Integration of mathematical model predictions into routine workflows to support clinical decision making in haematology

Abstract

Background: Individualization and patient-specific optimization of treatment is a major goal of modern health care. One way to achieve this goal is the application of high-resolution diagnostics together with the application of targeted therapies. However, the rising number of different treatment modalities also induces new challenges: Whereas randomized clinical trials focus on proving average treatment effects in specific groups of patients, direct conclusions at the individual patient level are problematic. Thus, the identification of the best patient-specific treatment options remains an open question. Systems medicine, specifically mechanistic mathematical models, can substantially support individual treatment optimization. In addition to providing a better general understanding of disease mechanisms and treatment effects, these models allow for an identification of patient-specific parameterizations and, therefore, provide individualized predictions for the effect of different treatment modalities. Results: In the following we describe a software framework that facilitates the integration of mathematical models and computer simulations into routine clinical processes to support decision-making. This is achieved by combining standard data management and data exploration tools, with the generation and visualization of mathematical model predictions for treatment options at an individual patient level. Conclusions: By integrating model results in an audit trail compatible manner into established clinical workflows, our framework has the potential to foster the use of systems-medical approaches in clinical practice. We illustrate the framework application by two use cases from the field of haematological oncology.

Individual prediction of thrombocytopenia at next chemotherapy cycle: Evaluation of dynamic model performances

“…Based on our model, we have developed a tool intended to support clinical decision-making regarding next-cycle management in dependence on the individual therapy response. 42 A prototype can be found elsewhere: (https://www.health-atlas.de/models/27? code=kcZgRmF9kriGUH0GEuGJF%252FMx7Pd6m8d6XI46iaTe).…”

“…Our mechanistic model was superior compared to the semimechanistic model proposed by Henrich et al 18 Time series data of only 1 cycle are required to achieve sufficiently accurate predictions of next‐cycle toxicity in the vast majority of cases. Based on our model, we have developed a tool intended to support clinical decision‐making regarding next‐cycle management in dependence on the individual therapy response 42 . A prototype can be found elsewhere: (https://www.health-atlas.de/models/27?code=kcZgRmF9kriGUH0GEuGJF%252FMx7Pd6m8d6XI46iaTe).…”

Finding new edges: systems approaches to MTOR signaling

“…The MTOR network is targeted directly and indirectly by many clinically approved small compounds [ 125 ]. Hence, patient specific and clinically validated MTOR network models might serve in the future to support therapy decisions for the treatment of cancer and other diseases [ 124 , 126 ] characterized by aberrant MTOR activity [ 22 ]. While some patents protect such applications for commercial use [ 127 , 128 ], they await their clinical validation.…”

MRD Tailored Therapy in AML: What We Have Learned So Far

“…In the future, applications or websites that calculate the individual risk of a relapse or survival based on treatment choice may play a larger role in supporting clinical decision making in AML. A good prediction model is needed to support this application ( 154 ). By using a multistage model for predicting outcome, genomic and clinical variables in AML, Gerstung and colleagues were capable of making an application that determines individual risk for each specific treatment choice ( 155 ).…”