Optimal dynamic regimens with artificial intelligence: The case of temozolomide

Abstract

We determine an optimal protocol for temozolomide using population variability and dynamic optimization techniques inspired by artificial intelligence. We use a Pharmacokinetics/Pharmacodynamics (PK/PD) model based on Faivre and coauthors (Faivre, et al., 2013) for the pharmacokinetics of temozolomide, as well as the pharmacodynamics of its efficacy. For toxicity, which is measured by the nadir of the normalized absolute neutrophil count, we formalize the myelosuppression effect of temozolomide with the physiological model of Panetta and coauthors (Panetta, et al., 2003). We apply the model to a population with variability as given in Panetta and coauthors (Panetta, et al., 2003). Our optimization algorithm is a variant in the class of Monte-Carlo tree search algorithms. We do not impose periodicity constraint on our solution. We set the objective of tumor size minimization while not allowing more severe toxicity levels than the standard Maximum Tolerated Dose (MTD) regimen. The protocol we propose achieves higher efficacy in the sense that –compared to the usual MTD regimen– it divides the tumor size by approximately 7.66 after 336 days –the 95% confidence interval being [7.36–7.97]. The toxicity is similar to MTD. Overall, our protocol, obtained with a very flexible method, gives significant results for the present case of temozolomide and calls for further research mixing operational research or artificial intelligence and clinical research in oncology.

Artificial Intelligence and Machine Learning Applied at the Point of Care

“…ML-based approaches can facilitate development of PMX computer models by streamlining screening and selection of covariates, while mechanistic PMX components can be incorporated in ML-based algorithms to enhance real-time clinical decision support (Hutchinson et al, 2018). Another application of AI in PMX is in the area of oncology (Houy and Le Grand, 2018). A Monte-Carlo tree search algorithm (from a class of AI) was embedded as part the protocol design to optimize the temozolmide dose using emerging exposure, toxicity, and efficacy data.…”

Understanding the effect of measurement time on drug characterization

“…Mathematical models have been widely used in the study of cancer treatment going back to the 1960s when models were developed to predict the growth of tumors [18][19][20][21]. More recently, models are being used to optimize [22,23] or even personalize [24][25][26] treatment regimens for patients. While mathematical models of tumor growth have become increasingly complex [27,28], simpler ordinary differential equation (ODE) models can still help provide insight into cancer dynamics.…”

Optimizing training programs for athletic performance: a Monte-Carlo Tree Search variant method

“…The second interest of our study is the introduction of a variant of the Monte-Carlo Tree Search (MCTS) algorithm [3] in order to find optimal training programs. The MCTS algorithm is widely used in artificial intelligence and the variant we use here has been recently implemented and proved useful in different contexts: the use of drugs to mitigate the spread of an infecting organism and the emergence and spread of resistance [14], drug regimen design in oncology [15, 18], immunotherapy [16] and chemotherapy [17].…”