Get Real: Integration of Real‐World Data to Improve Patient Care

Clinical decision support for chemotherapy-induced neutropenia using a hybrid pharmacodynamic/machine learning model

Consensus guidelines recommend use of granulocyte colony stimulating factor in patients deemed at risk of chemotherapy-induced neutropenia, however, these risk models are limited in the factors they consider and miss some cases of neutropenia. Clinical decision making could be supported using models that better tailor their predictions to the individual patient using the wealth of data available in electronic health records (EHRs). Here, we present a hybrid pharmacokinetic/pharmacodynamic (PKPD)/machine learning (ML) approach that uses predictions and individual Bayesian parameter estimates from a PKPD model to enrich an ML model built on her data. We demonstrate this approach using models developed on a large real-world data set of 9121 patients treated for lymphoma, breast, or thoracic cancer. We also investigate the benefits of augmenting the training data using synthetic data simulated with the PKPD model. We find that PKPD-enrichment of ML models improves prediction of grade 3-4 neutropenia, as measured by higher precision (61%) and recall (39%) compared to PKPD model predictions (47%, 33%) or base ML model predictions (51%, 31%). PKPD augmentation of ML models showed minor improvements in recall (44%) but not precision (56%), and data augmentation required careful tuning to control overfitting its predictions to the PKPD model. PKPD enrichment of ML shows promise for leveraging both the physiology-informed predictions of PKPD and the ability of ML to learn predictor-outcome relationships from large data sets to predict patient response to drugs in a clinical precision dosing context.

Model-based approach to identify predictors of paclitaxel-induced myelosuppression in "real-world" administration

Taxanes are currently the most frequently used chemotherapeutic agents in cancer care, where real-world use has focused on minimizing adverse events and standardizing the delivery. Myelosuppression is a well-characterized, adverse pharmacodynamic effect of taxanes. Electronic health records (EHRs) comprise data collected during routine clinical care that include patients with heterogeneous demographic, clinical, and treatment characteristics. Application of pharmacokinetic/pharmacodynamic (PK/PD) modeling to EHR data promises new insights on the real-world use of taxanes and strategies to improve therapeutic outcomes especially for populations who are typically excluded from clinical trials, including the elderly. This investigation: (i) leveraged previously published PK/PD models developed with clinical trial data and addressed challenges to fit EHR data, and (ii) evaluated predictors of paclitaxel-induced myelosuppression. Relevant EHR data were collected from patients treated with paclitaxel-containing chemotherapy at Inova Schar Cancer Institute between 2015 and 2019 (n = 405). Published PK models were used to simulate mean individual exposures of paclitaxel and carboplatin, which were linearly linked to absolute neutrophil count (ANC) using a published semiphysiologic myelosuppression model. Elderly patients (≥70 years) constituted 21.2% of the dataset and 2274 ANC measurements were included in the analysis. The PD parameters were estimated and matched previously reported values. The baseline ANC and chemotherapy regimen were significant predictors of paclitaxel-induced myelosuppression. The nadir ANC and use of supportive treatments, such as growth factors and antimicrobials, were consistent across age quantiles suggesting age had no effect on paclitaxel-induced myelosuppression. In conclusion, EHR data could complement clinical trial data in answering key therapeutic questions.

Clinical Decision Support for Precision Dosing: Opportunities for Enhanced Equity and Inclusion in Health Care

Precision dosing aims to tailor doses to individual patients with the goal of improving treatment efficacy and avoiding toxicity. Clinical decision support software (CDSS) plays a crucial role in mediating this process, translating knowledge derived from clinical trials and real-world data (RWD) into actionable insights for clinicians to use at the point of care. However, not all patient populations are proportionally represented in clinical trials and other data sources that inform CDSS tools, limiting the applicability of these tools for underrepresented populations. Here, we review some of the limitations of existing CDSS tools and discuss methods for overcoming these gaps. We discuss considerations for study design and modeling to create more inclusive CDSS, particularly with an eye toward better incorporation of biological indicators in place of race, ethnicity, or sex. We also review inclusive practices for collection of these demographic data, during both study design and in software user interface design. Because of the role CDSS plays in both recording routine clinical care data and disseminating knowledge derived from data, CDSS presents a promising opportunity to continuously improve precision dosing algorithms using RWD to better reflect the diversity of patient populations.

Status Toward the Implementation of Precision Dosing in Children

Precision dosing is progressing beyond the conceptual and proof-of-concept stages toward implementation. As the availability of dosing algorithms, tools, and platforms increases, so do the investment in technology services and actual implementation of clinical services offering these solutions to patients. Nowhere is this needed more than in pediatric populations, which are still reliant on adult drug development and bridging strategies to support dosing, often in the absence of actual dose-finding studies in the target pediatric population. Still, there is more work to be done to ensure that proper governance of these services is maintained, and that sustainability of these early implementations is guided by new science as it evolves and meaningful outcome data to confirm that such services deliver on both clinical and economic return on investment. In addition, the field should ensure that all approaches beyond a therapeutic drug monitoring-driven, pharmacokinetic-centric approach should be considered as the tools and services evolve, especially when pediatric-specific pharmacokinetic/pharmacodyamic and pharmacogenetic data are available and shown to be useful to guide dosing. This review evaluates current pediatric precision dosing efforts, highlighting their utility, longevity, and sustainability and assesses the current process for implementing such approaches examining current barriers that stand in the way of broader implementation and the stakeholders that must engage to ensure its ultimate success.

Reinforcement learning and Bayesian data assimilation for model-informed precision dosing in oncology

Model-informed precision dosing (MIPD) using therapeutic drug/biomarker monitoring offers the opportunity to significantly improve the efficacy and safety of drug therapies. Current strategies comprise model-informed dosing tables or are based on maximum a posteriori estimates. These approaches, however, lack a quantification of uncertainty and/or consider only part of the available patient-specific information. We propose three novel approaches for MIPD using Bayesian data assimilation (DA) and/or reinforcement learning (RL) to control neutropenia, the major dose-limiting side effect in anticancer chemotherapy. These approaches have the potential to substantially reduce the incidence of life-threatening grade 4 and subtherapeutic grade 0 neutropenia compared with existing approaches. We further show that RL allows to gain further insights by identifying patient factors that drive dose decisions. Due to its flexibility, the proposed combined DA-RL approach can easily be extended to integrate multiple end points or patient-reported outcomes, thereby promising important benefits for future personalized therapies.