Patient-Specific, Mechanistic Models of Tumor Growth Incorporating Artificial Intelligence and Big Data

Annual Review of Biomedical Engineering, Journal Year: 2024, Volume and Issue: 26(1), P. 529 - 560

Published: April 10, 2024

Despite the remarkable advances in cancer diagnosis, treatment, and management over past decade, malignant tumors remain a major public health problem. Further progress combating may be enabled by personalizing delivery of therapies according to predicted response for each individual patient. The design personalized requires integration patient-specific information with an appropriate mathematical model tumor response. A fundamental barrier realizing this paradigm is current lack rigorous yet practical theory initiation, development, invasion, therapy. We begin review overview different approaches modeling growth including mechanistic as well data-driven models based on big data artificial intelligence. then present illustrative examples manifesting their utility discuss limitations stand-alone models. potential not only predicting but also optimizing therapy basis. describe efforts future possibilities integrate conclude proposing five challenges that must addressed fully realize care patients driven computational

Language: Английский

---

Integrating mechanism-based modeling with biomedical imaging to build practical digital twins for clinical oncology

Biophysics Reviews, Journal Year: 2022, Volume and Issue: 3(2)

Published: May 17, 2022

Digital twins employ mathematical and computational models to virtually represent a physical object (e.g., planes human organs), predict the behavior of object, enable decision-making optimize future object. While digital have been widely used in engineering for decades, their applications oncology are only just emerging. Due advances experimental techniques quantitatively characterizing cancer, as well sciences, notion building applying understand tumor dynamics personalize care cancer patients has increasingly appreciated. In this review, we present opportunities challenges clinical oncology, with particular focus on integrating medical imaging mechanism-based, tissue-scale modeling. Specifically, first introduce general twin framework then illustrate existing image-guided healthcare. Next, detail both modeling that provide practical build patient-specific oncology. We describe current limitations developing image-guided, mechanism-based along potential solutions. conclude by outlining five fundamental questions can serve roadmap when designing attempt answers specific application brain cancer. hope contribution provides motivation science, communities develop technologies improve battling

Language: Английский

---

Optimizing fractionation schedules for de-escalation radiotherapy in head and neck cancers using deep reinforcement learning

Radiotherapy and Oncology, Journal Year: 2025, Volume and Issue: unknown, P. 110833 - 110833

Published: March 1, 2025

Language: Английский

---

Identifiability and model selection frameworks for models of high-grade glioma response to chemoradiation

Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences, Journal Year: 2025, Volume and Issue: 383(2293)

Published: April 2, 2025

We have developed a family of biology-based mathematical models high-grade glioma (HGG), capturing the key features tumour growth and response to chemoradiation. now seek quantify accuracy parameter estimation determine, when given virtual patient cohort, which model was used generate tumours. In this way, we systematically test both identifiability. Virtual patients are generated from unique parameters whose dynamics determined by family. then assessed ability recover select tumour. evaluated predictions using selected at four weeks post-chemoradiation. observed median errors 0.04% 72.96%. Our selection framework that data in 82% cases. Finally, predicted tumours resulting low error voxel-level (concordance correlation coefficient (CCC) ranged 0.66 0.99) global level (percentage total cellularity −12.35% 0.07%). These results demonstrate reliability our identify most appropriate under noisy conditions expected clinical setting. This article is part theme issue 'Uncertainty quantification for healthcare biological systems (Part 2)'.

Language: Английский

---

Mathematical modeling of radiotherapy and its impact on tumor interactions with the immune system

Neoplasia, Journal Year: 2022, Volume and Issue: 28, P. 100796 - 100796

Published: April 19, 2022

Radiotherapy is a primary therapeutic modality widely utilized with curative intent. Traditionally tumor response was hypothesized to be due high levels of cell death induced by irreparable DNA damage. However, the immunomodulatory aspect radiation now accepted. As such, interest into combination radiotherapy and immunotherapy increasing, synergy which has potential improve regression beyond that observed after either treatment alone. questions regarding timing (sequential vs concurrent) dose fractionation (hyper-, standard-, or hypo-fractionation) result in improved anti-tumor immune responses, thus potentially enhanced inhibition, remain. Here we discuss biological its properties before giving an overview pre-clinical data clinical trials concerned answering these questions. Finally, review published mathematical models impact on tumor-immune interactions. Ranging from considering microenvironment induction choice site setting metastatic disease, all have underlying feature common: push towards personalized therapy.

Language: Английский

---

The Hallmarks of Mathematical Oncology

Proceedings of the IEEE, Journal Year: 2022, Volume and Issue: 110(5), P. 523 - 540

Published: Feb. 1, 2022

Over the past 25 years, there has been an unparalleled increase in understanding of cancer biology. This transformation is exemplified by Hanahan and Weinberg's decision 2011 to expand their original Hallmarks Cancer from six traits ten! At same time, mathematical modeling emerged as a natural tool for unraveling complex processes that contribute initiation progression cancer, testing hypotheses about experimental clinical observations assisting with development new approaches improving its treatment. article starts reviewing some earliest models tumor growth responses radiotherapy. Following lead, attention then focuses on how closer collaboration scientists access data are stimulating increasingly detailed account, example, tumor–immune interactions immunotherapy. The concludes discussing ways which being integrated studies, outlining this could improve disease diagnosis delivery effective personalized treatments patients. As such, serves introduction treatments, suitable researchers seeking enter field.

Language: Английский

---

Opportunities for improving brain cancer treatment outcomes through imaging-based mathematical modeling of the delivery of radiotherapy and immunotherapy

Advanced Drug Delivery Reviews, Journal Year: 2022, Volume and Issue: 187, P. 114367 - 114367

Published: May 30, 2022

Language: Английский

---

To modulate or to skip: De-escalating PARP inhibitor maintenance therapy in ovarian cancer using adaptive therapy

Cell Systems, Journal Year: 2024, Volume and Issue: 15(6), P. 510 - 525.e6

Published: May 20, 2024

Language: Английский

---

Predicting Radiotherapy Patient Outcomes with Real-Time Clinical Data Using Mathematical Modelling

Bulletin of Mathematical Biology, Journal Year: 2024, Volume and Issue: 86(2)

Published: Jan. 18, 2024

Abstract Longitudinal tumour volume data from head-and-neck cancer patients show that tumours of comparable pre-treatment size and stage may respond very differently to the same radiotherapy fractionation protocol. Mathematical models are often proposed predict treatment outcome in this context, have potential guide clinical decision-making inform personalised protocols. Hindering effective use context is sparsity measurements juxtaposed with model complexity required produce full range possible patient responses. In work, we present a compartment composition, which, despite relative simplicity, capable producing wide We then develop novel statistical methodology leverage cohort existing predictive both progression associated level uncertainty evolves throughout patient’s course treatment. To capture inter-patient variability, all parameters specific, bootstrap particle filter-like Bayesian approach developed set training as prior knowledge. validate our against subset unseen data, demonstrate ability trained its limitations.

Language: Английский

---

Designing clinical trials for patients who are not average

iScience, Journal Year: 2023, Volume and Issue: 27(1), P. 108589 - 108589

Published: Nov. 29, 2023

The heterogeneity inherent in cancer means that even a successful clinical trial merely results therapeutic regimen achieves, on average, positive result only subset of patients. way to optimize an intervention for individual patient is reframe their treatment as own, personalized trial. Toward this goal, we formulate computational framework performing trials rely four mathematical techniques. First, models can be calibrated with patient-specific data make accurate predictions response. Second, digital twins built these capable simulating the effects interventions. Third, optimal control theory applied outcomes. Fourth, assimilation continually update and refine response In perspective, describe each techniques, quantify "state readiness", identify use cases trials.

Language: Английский

---