A delta-based multi-omics model to predict adaptive radiotherapy benefit in patients with non-small cell lung cancer during carbon-ion radiotherapy
Clinical Snapshot
PICO Framework
| P — Population | 69 patients with non-small cell lung cancer treated with carbon-ion radiotherapy |
| I — Intervention | Delta-based multi-omics prediction model using baseline and pre-treatment imaging features |
| C — Comparator | Standard clinical assessment for adaptive radiotherapy decisions |
| O — Outcomes | Prediction of adaptive radiotherapy benefit (AUC 0.897, sensitivity/specificity at different thresholds) |
Bottom Line
This retrospective study developed a promising delta-omics prediction model for adaptive radiotherapy decisions in NSCLC patients receiving carbon-ion therapy, achieving excellent discriminative performance (AUC 0.897). The model incorporates temporal changes in imaging features between planning and treatment, offering potential for optimised resource allocation. However, the study's limitations include small sample size (n=69), single-centre design, and lack of external validation. While the methodology is innovative and results encouraging, prospective validation in larger, multi-centre cohorts is essential before clinical implementation. The approach may have broader applications beyond carbon-ion therapy, though this requires further investigation. Australian clinicians should note that carbon-ion therapy is not currently available domestically, limiting immediate clinical relevance.
Key Findings
P Value: Not reported in abstract
Effect Size: AUC 0.897 for delta-omics model
Primary Outcome: Prediction of adaptive radiotherapy benefit requirement
Nnt Or Sensitivity: 100% sensitivity at threshold 0.11, 78.6% accuracy at optimal threshold 0.41
Confidence Interval: Interquartile range 0.833-0.950
Clinical Application
Requires advanced imaging analysis capabilities and multi-omics feature extraction, limiting to well-resourced centres Limited immediate applicability as carbon-ion therapy not currently available in Australia; methodology could potentially be adapted for conventional radiotherapy techniques NSCLC patients receiving carbon-ion radiotherapy in specialised centres
Abstract
Objective.Patients with non-small cell lung cancer (NSCLC) treated with carbon-ion radiotherapy (CIRT) are potential candidates for adaptive radiotherapy (ART). However, ART is time- and resource-intensive. This study aimed to develop a decision-support tool to estimate ART demand before treatment.Approach.This retrospective study included 69 patients with NSCLC treated with CIRT. Baseline clinical characteristics, dose-volume histogram (DVH) parameters, and radiomic and dosiomic features from the plan-computed tomography (CT) (1-2 weeks before treatment) and confirm-CT (1-2 d before treatment) were collected, and relative change rates in features (ΔDVH, Δradiomics, and Δdosiomics) were calculated. Feature selection involved univariable testing, correlation analysis, least absolute shrinkage and selection operator regression, and stepwise regression with 1000 bootstrap resamples. A multivariable logistic regression model was constructed and validated using 200 iterations of five-fold cross-validation.Main results.ART was triggered in 32 (46.4%) patients. A five-feature delta-omic model (one ΔDVH, two Δradiomic, and two Δdosiomic features) achieved a validated median area under the curve of 0.897 (interquartile range, 0.833-0.950) with good calibration. At a high-sensitivity threshold (0.11), the model identified all ART candidates while potentially reducing the frequency of weekly-CT evaluations in 21.4% of patients; at the maximum-Youden threshold (0.41), the median accuracy reached 78.6%, with up to 50.0% classified as low ART demand.Significance.A delta-omic model predicting ART demand in patients with NSCLC receiving CIRT was developed. The model may help optimize resource allocation and streamline ART workflows, although prospective validation in larger cohorts is warranted before widespread clinical adoption.
References
- 1.Ju, Z., Kubo, N., Meng, X., Sakai, M., Tashiro, M., & Ohno, T. (2026). A delta-based multi-omics model to predict adaptive radiotherapy benefit in patients with non-small cell lung cancer during carbon-ion radiotherapy. Physics in Medicine and Biology. https://doi.org/10.1088/1361-6560/ae64a6
Related Research
Medical physics
Reference-Free large language model agents for physician-guided radiotherapy treatment planning
2 Aug 2026
Cancer medicine
Applications of Artificial Intelligence in Cancer Diagnosis and Treatment
1 Aug 2026
Acta oncologica (Stockholm, Sweden)
User perceptions of machine learning models as decision support for colorectal cancer multidisciplinary team conferences (AID-SIM-2): a qualitative simulation study.
1 Aug 2026
This content is for educational purposes for healthcare professionals only and does not constitute clinical advice. Clinical decisions should be based on individual patient assessment, current guidelines, and appropriate specialist consultation. Editorial Standards · Privacy Policy · Terms of Service