Atorvastatin-linked rhabdomyolysis caused by the simultaneous intake of amoxicillin clavulanic acid

Multiple sampling schemes and deep learning improve active learning performance in drug-drug interaction information retrieval analysis from the literature

BACKGROUND

Drug-drug interaction (DDI) information retrieval (IR) is an important natural language process (NLP) task from the PubMed literature. For the first time, active learning (AL) is studied in DDI IR analysis. DDI IR analysis from PubMed abstracts faces the challenges of relatively small positive DDI samples among overwhelmingly large negative samples. Random negative sampling and positive sampling are purposely designed to improve the efficiency of AL analysis. The consistency of random negative sampling and positive sampling is shown in the paper.

RESULTS

PubMed abstracts are divided into two pools. Screened pool contains all abstracts that pass the DDI keywords query in PubMed, while unscreened pool includes all the other abstracts. At a prespecified recall rate of 0.95, DDI IR analysis precision is evaluated and compared. In screened pool IR analysis using supporting vector machine (SVM), similarity sampling plus uncertainty sampling improves the precision over uncertainty sampling, from 0.89 to 0.92 respectively. In the unscreened pool IR analysis, the integrated random negative sampling, positive sampling, and similarity sampling improve the precision over uncertainty sampling along, from 0.72 to 0.81 respectively. When we change the SVM to a deep learning method, all sampling schemes consistently improve DDI AL analysis in both screened pool and unscreened pool. Deep learning has significant improvement of precision over SVM, 0.96 vs. 0.92 in screened pool, and 0.90 vs. 0.81 in the unscreened pool, respectively.

CONCLUSIONS

By integrating various sampling schemes and deep learning algorithms into AL, the DDI IR analysis from literature is significantly improved. The random negative sampling and positive sampling are highly effective methods in improving AL analysis where the positive and negative samples are extremely imbalanced.

ALERT-LDL: adherence to guidelines in the treatment of patients with dyslipidemia

The association between LDL-c levels and cardiovascular outcomes suggests tailoring lipid-lowering therapies according to total cardiovascular risk. We aimed to evaluate the adherence to guidelines-oriented dyslipidaemia's treatment in an outpatient population referring to ARCA cardiologists, and assess the efficacy of treatment's optimization for each specific level of risk. Three thousand seventy-five patients enrolled in this prospective study were classified according to cardiovascular risk category, and their therapies were optimized. At the beginning and the 3 month follow-up visit, LDL-c data were collected, and further therapies were prescribed to the patients that did not reach the target. A significant LDL-c reduction was observed in all subgroups at different cardiovascular risk at the end of the study (p < 0.05). The number of patients assuming statins, both in monotherapy and in combination with ezetimibe, increased during the follow-up (63% at the enrollment vs 89% after 12 months). At the enrollment, only 1.4% of patients were treated with PCSK-9 inhibitors while after 12 months the percentage increased both in high (5.8%) and very high-risk (18.4%) patients. At the beginning of the study, only 698/3075 patients (22.7%) reached lipid targets. At the end of the study, carried out by the referring cardiologists in the pertaining healthcare districts and specifically aimed to control the lipid profile, the percentage of patients on target increased in all risk categories (68.5%). Our results suggest carefully implementing measures that encourage outpatients and their cardiologists to achieve the targeted lipid profile according to cardiovascular risk.

Beneficial Metabolic Effect of a Nutraceuticals Combination (Monacolin K, Yeasted Red Rice, Polyphenolic Extract of Annurca Apple and Berberine) on Acquired Hypercholesterolemia: A Prospective Analysis

Hypercholesterolemia represents a serious public health problem as it significantly increases the risk of developing cardiovascular diseases. Its treatment with statin is limited by costs, side effects, and drugs interactions. Nutraceuticals appear to have an important metabolic effect on cholesterol reduction as well as on body weight and glycemia. The aim of this study was to evaluate the effect of a nutraceutical combination (Melasterol) in eighty-seven patients with acquired hypercholesterolemia. Clinically relevant parameters were collected at baseline and after three and six months of Melasterol treatment, one tablet per day. The primary endpoint was the change in cholesterol and triglyceride levels. Six months of treatment resulted in a 19.2% decrease in total cholesterol, accompanied by a 19.8% decrease in low-density lipoprotein (LDL) and a 23% reduction in triglycerides (p < 0.001) but not in high-density lipoprotein (HDL) levels (p > 0.05). These results were paralleled by a significative blood glucose (108.3 ± 21.3 vs. 98.4 ± 18.6 mg/dL p < 0.001) and body mass index (BMI) reduction (27.8 ± 4.4 vs. 27.0 ± 4.2 mg/dL, p < 0.001). A subgroup of 12 patients performed flow-mediated dilation, with values increasing by 1.8% (p < 0.05). No significant side effects were reported. Besides its cholesterol-lowering effect, Melasterol was associated with a significant improvement in other relevant metabolic parameters such as BMI and glycemia.