Biology subjects

Rosenberg, M. A.

Publications and source records attributed to Rosenberg, M. A..

3 recordsLinked to original sources

bioRxiv2019

Multicenter Analysis of Dosing Protocols for Sotalol Initiation

Sotalol is a Vaughan-Williams Class III antiarrhythmic medication that is commonly used in the management of both atrial and ventricular arrhythmias. Like others in this class, sotalol carries a risk of the potentially lethal arrhythmia torsade de pointes due to its effect of prolonging the QT interval on ECG. For this reason, many centers admit patients for telemetry monitoring during the initial 2-3 days of dosing. However, despite its widespread use, little information is available about the dosing protocols used during this initiation process. In this multicenter investigation, we examine the characteristics of various dose protocols in 213 patients who initiated sotalol over a 4-year period. Of these patients, over 90% were able to successfully complete the dosing regimen (i.e., were discharged on the medication). Significant bradycardia, excessive QT prolongation, and ineffectiveness were the main reasons for failed completion. We found that any dose adjustment was one of the strongest univariate predictors of successful initiation (OR 6.6, 95%CI 1.3 - 32.7, p = 0.021), while initial dose, indication, and resting heart rate or QT interval on baseline ECG did not predict successful initiation. Several predictors of any dose adjustment were identified, and included diabetes, hypertension, presence of pacemaker, heart failure diagnosis, and depressed LV ejection fraction. Using marginal structural models (i.e., inverse probability weighting based on probability of a dose adjustment), we verified that these factors also predicted successful initiation via preventing any dose adjustment, and suggests that consideration of these factors may result in higher likelihood of successful initiation in future investigations. In conclusion, we found that the majority of patients admitted for sotalol initiation are successfully discharged on the medication, often without a single adjustment in the dose. Our findings suggest that several factors predicting lack of dose adjustment could be used clinically to identify patients who could potentially undergo outpatient initiation, although prospective studies are needed to verify this approach.

pharmacology and toxicology↗

bioRxiv2019

Applications of Machine Learning in Decision Analysis for Dose Management for Dofetilide

Initiation of the antiarrhythmic medication dofetilide requires an FDA-mandated 3 days of telemetry monitoring due to heightened risk of toxicity within this time period. Although a recommended dose management algorithm for dofetilide exists, there is a range of real-world approaches to dosing the medication. In this multicenter investigation, we examined the decision process for dose adjustment of dofetilide during the observation period using machine-learning approaches, including supervised, unsupervised, and reinforcement learning applications. Logistic regression approaches identified any dose-adjustment as a strong negative predictor of successful loading (i.e., discharged on dofetilide) of the medication (OR 0.19, 95%CI 0.12 - 0.31, p < 0.001 for discharge on dofetilide), indicating that these adjustments are strong determinants of whether patients "tolerate" the medication. Using multiple supervised approaches, including regularized logistic regression, random forest, boosted gradient decision trees, and neural networks, we were unable to identify any model that predicted dose adjustments better than a naive approach. A reinforcement-learning algorithm, in contrast, predicted which patient characteristics and dosing decisions that resulted in the lowest risk of failure to be discharged on the medication. Future studies could apply this algorithm prospectively to examine improvement over standard approaches.

pharmacology and toxicology↗

bioRxiv2019

Development of a Prediction Model for Incident Atrial Fibrillation using Machine Learning Applied to Harmonized Electronic Health Record Data

Atrial fibrillation (AF) is the most common sustained cardiac arrhythmia, whose early detection could lead to significant improvements in outcomes through appropriate prescription of anticoagulation. Although a variety of methods exist for screening for AF, there is general agreement that a targeted approach would be preferred. Implicit within this approach is the need for an efficient method for identification of patients at risk. In this investigation, we examined the strengths and weaknesses of an approach based on application of machine-learning algorithms to electronic health record (EHR) data that has been harmonized to the Observational Medical Outcomes Partnership (OMOP) common data model. We examined data from a total of 2.3M individuals, of whom 1.16% developed incident AF over designated 6-month time intervals. We examined and compared several approaches for data reduction, sample balancing (re-sampling) and predictive modeling using cross-validation for hyperparameter selection, and out-of-sample testing for validation. Although no approach provided outstanding classification accuracy, we found that the optimal approach for prediction of 6-month incident AF used a random forest classifier, raw features (no data reduction), and synthetic minority oversampling technique (SMOTE) resampling (F1 statistic 0.12, AUC 0.65). This model performed better than a predictive model based only on known AF risk factors, and highlighted the importance of using resampling methods to optimize ML approaches to imbalanced data as exists in EHRs. Further studies using EHR data in other medical systems are needed to validate the clinical applicability of these findings.

epidemiology↗