A data-driven approach to optimized medication dosing: a focus on heparin

By Marzyeh Ghassemi, S. Richter, I. Eche, Tszyi W. Chen, J. Danziger, Leo Anthony Celi. 2014

65 citations recorded by the source corpus.

PurposeTo 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.MethodsWe 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).ResultsWe 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.ConclusionsThis 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.

Subfields: Biomedical Engineering, Surgery

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Surgery

Citations in the corpus

Reinforcement Learning in Healthcare: A Survey (2019, background): “medical problems that perhaps have received less attention by researchers. One such problem is regarding the medication dosing, particulary, heparin dosing, in ICUs. A recent study by Ghassemi et al. [236] highlighted that the misdosing of medications in the ICU is both problematic and preventable, ”
Machine Learning and Decision Support in Critical Care (2016, methodology): “They describe a method for dose estimation similar to [148], but estimate optimal model parameters for each patient using a weighted combination of the incoming data from the individual and available data from a population of similar patients.”
State of the art review: the data revolution in critical care (2015, background): “These include the heterogeneity of treatment effect of red blood cell (RBC) transfusion [13], the impact of pre-admission selective serotonin reuptake inhibitors on mortality in the ICU [14], the interplay between clinical notes and structured data on mortality prediction [15], optimization of hepar”
Optimal medication dosing from suboptimal clinical examples: A deep reinforcement learning approach (2016, methodology): “The therapeutic range of anticoagulation was defined as an aPTT between 60 and 100 seconds [8].”
A Deep Deterministic Policy Gradient Approach to Medication Dosing and Surveillance in the ICU (2018, background): “In recent years, there has been a growing number of clinical studies both through prospective trials as well as retrospective analysis of electronic medical records [2], [3], [4] aimed at reﬁning the heparin dosing protocols.”