Canonical text (the exact bytes fingerprinted)

TRUVACE RECORD VERSION
record: TRV-2026-1006
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-09-07T06:06:58.335144Z
status: published
lens: p_space
sector: health
headline: The Translational Gap in AI for Oropharyngeal Squamous Cell Carcinoma: A TRIPOD+AI Scoping Review of Methodological Barriers to Treatment Deintensification
dek: Rationale and objectives To map artificial intelligence (AI) and radiomics applications in computed tomography (CT), magnetic resonance imaging (MRI), and fluorodeoxyglucose positron emission tomography/CT (FDG-PET/CT) for oropharyngeal squamous cell carcinoma (OPSCC) in the context of human papillomavirus (HPV) status and treatment deintensification, evaluate reporting quality using TRIPOD+AI (Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis + Artificial Intelligen…
gain_title: (none)
problem_title: CT, MRI, and FDG-PET/CT-based AI/radiomics models for oropharyngeal squamous cell carcinoma lack external validation, calibration, transparency, and nodal coverage, precluding safe clinical use to guide HPV-related treatment deintensification.
trace_subject: (none)
gain_reading: (none)
gain_evidence: (none)
problem_reading: CT, MRI, and FDG-PET/CT-based AI/radiomics models for oropharyngeal squamous cell carcinoma lack external validation, calibration, transparency, and nodal coverage, precluding safe clinical use to guide HPV-related treatment deintensification.
problem_evidence: external validation remained limited (22/61, 36.1%), often with performance decline | preclude safe clinical implementation
quick_read: A TRIPOD+AI scoping review of 61 studies examined AI and radiomics applied to CT, MRI, and FDG-PET/CT for histologically confirmed oropharyngeal squamous cell carcinoma, focusing on HPV status prediction and treatment deintensification. CT was the dominant modality, manual segmentation and handcrafted radiomics with machine learning were most common, and HPV models reported AUCs from 0.65 to 0.95.

Despite promising discrimination, the review found persistent methodological gaps that prevent clinical translation: only 36.1% had external validation often with performance decline, calibration and missing data handling were largely absent, code and data sharing were rare, and nodal disease was rarely analyzed. The authors concluded standardized protocols, rigorous validation, and structured reporting are needed before tools can safely guide deintensification.
limitation: Review scope was limited to CT, MRI, and FDG-PET/CT for HPV-oriented objectives and to PubMed/MEDLINE and Scopus searches, with findings not generalizable beyond those modalities and objectives.
tag: Evidence-backed problem
key_points: Scoping review included 61 studies from PubMed/MEDLINE and Scopus January 2015-December 2025 on AI/radiomics for histologically confirmed OPSCC. | CT was most frequent modality at 49.2%, followed by MRI 29.5% and FDG-PET/CT 21.3%, with manual segmentation 85.2% and handcrafted radiomics with machine learning 57.4%. | HPV prediction models reported AUCs of 0.65-0.95, but external validation was limited to 22/61 studies and often showed performance decline. | TRIPOD+AI assessment found calibration fully reported in only 6.6% and absent in 91.8%, missing data handling fully reported 3.3% and absent 54.1%, code availability 11.5%. | Most studies restricted analysis to primary tumor 78.7%; nodal disease incorporated in 11/61 and sole target in 2/61.
rundown: The review followed PRISMA-ScR and screened PubMed/MEDLINE and Scopus from January 2015 to December 2025, including 61 studies: 34 addressed HPV prediction, 29 survival or prognosis, and 3 treatment response, with overlap across objectives.

Reporting quality was scored with TRIPOD+AI 27 items 0-2 scoring, revealing low rates of full reporting for calibration, missing data handling, interpretable risk groups, data availability 19.7% and code availability 11.5%, and limited incorporation of nodal disease beyond primary tumor analysis.
sources:
- peer_reviewed | Academic Radiology | https://doi.org/10.1016/j.acra.2026.08.075 | 2026-09-05
prev: 0000000000000000000000000000000000000000000000000000000000000000

sha256

e54c698b4ac5605d316d4d4a6805703e062e17174290d18467f5bfc3d0e13f7d

previous

0000000000000000000000000000000000000000000000000000000000000000