What question did this study set out to answer?

The study aims to develop a deep learning model for predicting rib fractures in non-small cell lung cancer patients after radiotherapy.

April 5, 2026

Abstract 3732: Time-series deep learning radiomics for predicting post-radiotherapy rib fractures in non-small cell lung cancer

Key Result

A time-series deep learning radiomics model predicted post-radiotherapy rib fractures in non-small cell lung cancer with an AUC of 0.792, sensitivity of 0.85, and specificity of 0.78.

Key Points

The study aims to develop a deep learning model for predicting rib fractures in non-small cell lung cancer patients after radiotherapy.
Collected CT scans from 67 NSCLC patients, analyzing 1,605 separate rib instances.
Developed a Knowledge-aware Temporal Mixture of Experts (KA-TMoE) model for estimating fracture risk from time-series radiomics.
Evaluated model performance using AUC, sensitivity, specificity, F1 score, and SHapley Additive exPlanations for interpretability.
KA-TMoE model achieved an AUC of 0.792 in the validation cohort.
High sensitivity (0.85) and specificity (0.78) were observed, signifying strong predictive ability.
Statistically significant performance improvements were noted compared to ablation models, with key features stemming from postoperative radiomics.

Structured PICO

Does the KA-TMoE deep learning model accurately predict post-radiotherapy rib fractures in NSCLC patients undergoing SBRT?

Population

67 medically inoperable patients with non-small cell lung cancer (NSCLC) undergoing stereotactic body radiotherapy (SBRT), comprising 1,605 individual ribs

Intervention

Knowledge-aware Temporal Mixture of Experts (KA-TMoE) deep learning model using time-series CT radiomics

Comparator

Ablation variants and alternative approaches

Outcome

Prediction of post-radiotherapy rib fracture

A novel time-series deep learning radiomics model (KA-TMoE) demonstrated strong predictive performance for post-radiotherapy rib fractures in NSCLC patients, enabling personalized risk assessment.

Main Result

Absolute Event Rate: 0% vs 0%

Abstract

Abstract Background and purpose: Rib fracture is a recognized clinical complication in medically inoperable patients with non-small cell lung cancer (NSCLC) undergoing stereotactic body radiotherapy (SBRT), leading to diminished quality of life and delayed recovery. This study aimed to develop and validate a deep learning model for predicting post-radiotherapy rib fracture using time-series CT radiomics. Material and methods: This study retrospectively collected CT scans from 67 NSCLC patients, comprising 1,605 individual ribs as separate instances. We proposed a novel Knowledge-aware Temporal Mixture of Experts (KA-TMoE) model that integrates radiomics from sequential CT scans to estimate fracture risk for each rib. Model performance was evaluated using area under the curve (AUC), sensitivity, specificity, and F1 score. Model interpretability was achieved using SHapley Additive exPlanations analysis, which attributed predictive value to each input feature. Results: The KA-TMoE model demonstrated strong predictive performance, achieving favorable AUC in the validation cohort (0.792). The DeLong test confirmed statistically significant improvements over ablation variants, underscoring the importance of integrating temporal data and domain knowledge. High sensitivity (0.85) and specificity (0.78) reflected a well-balanced trade-off, surpassing alternative approaches. Whitney U tests further supported its robustness, which showed significant differences in output distributions across cohorts. Among the top 20 most influential features, half originated from three-month postoperative radiomics, emphasizing the critical role of temporal information. Conclusion: The KA-TMoE model provides a robust, accurate framework for predicting rib fractures after SBRT in NSCLC patients. Its predictive power enables personalized risk assessment, better patient management, and optimized clinical prognosis. Citation Format: Yijun Chen, Michael Farris, Ariel Choi, Nga Thi Thanh Nguyen, Amanda Goetz, Corbin A. Helis, Fei Xing, Liang Liu, Qing Lyu, Christopher T. Whitlow, Christina K. Cramer, Michael D. Chan, Dan Bourland, Michael T. Munley, Jeffrey S Willey, Yuming Jiang. Time-series deep learning radiomics for predicting post-radiotherapy rib fractures in non-small cell lung cancer abstract. In: Proceedings of the American Association for Cancer Research Annual Meeting 2026; Part 1 (Regular Abstracts); 2026 Apr 17-22; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2026;86(7 Suppl):Abstract nr 3732.

Bookmark