Developing hybrid mechanistic and data-driven personalized prediction models for platelet dynamics

TL;DR

This paper compares hybrid mechanistic and data-driven models for predicting platelet counts during chemotherapy, showing data-driven methods excel with abundant data while hybrid models perform better with sparse data, aiding personalized treatment.

Contribution

It introduces a framework for evaluating hybrid and data-driven models for personalized platelet prediction, highlighting their respective strengths in different data scenarios.

Findings

Data-driven models outperform hybrid models with sufficient data.

Hybrid models are more effective with limited or sparse data.

The framework is applicable to other treatment-related toxicity predictions.

Abstract

Hematotoxicity, drug-induced damage to the blood-forming system, is a frequent side effect of cytotoxic chemotherapy and poses a significant challenge in clinical practice due to its high inter-patient variability and limited predictability. Current mechanistic models often struggle to accurately forecast outcomes for patients with irregular or atypical trajectories. In this study, we develop and compare hybrid mechanistic and data-driven approaches for individualized time series modeling of platelet counts during chemotherapy. We consider hybrid models that combine mechanistic models with neural networks, known as universal differential equations. As a purely data-driven alternative, we utilize a nonlinear autoregressive exogenous model using gated recurrent units as the underlying architecture. These models are evaluated across a range of real patient scenarios, varying in data availability and sparsity, to assess predictive performance. Our findings demonstrate that data-driven methods, when provided with sufficient data, significantly improve prediction accuracy, particularly for high-risk patients with irregular platelet dynamics. This highlights the potential of data-driven approaches in enhancing clinical decision-making. In contrast, hybrid and mechanistic models are superior in scenarios with limited or sparse data. The proposed modeling and comparison framework is generalizable and could be extended to predict other treatment-related toxicities, offering broad applicability in personalized medicine.