Prediction model for the selection of patients with glioma to proton therapy
DOI:
https://doi.org/10.2340/1651-226X.2025.43883Keywords:
Glioma, Proton, Prediction modelsAbstract
Background and purpose: The selection of patients with low-grade gliomas for proton therapy (PT) is often based on the comparison of photon and PT plans and demonstrating meaningful dose reduction to the healthy brain or critical structures. The aim of this retrospective study was to identify clinical parameters associated with referral to PT and build a prediction model.
Patients and methods: The dataset consisted of patients with isocitrate dehydrogenase (IDH)-mutant grades 2 and 3 glioma and candidates for PT at the Aarhus University Hospital. Clinical (age, diagnosis, clinical target volume [CTV], and treatment) and dosimetric (prescribed dose and mean dose (Dmean) to healthy brain) parameters were collected. Univariate and multivariate logistic regression were used to assess the association with selection for PT. The dataset was split into training (n = 37, period 2019–2022) and test (n = 12, period 2023) cohorts. Prediction models were built using logistic regression algorithms and support vector machines (SVMs) and evaluated using the area under the precision-recall curve (AUC-PR).
Results: Age (p = 0.03) and CTV (p = 0.01) were significantly associated with the selection for PT and were used for model prediction. The logistic regression demonstrated AUC-PR at 0.999 (CI 0.999–1.000) and 0.998 (0.996–1.000) for training and test cohorts, respectively. SVM showed similar results with AUC-PR at 0.993 (0.993–0.994) for training and 0.999 (0.998–1.000) for test cohorts.
Interpretation: Logistic regression and SVM using age and CTV performed equally well and achieved a very high positive predictive value. With the pending external validation in a larger dataset, the prospects of this work suggest more consistent and efficient patient referral for PT.
Downloads
References
Harrabi SB, Bougatf N, Mohr A, Haberer T, Herfarth K, Combs SE, et al. Dosimetric advantages of PT over conventional radiotherapy with photons in young patients and adults with low-grade glioma. Strahlenther Onkol. 2016;192(11):759–69.
https://doi.org/10.1007/s00066-016-1005-9 DOI: https://doi.org/10.1007/s00066-016-1005-9
Eekers DBP, Roelofs E, Cubillos-Mesias M, Niel C, Smeenk RJ, Hoeben A, et al. Intensity-modulated PT decreases dose to organs at risk in low-grade glioma patients: results of a multicentric in silico ROCOCO trial. Acta Oncol. 2019;58(1):57–65.
https://doi.org/10.1080/0284186X.2018.1529424 DOI: https://doi.org/10.1080/0284186X.2018.1529424
Allen AM, Pawlicki T, Dong L, Fourkal E, Buyyounouski M, Cengel K, et al. An evidence based review of proton beam therapy: the report of ASTRO’s emerging technology committee. Radiother Oncol. 2012;103(1):8–11.
https://doi.org/10.1016/j.radonc.2012.02.001 DOI: https://doi.org/10.1016/j.radonc.2012.02.001
Weber DC, Lim PS, Tran S, Walser M, Bolsi A, Kliebsch U, et al. Proton therapy for brain tumours in the area of evidence-based medicine. Br J Radiol. 2020;93(1107):20190237.
https://doi.org/10.1259/bjr.20190237 DOI: https://doi.org/10.1259/bjr.20190237
Thurin E, Nystrom PW, Smits A, Werlenius K, Back A, Liljegren A, et al. Proton therapy for low-grade gliomas in adults: a systematic review. Clin Neurol Neurosurg. 2018;174:233––8.
https://doi.org/10.1016/j.clineuro.2018.08.003 DOI: https://doi.org/10.1016/j.clineuro.2018.08.003
Dutz A, Luhr A, Troost EGC, Agolli L, Butof R, Valentini C, et al. Identification of patient benefit from proton beam therapy in brain tumour patients based on dosimetric and NTCP analyses. Radiother Oncol. 2021;160:69–77.
https://doi.org/10.1016/j.radonc.2021.04.008 DOI: https://doi.org/10.1016/j.radonc.2021.04.008
Tohidinezhad F, Zegers CML, Vaassen F, Dijkstra J, Anten M, Van Elmpt W, et al. Predicting the risk of neurocognitive decline after brain irradiation in adult patients with a primary brain tumor. Neuro Oncol. 2024;26(8):1467–78.
https://doi.org/10.1093/neuonc/noae035 DOI: https://doi.org/10.1093/neuonc/noae035
Douw L, Klein M, Fagel SS, van den Heuvel J, Taphoorn MJ, Aaronson NK, et al. Cognitive and radiological effects of radiotherapy in patients with low-grade glioma: long-term follow-up. Lancet Neurol. 2009;8(9):810–8.
https://doi.org/10.1016/S1474-4422(09)70204-2 DOI: https://doi.org/10.1016/S1474-4422(09)70204-2
Haldbo-Classen L, Amidi A, Lukacova S, Wu LM, Oettingen GV, Lassen-Ramshad Y, et al. Cognitive impairment following radiation to hippocampus and other brain structures in adults with primary brain tumours. Radiother Oncol. 2020;148:1–7.
https://doi.org/10.1016/j.radonc.2020.03.023 DOI: https://doi.org/10.1016/j.radonc.2020.03.023
Lawrie TA, Gillespie D, Dowswell T, Evans J, Erridge S, Vale L, et al. Long-term neurocognitive and other side effects of radiotherapy, with or without chemotherapy, for glioma. Cochrane Database Syst Rev. 2019;8:CD013047.
https://doi.org/10.1002/14651858.CD013047.pub2 DOI: https://doi.org/10.1002/14651858.CD013047.pub2
Jaspers J, Mendez Romero A, Hoogeman MS, van den Bent M, Wiggenraad RGJ, Taphoorn MJB, et al. Evaluation of the hippocampal normal tissue complication model in a prospective cohort of low grade glioma patients – an analysis within the EORTC 22033 clinical trial. Front Oncol. 2019;9:991.
https://doi.org/10.3389/fonc.2019.00991 DOI: https://doi.org/10.3389/fonc.2019.00991
Gondi V, Hermann BP, Mehta MP, Tome WA. Hippocampal dosimetry predicts neurocognitive function impairment after fractionated stereotactic radiotherapy for benign or low-grade adult brain tumors. Int J Radiat Oncol Biol Phys. 2013;85(2):348–54.
https://doi.org/10.1016/j.ijrobp.2012.11.031 DOI: https://doi.org/10.1016/j.ijrobp.2012.11.031
DNOG. Nationale retningslinjer for proton behandling 2022 [Internet] 2025. [cited 2025 June 30] Available from: https://dnog.dk/onewebmedia/files/Retningslinier%20PDF/DNOG%202022%20Protonretningslinje.pdf.
van der Weide HL, Kramer MCA, Scandurra D, Eekers DBP, Klaver YLB, Wiggenraad RGJ, et al. Proton therapy for selected low grade glioma patients in the Netherlands. Radiother Oncol. 2021;154:283–90.
https://doi.org/10.1016/j.radonc.2020.11.004 DOI: https://doi.org/10.1016/j.radonc.2020.11.004
Saito T, Rehmsmeier M. The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets. PLoS One. 2015;10(3):e0118432.
https://doi.org/10.1371/journal.pone.0118432 DOI: https://doi.org/10.1371/journal.pone.0118432
Byskov CS, Muhic A, Dahlrot RH, Haslund CA, Guldberg TL, Hoyer M, et al. Selection for proton radiotherapy of grade 1–3 glioma patients. Clin Transl Radiat Oncol. 2024;48:100836.
https://doi.org/10.1016/j.ctro.2024.100836 DOI: https://doi.org/10.1016/j.ctro.2024.100836
Lyell D, Coiera E. Automation bias and verification complexity: a systematic review. J Am Med Inform Assn. 2017;24(2):423–31. DOI: https://doi.org/10.1093/jamia/ocw105
Amarasingham R, Patzer RE, Huesch M, Nguyen NQ, Xie B. Implementing electronic health care predictive analytics: considerations and challenges. Health Aff (Millwood). 2014;33(7):1148–54.
https://doi.org/10.1377/hlthaff.2014.0352 DOI: https://doi.org/10.1377/hlthaff.2014.0352
Additional Files
Published
How to Cite
License
Copyright (c) 2025 Jesper Folsted Kallehauge, Siri Grondahl, Camilla Skinnerup Byskov, Morten Høyer, Slavka Lukacova
This work is licensed under a Creative Commons Attribution 4.0 International License.
