From Linear-quadratic to Machine Learning in Radiobiological Modeling for Radiotherapy Planning: Resolving the Complexity-Utility Paradox with Hybrid Physics-informed Neural Networks
Abstract
Radiobiological modeling for radiotherapy planning has evolved across three overlapping paradigms: postplanning biological evaluation using empirical dose–response relationships (c. 1960), biological optimization integrated into treatment planning system objective functions (c. 2000), and artificial intelligence (AI)–driven adaptive prediction (c. 2012–present). Despite this progression, increasing model complexity has not produced proportional clinical utility – a tension we describe as the complexity–utility paradox. A structured search of PubMed, Scopus and Web of Science (January 1960 to March 2026) yielded 71 included studies; evidence is synthesized narratively with critical appraisal of landmark mechanistic models, consensus guidelines and recent meta-analytic data. We operationalize the paradox across three measurable gaps: A performance generalizability gap, in which external validation of machine-learning normal tissue complication probability (NTCP) models is approximately 9% lower in relative terms (absolute difference 0.07; pooled internal area under a receiver operating characteristic [AUROC]: 0.76, 95% confidence interval [CI]: 0.73–0.78, versus pooled external AUROC: 0.69, 95% CI: 0.64–0.73), noting that 121 of the 225 pooled models were rated at high risk of bias on PROBAST and that the internal and external estimates derive from different model sets; an adoption gap, in which Quantitative Analyses of Normal Tissue Effects in the Clinic-derived Lyman–Kutcher–Burman constraints retain primary plan-evaluation authority despite demonstrated AI improvements; and an interpretability gap, in which regulatory and clinical-trust barriers penalize opaque model architectures. We argue that principled integration, rather than paradigm replacement, offers the most tractable resolution. Hybrid physics-informed neural networks (PINNs), anchoring data-driven learning to validated mechanistic priors within a federated multi-institutional training framework and uncertainty propagation compliant with the Guide to the Expression of Uncertainty in Measurement, may narrow all three gaps simultaneously. This position is explicitly caveated: PINNs inherit the bias of the embedded prior, and current radiotherapy-specific evidence remains preliminary. To our knowledge, no externally validated PINN-based NTCP model has yet been published, so the proposal is offered as a research direction rather than as an evidenced clinical solution. A tiered validation framework is proposed for structured clinical translation.
Related
- Comparative Radiobiological Evaluation of Radiotherapy Techniques Using Equivalent Uniform Dose, Tumor Control Probability, and Normal Tissue Complication Probability in Postmastectomy Breast Cancer
- Estimation of radiobiological parameters and repopulation dose equivalents using classical cell kinetics with hypotheses concerning cellular changes during radiotherapy
- Separating active irradiation from passive outcome learning in radiotherapy: a finite-model computational benchmark
- Distinct Radiobiological Responses to BNCT in SAS Oral Squamous Cell Carcinoma and MCF-7 Breast Cancer Cells
- Deep learning-based self-supervised detection and localization of magnetic resonance imaging anomalies in artificial intelligence-supported radiotherapy workflows
BibTeX
@article{mondal2026from,
title = {{From Linear-quadratic to Machine Learning in Radiobiological Modeling for Radiotherapy Planning: Resolving the Complexity-Utility Paradox with Hybrid Physics-informed Neural Networks}},
author = {Kalyan Mondal and Anuj Vijay and Abhijit Mandal and Ganeshkumar Patel},
journal = {Journal of Medical Physics},
year = {2026},
month = jul,
doi = {10.4103/jmp.jmp_105_26},
url = {https://doi.org/10.4103/jmp.jmp_105_26},
note = {CC BY-NC-SA},
}
RIS
TY - JOUR
TI - From Linear-quadratic to Machine Learning in Radiobiological Modeling for Radiotherapy Planning: Resolving the Complexity-Utility Paradox with Hybrid Physics-informed Neural Networks
AU - Kalyan Mondal
AU - Anuj Vijay
AU - Abhijit Mandal
AU - Ganeshkumar Patel
PY - 2026
DA - 2026/07/01
JO - Journal of Medical Physics
DO - 10.4103/jmp.jmp_105_26
UR - https://doi.org/10.4103/jmp.jmp_105_26
AB - Radiobiological modeling for radiotherapy planning has evolved across three overlapping paradigms: postplanning biological evaluation using empirical dose–response relationships (c. 1960), biological optimization integrated into treatment planning system objective functions (c. 2000), and artificial intelligence (AI)–driven adaptive prediction (c. 2012–present). Despite this progression, increasing model complexity has not produced proportional clinical utility – a tension we describe as the complexity–utility paradox. A structured search of PubMed, Scopus and Web of Science (January 1960 to March 2026) yielded 71 included studies; evidence is synthesized narratively with critical appraisal of landmark mechanistic models, consensus guidelines and recent meta-analytic data. We operationalize the paradox across three measurable gaps: A performance generalizability gap, in which external validation of machine-learning normal tissue complication probability (NTCP) models is approximately 9% lower in relative terms (absolute difference 0.07; pooled internal area under a receiver operating characteristic [AUROC]: 0.76, 95% confidence interval [CI]: 0.73–0.78, versus pooled external AUROC: 0.69, 95% CI: 0.64–0.73), noting that 121 of the 225 pooled models were rated at high risk of bias on PROBAST and that the internal and external estimates derive from different model sets; an adoption gap, in which Quantitative Analyses of Normal Tissue Effects in the Clinic-derived Lyman–Kutcher–Burman constraints retain primary plan-evaluation authority despite demonstrated AI improvements; and an interpretability gap, in which regulatory and clinical-trust barriers penalize opaque model architectures. We argue that principled integration, rather than paradigm replacement, offers the most tractable resolution. Hybrid physics-informed neural networks (PINNs), anchoring data-driven learning to validated mechanistic priors within a federated multi-institutional training framework and uncertainty propagation compliant with the Guide to the Expression of Uncertainty in Measurement, may narrow all three gaps simultaneously. This position is explicitly caveated: PINNs inherit the bias of the embedded prior, and current radiotherapy-specific evidence remains preliminary. To our knowledge, no externally validated PINN-based NTCP model has yet been published, so the proposal is offered as a research direction rather than as an evidenced clinical solution. A tiered validation framework is proposed for structured clinical translation.
SN - 0971-6203
SN - 1998-3913
ER -