RESUMEN
BACKGROUND: Warfarin is a widely used anticoagulant with a narrow therapeutic index and large interpatient variability in the therapeutic dose. Warfarin sensitivity has been reported to be associated with increased incidence of international normalized ratio (INR) > 5. However, whether warfarin sensitivity is a risk factor for adverse outcomes in critically ill patients remains unknown. In the present study, we aimed to evaluate the utility of different machine learning algorithms for the prediction of warfarin sensitivity and to determine the impact of warfarin sensitivity on outcomes in critically ill patients. METHODS: Nine different machine learning algorithms for the prediction of warfarin sensitivity were tested in the International Warfarin Pharmacogenetic Consortium cohort and Easton cohort. Furthermore, a total of 7,647 critically ill patients was analyzed for warfarin sensitivity on in-hospital mortality by multivariable regression. Covariates that potentially confound the association were further adjusted using propensity score matching or inverse probability of treatment weighting. RESULTS: We found that logistic regression (AUC = 0.879, 95% CI: 0.834-0.924) was indistinguishable from support vector machine with a linear kernel, neural network, AdaBoost and light gradient boosting trees, and significantly outperformed all the other machine learning algorithms. Furthermore, we found that warfarin sensitivity predicted by the logistic regression model was significantly associated with worse in-hospital mortality in critically ill patients with an odds ratio (OR) of 1.33 (95% CI, 1.01-1.77). CONCLUSIONS: Our data suggest that the logistic regression model is the best model for the prediction of warfarin sensitivity clinically and that warfarin sensitivity is likely to be a risk factor for adverse outcomes in critically ill patients.
Asunto(s)
Enfermedad Crítica , Warfarina , Algoritmos , Anticoagulantes/efectos adversos , Resistencia a Medicamentos , Mortalidad Hospitalaria , Humanos , Relación Normalizada Internacional , Errores Innatos del Metabolismo , Warfarina/efectos adversosRESUMEN
An inverse correlation between the incidence of cancer and neurodegenerative disease has been observed, with the prevalence of cancer peaking around 60 years of age, then slowly tapering off as neurodegenerative diseases increase in the elderly. Although the diseases rarely occur concurrently, the same genes are differentially expressed between the diseases, with four transcription factors found to be in common for their expression. In the brain, mature astrocytes are the origin of astrocytoma, which make up 58.2% of malignant brain tumors in patients 65 or older, while GFAP+ astrocyte-like neural stem cells from the subventricular zone give rise to glioblastoma and anaplastic astrocytoma, which make up 41.6%. Likewise, in neurodegenerative disease, a decrease in astrocyte density is observed in early disease states, and senescent astrocytes increase. Because astrocytes coordinate synaptic function, astrocyte dysfunction likely contributes to or causes initial synapse loss and cognitive decline seen in neurodegenerative disease. In non-disease states, astrocytes retain their ability to successfully re-enter the cell cycle through adult astrogenesis to maintain the neuroenvironment, and controlled astrocytic proliferation could be an important contributor to neurological function. Disruption to this astrogenic balance could account for the inverse correlation of cell cycle dysregulation resulting in malignant astrocytes and tumorigenesis, and astrocytic senescence and cell death without self-renewal in aging resulting in neurodegenerative disease. The current understanding of the astrocytic roles of the transcription factors that could be the cause of this imbalance will be discussed, as well as possible therapeutic approaches to modulate their expression in the astrocyte.