Automated warfarin dose prediction for Asian, American, and Caucasian populations using a deep neural network

Jahmunah, V.; Chen, Sylvia; Oh, Shu Lih; Acharya, U. Rajendra; Chowbay, Balram

doi:10.1016/j.compbiomed.2023.106548

Cited by 10 publications

(4 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After removing duplicated articles, 3,346 studies were screened by the title and/or abstract, 3,175 irrelevant studies were excluded and 171 articles were included for full‐text review. Finally, 64 articles related to precision dosing using ML were included for analysis 11–74 . The PRISMA flow diagram representing the study selection process and review results is presented in Figure .…”

Section: Resultsmentioning

confidence: 99%

Machine Learning: A New Approach for Dose Individualization

Li,

Tang,

et al. 2023

Clin Pharma and Therapeutics

View full text Add to dashboard Cite

The application of machine learning (ML) has shown promising results in precision medicine due to its exceptional performance in dealing with complex multidimensional data. However, using ML for individualized dosing of medicines is still in its early stage, meriting further exploration. A systematic review of study designs and modeling details of using ML for individualized dosing of different drugs was performed. We have summarized the status of the study populations, predictive targets, and data sources for ML modeling, the selection of ML algorithms and features, and the evaluation and validation of their predictive performance. We also used the Prediction model Risk of Bias Assessment Tool (PROBAST) to assess the risk of bias of included studies. Currently, ML can be used for both a priori and a posteriori dose selection and optimization, and it can also assist the implementation of therapeutic drug monitoring. However, studies are mainly focused on drugs with narrow therapeutic windows, predominantly immunosuppressants (N=23, 35.9%) and anti‐infectives (N=21, 32.8%), and there is currently only very limited attention for special populations such as children (N=22, 34.4%). Most studies showed poor methodological quality and a high risk of bias. The lack of external validation and clinical utility evaluation currently limits the further clinical implementation of ML for dose individualization. We therefore have proposed several ways to improve the clinical relevance of the studies and facilitate the translation of ML models into clinical practice.

show abstract

Section: Resultsmentioning

confidence: 99%

Machine Learning: A New Approach for Dose Individualization

Li,

Tang,

et al. 2023

Clin Pharma and Therapeutics

View full text Add to dashboard Cite

show abstract

“…Theoretically, ML algorithms could be applied to develop predictive models to optimize warfarin dosing, using either regression or multi classification models. Nine studies were included [96][97][98][99][100][101][102][103][104] . Most of them derive from a multiethnic International Warfarin Pharmacogenetics Consortium (IWPC) dataset 105 using several ML regression models (Supplementary Table 5).…”

Section: Prediction Of a Personalized Anticoagulant Managementmentioning

confidence: 99%

“…Nine studies were included. 96 97 98 99 100 101 102 103 104 Most of them derive from a multiethnic International Warfarin Pharmacogenetics Consortium (IWPC) dataset 105 using several ML regression models ( Supplementary Table S5 , available in the online version). Sharabiani et al 96 have incorporated patient-specific clinical and genetic data to predict a personalized warfarin dose in the IWPC dataset using relevance vector machines.…”

Section: Prediction Of a Personalized Anticoagulant Managementmentioning

confidence: 99%

Machine Learning-Based Predictive Models for Patients with Venous Thromboembolism: A Systematic Review

Danilatou,

Dimopoulos,

Kostoulas

et al. 2024

Thromb Haemost

View full text Add to dashboard Cite

Background: Venous thromboembolism (VTE) is a chronic disorder with a significant health and economic burden. Several VTE-specific Clinical Prediction Models (CPMs) have been used to assist physicians in decision-making but have several limitations. This systematic review explores if machine learning (ML) can enhance CPMs by analyzing extensive patient data derived from electronic health records (EHRs). We aimed to explore ML-CPMs applications in VTE for risk stratification, outcome prediction, diagnosis, and treatment. Methods: Three databases were searched, PubMed, Google Scholar, and IEEE electronic library. Inclusion criteria focused on studies using structured data, excluding non-English publications, studies on non-humans, and certain data types such as natural language processing and image processing. Studies involving pregnant women, cancer patients, and children were also excluded. After excluding irrelevant studies, a total of 77 studies were included. Results: Most studies report that ML-CPMs outperformed traditional CPMs in terms of receiver operating area under the curve in the four clinical domains that were explored. However, the majority of the studies were retrospective, monocentric, and lacked detailed model architecture description and external validation, which are essential for quality audit. This review identified research gaps and highlighted challenges related to standardized reporting, reproducibility, and model comparison. Conclusion: ML-CPMs show promise in improving risk assessment and individualized treatment recommendations in VTE. Apparently, there is an urgent need for standardized reporting and methodology for ML models, external validation, prospective and real-world data studies, as well as interventional studies to evaluate the impact of AI in VTE.

show abstract

“…Artificial intelligence models have rapidly gained attention in pharmacological field. In pharmacogenomics, indicatively, studies published so far highlight the use of artificial intelligence models for warfarin dose prediction in Asian populations ( Jahmunah et al, 2023 ) and antidepressant response ( Bobo et al, 2022 ). Initial data for the use of machine learning and artificial intelligence in FP treatment are also available, focusing on DPYD variant classification ( Shrestha et al, 2018 ) and on identification of genomic and transcriptomic biomarkers for 5-FU response ( Kong et al, 2020 ).…”

Section: A Polygenic Algorithm For Fp Dosing: New Challenges In Oncologymentioning

confidence: 99%

Pharmacogenomic-guided dosing of fluoropyrimidines beyond DPYD: time for a polygenic algorithm?

2023

View full text Add to dashboard Cite

Fluoropyrimidines are chemotherapeutic agents widely used for the treatment of various solid tumors. Commonly prescribed FPs include 5-fluorouracil (5-FU) and its oral prodrugs capecitabine (CAP) and tegafur. Bioconversion of 5-FU prodrugs to 5-FU and subsequent metabolic activation of 5-FU are required for the formation of fluorodeoxyuridine triphosphate (FdUTP) and fluorouridine triphosphate, the active nucleotides through which 5-FU exerts its antimetabolite actions. A significant proportion of FP-treated patients develop severe or life-threatening, even fatal, toxicity. It is well known that FP-induced toxicity is governed by genetic factors, with dihydropyrimidine dehydrogenase (DPYD), the rate limiting enzyme in 5-FU catabolism, being currently the cornerstone of FP pharmacogenomics. DPYD-based dosing guidelines exist to guide FP chemotherapy suggesting significant dose reductions in DPYD defective patients. Accumulated evidence shows that additional variations in other genes implicated in FP pharmacokinetics and pharmacodynamics increase risk for FP toxicity, therefore taking into account more gene variations in FP dosing guidelines holds promise to improve FP pharmacotherapy. In this review we describe the current knowledge on pharmacogenomics of FP-related genes, beyond DPYD, focusing on FP toxicity risk and genetic effects on FP dose reductions. We propose that in the future, FP dosing guidelines may be expanded to include a broader ethnicity-based genetic panel as well as gene*gene and gender*gene interactions towards safer FP prescription.

show abstract

Automated warfarin dose prediction for Asian, American, and Caucasian populations using a deep neural network

Cited by 10 publications

References 30 publications

Machine Learning: A New Approach for Dose Individualization

Machine Learning: A New Approach for Dose Individualization

Machine Learning-Based Predictive Models for Patients with Venous Thromboembolism: A Systematic Review

Pharmacogenomic-guided dosing of fluoropyrimidines beyond DPYD: time for a polygenic algorithm?

Contact Info

Product

Resources

About