RESUMEN
The development and deployment of machine learning (ML) models for biomedical research and healthcare currently lacks standard methodologies. Although tools for model replication are numerous, without a unifying blueprint it remains difficult to scientifically reproduce predictive ML models for any number of reasons (e.g., assumptions regarding data distributions and preprocessing, unclear test metrics, etc.) and ultimately, questions around generalizability and transportability are not readily answered. To facilitate scientific reproducibility, we built upon the Predictive Model Markup Language (PMML) to capture essential information. As a key component of the PREdictive Model Index and Exchange REpository (PREMIERE) platform, we present the Automated Metadata Pipeline (AMP) for conversion of a given predictive ML model into an extended PMML file that autocompletes an ML-based checklist, assessing model elements for interoperability and reproducibility. We demonstrate this pipeline on multiple test cases with three different ML algorithms and health-related datasets, providing a foundation for future predictive model reproducibility, sharing, and comparison.
Asunto(s)
Investigación Biomédica , Reproducibilidad de los Resultados , Algoritmos , Registros , MetadatosRESUMEN
PURPOSE OF REVIEW: CYP2C19 is the primary enzyme involved in the activation of clopidogrel, an antiplatelet agent used for secondary stroke prevention. An individual's CYP2C19 alleles are used to understand their CYP2C19-clopidogrel metabolizer phenotype. Single nucleotide polymorphisms of the CYP2C19 gene result in altered metabolism of this prodrug. RECENT FINDINGS: Three ischemic stroke cases were treated with clopidogrel. Despite confirming adequate drug exposure, medication adherence, and ruling out drug-drug interactions, all had recurrent ischemic stroke. Each case had a CYP2C19 *2/*17 genotype, categorizing them as intermediate clopidogrel metabolizers. Even with the gain-of-function allele, the loss-of-function allele resulted in lack of prodrug activation, leading to decreased efficacy in platelet inhibition. SUMMARY: These cases illustrate the importance of a thoughtful approach to secondary stroke prevention and demonstrate the utility of pharmacogenomic testing in clopidogrel hyporesponders. Recognition of the importance of CYP2C19 genotyping has the potential to enable better selection of appropriate secondary prevention strategies.