Evidence map›Paper›PMID 41856253›Full record

ArticleRadiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology2026

A multi-toxicity deep learning approach for normal tissue complication probability modelling in head and neck cancer patients receiving radiotherapy.

D C MacRae, L van der Hoek, S P M de Vette, H Neh, A C Moreno, C D Fuller, J A Langendijk, M A Valdenegro-Toro, N M Sijtsema, P M A van Ooijen and 1 more

Abstract readMulticenter Study
PubMed Full text at PMC Publisher
In one paragraph

Article in Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 2 papers.

0numbers the graph read from it
0cells of the map it votes in
2citing papers in PubMed
–field-weighted citation impact
1 · What the graph read from it

What it found

Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.

The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.

2 · The registry

The trial behind it

Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.

Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.

3 · Its place in the literature

Who cites it

2 citing papers in PubMed.

  1. Review
  2. Review
4 · The record

Corrections and comments

PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.

5 · Who and what money

Authors and funding

11 authors.

D C MacRaeDepartment of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, the Netherlands. Electronic address: d.c.macrae@umcg.nl.
L van der HoekDepartment of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, the Netherlands.
S P M de VetteDepartment of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, the Netherlands.
H NehDepartment of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, the Netherlands.
A C MorenoDepartment of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, USA.
C D FullerDepartment of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, USA.
J A LangendijkDepartment of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, the Netherlands.
M A Valdenegro-ToroDepartment of Artificial Intelligence, Bernoulli Institute, University of Groningen, the Netherlands.
N M SijtsemaDepartment of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, the Netherlands.
P M A van OoijenDepartment of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, the Netherlands.
L V van DijkDepartment of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, the Netherlands. Electronic address: l.v.van.dijk@umcg.nl.

Funding

Project 3: OPC-RADP01CA285249 · NCI · UNIVERSITY OF TX MD ANDERSON CAN CTR · PI Carly E. A. Barbon · 2024 to 2026
$9.4M
Longitudinal Spatial-Nonspatial Decision Support for Competing Outcomes in Head and Neck Cancer TherapyR01CA258827 · NCI · UNIVERSITY OF ILLINOIS AT CHICAGO · PI CANAHUATE, GUADALUPE, FULLER, CLIFTON DAVID · 2021 to 2025
$2.9M
Ontology-based aPplications of mUlti-discipLinary knowlEdge on orodeNtal Conditions and outcomEs (OPULENCE)R01DE034406 · NIDCR · UNIVERSITY OF TX MD ANDERSON CAN CTR · PI Amy Catherine Moreno · 2025 to 2026
$1.5M
Harvard MD Anderson Collaborative to Reduce LyMphatic MOrbidity in Head and Neck Cancer with Artificial Intelligence (HARMONiC-AI)R01DE034780 · NIDCR · UNIVERSITY OF TX MD ANDERSON CAN CTR · PI Clifton David Fuller, Katherine Arnold Hutcheson · 2025 to 2026
$1.4M
Provider and Patient-generated Remote Oro-Dental Health Electronic Data Capture for Algorithmic Longitudinal Evaluation and Risk-Assessment (PROHEALER)K01DE030524 · NIDCR · UNIVERSITY OF TX MD ANDERSON CAN CTR · PI MORENO, AMY CATHERINE · 2022 to 2024
$479k
Radiation-specific Automated Dental Dose Distributions via Machine-learning based Mapping for Accurate Predictions of (Peri)odontal Problems (RADMAP)R21DE031082 · NIDCR · UNIVERSITY OF TX MD ANDERSON CAN CTR · PI MORENO, AMY CATHERINE · 2021 to 2022
$452k
NCI NIH HHS P01 CA285249NCI NIH HHS R01 CA258827NIDCR NIH HHS K01 DE030524NIDCR NIH HHS R01 DE034406NIDCR NIH HHS R01 DE034780NIDCR NIH HHS R21 DE031082
6 · The paper itself

Abstract

purposeToxicities after radiotherapy for head and neck cancer (HNC) often co-occur and share underlying mechanisms, yet most conventional and deep learning (DL) NTCP models predict only a single endpoint. By developing DL NTCP models which can predict multiple toxicities simultaneously, this study aimed to capture inter-toxicity relationships to improve prediction performance. METHODS AND MATERIALS: A multi-institutional cohort of 1,418 HNC patients was used to develop and validate a multi-toxicity (MT) DL model, incorporating 3D dose distributions, CT scans, organ-at-risk segmentations and patient-related features, that simultaneously predicts five toxicities; aspiration, dysphagia, sticky saliva, taste alteration and xerostomia, all evaluated six months after treatment. Results are compared to conventional NTCP models, as well as a set of single-toxicity (ST) 3D DL models.

resultsThe MT model outperformed both the conventional and ST models for dysphagia (AUC = 0.83 versus 0.81 and 0.82) and xerostomia (0.80 versus 0.75 and 0.78) prediction on the independent validation cohort. The latter models achieved better performance for sticky saliva (0.72 and 0.71 versus 0.69) and taste alteration (both 0.67 versus 0.71). The MT model achieved a higher AUC on aspiration than the ST model (0.71), but performed as well as the reference model (both 0.74). Within the external validation cohort, all models performed comparably to each other, with the MT model achieving a slightly higher average AUC (0.64) across all endpoints than the conventional and ST models (both 0.63). Sub-analyses revealed that the benefit of the proposed multi-toxicity modelling varied by endpoint.

conclusionMT models offer comparable-and in some cases improved-performance over conventional single-endpoint approaches, indicating their promise for NTCP modelling. However, benefits are not uniform across all endpoints, highlighting the importance of considering toxicity-specific features when designing multi-toxicity models.

Indexed as

Deep LearningHead and Neck NeoplasmsRadiation InjuriesAgedDeglutition DisordersFemaleHumansMaleMiddle AgedOrgans at RiskProbabilityRadiotherapy DosageXerostomiaAspirationDeep learningDysphagiaMulti-toxicityNormal tissue complication probabilityRadiotherapySticky salivaTaste alterationXerostomia

Identifiers

PMID41856253
PMCPMC13039088

What OpenQuestion holds

Textmetadata
LicenceCC BY
Read underepoch 390

Registered trials

None linked

Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.