Deep architecture for Heparin dosage prediction during continuous renal replacement therapy

Kong, Ning; Liu, Xiaoxi; Liu, Chunyan; Lian, Jie; Wang, Hongwei

doi:10.23919/chicc.2017.8029139

Cited by 5 publications

(33 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Models for predicting aPTT were assessed in four studies, 27,30,33,34 a model for predicting bleeding and clotting risk linked to out-of-range aPTT in one study 28 and models for predicting UFH dose among dialysis patients in three studies. 29,31,32 Smith et al 34 predicted aPTT levels as outputs of their Neural Network (NN) whose accuracy was compared to that of conventional prediction models. 34 In the two studies by Ghassemi et al, 30,33 outcomes of interest were aPTT levels within 4 to 8 hours after bolus dose and initiation of the maintenance infusion.…”

Section: Discussionmentioning

confidence: 99%

“…32 Lin et al 28 used clotting and bleeding events as surrogates for sub-and supratherapeutic outcomes, respectively, although how these events were defined and ascertained was unclear. 28 Kong et al 31 used a regression formula as part of a deep learning model to predict an initial UFH dose during dialysis, whose accuracy was compared with that of traditional weight-based dosing nomograms, multivariable logistic regression, NN and radial basis function. 31…”

Section: Discussionmentioning

confidence: 99%

“…28 Kong et al 31 used a regression formula as part of a deep learning model to predict an initial UFH dose during dialysis, whose accuracy was compared with that of traditional weight-based dosing nomograms, multivariable logistic regression, NN and radial basis function. 31…”

Section: Discussionmentioning

confidence: 99%

“…Five studies 27,28,30,32,33 described ML models aimed at achieving a therapeutic aPTT in the intensive care unit (ICU) setting. Three studies 29,31,34 conference proceedings [28][29][30][31][32] and three in peer reviewed journals. 27,33,34 All studies, except that by Smith et al, 34 Hospital (see Table 1).…”

Section: Study Characteristicsmentioning

confidence: 99%

“…Only the three studies of UFH dosing in dialysis reliably determined the indication for UFH. 29,31,34 Ghassemi et al 33 stated the indication could not be definitively determined from the dataset and used admission to ICU for critical illness as a proxy, although putative indications for UFH were evaluated in a subset analysis using ICD-9 codes.…”

Section: Indication For Anticoagulationmentioning

confidence: 99%

See 4 more Smart Citations

Systematic review of machine learning models for personalised dosing of heparin

Falconer

Abdel-Hafez

Scott

et al. 2021

Brit J Clinical Pharma

View full text Add to dashboard Cite

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Study Characteristicsmentioning

confidence: 99%

Section: Indication For Anticoagulationmentioning

confidence: 99%

See 3 more Smart Citations

Systematic review of machine learning models for personalised dosing of heparin

Falconer

Abdel-Hafez

Scott

et al. 2021

Brit J Clinical Pharma

View full text Add to dashboard Cite

show abstract

Predicting Therapeutic Response to Unfractionated Heparin Therapy: Machine Learning Approach

Abdel-Hafez¹,

Scott²,

Falconer³

et al. 2022

Interact J Med Res

View full text Add to dashboard Cite

Background Unfractionated heparin (UFH) is an anticoagulant drug that is considered a high-risk medication because an excessive dose can cause bleeding, whereas an insufficient dose can lead to a recurrent embolic event. Therapeutic response to the initiation of intravenous UFH is monitored using activated partial thromboplastin time (aPTT) as a measure of blood clotting time. Clinicians iteratively adjust the dose of UFH toward a target, indication-defined therapeutic aPTT range using nomograms, but this process can be imprecise and can take ≥36 hours to achieve the target range. Thus, a more efficient approach is required. Objective In this study, we aimed to develop and validate a machine learning (ML) algorithm to predict aPTT within 12 hours after a specified bolus and maintenance dose of UFH. Methods This was a retrospective cohort study of 3019 patient episodes of care from January 2017 to August 2020 using data collected from electronic health records of 5 hospitals in Queensland, Australia. Data from 4 hospitals were used to build and test ensemble models using cross-validation, whereas data from the fifth hospital were used for external validation. We built 2 ML models: a regression model to predict the aPTT value after a UFH bolus dose and a multiclass model to predict the aPTT, classified as subtherapeutic (aPTT <70 seconds), therapeutic (aPTT 70-100 seconds), or supratherapeutic (aPTT >100 seconds). Modeling was performed using Driverless AI (H2O), an automated ML tool, and 17 different experiments were iteratively conducted to optimize model accuracy. Results In predicting aPTT, the best performing model was an ensemble with 4x LightGBM models with a root mean square error of 31.35 (SD 1.37). In predicting the aPTT class using a repurposed data set, the best performing ensemble model achieved an accuracy of 0.599 (SD 0.0289) and an area under the receiver operating characteristic curve of 0.735. External validation yielded similar results: root mean square error of 30.52 (SD 1.29) for the aPTT prediction model, and accuracy of 0.568 (SD 0.0315) and area under the receiver operating characteristic curve of 0.724 for the aPTT multiclassification model. Conclusions To the best of our knowledge, this is the first ML model applied to intravenous UFH dosing that has been developed and externally validated in a multisite adult general medical and surgical inpatient setting. We present the processes of data collection, preparation, and feature engineering for replication.

show abstract

A Recurrent Neural Network Model for Predicting Activated Partial Thromboplastin Time After Treatment With Heparin: Retrospective Study

Boie¹,

Engelhardt²,

Coenen³

et al. 2022

JMIR Med Inform

View full text Add to dashboard Cite

Background Anticoagulation therapy with heparin is a frequent treatment in intensive care units and is monitored by activated partial thromboplastin clotting time (aPTT). It has been demonstrated that reaching an established anticoagulation target within 24 hours is associated with favorable outcomes. However, patients respond to heparin differently and reaching the anticoagulation target can be challenging. Machine learning algorithms may potentially support clinicians with improved dosing recommendations. Objective This study evaluates a range of machine learning algorithms on their capability of predicting the patients’ response to heparin treatment. In this analysis, we apply, for the first time, a model that considers time series. Methods We extracted patient demographics, laboratory values, dialysis and extracorporeal membrane oxygenation treatments, and scores from the hospital information system. We predicted the numerical values of aPTT laboratory values 24 hours after continuous heparin infusion and evaluated 7 different machine learning models. The best-performing model was compared to recently published models on a classification task. We considered all data before and within the first 12 hours of continuous heparin infusion as features and predicted the aPTT value after 24 hours. Results The distribution of aPTT in our cohort of 5926 hospital admissions was highly skewed. Most patients showed aPTT values below 75 s, while some outliers showed much higher aPTT values. A recurrent neural network that consumes a time series of features showed the highest performance on the test set. Conclusions A recurrent neural network that uses time series of features instead of only static and aggregated features showed the highest performance in predicting aPTT after heparin treatment.

show abstract

Deep architecture for Heparin dosage prediction during continuous renal replacement therapy

Cited by 5 publications

References 14 publications

Systematic review of machine learning models for personalised dosing of heparin

Systematic review of machine learning models for personalised dosing of heparin

Predicting Therapeutic Response to Unfractionated Heparin Therapy: Machine Learning Approach

A Recurrent Neural Network Model for Predicting Activated Partial Thromboplastin Time After Treatment With Heparin: Retrospective Study

Contact Info

Product

Resources

About