i-ECO: a novel method for the analysis and visualization of fMRI results in Psychiatry
Bibliographic record
Abstract
Introduction The high technical barrier to entry in the field of neuroimaging can hinder early insight from promising results and the development of evidence-based clinical practice. Objectives The working group focused on published literature in order to develop a new methodology in the analysis, visualization, and representation of fMRI data in the psychiatric setting. Methods Three valid and established measures were chosen, in order to achieve dimensionality reduction, stability and explainability of results, namely Regional-Homogeneity; fractional Amplitude of Low-Frequency Fluctuations; Eigenvector-Centrality. Each measure was color coded and individual images per subject compiled, averaging results by functional networks as described the FIND lab of the University of Stanford. 272 individual scans were processed (130 neurotypicals, 50 patients with Schizophrenia, 49 with Bipolar Disorder, 43 with ADHD). Results The discriminative power between clinical groups of the novel method was significant both by human eye, and later confirmation by statistical tests, and by computer vision algorithms (Convolutional Neural Networks). The precision-recall Area Under the Curve, dividing by 80/20 proportion between train and test sets, was >84.5% for each group. The group of patients with Bipolar Disorder showed a partial overlap with the group of patients suffering from Schizophrenia – by a dominance of Eigenvector-Centrality and Regional-Homogeneity, as well as a lower prevalence of fractional Amplitude of Low-Frequency Fluctuations, for both in comparison to controls. Conclusions The present study offers preliminary evidence for the adoption of i-ECO (integrated-Explainability through Color Coding) in fMRI analyses during rest in the Psychiatric field. Disclosure No significant relationships.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.006 | 0.003 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.003 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.007 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".