Background:
This study was aimed to develop a new method for personalising chemotherapeutic and granulocyte colony-stimulating factor (G-CSF) combined schedules, and use it for suggesting efficacious chemotherapy with reduced neutropenia.
Methods:
Clinical data from 38 docetaxel (Doc)-treated metastatic breast cancer patients were employed for validating a new pharmacokinetic/pharmacodynamics model for Doc, combined with a mathematical model for granulopoiesis. An optimisation procedure was constructed and used for selecting improved treatment schedules.
Results:
The combined model accurately predicted observed nadir timing (
r
=0.99), grade 3 or 4 neutropenia (86% success) and neutrophil counts over time in individual patients (
r
=0.63), and showed robustness to CYP3A-induced variability in Doc clearance. For average patients, the predicted optimal support for the standard chemotherapy regimen, Doc 100
μ
g m
−2
tri-weekly, is G-CSF, 300
μ
g, Q1D × 3, starting day 7 post-Doc. This regimen largely moderates chemotherapy-induced neutrophil nadir and neutropenia duration. The more intensive Doc dose, 150 mg m
−2
, is optimally supported by the slightly less cost-effective G-CSF 300
μ
g, Q1D × 4, 5 days post-Doc. The latter regimen is optimal for borderline patients (2000 neutrophils per
μ
l) under Doc, 100–150 mg m
−2
tri-weekly.
Conclusions:
The new computational method can serve for tailoring efficacious cytotoxic and supportive treatments, minimising side effects to individual patients. Prospective clinical validation is warranted.
6556 Background: Survival prediction models for lung cancer patients could help guide their care and therapy decisions. The objectives of this study were to predict probability of survival beyond 90, 180 and 360 days from any point in a lung cancer patient’s journey. Methods: We developed a Gradient Boosting model (XGBoost) using data from 55k lung cancer patients in the ASCO CancerLinQ database that used 3958 unique variables including Dx and Rx codes, biomarkers, surgeries and lab tests from ≤1 year prior to the prediction point, which was chosen at random for each patient. We used 40% data for training, 25% for hyper-parameter tuning, 20% for testing and 15% for holdout validation. Death date available in the Electronic Health Record was cross checked by linkage to death registries. Results: The model was validated on the holdout set of 8,468 patients. The Area Under the Curve (AUC) for the model was 0.79. The precision and recall for predicting survival beyond the three time points were between 0.7-0.8 and 0.8-0.9 respectively (see table). This compares favourably to other lung cancer survival models created using different machine learning techniques (Jochems 2017, Dekker 2009). A Cox-PH model created using the top 20 variables also had a significantly lower performance (see table). Analysis of input variables yielded distinctive patterns for patient subgroups and time points. Tumor status, medications, lab values and functional status were found to be significant in patient sub cohorts. Conclusions: An AI model to predict survival of lung cancer patients built using a large real world dataset yielded high accuracy. This general model can further be used to predict survival of sub cohorts stratified by variables such as stage or various treatment effects. Such a model could be useful for assessing patient risk and treatment options, evaluating cost and quality of care or determining clinical trial eligibility. [Table: see text]
to make reproductive and healthcare decisions. Screening for breast/ovarian cancer in older women may offer lower value in isolation, but its cost-effectiveness should be assessed within the context of a broader screening panel for other diseases.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.