Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Observational Study
. 2025 Jun:207:110890.
doi: 10.1016/j.radonc.2025.110890. Epub 2025 Apr 11.

Externally validated digital decision support tool for time-to-osteoradionecrosis risk-stratification using right-censored multi-institutional observational cohorts

Laia Humbert-Vidan  1 , Serageldin Kamel  1 , Andrew Wentzel  2 , Zaphanlene Kaffey  1 , Moamen Abdelaal  3 , Kyle B Spier  4 , Natalie A West  1 , G Elisabeta Marai  2 , Guadalupe Canahuate  5 , Xinhua Zhang  2 , Melissa M Chen  1 , Kareem A Wahid  1 , Jillian Rigert  1 , Seyedmohammadhossein Hosseinian  6 , Andrew J Schaefer  7 , Kristy K Brock  1 , Mark Chambers  1 , Adegbenga O Otun  1 , Ruth Aponte-Wesson  1 , Vinod Patel  8 , Andrew Hope  9 , Jack Phan  1 , Adam S Garden  1 , Steven J Frank  1 , William H Morrison  1 , Michael T Spiotto  1 , David Rosenthal  1 , Anna Lee  1 , Renjie He  1 , Mohamed A Naser  1 , Erin Watson  10 , Katherine A Hutcheson  1 , Abdallah S R Mohamed  1 , Vlad C Sandulache  11 , Lisanne V van Dijk  12 , Amy C Moreno  1 , Teresa Guerrero Urbano  13 , Clifton D Fuller  14 , Stephen Y Lai  15 ; MD Anderson Head and Neck Cancer Symptom Working Group
Collaborators, Affiliations
Observational Study

Externally validated digital decision support tool for time-to-osteoradionecrosis risk-stratification using right-censored multi-institutional observational cohorts

Laia Humbert-Vidan et al. Radiother Oncol. 2025 Jun.

Abstract

Background: Existing studies on osteoradionecrosis of the jaw (ORNJ) have primarily used cross-sectional data, assessing risk factors at a single time point. Determining the time-to-event profile of ORNJ has important implications to monitor oral health in head and neck cancer (HNC) long-term survivors.

Methods: Data were retrospectively obtained for a clinical observational cohort of 1129 patients (198 ORNJ cases) with HNC treated with radiotherapy (RT) at The University of Texas MD Anderson Cancer Center. A Weibull Accelerated Failure Time model was trained on previously identified dosimetric, clinical and demographic predictors. External validation was performed using an independent cohort of 265 patients (92 ORNJ cases) treated at Guy's and St. Thomas' Hospitals. To facilitate clinical implementation of the model, an online graphical user interface (GUI) was developed, including formal stakeholder usability testing.

Results: Our model identified that gender (males), pre-RT dental extractions and D25% were associated with a 38 %, 27 % and 12 % faster onset of ORNJ, respectively, with adjusted time ratios of 0.62 (p = 0.11), 0.73 (p = 0.13) and 0.88 (p < 0.005). The model demonstrated strong internal calibration (integrated Brier score of 0.133, D-calibration p-value 0.998) and optimal discrimination at 72 months (Harrell's C-index of 0.72).

Conclusion: This study is the first to demonstrate a direct relationship between radiation dose and the time to ORNJ onset, providing a novel characterization of the impact of delivered dose and patient-related factors not only on the probability of a late effect (ORNJ), but the conditional risk during survivorship.

Keywords: Decision support tool; Head and neck cancers; Normal tissue complication prediction; Osteoradionecrosis of the jaw; Radiation-induced toxicity; Radiotherapy; Time-to-event prediction models.

PubMed Disclaimer

Conflict of interest statement

Declaration of competing interest The authors declare the following financial interests/personal relationships which may be considered as potential competing interests: CDF has received unrelated grant support from Elekta AB and holds unrelated patents licensed to Kallisio, Inc. (US PTO 11730561) through the University of Texas, from which they receive patent royalties. CDF has also received unrelated travel and honoraria from Elekta AB, Philips Medical Systems, Siemens Healthineers/Varian, and Corewell Health. Additionally, CDF has served in an unpaid advisory capacity for Siemens Healthineers/Varian and has served on the guidelines/scientific committee for Osteoradionecrosis for the American Society of Clinical Oncology. VCS is a consultant and equity holder in Femtovox Inc and a consultant for PDS Biotechnology. KAW serves as an Editorial Board Member for Physics and Imaging in Radiation Oncology. The authors declare that no other competing interests exist.

Figures

Figure 1.
Figure 1.
Screenshot of the WAFT-based time-to-ORNJ online calculator GUI. The user can either obtain a predicted risk of developing ORNJ at a specific time point or visually assess the time-dependency of ORNJ risk with the different covariates of the ORNJ WAFT model.
Figure 2.
Figure 2.
Frequency plot of actuarial time-to-event in months by ORNJ status for the MD Anderson dataset, where cases with diagnosed ORNJ are in blue and censored (either death or last follow-up) cases are in green; note that deeper blue also corresponds to ORNJ cases but with frequency bars overlapping with those of the censored group. Supplement D includes frequency plots for the training (Figure D1a), test (Figure D1b) and external (Figure D1c) datasets separately.
Figure 3.
Figure 3.
ORNJ WAFT survival curves and number of patients at risk tables for the different covariates considered in the model: (a) gender, (b) D25% and (c) pre-RT dental extractions.
Figure 3.
Figure 3.
ORNJ WAFT survival curves and number of patients at risk tables for the different covariates considered in the model: (a) gender, (b) D25% and (c) pre-RT dental extractions.
Figure 3.
Figure 3.
ORNJ WAFT survival curves and number of patients at risk tables for the different covariates considered in the model: (a) gender, (b) D25% and (c) pre-RT dental extractions.
Figure 4:
Figure 4:
ORNJ WAFT model performance plots at internal validation. Discrimination performance variation over time is described by the Harrell’s C-index (a). Overall model performance over time is described by the Brier score and integrated Brier score (IBS) (b). Model calibration is described by the Distributional calibration curve (c), which represents the computed squared difference between the observed and predicted number of events within different time intervals.
Figure 4:
Figure 4:
ORNJ WAFT model performance plots at internal validation. Discrimination performance variation over time is described by the Harrell’s C-index (a). Overall model performance over time is described by the Brier score and integrated Brier score (IBS) (b). Model calibration is described by the Distributional calibration curve (c), which represents the computed squared difference between the observed and predicted number of events within different time intervals.
Figure 4:
Figure 4:
ORNJ WAFT model performance plots at internal validation. Discrimination performance variation over time is described by the Harrell’s C-index (a). Overall model performance over time is described by the Brier score and integrated Brier score (IBS) (b). Model calibration is described by the Distributional calibration curve (c), which represents the computed squared difference between the observed and predicted number of events within different time intervals.
Figure 5:
Figure 5:
GUI System Usability Scale (SUS) score distribution by survey participant specialty group.
See this image and copyright information in PMC

References

    1. Frankart AJ; Frankart MJ; Cervenka B; Tang AL; Krishnan DG; Takiar V Osteoradionecrosis: Exposing the Evidence Not the Bone. International Journal of Radiation Oncology Biology Physics 2021, 109 (5), 1206–1218. 10.1016/j.ijrobp.2020.12.043. - DOI - PubMed
    1. Laraway DC; Rogers SN A Structured Review of Journal Articles Reporting Outcomes Using the University of Washington Quality of Life Scale. British Journal of Oral and Maxillofacial Surgery 2012, 50 (2), 122–131. 10.1016/j.bjoms.2010.12.005. - DOI - PubMed
    1. O’Dell K; Sinha U Osteoradionecrosis. Oral Maxillofac Surg Clin North Am 2011, 23 (3), 455–464. 10.1016/j.coms.2011.04.011. - DOI - PubMed
    1. Habib S; Sassoon I; Thompson I; Patel V Risk Factors Associated with Osteoradionecrosis. Oral Surgery 2021, 14 (3), 227–235. 10.1111/ors.12597. - DOI
    1. MD Anderson Head and Neck Cancer Symptom Working Group. Dose-Volume Correlates of Mandibular Osteoradionecrosis in Oropharynx Cancer Patients Receiving Intensity-Modulated Radiotherapy: Results from a Case-Matched Comparison. Radiother Oncol 2017, 124 (2), 232–239. 10.1016/j.radonc.2017.06.026. - DOI - PMC - PubMed

Publication types