Adaptive tumor growth forecasting via neural & universal ODEs
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911291578253312 |
|---|---|
| author | Subramanian, Kavya Joshi, Prathamesh Dinesh Dandekar, Raj Abhijit Dandekar, Rajat Panat, Sreedath |
| author_facet | Subramanian, Kavya Joshi, Prathamesh Dinesh Dandekar, Raj Abhijit Dandekar, Rajat Panat, Sreedath |
| contents | Forecasting tumor growth is critical for optimizing treatment. Classical growth models such as the Gompertz and Bertalanffy equations capture general tumor dynamics but may fail to adapt to patient-specific variability, particularly with limited data available. In this study, we leverage Neural Ordinary Differential Equations (Neural ODEs) and Universal Differential Equations (UDEs), two pillars of Scientific Machine Learning (SciML), to construct adaptive tumor growth models capable of learning from experimental data. Using the Gompertz model as a baseline, we replace rigid terms with adaptive neural networks to capture hidden dynamics through robust modeling in the Julia programming language. We use our models to perform forecasting under data constraints and symbolic recovery to transform the learned dynamics into explicit mathematical expressions. Our approach has the potential to improve predictive accuracy, guiding dynamic and effective treatment strategies for improved clinical outcomes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_22292 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Adaptive tumor growth forecasting via neural & universal ODEs Subramanian, Kavya Joshi, Prathamesh Dinesh Dandekar, Raj Abhijit Dandekar, Rajat Panat, Sreedath Machine Learning Artificial Intelligence Forecasting tumor growth is critical for optimizing treatment. Classical growth models such as the Gompertz and Bertalanffy equations capture general tumor dynamics but may fail to adapt to patient-specific variability, particularly with limited data available. In this study, we leverage Neural Ordinary Differential Equations (Neural ODEs) and Universal Differential Equations (UDEs), two pillars of Scientific Machine Learning (SciML), to construct adaptive tumor growth models capable of learning from experimental data. Using the Gompertz model as a baseline, we replace rigid terms with adaptive neural networks to capture hidden dynamics through robust modeling in the Julia programming language. We use our models to perform forecasting under data constraints and symbolic recovery to transform the learned dynamics into explicit mathematical expressions. Our approach has the potential to improve predictive accuracy, guiding dynamic and effective treatment strategies for improved clinical outcomes. |
| title | Adaptive tumor growth forecasting via neural & universal ODEs |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2511.22292 |