AI Science Tracker
EN

Nihon University

1 discovery from 2022

Discoveries

Nihon University

Chest radiograph learning estimates invasively measured filling pressure

Source check: Source checked. Not independent scientific confirmation.

Finding: A VGG16-based regression network estimated pulmonary artery wedge pressure from chest radiographs in 936 cardiovascular patients. In 188 held-out patients, estimates correlated moderately with catheter measurements (r = 0.62), with wide agreement limits around plus or minus 11 mmHg and underestimation at high pressures. This clinical measurement study does not establish catheter replacement, prognosis or improved care.

Technology: VGG16-based regression convolutional neural network

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

AI contribution
A transfer-learned convolutional network regresses radiograph features onto measured pulmonary artery wedge pressure.
Test and result
Separate 188-patient internal test against right-heart catheter pressure, after model tuning within the 748-patient development set.
Limitation / still unknown
External clinical utility remains unestablished; radiographs and catheter measurements were not simultaneous, high pressures were underestimated and several lung/device conditions were excluded.
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/PMC9239946/

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: Primary relevant model Methods, Results and limitations; exact primary identity and current primary PubMed correction/retraction relationships checked..

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.