Canonical text (the exact bytes fingerprinted)

TRUVACE RECORD VERSION
record: TRV-2026-1027
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-09-09T06:05:43.822095Z
status: published
lens: g_space
sector: health
headline: A Multiparametric Approach Integrating Multimodal Ultrasound and Serum TPO-Ab for Differentiating Thyroid Carcinoma in Hashimoto's Thyroiditis: A Comparative Diagnostic Study with Internal Validation
dek: Objectives To evaluate whether a multiparametric approach combining grayscale ultrasound (2D-US), contrast-enhanced ultrasound (CEUS), and serum anti-thyroid peroxidase antibody (TPO-Ab) improves the differentiation of benign from malignant thyroid nodules (TNs) in patients with Hashimoto's thyroiditis (HT) and to assess the stability of the combined diagnostic model through internal validation. Methods This retrospective study enrolled 600 HT patients with 650 pathologically confirmed TNs. All patients underwen…
gain_title: A logistic regression model combining grayscale ultrasound, contrast-enhanced ultrasound, and serum TPO-Ab improved differentiation of benign versus malignant thyroid nodules in Hashimoto's thyroiditis, reaching cross-validated AUC 0.849 with 77.3% sensitivity and 77.8% specificity.
problem_title: (none)
trace_subject: (none)
gain_reading: A logistic regression model combining grayscale ultrasound, contrast-enhanced ultrasound, and serum TPO-Ab improved differentiation of benign versus malignant thyroid nodules in Hashimoto's thyroiditis, reaching cross-validated AUC 0.849 with 77.3% sensitivity and 77.8% specificity.
gain_evidence: The combined model integrating 2D-US, CEUS, and TPO-Ab achieved a cross-validated AUC of 0.849 with sensitivity of 77.3% and specificity of 77.8%, outperforming any single modality
problem_reading: (none)
problem_evidence: (none)
quick_read: Researchers retrospectively analyzed 600 patients with Hashimoto's thyroiditis and 650 pathology-confirmed thyroid nodules to test whether combining grayscale ultrasound, contrast-enhanced ultrasound, and serum anti-thyroid peroxidase antibody improves malignancy differentiation. They built a logistic regression model on patients with complete data and performed stratified 5-fold cross-validation, also comparing six machine learning classifiers.

By the September 2026 publication date, the combined model showed higher discrimination than any single modality, with reported cross-validated AUC 0.849, sensitivity 77.3% and specificity 77.8%. The authors position it as a potential supplementary tool for risk stratification in surgical candidates, while noting that lack of prospective external validation leaves generalizability and clinical implementation uncertain.
limitation: Model was developed retrospectively with internal validation only and has not been tested prospectively in external populations, limiting readiness for clinical use.
tag: Evidence-backed gain
key_points: Retrospective study of 600 Hashimoto's patients with 650 pathologically confirmed thyroid nodules evaluated 2D-US, CEUS, TPO-Ab, and exploratory SWE. | Primary combined diagnostic model was built on subset with complete 2D-US, CEUS, and TPO-Ab data using logistic regression with stratified 5-fold cross-validation. | Six machine learning classifiers were compared; logistic regression showed most stable performance and best balance between sensitivity and specificity.
rundown: The study enrolled 600 HT patients with 650 pathologically confirmed nodules; all had 2D-US, while CEUS was performed in 475, TPO-Ab testing in 452, and shear wave elastography in an exploratory subset of 88. The primary model used the complete-data subset for 2D-US, CEUS, and TPO-Ab.

Single-modality cross-validated AUCs were 0.831 for 2D-US, 0.671 for CEUS, and 0.621 for TPO-Ab. The combined LR model reached 0.849 AUC, and among six classifiers tested, LR was reported as most stable.
sources:
- peer_reviewed | Journal of Ultrasound in Medicine | https://doi.org/10.1002/jum.70419 | 2026-09-08
prev: 0000000000000000000000000000000000000000000000000000000000000000

sha256

f1a3a9b728422d1fac749fd7941f1bf1723e5ca7e7d50cc639c33be630c1acdd

previous

0000000000000000000000000000000000000000000000000000000000000000