AI Science Tracker
EN

University of Sheffield

1 discovery from 2021

Discoveries

Consensus learning nominates a pulmonary-hypertension miRNA pattern

Source check: Source checked. Not independent scientific confirmation.

Finding: Four fitted feature-selection approaches consistently selected miR-636 and miR-187-5p in a pulmonary arterial hypertension study. The clinical miRNA models showed moderate discrimination in a small held-out subset. These are exploratory diagnostic-reference and feature-association findings, not established clinical utility or causal pulmonary mechanisms.

Technology: Boruta random forest; LASSO; regression partition trees; XGBoost

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

AI contribution
Learned forests, boosted trees and regularized/partition models select diagnostic features and produce patient-level predictions; agreement of selected features and held-out reference discrimination supply the scoped finding.
Test and result
The miRNA cohort comprised 64 PAH cases and 43 combined healthy/systemic-sclerosis-without-PH controls. Models were developed using 72 people and assessed on 35; repeated cross-validation supported feature selection and tuning. Both nominated miRNAs recurred across the four approaches and alternative selection analyses.
Limitation / still unknown
Model and feature comparisons used the same small validation sample. The Results claim 30/35 correct for Boruta, while the table reports a different classification rate; no single accuracy is promoted here. Whole-data filtering and multiple selection analyses require caution. Whole-blood gene-target classification involved refitting on different features and is not external validation of the original miRNA classifier. A five-year follow-up does not make the already-collected diagnostic evaluation prospective. No pathway causality or laboratory mechanism is adopted.
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/PMC8243351/

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: 21 Nov 2026. Review scope: Exact primary front and selected computational/clinical Methods and corresponding high-level Results; operational laboratory protocols excluded from review.

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 2/5 · Validation 2/5 · Novelty 2/5. 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.