Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Accepted for/Published in: Journal of Medical Internet Research

Date Submitted: Jan 12, 2021
Date Accepted: Mar 24, 2021

The final, peer-reviewed published version of this preprint can be found here:

A Clinical Prediction Model to Predict Heparin Treatment Outcomes and Provide Dosage Recommendations: Development and Validation Study

Li D, Gao J, Hong N, Wang H, Su L, Liu C, Jiang H, Wang Q, Long Y, Zhu W

A Clinical Prediction Model to Predict Heparin Treatment Outcomes and Provide Dosage Recommendations: Development and Validation Study

J Med Internet Res 2021;23(5):e27118

DOI: 10.2196/27118

PMID: 34014171

PMCID: 8176336

A clinical prediction model to predict heparin treatment outcomes and provide dosage recommendations: Retrospective Study

  • Dongkai Li; 
  • Jianwei Gao; 
  • Na Hong; 
  • Hao Wang; 
  • Longxiang Su; 
  • Chun Liu; 
  • Huizhen Jiang; 
  • Qiang Wang; 
  • Yun Long; 
  • Weiguo Zhu

ABSTRACT

Background:

Unfractionated heparin (UFH) is widely used in the ICU as an anticoagulant. However, weight-based heparin dosing has been shown to be suboptimal and may place patients at unnecessary risk during their ICU stay.

Objective:

In this study, we therefore intended to develop and validate machine learning based model to predict heparin treatment outcomes and to provide dosage recommendations to clinicians.

Methods:

A shallow neural network model was adopted on a retrospective cohort of patients from the Multi-Parameter Intelligent Monitoring in Intensive Care III (MIMIC III) database and patients admitted to the Peking Union Medical College Hospital (PUMCH). We modeled the subtherapeutic, normal, and supratherapeutic activated partial thromboplastin time (aPTT) as the outcomes of heparin treatment and used a group of clinical features for modeling. Our model classifies patients into three different therapeutic states. We tested the prediction ability of our model and evaluated its performance by using accuracy, the kappa coefficient, precision, recall, and the F1 score. Furthermore, a dosage recommendation module was designed and evaluated for clinical decision support purpose.

Results:

A total of 3,607 patients selected from MIMIC III and 1,549 patients admitted to the PUMCH that met our criteria were included in this study. The shallow neural network model showed results of F1 scores 0.887 (MIMIC III) and 0.925 (PUMCH). When compared with actual dosage prescribed, our model recommended increasing dosage for 72.2% (MIMIC III) and 64.7% (PUMCH) subtherapeutic patients and decreasing dosage for 80.9% (MIMIC III) and 76.7% (PUMCH) supratherapeutic patients, suggesting that the recommendations can contribute to clinical improvements and that they may effectively reduce the time to optimal dosage in the clinical setting.

Conclusions:

The evaluation of our model for predicting heparin treatment outcomes demonstrated that the developed model is potentially applicable to reducing the mis-dosage of heparin and providing appropriate decision recommendations to clinicians.


 Citation

Please cite as:

Li D, Gao J, Hong N, Wang H, Su L, Liu C, Jiang H, Wang Q, Long Y, Zhu W

A Clinical Prediction Model to Predict Heparin Treatment Outcomes and Provide Dosage Recommendations: Development and Validation Study

J Med Internet Res 2021;23(5):e27118

DOI: 10.2196/27118

PMID: 34014171

PMCID: 8176336

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.