AI Science Tracker
EN

The First Affiliated Hospital of Anhui Medical University

2 discoveries from 2025 to 2026

Discoveries

EEG biomarkers can predict early-stage Alzheimer's disease and correlate with intracerebral pathology: a multimodal machine learning study.

Source check: Source checked. Not independent scientific confirmation.

Finding: Resting-state EEG features and ML distinguish early Alzheimer disease from healthy controls; test-set multimodal PSD/microstate AUC is reported alongside correlations with intracerebral pathology/cognition. The result is cohort-specific. The result is reported in the Alzheimer's Research & Therapy. It does not establish generalization beyond the reported setting or prospective real-world benefit.

Technology: Resting-state EEG features and ML distinguish early Alzheimer disease from healthy controls

Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.

AI contribution
Resting-state EEG features and ML distinguish early Alzheimer disease from healthy controls
Test and result
Resting-state EEG features and ML distinguish early Alzheimer disease from healthy controls; test-set multimodal PSD/microstate AUC is reported alongside correlations with intracerebral pathology/cognition. The result is cohort-specific.
Limitation / still unknown
Independent replication and prospective real-world benefit are not established in the reviewed study.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC13425775/ · https://doi.org/10.1186/s13195-026-02096-3 · https://europepmc.org/article/MED/42216097

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.

Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Development of a Diagnostic Model for Focal Segmental Glomerulosclerosis: Integrating Machine Learning on Activated Pathways and Clinical Validation

Source check: Source checked. Not independent scientific confirmation.

Finding: Across 163 patients with focal segmental glomerulosclerosis and 42 living-donor controls in GEO cohorts, the glmBoost+Ridge model using six genes distinguished FSGS from controls. Its AUCs were 1.000, 0.994 and 1.000 across three development/validation cohorts and 0.910 and 0.775 in two platforms of the external cohort (overall AUC about 0.885). Immunohistochemistry supported elevated CD99 and OAZ2 expression. These retrospective expression-cohort results and small tissue validation do not establish clinical diagnostic utility.

Technology: glmBoost+Ridge

Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.

AI contribution
glmBoost+Ridge combines six gene-expression features (BANF1, TUSC2, SMAD3, TGFB1, CD99 and OAZ2) to classify focal segmental glomerulosclerosis.
Test and result
The glmBoost+Ridge six-gene FSGS model was tested across three GEO cohorts and an independent GEO cohort; internal AUCs were 1.000, 0.994 and 1.000, while the external cohort platform AUCs were 0.910 and 0.775 (combined about 0.885). Immunohistochemistry in 16 FSGS patients and 7 controls supported CD99/OAZ2 expression differences.
Limitation / still unknown
Near-perfect cohort AUCs may not generalize; the independent GEO platform results differed, and clinical diagnostic utility was not demonstrated.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC11872063/ · https://europepmc.org/article/MED/40026806

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.

Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open the interactive profile for the timeline, or browse all organizations and model families.