly into high-throughput workflows to prioritize candidates for experimental validation.
View Article and Find Full Text PDFA revised circumscription of Marthamycetales based on a complete sampling of the types of genera, Propoliaceae, fam. nov., and placement of in Leotiomycetes.
Mycologia
September 2025
Herbarium, University of Michigan, 3600 Varsity Drive, Ann Arbor, Michigan 48108, USA.
Marthamycetales species are widely distributed, non-lichenized, apothecial ascomycetes that are associated with various woody plants and grasses. Most species are presumed to be saprobes, although a few are pathogens. Apothecia are small and erumpent, with farinose discs that are encircled by ragged, projecting flaps of degraded plant tissue.
View Article and Find Full Text PDFPredicting complex time series with deep echo state networks.
Chaos
September 2025
School of Computational Science and Engineering, Georgia Institute of Technology, Atlanta, Georgia 30332, USA.
Although many real-world time series are complex, developing methods that can learn from their behavior effectively enough to enable reliable forecasting remains challenging. Recently, several machine-learning approaches have shown promise in addressing this problem. In particular, the echo state network (ESN) architecture, a type of recurrent neural network where neurons are randomly connected and only the read-out layer is trained, has been proposed as suitable for many-step-ahead forecasting tasks.
View Article and Find Full Text PDFFarm Injury Deaths and Workers' Compensation Claims in Australia and Their Economic Costs.
Aust J Rural Health
October 2025
AgHealth Australia, School of Rural Health, Faculty of Medicine and Health, The University of Sydney, Sydney, New South Wales, Australia.
Objective: To describe the pattern and estimated direct economic burdens associated with unintentional deaths and injuries on Australian farms over the past 11 years (2013-2023).
Design: Descriptive retrospective epidemiological study of National Coronial Information System (NCIS) data for persons fatally injured on a farm and workers' compensation injuries data from the National Data Set.
Setting: Australia.