Machine Learning Algorithm for Predicting Warfarin Dose in Caribbean Hispanics Using Pharmacogenetic Data.

Despite some previous examples of successful application to the field of pharmacogenomics, the utility of machine learning (ML) techniques for warfarin dose predictions in Caribbean Hispanic patients has yet to be fully evaluated. This study compares seven ML methods to predict warfarin dosing in Caribbean Hispanics. This is a secondary analysis of genetic and non-genetic clinical data from 190 cardiovascular Hispanic patients. Seven ML algorithms were applied to the data. Data was divided into 80 and 20% to be used as training and test sets. ML algorithms were trained with the training set to obtain the models. Model performance was determined by computing the corresponding mean absolute error (MAE) and % patients whose predicted optimal dose were within ±20% of the actual stabilization dose, and then compared between groups of patients with "normal" (i.e., > 21 but <49 mg/week), low (i.e., ≤21 mg/week, "sensitive"), and high (i.e., ≥49 mg/week, "resistant") dose requirements. Random forest regression (RFR) significantly outperform all other methods, with a MAE of 4.73 mg/week and 80.56% of cases within ±20% of the actual stabilization dose. Among those with "normal" dose requirements, RFR performance is also better than the rest of models (MAE = 2.91 mg/week). In the "sensitive" group, support vector regression (SVR) shows superiority over the others with lower MAE of 4.79 mg/week. Finally, multivariate adaptive splines (MARS) shows the best performance in the resistant group (MAE = 7.22 mg/week) and 66.7% of predictions within ±20%. Models generated by using RFR, MARS, and SVR algorithms showed significantly better predictions of weekly warfarin dosing in the studied cohorts than other algorithms. Better performance of the ML models for patients with "normal," "sensitive," and "resistant" to warfarin were obtained when compared to other populations and previous statistical models.

The shear bond strength of self-adhesive resin cements to dentin and enamel: an in vitro study.

STATEMENT OF PROBLEM: Clinicians continue to search for ways to simplify bonding procedures without compromising clinical efficacy. PURPOSE: The purpose of this study was to evaluate the shear strength of self-adhesive cements RelyX U100 and RelyX U200, and conventional resin cement RelyX ARC to enamel and dentin after different surface treatments. MATERIAL AND METHODS: The crowns of 120 bovine incisor teeth were separated from the roots and embedded in epoxy resin in polyvinyl chloride tubes. In each tooth, the area to be cemented was delimited with central holed adhesive tape. The teeth were distributed into 12 groups (n=10) according to the substrate; etched or not with 37% phosphoric acid; and cement type of enamel-U100, enamel-phosphoric acid-U100, enamel-U200, enamel-phosphoric acid-U200, enamel-ARC, enamel-phosphoric acid-ARC, dentin-U100, dentin-phosphoric acid-U100, dentin-U200, dentin-phosphoric acid-U200, dentin-ARC, and dentin-phosphoric acid-ARC. After 7 days of storage in artificial saliva, shear strength tests were performed by using a universal testing machine (0.5 mm/min). The data were analyzed with 3-way ANOVA and the Tukey test (α=.05). Fracture analysis was performed with a light microscope. Two specimens from each group were analyzed with a scanning electron microscope. RESULTS: In enamel, ARC (9.96 MPa) had higher shear strength (P=.038) than U100 (5.14 MPa); however, after surface etching, U100 (17.81 MPa) and U200 (17.52 MPa) had higher shear strength (P<.001). With dentin, no significant differences were observed (P=.999), except for dentin-ARC (0.34 MPa) (P=.001). Most fractures were of the adhesive type. CONCLUSIONS: U200 self-adhesive cement had similar bond strength to the ARC in enamel, but the combination with phosphoric acid had the best bond strength. For dentin, self-adhesive resin cements are equally effective alternatives to conventional resin cement.

The effects of hypertension on the cerebral circulation.

Maintenance of brain function depends on a constant blood supply. Deficits in cerebral blood flow are linked to cognitive decline, and they have detrimental effects on the outcome of ischemia. Hypertension causes alterations in cerebral artery structure and function that can impair blood flow, particularly during an ischemic insult or during periods of low arterial pressure. This review will focus on the historical discoveries, novel developments, and knowledge gaps in 1) hypertensive cerebral artery remodeling, 2) vascular function with emphasis on myogenic reactivity and endothelium-dependent dilation, and 3) blood-brain barrier function. Hypertensive artery remodeling results in reduction in the lumen diameter and an increase in the wall-to-lumen ratio in most cerebral arteries; this is linked to reduced blood flow postischemia and increased ischemic damage. Many factors that are increased in hypertension stimulate remodeling; these include the renin-angiotensin-aldosterone system and reactive oxygen species levels. Endothelial function, vital for endothelium-mediated dilation and regulation of myogenic reactivity, is impaired in hypertension. This is a consequence of alterations in vasodilator mechanisms involving nitric oxide, epoxyeicosatrienoic acids, and ion channels, including calcium-activated potassium channels and transient receptor potential vanilloid channel 4. Hypertension causes blood-brain barrier breakdown by mechanisms involving inflammation, oxidative stress, and vasoactive circulating molecules. This exposes neurons to cytotoxic molecules, leading to neuronal loss, cognitive decline, and impaired recovery from ischemia. As the population ages and the incidence of hypertension, stroke, and dementia increases, it is imperative that we gain a better understanding of the control of cerebral artery function in health and disease.