Ultrasonic texture features for assessing abnormal interventricular septum motion following cardiac surgery
Source check: Source checked. Not independent scientific confirmation.
Finding: Ultrasound texture features differed with abnormal postoperative septal motion, and an SVM classifier distinguished the groups in a retrospective two-center study. External-center AUC was 0.803, below internal performance; the result supports a diagnostic association, not improved clinical outcomes.
Technology: LASSO feature selection and logistic-regression, random-forest, and SVM classifiers analyze ultrasound texture and shape features.
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- Learned classification of echocardiographic features enabled an evaluated association with postoperative septal motion.
- Test and result
- Among 650 patients, texture differences were associated with abnormal septal motion; SVM AUC was 0.943 in training, 0.948 internally, and 0.803 in an external-center cohort.
- Limitation / still unknown
- Retrospective diagnostic study; external performance was lower, and prospective clinical benefit was not tested. Online date 2026-10-19 precedes the 2026-11-01 issue date.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://qims.amegroups.org/article/view/161772
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 source full-text Methods and Results; version date and reported validation scope 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 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.