A data-driven approach to optimized medication dosing: a focus on heparin
- 839 Downloads
To demonstrate a novel method that utilizes retrospective data to develop statistically optimal dosing strategies for medications with sensitive therapeutic windows. We illustrate our approach on intravenous unfractionated heparin, a medication which typically considers only patient weight and is frequently misdosed.
We identified available clinical features which impact patient response to heparin and extracted 1,511 patients from the multi-parameter intelligent monitoring in intensive care II database which met our inclusion criteria. These were used to develop two multivariate logistic regressions, modeling sub- and supra-therapeutic activated partial thromboplastin time (aPTT) as a function of clinical features. We combined information from these models to estimate an initial heparin dose that would, on a per-patient basis, maximize the probability of a therapeutic aPTT within 4–8 h of the initial infusion. We tested our model’s ability to classifying therapeutic outcomes on a withheld dataset and compared performance to a weight-alone alternative using volume under surface (VUS) (a multiclass version of AUC).
We observed statistically significant associations between sub- and supra-therapeutic aPTT, race, ICU type, gender, heparin dose, age and Sequential Organ Failure Assessment scores with mean validation AUC of 0.78 and 0.79 respectively. Our final model improved outcome classification over the weight-alone alternative, with VUS values of 0.48 vs. 0.42.
This work represents an important step in the secondary use of health data in developing models to optimize drug dosing. The next step would be evaluating whether this approach indeed achieves target aPTT more reliably than the current weight-based heparin dosing in a randomized controlled trial.
KeywordsObservational Heparin Clinical informatics Dosing Optimization
Grant R01 EB001659 from the National Institute of Biomedical Imaging and Bioengineering (NIBIB) of the National Institutes of Health (NIH). The sponsors of this research played no role in the research process of this work beyond their important financial contribution.
Conflicts of interest
The authors declare that they have no conflict of interest. None of the authors involved in this study have associations (intellectual, financial, or otherwise) that would affect, or be perceived to affect the author’s research conduct or judgment
.All data used for this study was de-identified and publically accessible. Hence, it did not require an IRB for the purposes of investigation.
- 8.Lee MS, Wali AU, Menon V et al (2001) The determinants of activated partial thromboplastin time, relation of activated partial thromboplastin time to clinical outcomes, and optimal dosing regimens for heparin treated patients with acute coronary syndromes: a review of gusto-IIb. J Thromb Thrombolysis 14(2):91–101CrossRefGoogle Scholar
- 15.César F, Hernández-Orallo J, Salido MA (2003) Volume under the ROC Surface for Multi-class Problems. Machine learning: ECML 2003. Springer, Berlin, 108–120Google Scholar
- 19.Squara P, Foruquet E, Jacquet L et al (2003) A computer program for interpreting pulmonary artery catheterization data: results of the European HEMODYN Resident Study. Intens Care Med 29:735–741Google Scholar